WO2024023921A1 - Sign recognition device, sign recognition system, and sign recognition method - Google Patents

Sign recognition device, sign recognition system, and sign recognition method Download PDF

Info

Publication number
WO2024023921A1
WO2024023921A1 PCT/JP2022/028750 JP2022028750W WO2024023921A1 WO 2024023921 A1 WO2024023921 A1 WO 2024023921A1 JP 2022028750 W JP2022028750 W JP 2022028750W WO 2024023921 A1 WO2024023921 A1 WO 2024023921A1
Authority
WO
WIPO (PCT)
Prior art keywords
traffic
bulletin board
vehicle
notice
recognition
Prior art date
Application number
PCT/JP2022/028750
Other languages
French (fr)
Japanese (ja)
Inventor
邦亮 柏木
譲 中谷
浩平 石川
Original Assignee
三菱電機株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 三菱電機株式会社 filed Critical 三菱電機株式会社
Priority to PCT/JP2022/028750 priority Critical patent/WO2024023921A1/en
Publication of WO2024023921A1 publication Critical patent/WO2024023921A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions

Definitions

  • the present disclosure relates to recognition of traffic notices.
  • Patent Document 1 discloses a system that recognizes a sign in front of a vehicle by pattern matching an image taken in front of the vehicle by an on-vehicle camera with a template image of a road sign or the like provided in the vehicle in advance.
  • Patent Document 1 targets all areas within a photographed image for pattern matching, so it takes time to recognize the road sign. There is a problem that road signs cannot be notified.
  • the present disclosure has been made in order to solve the above-mentioned problems, and the time required to recognize the traffic bulletin board when recognizing the traffic bulletin board around the vehicle by pattern matching the photographed image with the template image.
  • the purpose is to shorten it.
  • a bulletin board recognition device of the present disclosure includes: an image acquisition unit that acquires a photographed image of the surroundings of a vehicle; a reception unit that receives an identification signal transmitted from a traffic bulletin board mounted on the vehicle and installed on a road; Based on the identification signal, there is a bulletin board position determination unit that estimates the position information of the traffic bulletin board indicating the position of the traffic bulletin board relative to the vehicle, and a bulletin board position determination unit that estimates the position information of the traffic bulletin board that indicates the position of the traffic bulletin board with respect to the vehicle, and a plurality of template images prepared for each type of traffic bulletin board according to a predetermined priority order.
  • the present invention includes a recognition unit that recognizes a traffic bulletin board appearing in a photographed image by pattern matching with the photographed image.
  • the recognition unit identifies a part of the photographed image as the target range in which the traffic bulletin was photographed, based on the position information of the traffic bulletin estimated by the bulletin position determination unit, and sets the target range as a target for pattern matching. .
  • the bulletin board recognition device of the present disclosure estimates the position information of the traffic bulletin board based on the identification signal received from the traffic bulletin board, and specifies the target range of the photographed image that is pattern-matched with the template image based on the position information. Therefore, according to the notice recognition device of the present disclosure, compared to the case where the entire range of a photographed image is matched with a template image, the processing time for pattern matching can be shortened and traffic notices can be quickly recognized. As a result, the information on the traffic bulletin board can be notified to the vehicle occupants at an appropriate timing.
  • FIG. 1 is a block diagram showing the configuration of a notice recognition system according to Embodiment 1.
  • FIG. 3 is a flowchart showing the operation of the notice recognition device according to the first embodiment.
  • FIG. 3 is a diagram showing the horizontal angle and distance of a road sign with respect to a camera.
  • FIG. 3 is a diagram showing a recognition target range in a photographed image.
  • FIG. 3 is a diagram showing how the notice recognition device receives radio waves from traffic notices at three different locations. It is a figure which shows the example of a display of traffic bulletin board information on HUD.
  • FIG. 3 is a diagram illustrating how the notice recognition device incorrectly recognizes the position of a traffic notice by receiving reflected waves.
  • FIG. 2 is a block diagram showing the configuration of a notice recognition system according to Embodiment 2.
  • FIG. 7 is a flowchart showing the operation of the notice recognition device according to Embodiment 2.
  • FIG. 6 is a diagram illustrating how the notice recognition device changes the priority order of template images that match an image captured by a camera, based on type information received from a road sign.
  • FIG. 3 is a block diagram showing the configuration of a notice recognition system according to Embodiment 3.
  • FIG. 7 is a flowchart showing the operation of the notice recognition device according to Embodiment 3. It is a diagram showing the hardware configuration of a notice recognition device and a road sign.
  • FIG. 1 is a block diagram showing the configuration of a notice recognition system 1001 according to the first embodiment.
  • the bulletin board recognition system 1001 includes a traffic bulletin board 201 and a vehicle 301.
  • the bulletin board recognition system 1001 is a system that recognizes traffic bulletin boards 201 around the vehicle 301 and notifies the driver of the vehicle 301 of information about the recognized traffic bulletin boards 201.
  • the traffic bulletin board 201 is a bulletin board placed on a road that displays traffic information necessary for drivers to drive smoothly.
  • the traffic bulletin board 201 is, for example, a traffic light, a road sign, or a road marking. In the following description, the traffic bulletin board 201 is assumed to be a road sign.
  • the vehicle 301 is provided with a camera 51, a display 53, and a speaker 54.
  • the notice recognition device 101 will be described as a device mounted on a vehicle 301.
  • components other than the receiving unit 12 of the notice recognition device 101 do not necessarily have to be provided in the vehicle 301, and may be provided in a server outside the vehicle 301, for example.
  • the bulletin board recognition device 101 is connected to a camera 51, a display 53, and a speaker 54, and is configured to be able to use these.
  • the camera 51 photographs the surroundings of the vehicle 301.
  • the area around the vehicle 301 typically includes the road in front of the vehicle 301, and includes, for example, a range up to a point 300 meters in front of the vehicle 301.
  • the display 53 and the speaker 54 are output devices that notify the driver of the vehicle 301 of information on traffic bulletins 201 around the vehicle 301 recognized by the bulletin recognition device 101.
  • the notice recognition device 101 may include only one of the display 53 and the speaker 54.
  • the display 53 displays information about the traffic bulletin board 201 around the vehicle 301 recognized by the bulletin recognition device 101.
  • the display 53 is, for example, a CID (Center Information Display) or a HUD (Head-Up Display).
  • the speaker 54 outputs information on the traffic bulletin board 201 around the vehicle 301 recognized by the bulletin board recognition device 101 in audio.
  • the display 53 and the speaker 54 are both mounted on the vehicle 301 and are configured so that the driver of the vehicle 301 can recognize the information on the traffic bulletin board 201 outputted by the display 53 and the speaker 54. .
  • the notice recognition device 101 includes an image acquisition section 11 , a reception section 12 , a notice position determination section 13 , a recognition section 14 , a template storage section 15 , and an output control section 16 .
  • the image acquisition unit 11 acquires captured images of the surroundings of the vehicle 301 from the camera 51.
  • the receiving unit 12 performs wireless communication with the traffic bulletin board 201.
  • the receiving unit 12 receives radio waves transmitted from the traffic bulletin board 201, demodulates the radio waves, and outputs a demodulated signal to the bulletin position determining unit 13.
  • the radio wave transmitted from the traffic bulletin board 201 includes an identification signal indicating that the transmission source of the radio wave is the traffic bulletin board 201.
  • the receiving section 12 demodulates this identification signal and outputs it to the notice position determining section 13. In other words, the receiving unit 12 receives the identification signal from the traffic bulletin board 201.
  • the bulletin position determining unit 13 determines the relative position of the traffic bulletin board 201 with respect to the vehicle 301 based on the identification signal received from the traffic bulletin board 201 by the receiving unit 12.
  • the relative position of the traffic bulletin board 201 determined by the bulletin position determination unit 13 includes the direction of the traffic bulletin board 201 with respect to the vehicle 301 and the distance between the vehicle 301 and the traffic bulletin board 201.
  • the template storage unit 15 stores a plurality of template images for each type of traffic bulletin board 201.
  • the template image of the traffic bulletin board 201 is an image of the appearance of the traffic bulletin board 201.
  • the traffic bulletin board 201 is classified into traffic lights, road signs, and road markings as described above. Template images may be stored for different shapes of traffic lights, such as pedestrian traffic lights or vertical traffic lights. Template images are stored for each type of road signs and road markings.
  • the recognition unit 14 acquires a photographed image of the surroundings of the vehicle 301 from the image acquisition unit 11, and determines whether the traffic bulletin 201 is located in the photographed image based on the relative position of the traffic bulletin 201 with respect to the vehicle 301 acquired from the bulletin position determination unit 13. The area that appears to be reflected is identified as the target area. Then, the recognition unit 14 pattern-matches only the target area of the photographed image with a plurality of template images stored in the template storage unit 15, and when a certain template image matches the target area, the recognition unit 14 performs pattern matching on only the target area of the photographed image, and when a certain template image matches the target area, a traffic sign of the type of the template image is detected. 201 is recognized as being in the vicinity of vehicle 301. Then, the recognition unit 14 outputs the recognized type of traffic bulletin board 201 and the relative position of the traffic bulletin board 201 with respect to the vehicle 301 to the output control unit 16.
  • the order of template images in which the recognition unit 14 performs pattern matching with the target area of the captured image (hereinafter referred to as "matching order") is predetermined.
  • the recognition unit 14 acquires a desired template image from the template storage unit 15 in accordance with the matching order, and pattern-matches the template image with the target area of the photographed image. If the two do not match, the recognition unit 14 acquires the next template image from the template storage unit 15 and performs pattern matching with the target area of the photographed image.
  • the recognition unit 14 may perform pattern matching for one sheet at a time, or may perform pattern matching for a plurality of sheets.
  • the matching order is determined, for example, in descending order of the risk that the driver will miss the traffic bulletin board 201.
  • the matching order is determined in the following order: a template image of a road sign "No Vehicles Entry", a template image of a road sign related to speed, and a template image of a stop road sign. Good too.
  • the magnitude of the risk that the driver will miss the traffic bulletin board 201 may be determined by the amount of a fine for violating the traffic rules posted on the traffic bulletin board 201.
  • the output control unit 16 acquires the recognition result of the traffic bulletin board 201 by the recognition unit 14 and the relative position of the traffic bulletin board 201 with respect to the vehicle 301 from the recognition unit 14, and outputs these from the display 53 or the speaker 54.
  • the traffic bulletin board 201 includes a transmitter 21 and a controller 22.
  • the transmitter 21 performs wireless communication with the receiver 12 of the notice recognition device 101.
  • the transmitter 21 receives an instruction from the controller 22 and transmits an identification signal for the traffic bulletin board 201 to the receiver 12 .
  • the identification signal includes at least information indicating that the transmission source is a traffic bulletin board.
  • the transmitting section 21 transmits the identification signal to the receiving section 12, for example, at regular intervals.
  • the control unit 22 controls the transmission of the identification signal by the transmitting unit 21.
  • FIG. 2 is a flowchart showing the operation of the notice recognition device 101.
  • the operation of the notice recognition device 101 will be described below along the flowchart of FIG. 2.
  • the flow in FIG. 2 starts, for example, when the vehicle 301 starts traveling.
  • step S101 it is determined whether the receiving unit 12 has received an identification signal. If the receiving unit 12 has not received the identification signal in step S101, the process of the notice recognition device 101 proceeds to step S105.
  • step S105 the recognition unit 14 sequentially performs pattern matching on the entire range of the image captured by the camera 51 acquired by the image acquisition unit 11 with the plurality of template images stored in the template storage unit 15 according to the default matching order.
  • the default matching order (priority order) is determined, for example, in descending order of risk if the driver misses the traffic bulletin board 201.
  • the risk is, for example, the amount of a fine if the traffic information posted by the traffic bulletin board 201 is violated. If there is a pattern in the photographed image that matches the template image, the recognition unit 14 ends the pattern matching at that point, and the process of the notice recognition device 101 proceeds to step S106.
  • the recognition unit 14 determines that the traffic bulletin board corresponding to the template image exists at the position corresponding to the matched pattern in the photographed image. That is, the recognition unit 14 detects the traffic bulletin board 201 corresponding to the matched template image. The recognition unit 14 ends the pattern matching at that point, and the process of the notice recognition device 101 proceeds to step S106. Further, if the recognition unit 14 does not match the target range of the photographed image even after performing pattern matching on all template images, the recognition unit 14 ends the pattern matching, and the process of the notice recognition device 101 proceeds to step S106.
  • step S101 If the receiving unit 12 has received the identification signal in step S101, the process of the notice recognition device 101 proceeds to step S102.
  • step S102 the notice position determining unit 13 estimates the relative position of the traffic notice 201 with respect to the vehicle 301 based on the identification signal received by the receiving unit 12. Specifically, the bulletin position determination unit 13 calculates the direction and distance of the traffic bulletin board 201 with respect to the vehicle 301 based on the radio wave intensity of the identification signal received by the receiving unit 12.
  • FIG. 3 is a diagram showing a method of calculating the position of the traffic bulletin board 201 based on the radio wave intensity of the identification signal.
  • the receiving unit 12 receives radio waves from the traffic bulletin board 201 at three different positions. First, it can be seen from the intensity of the first radio wave received by the receiving unit 12 that the traffic bulletin board 201 is located on a circle 62 with a radius of 50 m from the receiving point. Next, based on the intensity of the second radio wave received by the receiver 12, it can be seen that the traffic bulletin board 201 is located on a circle 63 with a radius of 40 m from the receiving point.
  • the traffic bulletin board 201 is located on the circle 64 with a radius of 30 m from the receiving point. Therefore, the position of the traffic bulletin board 201 is specified at the intersection of circles 62, 63, and 64.
  • step S103 the recognition unit 14 identifies a part of the image taken by the camera 51 as a pattern matching target range based on the relative position of the traffic bulletin board 201 estimated by the bulletin position determination unit 13.
  • FIG. 4 shows the horizontal positional relationship between the camera 51 mounted on the vehicle 301 and the traffic bulletin board 201.
  • the horizontal angle of view of the camera 51 is assumed to be ⁇ 1. It is assumed that the camera 51 is installed facing the direction of travel of the vehicle 301.
  • the horizontal angle that the line connecting the traffic bulletin board 201 and the camera 51 makes with respect to the traveling direction of the vehicle 301 is defined as the horizontal deviation angle ⁇ 2 of the traffic bulletin board 201.
  • FIG. 5 shows a target range 61 in an image taken by the camera 51.
  • the horizontal position of the target range 61 in the photographed image is determined based on the horizontal angle of view ⁇ 1 of the camera 51 and the horizontal declination angle ⁇ 2 of the traffic bulletin board 201.
  • the vertical position of the target range 61 in the captured image is determined based on the vertical viewing angle of the camera 51 and the distance between the traffic bulletin board 201 and the vehicle 301.
  • step S104 the recognition unit 14 sequentially performs pattern matching on the target range of the captured image of the camera 51 with a plurality of template images stored in the template storage unit 15 according to a default matching order. If the pattern in the target range of the photographed image matches the template image, the recognition unit 14 determines that the traffic bulletin board corresponding to the template image exists at the position corresponding to the matched pattern in the target range. That is, the recognition unit 14 detects the traffic bulletin board 201 corresponding to the matching template image. The recognition unit 14 ends the pattern matching at that point, and the process of the notice recognition device 101 proceeds to step S106. Further, if the recognition unit 14 does not match the target range of the photographed image even after performing pattern matching on all template images, the recognition unit 14 ends the pattern matching, and the process of the notice recognition device 101 proceeds to step S106.
  • step S106 the recognition unit 14 determines whether or not the traffic bulletin board 201 has been detected. If the traffic bulletin board 201 is not detected in step S106, the processing of the bulletin board recognition device 101 returns to step S108. If the traffic bulletin board 201 is detected in step S106, the processing of the bulletin board recognition device 101 proceeds to step S107.
  • step S107 the output control unit 16 acquires the type and position information of the detected traffic bulletin board 201 from the recognition unit 14, and outputs this information from the display 53 or the speaker 54.
  • FIG. 6 shows an example of display of the type and position of the traffic bulletin board 201 on the HUD, which is an example of the display 53.
  • FIG. 6 is a display example when the recognition unit 14 detects speed limit, stop, and crosswalk road signs on the road ahead of the vehicle 301.
  • a double broken line frame is displayed on the HUD area so as to surround the road sign.
  • a display object 65 that displays the road sign along with the current speed of the vehicle 301 is displayed in an area of the HUD superimposed on the road ahead of the vehicle 301. Thereby, the driver can recognize the road signs in front of the vehicle 301 and try to drive in accordance with the road signs.
  • step S108 the notice recognition device 101 determines whether or not the vehicle 301 has finished traveling. If the vehicle 301 has not finished traveling in step S108, the process of the notice recognition device 101 returns to step S101. If the vehicle 301 has finished traveling in step S108, the processing of the notice recognition device 101 ends.
  • the radio waves transmitted by the traffic bulletin board 201 reach the vehicle 301 as direct waves, and may also reach the vehicle 301 as reflected waves reflected from buildings. Therefore, the notice recognition device 101 may mistakenly recognize the arrival direction of the reflected wave as the direction of the traffic notice 201, or may incorrectly recognize the distance to the traffic notice 201 as being short due to the attenuated radio wave intensity of the reflected wave. There is a possibility of relaxing.
  • the radio waves of the sign signal transmitted from the transmitter 21 of the traffic bulletin board 201 have directivity toward the target road of the traffic information posted by the traffic bulletin board 201. This prevents the notice recognition device 101 from erroneously recognizing the position of the traffic notice 201 due to reflected waves.
  • the bulletin board recognition device 101 includes an image acquisition unit 11 that acquires captured images of the surroundings of a vehicle 301, and an identification device 11 that acquires a photographed image of the surroundings of a vehicle 301, and an identification device that is transmitted from a traffic bulletin board 201 mounted on the vehicle 301 and installed on the road.
  • a receiving unit 12 that receives a signal
  • a bulletin board position determining unit 13 that estimates position information of the traffic bulletin board 201 including at least the direction of the traffic bulletin board 201 with respect to the vehicle based on the identification signal
  • a bulletin board position determination unit 13 that is prepared for each type of traffic bulletin board 201.
  • the present invention includes a recognition unit 14 that recognizes the traffic bulletin board 201 shown in the photographed image by pattern matching the plurality of template images taken with the photographed image according to a predetermined priority order. Based on the position information of the traffic bulletin board 201 estimated by the bulletin position determination unit 13, the recognition unit 14 identifies a part of the captured image as the target range in which the traffic bulletin board 201 was photographed, and performs pattern matching on the target range. be subject to.
  • the processing time for pattern matching can be shortened compared to the case where the entire range of a photographed image is pattern matched with a template image. As a result, it becomes possible to quickly recognize the traffic bulletin board 201 and notify the driver of the information on the traffic bulletin board 201 at an appropriate timing.
  • the identification signal received by the receiving unit 12 may include three or more identification signals received at three or more different traveling positions of the vehicle 301. .
  • the bulletin board recognition device 101 can estimate the position of the traffic bulletin board 201 with high accuracy.
  • the radio waves used when transmitting the identification signal from the surrounding traffic bulletin board 201 may have directivity with respect to the target road of the nearby traffic bulletin board. In this case, it is possible to prevent the notice recognition device 101 from erroneously recognizing the position of the traffic notice 201 based on the received intensity of reflected waves from buildings or the like or the direction of arrival.
  • the bulletin board recognition system includes a traffic bulletin board 201 that is installed on a road and transmits an identification signal, and a bulletin board recognition device 101 that recognizes traffic bulletin boards around a vehicle 301. Therefore, according to the bulletin board recognition system according to the first embodiment, the processing time for pattern matching can be reduced compared to the case where the entire range of a photographed image is pattern matched with a template image. As a result, it becomes possible to quickly recognize the traffic bulletin board 201 and notify the driver of the information on the traffic bulletin board 201 at an appropriate timing.
  • an image acquisition unit 11 acquires a captured image of the surroundings of a vehicle 301, and a reception unit 12 mounted on the vehicle 301 detects a traffic bulletin board 201 installed on a road.
  • the notice position determination unit 13 estimates the position information of the traffic notice 201 indicating the position of the traffic notice 201 with respect to the vehicle 301 based on the identification signal, and the recognition unit 14 estimates the position information of the traffic notice 201 indicating the position of the traffic notice 201 with respect to the vehicle
  • the traffic bulletin board 201 shown in the photographed image is recognized, and the bulletin position determination unit 13 estimates the position of the traffic bulletin board 201.
  • the recognition unit 14 Based on the position information of the traffic bulletin board 201, the recognition unit 14 identifies a part of the photographed image as the target range in which the traffic bulletin board 201 was photographed, and sets the target range as a target for pattern matching. Therefore, according to the bulletin board recognition method according to the first embodiment, the processing time for pattern matching can be shortened compared to the case where the entire range of a photographed image is pattern matched with a template image. As a result, it becomes possible to quickly recognize the traffic bulletin board 201 and notify the driver of the information on the traffic bulletin board 201 at an appropriate timing.
  • FIG. 8 is a block diagram showing the configuration of a notice recognition system 1002 according to the second embodiment.
  • the bulletin board recognition system 1002 includes a traffic bulletin board 202 and a vehicle 301.
  • the same reference numerals are given to the same components as in Embodiment 1, and explanations of parts common to Embodiment 1 are omitted as appropriate.
  • the traffic bulletin board 202 includes an identification signal storage section 23 in addition to the configuration of the traffic bulletin board 201 according to the first embodiment.
  • the identification signal storage unit 23 stores type information 231 indicating the type of traffic bulletin board 202.
  • the transmitting unit 21 transmits the identification signal of the traffic bulletin board 202 in response to instructions from the control unit 22.
  • This identification signal includes type information 231. That is, the transmitting unit 21 retrieves the type information 231 from the identification signal storage unit 23, includes the type information 231 in the identification signal, and transmits the identification signal.
  • the vehicle 301 is provided with a camera 51, a display 53, and a speaker 54 in addition to the bulletin board recognition device 102.
  • the bulletin board recognition device 102 has the same configuration as the bulletin board recognition device 101 according to Embodiment 1, but the processing of the recognition unit 14 is partially different.
  • the recognition unit 14 of this embodiment changes the priority order of template images to be pattern matched from the default according to the type information 231 included in the identification signal received by the reception unit 12. Specifically, the recognition unit 14 changes the priority order so that the template image of the traffic bulletin board 202 of the type indicated by the type information 231 is pattern matched with the highest priority.
  • FIG. 9 is a flowchart showing the operation of the notice recognition device 102.
  • the flow in FIG. 9 starts, for example, when the vehicle 301 starts traveling.
  • the flow in FIG. 9 is obtained by adding steps S201 and S202 between step S103 and step S104 in the flow in FIG. 2 described in the first embodiment.
  • step S201 the recognition unit 14 determines whether the type information 231 is included in the identification signal received by the reception unit 12. If the type information 231 is included in the identification signal in step S201, the process of the notice recognition device 102 moves to step S202.
  • step S202 the recognition unit 14 changes the priority order of the template image that pattern matches the target range of the photographed image from the default.
  • FIG. 10 is a diagram showing an example of changing the priority order.
  • the road sign identification signal received by the receiving unit 12 from the transmitting unit 21 includes road sign type information 231.
  • the type information 231 indicates a speed limit road sign as the type of road sign.
  • the recognition unit 14 changes the priority order of the template images so that the template image of the speed limit road sign has the highest priority. For example, if the default order of priority for template image matching is set in the following order: No Entry Road Sign, Speed Limit Road Sign, Stop Road Sign, the recognition unit 14 determines the priority order by speed Change in the order of restriction road signs, no entry road signs, and stop road signs.
  • the identification signal transmitted from the traffic bulletin board 202 includes type information indicating the type of the traffic bulletin board 202.
  • the recognition unit 14 of the bulletin board recognition device 102 changes the priority order of pattern matching of template images so that the template image of the traffic bulletin board 202 of the type represented by the type information has the highest priority.
  • the recognition unit 14 can shorten the processing time for pattern matching between the photographed image and the template image.
  • the bulletin board recognition device 102 can quickly recognize the traffic bulletin board 202 and notify the driver of the information on the traffic bulletin board 202 at an appropriate timing.
  • FIG. 11 is a block diagram showing the configuration of a notice recognition system 1003 according to the third embodiment.
  • the bulletin board recognition system 1003 includes a traffic bulletin board 203 and a vehicle 301.
  • the same reference numerals are given to the same components as in Embodiments 1 and 2, and descriptions of parts common to Embodiments 1 and 2 are omitted as appropriate.
  • the traffic bulletin board 203 of the third embodiment is different from the traffic bulletin board 202 of the second embodiment in the storage information stored in the identification signal storage unit 23.
  • the identification signal storage section 23 of the traffic bulletin board 203 stores target road information 232 in addition to type information 231.
  • the target road information 232 is information about the target road of the traffic information posted by the traffic bulletin board 203.
  • the transmitter 21 of the third embodiment transmits the identification signal of the traffic bulletin board 203 in response to instructions from the controller 22.
  • This identification signal includes type information 231 and target road information 232. That is, the transmitting unit 21 takes out the type information 231 and the target road information 232 from the identification signal storage unit 23, includes them in the identification signal, and transmits them.
  • the vehicle 301 is provided with a camera 51, a GPS (Global Positioning System) sensor 52, a display 53, and a speaker 54 in addition to the bulletin board recognition device 103.
  • GPS Global Positioning System
  • the GPS sensor 52 receives a GPS signal from a GPS satellite, measures the position of the vehicle 301, and outputs it to the notice recognition device 103.
  • the notice recognition device 103 includes a vehicle position determination unit 17 in addition to the configuration of the notice recognition device 102 according to the second embodiment. Further, in the notice recognition device 103, the processing of the recognition unit 14 is partially different from that in the second embodiment.
  • the vehicle position determining unit 17 determines whether the vehicle 301 is on the target road of the traffic bulletin board 203 based on the position information of the vehicle 301 acquired from the GPS sensor 52 and the target road information 232 of the traffic bulletin board 203 acquired from the receiving unit 12. Determine whether the vehicle is running or not.
  • the recognition unit 14 of this embodiment changes the priority order of template image matching according to the type of the traffic bulletin board 203, and If the vehicle is not traveling on the target road of the traffic bulletin board 203, the template image is matched with the photographed image according to the default priority order.
  • FIG. 12 is a flowchart showing the operation of the notice recognition device 103.
  • the flow in FIG. 12 starts, for example, when the vehicle 301 starts traveling.
  • the flow in FIG. 12 is obtained by adding steps S301, S302, and S303 between step S202 and step S104 in the flow in FIG. 9 described in the second embodiment.
  • step S301 the vehicle position determining unit 17 determines whether the target road information 232 is included in the identification signal received by the receiving unit 12. If the target road information 232 is included in the identification signal in step S301, the process of the notice recognition device 103 moves to step S302.
  • step 302 the vehicle position determination unit 17 determines whether the vehicle 301 is traveling on the target road based on the GPS signal acquired from the GPS sensor 52 and the target road information 232 acquired from the reception unit 12. .
  • step S302 If the vehicle 301 is traveling on the target road in step S302, the processing of the notice recognition device 103 proceeds to step S104.
  • step S302 If the vehicle 301 is not traveling on the target road in step S302, the processing of the notice recognition device 103 proceeds to step S303.
  • step S303 the recognition unit 14 returns the priority order of matching of the template image with the photographed image changed in step S202 to the default.
  • the identification signal that the bulletin board recognition device 103 receives from the traffic bulletin board 203 includes target road information 232 representing the target road of the traffic bulletin board 203. If the target road represented in the target road information 232 is not the road on which the vehicle 301 is traveling, the recognition unit 14 does not change the priority order of pattern matching of the template image. Therefore, according to the notice recognition device 103, even if identification information is received from a traffic notice 203 unrelated to the vehicle 301, it is possible to avoid performing pattern matching processing tailored to the traffic notice 203. .
  • the reception section 12 is realized by the communication device 83
  • the template storage section 15 is realized by the memory 82
  • the image acquisition section 11 is realized by the bulletin position judgment section 13, the recognition section 14, and the output control section 16.
  • the processor 81 executing a program stored in the memory 82.
  • the transmitter 21 is implemented by the communication device 83
  • the identification signal storage unit 23 is implemented by the memory 82
  • the controller 22 is implemented by the processor 81 executing a program stored in the memory 82. This is realized by
  • the processor 81 is, for example, a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, a DSP (Digital Signal Processor), or the like.
  • the program stored in the memory 82 causes the computer to execute the method of each part of the bulletin board recognition devices 101-103 or the traffic bulletin boards 201-203.
  • the memory 82 is a nonvolatile or Volatile semiconductor memory, HDD (Hard Disk Drive), magnetic disk, flexible disk, optical disk, compact disk, mini disk, DVD (Digital Versatile Disk) and its drive device, etc., or any storage media that will be used in the future. It's okay.
  • bulletin board recognition devices 101-103 have been described above as in-vehicle devices, PNDs (Portable Navigation Devices), communication terminals (for example, mobile terminals such as mobile phones, smartphones, and tablets), and applications installed on these devices It can also be applied to a system constructed by appropriately combining the functions of , servers, etc.
  • each function or each component of the bulletin board recognition devices 101-103 explained above may be distributed and arranged in each device constructing the system, or may be arranged centrally in one of the devices. It's okay.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The purpose of the present disclosure is to shorten the time required to recognize a traffic sign, when a traffic sign in the vehicle periphery is recognized by pattern-matching a captured image with a template image. A sign recognition device (101) of the present disclosure comprises: a reception unit (12) that is mounted in a vehicle (301) and receives an identification signal transmitted from a traffic sign (201) installed on the road; a display position determination unit (13) that estimates position information of the traffic sign (201) on the basis of the identification signal; and a recognition unit (14) that recognizes the traffic sign (201) shown in a captured image of the periphery of the vehicle (301), by executing pattern matching, in accordance with a predetermined priority order, between the captured image and a plurality of template images which were prepared for each type of the traffic sign (201). The recognition unit (14) identifies, on the basis of the position information of the traffic sign, a partial area of the captured image as a target area where the traffic sign is captured, and sets the target area as a target for pattern matching.

Description

掲示物認識装置、掲示物認識システムおよび掲示物認識方法Postage recognition device, postage recognition system, and postage recognition method
　本開示は、交通掲示物の認識に関する。 The present disclosure relates to recognition of traffic notices.
　道路上には、信号機、道路標識または道路標示など、交通に必要な情報を掲示する交通掲示物がある。運転者はこれらの交通掲示物を視認することにより、交通に必要な情報を把握し、円滑な交通を実行する。運転者が交通掲示物を見逃すと円滑な交通が担保されない。従って、車両の周辺の交通掲示物を検知して運転者に通知するシステムは有用である。 On the road, there are traffic signs, such as traffic lights, road signs, or road markings, that display information necessary for traffic. By visually checking these traffic notices, drivers can grasp the information necessary for traffic and drive smooth traffic. If drivers miss traffic signs, smooth traffic cannot be ensured. Therefore, a system that detects traffic bulletins around a vehicle and notifies the driver is useful.
　車両の周辺の道路標識を認識し、必要に応じて道路標識への注意を促す運転支援システムが既に実用化されている。例えば特許文献１には、車載カメラによる車両前方の撮影画像内を予め車両に備えられた道路標識等のテンプレート画像とパターンマッチングすることにより、車両前方の標識を認識するシステムが開示されている。 Driving support systems that recognize road signs around the vehicle and call attention to road signs as necessary are already in practical use. For example, Patent Document 1 discloses a system that recognizes a sign in front of a vehicle by pattern matching an image taken in front of the vehicle by an on-vehicle camera with a template image of a road sign or the like provided in the vehicle in advance.
特開平１１－３０６４９８号公報Japanese Patent Application Publication No. 11-306498
　しかし、特許文献１に記載された道路標識の認識方法は、撮影画像内の全ての領域をパターンマッチングの対象とするため、道路標識の認識に時間がかかってしまい、適切なタイミングで運転者に道路標識を通知することができないという問題がある。 However, the road sign recognition method described in Patent Document 1 targets all areas within a photographed image for pattern matching, so it takes time to recognize the road sign. There is a problem that road signs cannot be notified.
　本開示は、上記の問題点を解決するためになされたものであり、撮影画像をテンプレート画像とパターンマッチングすることにより車両周辺の交通掲示物を認識するにあたり、交通掲示物の認識に要する時間を短縮することを目的とする。 The present disclosure has been made in order to solve the above-mentioned problems, and the time required to recognize the traffic bulletin board when recognizing the traffic bulletin board around the vehicle by pattern matching the photographed image with the template image. The purpose is to shorten it.
　本開示の掲示物認識装置は、車両の周辺の撮影画像を取得する画像取得部と、車両に搭載され、道路上に設置された交通掲示物から送信される識別信号を受信する受信部と、識別信号に基づき、交通掲示物の車両に対する位置を表す交通掲示物の位置情報を推定する掲示位置判断部と、交通掲示物の種類別に用意された複数のテンプレート画像を予め定められた優先順位に従い撮影画像とパターンマッチングすることにより、撮影画像に映った交通掲示物を認識する認識部と、を備える。認識部は、掲示位置判断部が推定した交通掲示物の位置情報に基づき、撮影画像の一部の範囲を交通掲示物が撮影された対象範囲と特定し、対象範囲をパターンマッチングの対象とする。 A bulletin board recognition device of the present disclosure includes: an image acquisition unit that acquires a photographed image of the surroundings of a vehicle; a reception unit that receives an identification signal transmitted from a traffic bulletin board mounted on the vehicle and installed on a road; Based on the identification signal, there is a bulletin board position determination unit that estimates the position information of the traffic bulletin board indicating the position of the traffic bulletin board relative to the vehicle, and a bulletin board position determination unit that estimates the position information of the traffic bulletin board that indicates the position of the traffic bulletin board with respect to the vehicle, and a plurality of template images prepared for each type of traffic bulletin board according to a predetermined priority order. The present invention includes a recognition unit that recognizes a traffic bulletin board appearing in a photographed image by pattern matching with the photographed image. The recognition unit identifies a part of the photographed image as the target range in which the traffic bulletin was photographed, based on the position information of the traffic bulletin estimated by the bulletin position determination unit, and sets the target range as a target for pattern matching. .
　本開示の掲示物認識装置は、交通掲示物から受信した識別信号に基づき交通掲示物の位置情報を推定し、位置情報に基づきテンプレート画像とパターンマッチングする撮影画像の対象範囲を特定する。従って、本開示の掲示物認識装置によれば、撮影画像の全範囲をテンプレート画像とマッチングする場合に比べて、パターンマッチングの処理時間を短縮し、迅速に交通掲示物を認識することができる。その結果、適切なタイミングで交通掲示物の情報を車両の搭乗者に通知することができる。 The bulletin board recognition device of the present disclosure estimates the position information of the traffic bulletin board based on the identification signal received from the traffic bulletin board, and specifies the target range of the photographed image that is pattern-matched with the template image based on the position information. Therefore, according to the notice recognition device of the present disclosure, compared to the case where the entire range of a photographed image is matched with a template image, the processing time for pattern matching can be shortened and traffic notices can be quickly recognized. As a result, the information on the traffic bulletin board can be notified to the vehicle occupants at an appropriate timing.
　本開示の目的、特徴、態様、および利点は、以下の詳細な説明と添付図面とによって、より明白となる。 Objects, features, aspects, and advantages of the present disclosure will become more apparent from the following detailed description and accompanying drawings.
実施の形態１に係る掲示物認識システムの構成を示すブロック図である。1 is a block diagram showing the configuration of a notice recognition system according to Embodiment 1. FIG. 実施の形態１に係る掲示物認識装置の動作を示すフローチャートである。3 is a flowchart showing the operation of the notice recognition device according to the first embodiment. 道路標識のカメラに対する水平方向の角度および距離を示す図である。FIG. 3 is a diagram showing the horizontal angle and distance of a road sign with respect to a camera. 撮影画像中の認識対象範囲を示す図である。FIG. 3 is a diagram showing a recognition target range in a photographed image. 掲示物認識装置が交通掲示物からの電波を異なる３箇所で受信する様子を示す図である。FIG. 3 is a diagram showing how the notice recognition device receives radio waves from traffic notices at three different locations. ＨＵＤにおける交通掲示物情報の表示例を示す図である。It is a figure which shows the example of a display of traffic bulletin board information on HUD. 掲示物認識装置が反射波を受信することにより交通掲示物の位置を誤認識する様子を示す図である。FIG. 3 is a diagram illustrating how the notice recognition device incorrectly recognizes the position of a traffic notice by receiving reflected waves. 実施の形態２に係る掲示物認識システムの構成を示すブロック図である。FIG. 2 is a block diagram showing the configuration of a notice recognition system according to Embodiment 2. FIG. 実施の形態２に係る掲示物認識装置の動作を示すフローチャートである。7 is a flowchart showing the operation of the notice recognition device according to Embodiment 2. FIG. 掲示物認識装置が道路標識から受信した種別情報により、カメラの撮影画像とマッチングするテンプレート画像の優先順位を変更する様子を示す図である。FIG. 6 is a diagram illustrating how the notice recognition device changes the priority order of template images that match an image captured by a camera, based on type information received from a road sign. 実施の形態３に係る掲示物認識システムの構成を示すブロック図である。FIG. 3 is a block diagram showing the configuration of a notice recognition system according to Embodiment 3. FIG. 実施の形態３に係る掲示物認識装置の動作を示すフローチャートである。7 is a flowchart showing the operation of the notice recognition device according to Embodiment 3. 掲示物認識装置および道路標識のハードウェア構成を示す図である。It is a diagram showing the hardware configuration of a notice recognition device and a road sign.
　＜Ａ．実施の形態１＞
　＜Ａ－１．構成＞
　図１は、実施の形態１に係る掲示物認識システム１００１の構成を示すブロック図である。掲示物認識システム１００１は、交通掲示物２０１と車両３０１とを備えて構成される。 <A. Embodiment 1>
<A-1. Configuration>
FIG. 1 is a block diagram showing the configuration of a notice recognition system 1001 according to the first embodiment. The bulletin board recognition system 1001 includes a traffic bulletin board 201 and a vehicle 301.
　掲示物認識システム１００１は、車両３０１の周辺にある交通掲示物２０１を認識し、認識した交通掲示物２０１の情報を車両３０１の運転者に通知するシステムである。交通掲示物２０１は、運転者が円滑な交通を実施するために必要な交通情報を掲示する道路上に設置された掲示物である。交通掲示物２０１は、例えば信号機、道路標識、または道路標示である。以下の説明では、交通掲示物２０１を道路標識とする。 The bulletin board recognition system 1001 is a system that recognizes traffic bulletin boards 201 around the vehicle 301 and notifies the driver of the vehicle 301 of information about the recognized traffic bulletin boards 201. The traffic bulletin board 201 is a bulletin board placed on a road that displays traffic information necessary for drivers to drive smoothly. The traffic bulletin board 201 is, for example, a traffic light, a road sign, or a road marking. In the following description, the traffic bulletin board 201 is assumed to be a road sign.
　車両３０１には、掲示物認識装置１０１の他、カメラ５１、ディスプレイ５３、およびスピーカ５４が設けられる。図１では、掲示物認識装置１０１を車両３０１に搭載された装置として説明する。しかし、掲示物認識装置１０１の受信部１２以外の構成は必ずしも車両３０１に設けられていなくてもよく、例えば車両３０１の外部のサーバに設けられていてもよい。 In addition to the notice recognition device 101, the vehicle 301 is provided with a camera 51, a display 53, and a speaker 54. In FIG. 1, the notice recognition device 101 will be described as a device mounted on a vehicle 301. However, components other than the receiving unit 12 of the notice recognition device 101 do not necessarily have to be provided in the vehicle 301, and may be provided in a server outside the vehicle 301, for example.
　掲示物認識装置１０１は、カメラ５１、ディスプレイ５３、およびスピーカ５４と接続され、これらを利用可能に構成されている。 The bulletin board recognition device 101 is connected to a camera 51, a display 53, and a speaker 54, and is configured to be able to use these.
　カメラ５１は、車両３０１の周辺を撮影する。車両３０１の周辺とは、典型的には車両３０１の前方の道路を含み、例えば車両３０１から３００ｍ前方の地点までの範囲を含む。 The camera 51 photographs the surroundings of the vehicle 301. The area around the vehicle 301 typically includes the road in front of the vehicle 301, and includes, for example, a range up to a point 300 meters in front of the vehicle 301.
　ディスプレイ５３およびスピーカ５４は、掲示物認識装置１０１が認識した車両３０１の周辺の交通掲示物２０１の情報を、車両３０１の運転者に通知する出力装置である。ディスプレイ５３およびスピーカ５４のうちいずれか一方のみが掲示物認識装置１０１に備えられていてもよい。 The display 53 and the speaker 54 are output devices that notify the driver of the vehicle 301 of information on traffic bulletins 201 around the vehicle 301 recognized by the bulletin recognition device 101. The notice recognition device 101 may include only one of the display 53 and the speaker 54.
　ディスプレイ５３は、掲示物認識装置１０１が認識した車両３０１の周辺の交通掲示物２０１の情報を表示する。ディスプレイ５３は、例えばＣＩＤ（Ｃｅｎｔｅｒ　Ｉｎｆｏｒｍａｔｉｏｎ　Ｄｉｓｐｌａｙ）、またはＨＵＤ（Ｈｅａｄ－Ｕｐ　Ｄｉｓｐｌａｙ）である。 The display 53 displays information about the traffic bulletin board 201 around the vehicle 301 recognized by the bulletin recognition device 101. The display 53 is, for example, a CID (Center Information Display) or a HUD (Head-Up Display).
　スピーカ５４は、掲示物認識装置１０１が認識した車両３０１の周辺の交通掲示物２０１の情報を音声で出力する。ディスプレイ５３およびスピーカ５４は、いずれも車両３０１に搭載されており、ディスプレイ５３およびスピーカ５４により出力された交通掲示物２０１の情報を車両３０１の運転者が認識することができるように構成されている。 The speaker 54 outputs information on the traffic bulletin board 201 around the vehicle 301 recognized by the bulletin board recognition device 101 in audio. The display 53 and the speaker 54 are both mounted on the vehicle 301 and are configured so that the driver of the vehicle 301 can recognize the information on the traffic bulletin board 201 outputted by the display 53 and the speaker 54. .
　次に、掲示物認識装置１０１の構成を説明する。掲示物認識装置１０１は、画像取得部１１、受信部１２、掲示位置判断部１３、認識部１４、テンプレート格納部１５および出力制御部１６を備えて構成される。 Next, the configuration of the notice recognition device 101 will be explained. The notice recognition device 101 includes an image acquisition section 11 , a reception section 12 , a notice position determination section 13 , a recognition section 14 , a template storage section 15 , and an output control section 16 .
　画像取得部１１は、カメラ５１から車両３０１の周辺の撮影画像を取得する。 The image acquisition unit 11 acquires captured images of the surroundings of the vehicle 301 from the camera 51.
　受信部１２は、交通掲示物２０１との無線通信を行う。受信部１２は、交通掲示物２０１から送信される電波を受信し、当該電波を復調した復調信号を掲示位置判断部１３に出力する。交通掲示物２０１から送信される電波には、当該電波の送信元が交通掲示物２０１であることを表す識別信号が含まれている。受信部１２はこの識別信号を復調し、掲示位置判断部１３に出力する。言い換えれば、受信部１２は交通掲示物２０１から識別信号を受信する。 The receiving unit 12 performs wireless communication with the traffic bulletin board 201. The receiving unit 12 receives radio waves transmitted from the traffic bulletin board 201, demodulates the radio waves, and outputs a demodulated signal to the bulletin position determining unit 13. The radio wave transmitted from the traffic bulletin board 201 includes an identification signal indicating that the transmission source of the radio wave is the traffic bulletin board 201. The receiving section 12 demodulates this identification signal and outputs it to the notice position determining section 13. In other words, the receiving unit 12 receives the identification signal from the traffic bulletin board 201.
　掲示位置判断部１３は、受信部１２が交通掲示物２０１から受信した識別信号に基づき、車両３０１に対する交通掲示物２０１の相対位置を判断する。掲示位置判断部１３が判断する交通掲示物２０１の相対位置は、車両３０１に対する交通掲示物２０１の方向と、車両３０１と交通掲示物２０１との距離を含む。 The bulletin position determining unit 13 determines the relative position of the traffic bulletin board 201 with respect to the vehicle 301 based on the identification signal received from the traffic bulletin board 201 by the receiving unit 12. The relative position of the traffic bulletin board 201 determined by the bulletin position determination unit 13 includes the direction of the traffic bulletin board 201 with respect to the vehicle 301 and the distance between the vehicle 301 and the traffic bulletin board 201.
　テンプレート格納部１５には、交通掲示物２０１の種別ごとのテンプレート画像が複数格納されている。交通掲示物２０１のテンプレート画像は、交通掲示物２０１の外観の画像である。交通掲示物２０１は、上述のとおり信号機、道路標識、および道路標示に分類される。信号機については、歩行者用信号機または縦型信号機など、異なる形状ごとに異なる種別と捉えてテンプレート画像が格納されていてもよい。道路標識および道路標示については、それらの種別ごとにテンプレート画像が格納される。 The template storage unit 15 stores a plurality of template images for each type of traffic bulletin board 201. The template image of the traffic bulletin board 201 is an image of the appearance of the traffic bulletin board 201. The traffic bulletin board 201 is classified into traffic lights, road signs, and road markings as described above. Template images may be stored for different shapes of traffic lights, such as pedestrian traffic lights or vertical traffic lights. Template images are stored for each type of road signs and road markings.
　認識部１４は、画像取得部１１から車両３０１の周辺の撮影画像を取得し、掲示位置判断部１３から取得した交通掲示物２０１の車両３０１に対する相対位置に基づき、撮影画像において交通掲示物２０１が映っていると思われる領域を対象領域と特定する。そして、認識部１４は、撮影画像の対象領域のみをテンプレート格納部１５に格納された複数のテンプレート画像とパターンマッチングし、あるテンプレート画像が対象領域に一致すると、当該テンプレート画像の種別の交通掲示物２０１が車両３０１の周辺にあると認識する。そして、認識部１４は、認識した交通掲示物２０１の種別と、交通掲示物２０１の車両３０１に対する相対位置とを出力制御部１６に出力する。 The recognition unit 14 acquires a photographed image of the surroundings of the vehicle 301 from the image acquisition unit 11, and determines whether the traffic bulletin 201 is located in the photographed image based on the relative position of the traffic bulletin 201 with respect to the vehicle 301 acquired from the bulletin position determination unit 13. The area that appears to be reflected is identified as the target area. Then, the recognition unit 14 pattern-matches only the target area of the photographed image with a plurality of template images stored in the template storage unit 15, and when a certain template image matches the target area, the recognition unit 14 performs pattern matching on only the target area of the photographed image, and when a certain template image matches the target area, a traffic sign of the type of the template image is detected. 201 is recognized as being in the vicinity of vehicle 301. Then, the recognition unit 14 outputs the recognized type of traffic bulletin board 201 and the relative position of the traffic bulletin board 201 with respect to the vehicle 301 to the output control unit 16.
　認識部１４が撮影画像の対象領域とパターンマッチングを行うテンプレート画像の順番（以下、「マッチング順番」と称する）は予め定められている。認識部１４はマッチング順番に沿ってテンプレート格納部１５から所望のテンプレート画像を取得し、当該テンプレート画像を撮影画像の対象領域とパターンマッチングする。両者が一致しなければ、認識部１４は次のテンプレート画像をテンプレート格納部１５から取得し、撮影画像の対象領域とパターンマッチングする。なお、認識部１４は１枚ずつパターンマッチングを行ってもよいし、複数枚の単位でパターンマッチングを行ってもよい。 The order of template images in which the recognition unit 14 performs pattern matching with the target area of the captured image (hereinafter referred to as "matching order") is predetermined. The recognition unit 14 acquires a desired template image from the template storage unit 15 in accordance with the matching order, and pattern-matches the template image with the target area of the photographed image. If the two do not match, the recognition unit 14 acquires the next template image from the template storage unit 15 and performs pattern matching with the target area of the photographed image. Note that the recognition unit 14 may perform pattern matching for one sheet at a time, or may perform pattern matching for a plurality of sheets.
　マッチング順番は、例えば運転者が交通掲示物２０１を見逃すリスクの大きい順に定められる。例えば、交通掲示物２０１が道路標識である場合、「車両進入禁止」の道路標識のテンプレート画像、速度に関する道路標識のテンプレート画像、一時停止の道路標識のテンプレート画像の順にマッチング順番が定められていてもよい。運転者が交通掲示物２０１を見逃すリスクの大小は、交通掲示物２０１で掲示された交通ルールに違反したときの罰金の額により定められてもよい。 The matching order is determined, for example, in descending order of the risk that the driver will miss the traffic bulletin board 201. For example, if the traffic bulletin board 201 is a road sign, the matching order is determined in the following order: a template image of a road sign "No Vehicles Entry", a template image of a road sign related to speed, and a template image of a stop road sign. Good too. The magnitude of the risk that the driver will miss the traffic bulletin board 201 may be determined by the amount of a fine for violating the traffic rules posted on the traffic bulletin board 201.
　出力制御部１６は、認識部１４による交通掲示物２０１の認識結果と、交通掲示物２０１の車両３０１に対する相対位置とを認識部１４から取得し、これらをディスプレイ５３またはスピーカ５４から出力させる。 The output control unit 16 acquires the recognition result of the traffic bulletin board 201 by the recognition unit 14 and the relative position of the traffic bulletin board 201 with respect to the vehicle 301 from the recognition unit 14, and outputs these from the display 53 or the speaker 54.
　次に、交通掲示物２０１の構成を説明する。交通掲示物２０１は、送信部２１および制御部２２を備えて構成される。 Next, the configuration of the traffic bulletin board 201 will be explained. The traffic bulletin board 201 includes a transmitter 21 and a controller 22.
　送信部２１は、掲示物認識装置１０１の受信部１２と無線通信を行う。送信部２１は、制御部２２の指示を受けて、受信部１２に対して交通掲示物２０１の識別信号を送信する。識別信号は、少なくとも送信元が交通掲示物であることを表す情報を含む。送信部２１は、例えば一定周期で識別信号を受信部１２に送信する。 The transmitter 21 performs wireless communication with the receiver 12 of the notice recognition device 101. The transmitter 21 receives an instruction from the controller 22 and transmits an identification signal for the traffic bulletin board 201 to the receiver 12 . The identification signal includes at least information indicating that the transmission source is a traffic bulletin board. The transmitting section 21 transmits the identification signal to the receiving section 12, for example, at regular intervals.
　制御部２２は、送信部２１による識別信号の送信を制御する。 The control unit 22 controls the transmission of the identification signal by the transmitting unit 21.
　＜Ａ－２．動作＞
　図２は、掲示物認識装置１０１の動作を示すフローチャートである。以下、図２のフローに沿って掲示物認識装置１０１の動作を説明する。図２のフローは、例えば車両３０１の走行開始と共に開始する。 <A-2. Operation＞
FIG. 2 is a flowchart showing the operation of the notice recognition device 101. The operation of the notice recognition device 101 will be described below along the flowchart of FIG. 2. The flow in FIG. 2 starts, for example, when the vehicle 301 starts traveling.
　まず、ステップＳ１０１において、受信部１２が識別信号を受信したか否かを判断する。ステップＳ１０１において受信部１２が識別信号を受信していなければ、掲示物認識装置１０１の処理はステップＳ１０５に進む。 First, in step S101, it is determined whether the receiving unit 12 has received an identification signal. If the receiving unit 12 has not received the identification signal in step S101, the process of the notice recognition device 101 proceeds to step S105.
　ステップＳ１０５において、認識部１４は画像取得部１１が取得したカメラ５１の撮影画像の全範囲を、テンプレート格納部１５に格納された複数のテンプレート画像と、デフォルトのマッチング順番に従い順番にパターンマッチングする。デフォルトのマッチング順番（優先順位）は、例えば運転者が交通掲示物２０１を見逃した場合のリスクが大きい順に定められる。ここで、リスクとは、例えば交通掲示物２０１が掲示する交通情報に違反した場合の罰金額である。テンプレート画像に一致するパターンが撮影画像中にあれば、認識部１４はその時点でパターンマッチングを終了し、掲示物認識装置１０１の処理はステップＳ１０６に進む。撮影画像中のパターンがテンプレート画像に一致すれば、認識部１４は、そのテンプレート画像に対応する交通掲示物が撮影画像中の一致したパターンに対応する位置に存在するものと判断する。すなわち、認識部１４は一致したテンプレート画像に対応する交通掲示物２０１を検知する。認識部１４はその時点でパターンマッチングを終了し、掲示物認識装置１０１の処理はステップＳ１０６に進む。また、認識部１４は、全てのテンプレート画像についてパターンマッチングを行っても撮影画像の対象範囲と一致しなければ、パターンマッチングを終了し、掲示物認識装置１０１の処理はステップＳ１０６に進む。 In step S105, the recognition unit 14 sequentially performs pattern matching on the entire range of the image captured by the camera 51 acquired by the image acquisition unit 11 with the plurality of template images stored in the template storage unit 15 according to the default matching order. The default matching order (priority order) is determined, for example, in descending order of risk if the driver misses the traffic bulletin board 201. Here, the risk is, for example, the amount of a fine if the traffic information posted by the traffic bulletin board 201 is violated. If there is a pattern in the photographed image that matches the template image, the recognition unit 14 ends the pattern matching at that point, and the process of the notice recognition device 101 proceeds to step S106. If the pattern in the photographed image matches the template image, the recognition unit 14 determines that the traffic bulletin board corresponding to the template image exists at the position corresponding to the matched pattern in the photographed image. That is, the recognition unit 14 detects the traffic bulletin board 201 corresponding to the matched template image. The recognition unit 14 ends the pattern matching at that point, and the process of the notice recognition device 101 proceeds to step S106. Further, if the recognition unit 14 does not match the target range of the photographed image even after performing pattern matching on all template images, the recognition unit 14 ends the pattern matching, and the process of the notice recognition device 101 proceeds to step S106.
　ステップＳ１０１において受信部１２が識別信号を受信している場合、掲示物認識装置１０１の処理はステップＳ１０２に進む。 If the receiving unit 12 has received the identification signal in step S101, the process of the notice recognition device 101 proceeds to step S102.
　ステップＳ１０２において、掲示位置判断部１３は受信部１２が受信した識別信号に基づき、交通掲示物２０１の車両３０１に対する相対位置を推定する。具体的には、掲示位置判断部１３は、受信部１２が受信した識別信号の電波強度に基づき、交通掲示物２０１の車両３０１に対する方向および距離を算出する。 In step S102, the notice position determining unit 13 estimates the relative position of the traffic notice 201 with respect to the vehicle 301 based on the identification signal received by the receiving unit 12. Specifically, the bulletin position determination unit 13 calculates the direction and distance of the traffic bulletin board 201 with respect to the vehicle 301 based on the radio wave intensity of the identification signal received by the receiving unit 12.
　図３は、識別信号の電波強度により交通掲示物２０１の位置を算出する方法を示す図である。例えば、図３に示されるように、車両３０１の走行に伴い、受信部１２は異なる３つの位置で交通掲示物２０１からの電波を受信する。まず、受信部１２が１回目に受信した電波の強度により、受信地点から半径５０ｍの円６２上に交通掲示物２０１があることが分かる。次に、受信部１２が２回目に受信した電波の強度により、受信地点から半径４０ｍの円６３上に交通掲示物２０１があることが分かる。さらに、受信部１２が３回目に受信した電波の強度により、受信地点から半径３０ｍの円６４上に交通掲示物２０１があることが分かる。従って、交通掲示物２０１の位置が円６２，６３，６４の交点に特定される。 FIG. 3 is a diagram showing a method of calculating the position of the traffic bulletin board 201 based on the radio wave intensity of the identification signal. For example, as shown in FIG. 3, as the vehicle 301 travels, the receiving unit 12 receives radio waves from the traffic bulletin board 201 at three different positions. First, it can be seen from the intensity of the first radio wave received by the receiving unit 12 that the traffic bulletin board 201 is located on a circle 62 with a radius of 50 m from the receiving point. Next, based on the intensity of the second radio wave received by the receiver 12, it can be seen that the traffic bulletin board 201 is located on a circle 63 with a radius of 40 m from the receiving point. Further, based on the intensity of the radio wave received by the receiving unit 12 for the third time, it can be seen that the traffic bulletin board 201 is located on the circle 64 with a radius of 30 m from the receiving point. Therefore, the position of the traffic bulletin board 201 is specified at the intersection of circles 62, 63, and 64.
　図２のフローチャートの説明に戻る。ステップＳ１０２の後、ステップＳ１０３において、認識部１４は、掲示位置判断部１３が推定した交通掲示物２０１の相対位置に基づき、カメラ５１の撮影画像の一部をパターンマッチングの対象範囲として特定する。 Returning to the explanation of the flowchart in FIG. 2. After step S102, in step S103, the recognition unit 14 identifies a part of the image taken by the camera 51 as a pattern matching target range based on the relative position of the traffic bulletin board 201 estimated by the bulletin position determination unit 13.
　図４は、車両３０１に搭載されたカメラ５１と交通掲示物２０１との水平方向の位置関係を示している。カメラ５１の水平方向の画角をθ１とする。カメラ５１は車両３０１の進行方向に向けて設置されているものとする。交通掲示物２０１とカメラ５１とを結ぶ線が車両３０１の進行方向に対してなす水平方向の角を、交通掲示物２０１の水平偏角θ２とする。 FIG. 4 shows the horizontal positional relationship between the camera 51 mounted on the vehicle 301 and the traffic bulletin board 201. The horizontal angle of view of the camera 51 is assumed to be θ1. It is assumed that the camera 51 is installed facing the direction of travel of the vehicle 301. The horizontal angle that the line connecting the traffic bulletin board 201 and the camera 51 makes with respect to the traveling direction of the vehicle 301 is defined as the horizontal deviation angle θ2 of the traffic bulletin board 201.
　図５は、カメラ５１の撮影画像中の対象範囲６１を示している。対象範囲６１の撮影画像における左右方向の位置は、カメラ５１の水平方向の画角θ１と、交通掲示物２０１の水平偏角θ２に基づき定められる。なお、対象範囲６１の撮影画像における上下方向の位置は、カメラ５１の垂直方向の画角と、交通掲示物２０１の車両３０１との距離とに基づき定められる。 FIG. 5 shows a target range 61 in an image taken by the camera 51. The horizontal position of the target range 61 in the photographed image is determined based on the horizontal angle of view θ1 of the camera 51 and the horizontal declination angle θ2 of the traffic bulletin board 201. Note that the vertical position of the target range 61 in the captured image is determined based on the vertical viewing angle of the camera 51 and the distance between the traffic bulletin board 201 and the vehicle 301.
　図２のフローチャートの説明に戻る。ステップＳ１０３の後、ステップＳ１０４において、認識部１４は、カメラ５１の撮影画像の対象範囲を、テンプレート格納部１５に格納された複数のテンプレート画像と、デフォルトのマッチング順番に従い順番にパターンマッチングする。撮影画像の対象範囲中のパターンがテンプレート画像に一致すれば、認識部１４は、そのテンプレート画像に対応する交通掲示物が対象範囲中の一致したパターンに対応する位置に存在するものと判断する。すなわち、認識部１４は一致したテンプレート画像に対応する交通掲示物２０１を検知する。認識部１４はその時点でパターンマッチングを終了し、掲示物認識装置１０１の処理はステップＳ１０６に進む。また、認識部１４は、全てのテンプレート画像についてパターンマッチングを行っても撮影画像の対象範囲と一致しなければ、パターンマッチングを終了し、掲示物認識装置１０１の処理はステップＳ１０６に進む。 Returning to the explanation of the flowchart in FIG. 2. After step S103, in step S104, the recognition unit 14 sequentially performs pattern matching on the target range of the captured image of the camera 51 with a plurality of template images stored in the template storage unit 15 according to a default matching order. If the pattern in the target range of the photographed image matches the template image, the recognition unit 14 determines that the traffic bulletin board corresponding to the template image exists at the position corresponding to the matched pattern in the target range. That is, the recognition unit 14 detects the traffic bulletin board 201 corresponding to the matching template image. The recognition unit 14 ends the pattern matching at that point, and the process of the notice recognition device 101 proceeds to step S106. Further, if the recognition unit 14 does not match the target range of the photographed image even after performing pattern matching on all template images, the recognition unit 14 ends the pattern matching, and the process of the notice recognition device 101 proceeds to step S106.
　ステップＳ１０４またはステップＳ１０５におけるパターンマッチングの後、ステップＳ１０６において、認識部１４は交通掲示物２０１を検知したか否かを判断する。ステップＳ１０６において交通掲示物２０１を検知していなければ、掲示物認識装置１０１の処理はステップＳ１０８に戻る。ステップＳ１０６において交通掲示物２０１を検知していれば、掲示物認識装置１０１の処理はステップＳ１０７に進む。 After pattern matching in step S104 or step S105, in step S106, the recognition unit 14 determines whether or not the traffic bulletin board 201 has been detected. If the traffic bulletin board 201 is not detected in step S106, the processing of the bulletin board recognition device 101 returns to step S108. If the traffic bulletin board 201 is detected in step S106, the processing of the bulletin board recognition device 101 proceeds to step S107.
　ステップＳ１０７において、出力制御部１６は認識部１４から検知した交通掲示物２０１の種別および位置情報を取得し、それらの情報をディスプレイ５３またはスピーカ５４から出力させる。 In step S107, the output control unit 16 acquires the type and position information of the detected traffic bulletin board 201 from the recognition unit 14, and outputs this information from the display 53 or the speaker 54.
　図６は、ディスプレイ５３の一例であるＨＵＤにおける交通掲示物２０１の種別および位置の表示例を示している。図６は、認識部１４が車両３０１の前方道路上の制限速度、一時停止および横断歩道の道路標識を検知した場合の表示例である。道路標識を囲むように二重の破線枠がＨＵＤの領域上に表示されている。また、制限速度の道路標識については、現在の車両３０１の速度とあわせて当該道路標識を表示する表示オブジェクト６５が車両３０１の前方道路に重畳するＨＵＤの領域に表示されている。これにより、運転者は車両３０１前方の道路標識を認識し、道路標識に沿った運転を心がけることができる。 FIG. 6 shows an example of display of the type and position of the traffic bulletin board 201 on the HUD, which is an example of the display 53. FIG. 6 is a display example when the recognition unit 14 detects speed limit, stop, and crosswalk road signs on the road ahead of the vehicle 301. A double broken line frame is displayed on the HUD area so as to surround the road sign. Furthermore, regarding the speed limit road sign, a display object 65 that displays the road sign along with the current speed of the vehicle 301 is displayed in an area of the HUD superimposed on the road ahead of the vehicle 301. Thereby, the driver can recognize the road signs in front of the vehicle 301 and try to drive in accordance with the road signs.
　図２のフローチャートの説明に戻る。ステップＳ１０７の後、ステップＳ１０８において、掲示物認識装置１０１は車両３０１の走行が終了したか否かを判断する。ステップＳ１０８において車両３０１の走行が終了していなければ、掲示物認識装置１０１の処理はステップＳ１０１に戻る。ステップＳ１０８において車両３０１の走行が終了していれば、掲示物認識装置１０１の処理は終了する。 Returning to the explanation of the flowchart in FIG. 2. After step S107, in step S108, the notice recognition device 101 determines whether or not the vehicle 301 has finished traveling. If the vehicle 301 has not finished traveling in step S108, the process of the notice recognition device 101 returns to step S101. If the vehicle 301 has finished traveling in step S108, the processing of the notice recognition device 101 ends.
　＜Ａ－３．変形例＞
　図７に示すように、交通掲示物２０１が送信した電波は、直接波として車両３０１に到達する他、建物に反射した反射波として車両３０１に到達する場合もある。そのため、掲示物認識装置１０１が反射波の到来方向を交通掲示物２０１の方向と誤認識してしまったり、減衰した反射波の電波強度により交通掲示物２０１までの距離を短く誤認識してしまったりする可能性がある。 <A-3. Modified example>
As shown in FIG. 7, the radio waves transmitted by the traffic bulletin board 201 reach the vehicle 301 as direct waves, and may also reach the vehicle 301 as reflected waves reflected from buildings. Therefore, the notice recognition device 101 may mistakenly recognize the arrival direction of the reflected wave as the direction of the traffic notice 201, or may incorrectly recognize the distance to the traffic notice 201 as being short due to the attenuated radio wave intensity of the reflected wave. There is a possibility of relaxing.
　そこで、交通掲示物２０１の送信部２１から送信される標識信号の電波には、交通掲示物２０１が掲示する交通情報の対象道路への指向性を持たせることが望ましい。これにより、掲示物認識装置１０１において反射波により交通掲示物２０１の位置を誤認識することが抑制される。 Therefore, it is desirable that the radio waves of the sign signal transmitted from the transmitter 21 of the traffic bulletin board 201 have directivity toward the target road of the traffic information posted by the traffic bulletin board 201. This prevents the notice recognition device 101 from erroneously recognizing the position of the traffic notice 201 due to reflected waves.
　＜Ａ－４．効果＞
　実施の形態１に係る掲示物認識装置１０１は、車両３０１の周辺の撮影画像を取得する画像取得部１１と、車両３０１に搭載され、道路上に設置された交通掲示物２０１から送信される識別信号を受信する受信部１２と、識別信号に基づき、交通掲示物２０１の車両に対する方向を少なくとも含む交通掲示物２０１の位置情報を推定する掲示位置判断部１３と、交通掲示物２０１の種類別に用意された複数のテンプレート画像を予め定められた優先順位に従い撮影画像とパターンマッチングすることにより、撮影画像に映った交通掲示物２０１を認識する認識部１４と、を備える。認識部１４は、掲示位置判断部１３が推定した交通掲示物２０１の位置情報に基づき、撮影画像の一部の範囲を交通掲示物２０１が撮影された対象範囲と特定し、対象範囲をパターンマッチングの対象とする。 <A-4. Effect>
The bulletin board recognition device 101 according to the first embodiment includes an image acquisition unit 11 that acquires captured images of the surroundings of a vehicle 301, and an identification device 11 that acquires a photographed image of the surroundings of a vehicle 301, and an identification device that is transmitted from a traffic bulletin board 201 mounted on the vehicle 301 and installed on the road. A receiving unit 12 that receives a signal, a bulletin board position determining unit 13 that estimates position information of the traffic bulletin board 201 including at least the direction of the traffic bulletin board 201 with respect to the vehicle based on the identification signal, and a bulletin board position determination unit 13 that is prepared for each type of traffic bulletin board 201. The present invention includes a recognition unit 14 that recognizes the traffic bulletin board 201 shown in the photographed image by pattern matching the plurality of template images taken with the photographed image according to a predetermined priority order. Based on the position information of the traffic bulletin board 201 estimated by the bulletin position determination unit 13, the recognition unit 14 identifies a part of the captured image as the target range in which the traffic bulletin board 201 was photographed, and performs pattern matching on the target range. be subject to.
　従って、掲示物認識装置１０１によれば、撮影画像の全範囲をテンプレート画像とパターンマッチングする場合に比べて、パターンマッチングの処理時間を短縮することができる。その結果、交通掲示物２０１を迅速に認識し、適切なタイミングで運転者に交通掲示物２０１の情報を通知することが可能となる。 Therefore, according to the bulletin board recognition device 101, the processing time for pattern matching can be shortened compared to the case where the entire range of a photographed image is pattern matched with a template image. As a result, it becomes possible to quickly recognize the traffic bulletin board 201 and notify the driver of the information on the traffic bulletin board 201 at an appropriate timing.
　また、実施の形態１に係る掲示物認識装置１０１において、受信部１２が受信する識別信号は、車両３０１の異なる３か所以上の走行位置において受信された３つ以上の識別信号を含んでもよい。この場合、掲示物認識装置１０１は高精度に交通掲示物２０１の位置を推定することができる。 Further, in the notice recognition device 101 according to the first embodiment, the identification signal received by the receiving unit 12 may include three or more identification signals received at three or more different traveling positions of the vehicle 301. . In this case, the bulletin board recognition device 101 can estimate the position of the traffic bulletin board 201 with high accuracy.
　また、周辺の交通掲示物２０１から識別信号を送信する際に用いられる電波は、周辺の交通掲示物の対象道路に対する指向性を有していてもよい。この場合、掲示物認識装置１０１が建物などの反射波の受信強度または到来方向に基づき交通掲示物２０１の位置を誤認識することを抑制することができる。 Furthermore, the radio waves used when transmitting the identification signal from the surrounding traffic bulletin board 201 may have directivity with respect to the target road of the nearby traffic bulletin board. In this case, it is possible to prevent the notice recognition device 101 from erroneously recognizing the position of the traffic notice 201 based on the received intensity of reflected waves from buildings or the like or the direction of arrival.
　実施の形態１に係る掲示物認識システムは、道路上に設置され識別信号を送信する交通掲示物２０１と、車両３０１の周辺の交通掲示物を認識する掲示物認識装置１０１と、を備える。従って、実施の形態１に係る掲示物認識システムによれば、撮影画像の全範囲をテンプレート画像とパターンマッチングする場合に比べて、パターンマッチングの処理時間を短縮することができる。その結果、交通掲示物２０１を迅速に認識し、適切なタイミングで運転者に交通掲示物２０１の情報を通知することが可能となる。 The bulletin board recognition system according to the first embodiment includes a traffic bulletin board 201 that is installed on a road and transmits an identification signal, and a bulletin board recognition device 101 that recognizes traffic bulletin boards around a vehicle 301. Therefore, according to the bulletin board recognition system according to the first embodiment, the processing time for pattern matching can be reduced compared to the case where the entire range of a photographed image is pattern matched with a template image. As a result, it becomes possible to quickly recognize the traffic bulletin board 201 and notify the driver of the information on the traffic bulletin board 201 at an appropriate timing.
　実施の形態１に係る掲示物認識方法は、画像取得部１１が、車両３０１の周辺の撮影画像を取得し、車両３０１に搭載された受信部１２が、道路上に設置された交通掲示物２０１から送信される識別信号を受信し、掲示位置判断部１３が、識別信号に基づき、交通掲示物２０１の車両３０１に対する位置を表す交通掲示物２０１の位置情報を推定し、認識部１４が、交通掲示物２０１の種類別に用意された複数のテンプレート画像を予め定められた優先順位に従い撮影画像とパターンマッチングすることにより、撮影画像に映った交通掲示物２０１を認識し、掲示位置判断部１３が推定した交通掲示物２０１の位置情報に基づき、認識部１４が撮影画像の一部の範囲を交通掲示物２０１が撮影された対象範囲と特定し、対象範囲をパターンマッチングの対象とする。従って、実施の形態１に係る掲示物認識方法によれば、撮影画像の全範囲をテンプレート画像とパターンマッチングする場合に比べて、パターンマッチングの処理時間を短縮することができる。その結果、交通掲示物２０１を迅速に認識し、適切なタイミングで運転者に交通掲示物２０１の情報を通知することが可能となる。 In the bulletin board recognition method according to the first embodiment, an image acquisition unit 11 acquires a captured image of the surroundings of a vehicle 301, and a reception unit 12 mounted on the vehicle 301 detects a traffic bulletin board 201 installed on a road. The notice position determination unit 13 estimates the position information of the traffic notice 201 indicating the position of the traffic notice 201 with respect to the vehicle 301 based on the identification signal, and the recognition unit 14 estimates the position information of the traffic notice 201 indicating the position of the traffic notice 201 with respect to the vehicle By pattern matching a plurality of template images prepared for each type of bulletin board 201 with the photographed image according to a predetermined priority order, the traffic bulletin board 201 shown in the photographed image is recognized, and the bulletin position determination unit 13 estimates the position of the traffic bulletin board 201. Based on the position information of the traffic bulletin board 201, the recognition unit 14 identifies a part of the photographed image as the target range in which the traffic bulletin board 201 was photographed, and sets the target range as a target for pattern matching. Therefore, according to the bulletin board recognition method according to the first embodiment, the processing time for pattern matching can be shortened compared to the case where the entire range of a photographed image is pattern matched with a template image. As a result, it becomes possible to quickly recognize the traffic bulletin board 201 and notify the driver of the information on the traffic bulletin board 201 at an appropriate timing.
　＜Ｂ．実施の形態２＞
　＜Ｂ－１．構成＞
　図８は、実施の形態２に係る掲示物認識システム１００２の構成を示すブロック図である。掲示物認識システム１００２は、交通掲示物２０２と車両３０１とを備えて構成される。本実施の形態では、実施の形態１と同一の構成に同一の参照符号を付し、実施の形態１と共通する部分の説明を適宜省略する。 <B. Embodiment 2>
<B-1. Configuration>
FIG. 8 is a block diagram showing the configuration of a notice recognition system 1002 according to the second embodiment. The bulletin board recognition system 1002 includes a traffic bulletin board 202 and a vehicle 301. In this embodiment, the same reference numerals are given to the same components as in Embodiment 1, and explanations of parts common to Embodiment 1 are omitted as appropriate.
　交通掲示物２０２は、実施の形態１に係る交通掲示物２０１の構成に加えて識別信号格納部２３を備える。識別信号格納部２３には、交通掲示物２０２の種別を表す種別情報２３１が格納されている。 The traffic bulletin board 202 includes an identification signal storage section 23 in addition to the configuration of the traffic bulletin board 201 according to the first embodiment. The identification signal storage unit 23 stores type information 231 indicating the type of traffic bulletin board 202.
　送信部２１は、制御部２２の指示を受けて、交通掲示物２０２の識別信号を送信する。この識別信号には種別情報２３１が含まれる。すなわち、送信部２１は識別信号格納部２３から種別情報２３１を取り出し、種別情報２３１を識別信号に含めて送信する。 The transmitting unit 21 transmits the identification signal of the traffic bulletin board 202 in response to instructions from the control unit 22. This identification signal includes type information 231. That is, the transmitting unit 21 retrieves the type information 231 from the identification signal storage unit 23, includes the type information 231 in the identification signal, and transmits the identification signal.
　掲示物認識システム１００２において、車両３０１には、掲示物認識装置１０２の他、カメラ５１、ディスプレイ５３、およびスピーカ５４が設けられる。 In the bulletin board recognition system 1002, the vehicle 301 is provided with a camera 51, a display 53, and a speaker 54 in addition to the bulletin board recognition device 102.
　掲示物認識装置１０２は、実施の形態１に係る掲示物認識装置１０１の構成と同様であるが、認識部１４の処理が一部異なる。本実施の形態の認識部１４は、受信部１２が受信した識別信号に含まれる種別情報２３１に応じて、パターンマッチングを行うテンプレート画像の優先順位をデフォルトから変更する。具体的には、認識部１４は、種別情報２３１に示される種別の交通掲示物２０２のテンプレート画像が最優先でパターンマッチングされるよう、優先順位を変更する。 The bulletin board recognition device 102 has the same configuration as the bulletin board recognition device 101 according to Embodiment 1, but the processing of the recognition unit 14 is partially different. The recognition unit 14 of this embodiment changes the priority order of template images to be pattern matched from the default according to the type information 231 included in the identification signal received by the reception unit 12. Specifically, the recognition unit 14 changes the priority order so that the template image of the traffic bulletin board 202 of the type indicated by the type information 231 is pattern matched with the highest priority.
　＜Ｂ－２．動作＞
　図９は、掲示物認識装置１０２の動作を示すフローチャートである。図９のフローは、例えば車両３０１の走行開始と共に開始する。図９のフローは、実施の形態１で説明した図２のフローのステップＳ１０３とステップＳ１０４との間にステップＳ２０１，Ｓ２０２を追加したものである。 <B-2. Operation＞
FIG. 9 is a flowchart showing the operation of the notice recognition device 102. The flow in FIG. 9 starts, for example, when the vehicle 301 starts traveling. The flow in FIG. 9 is obtained by adding steps S201 and S202 between step S103 and step S104 in the flow in FIG. 2 described in the first embodiment.
　ステップＳ２０１において認識部１４は、受信部１２が受信した識別信号に種別情報２３１が含まれるか否かを判断する。ステップＳ２０１において識別信号に種別情報２３１が含まれる場合、掲示物認識装置１０２の処理はステップＳ２０２に移行する。 In step S201, the recognition unit 14 determines whether the type information 231 is included in the identification signal received by the reception unit 12. If the type information 231 is included in the identification signal in step S201, the process of the notice recognition device 102 moves to step S202.
　ステップＳ２０２において認識部１４は、撮影画像の対象範囲とパターンマッチングするテンプレート画像の優先順位をデフォルトから変更する。 In step S202, the recognition unit 14 changes the priority order of the template image that pattern matches the target range of the photographed image from the default.
　図１０は、優先順位の変更例を示す図である。図１０の例において、受信部１２が送信部２１から受信した道路標識の識別信号に、道路標識の種別情報２３１が含まれているものとする。また、種別情報２３１は、道路標識の種別として速度制限の道路標識を示すものとする。認識部１４は、速度制限の道路標識のテンプレート画像が最優先になるよう、テンプレート画像の優先順位を変更する。例えば、進入禁止の道路標識、速度制限の道路標識、一時停止の道路標識、の順が、テンプレート画像のマッチングのデフォルトの優先順位として定められている場合、認識部１４は、優先順位を、速度制限の道路標識、進入禁止の道路標識、一時停止の道路標識、の順に変更する。 FIG. 10 is a diagram showing an example of changing the priority order. In the example of FIG. 10, it is assumed that the road sign identification signal received by the receiving unit 12 from the transmitting unit 21 includes road sign type information 231. Further, the type information 231 indicates a speed limit road sign as the type of road sign. The recognition unit 14 changes the priority order of the template images so that the template image of the speed limit road sign has the highest priority. For example, if the default order of priority for template image matching is set in the following order: No Entry Road Sign, Speed Limit Road Sign, Stop Road Sign, the recognition unit 14 determines the priority order by speed Change in the order of restriction road signs, no entry road signs, and stop road signs.
　＜Ｂ－３．効果＞
　実施の形態２において、交通掲示物２０２から送信される識別信号は、交通掲示物２０２の種別を表す種別情報を含む。そして、掲示物認識装置１０２の認識部１４は、種別情報に表された種別の交通掲示物２０２のテンプレート画像が最優先となるようテンプレート画像のパターンマッチングの優先順位を変更する。これにより、認識部１４は撮影画像とテンプレート画像とのパターンマッチングの処理時間を短縮することができる。その結果、その結果、掲示物認識装置１０２は交通掲示物２０２を迅速に認識し、適切なタイミングで運転者に交通掲示物２０２の情報を通知することが可能となる。 <B-3. Effect>
In the second embodiment, the identification signal transmitted from the traffic bulletin board 202 includes type information indicating the type of the traffic bulletin board 202. Then, the recognition unit 14 of the bulletin board recognition device 102 changes the priority order of pattern matching of template images so that the template image of the traffic bulletin board 202 of the type represented by the type information has the highest priority. Thereby, the recognition unit 14 can shorten the processing time for pattern matching between the photographed image and the template image. As a result, the bulletin board recognition device 102 can quickly recognize the traffic bulletin board 202 and notify the driver of the information on the traffic bulletin board 202 at an appropriate timing.
　＜Ｃ．実施の形態３＞
　＜Ｃ－１．構成＞
　図１１は、実施の形態３に係る掲示物認識システム１００３の構成を示すブロック図である。掲示物認識システム１００３は、交通掲示物２０３と車両３０１とを備えて構成される。本実施の形態では、実施の形態１，２と同一の構成に同一の参照符号を付し、実施の形態１，２と共通する部分の説明を適宜省略する。 <C. Embodiment 3>
<C-1. Configuration>
FIG. 11 is a block diagram showing the configuration of a notice recognition system 1003 according to the third embodiment. The bulletin board recognition system 1003 includes a traffic bulletin board 203 and a vehicle 301. In this embodiment, the same reference numerals are given to the same components as in Embodiments 1 and 2, and descriptions of parts common to Embodiments 1 and 2 are omitted as appropriate.
　実施の形態３の交通掲示物２０３は、識別信号格納部２３に格納される格納情報が実施の形態２の交通掲示物２０２とは異なる。交通掲示物２０３の識別信号格納部２３は、種別情報２３１に加えて対象道路情報２３２を格納している。対象道路情報２３２は、交通掲示物２０３が掲示する交通情報の対象道路の情報である。 The traffic bulletin board 203 of the third embodiment is different from the traffic bulletin board 202 of the second embodiment in the storage information stored in the identification signal storage unit 23. The identification signal storage section 23 of the traffic bulletin board 203 stores target road information 232 in addition to type information 231. The target road information 232 is information about the target road of the traffic information posted by the traffic bulletin board 203.
　実施の形態３の送信部２１は、制御部２２の指示を受けて、交通掲示物２０３の識別信号を送信する。この識別信号には種別情報２３１と対象道路情報２３２とが含まれる。すなわち、送信部２１は識別信号格納部２３から種別情報２３１と対象道路情報２３２とを取り出し、識別信号に含めて送信する。 The transmitter 21 of the third embodiment transmits the identification signal of the traffic bulletin board 203 in response to instructions from the controller 22. This identification signal includes type information 231 and target road information 232. That is, the transmitting unit 21 takes out the type information 231 and the target road information 232 from the identification signal storage unit 23, includes them in the identification signal, and transmits them.
　掲示物認識システム１００３において、車両３０１には、掲示物認識装置１０３の他、カメラ５１、ＧＰＳ（Global Positioning System）センサ５２、ディスプレイ５３、およびスピーカ５４が設けられる。 In the bulletin board recognition system 1003, the vehicle 301 is provided with a camera 51, a GPS (Global Positioning System) sensor 52, a display 53, and a speaker 54 in addition to the bulletin board recognition device 103.
　ＧＰＳセンサ５２は、ＧＰＳ衛星からＧＰＳ信号を受信し、車両３０１の位置を測定し、掲示物認識装置１０３に出力する。 The GPS sensor 52 receives a GPS signal from a GPS satellite, measures the position of the vehicle 301, and outputs it to the notice recognition device 103.
　掲示物認識装置１０３は、実施の形態２に係る掲示物認識装置１０２の構成に加えて、車両位置判断部１７を備える。また、掲示物認識装置１０３において認識部１４の処理が実施の形態２とは一部異なる。 The notice recognition device 103 includes a vehicle position determination unit 17 in addition to the configuration of the notice recognition device 102 according to the second embodiment. Further, in the notice recognition device 103, the processing of the recognition unit 14 is partially different from that in the second embodiment.
　車両位置判断部１７は、ＧＰＳセンサ５２から取得した車両３０１の位置情報と、受信部１２から取得した交通掲示物２０３の対象道路情報２３２とに基づき、車両３０１が交通掲示物２０３の対象道路を走行しているか否かを判断する。 The vehicle position determining unit 17 determines whether the vehicle 301 is on the target road of the traffic bulletin board 203 based on the position information of the vehicle 301 acquired from the GPS sensor 52 and the target road information 232 of the traffic bulletin board 203 acquired from the receiving unit 12. Determine whether the vehicle is running or not.
　本実施の形態の認識部１４は、車両３０１が交通掲示物２０３の対象道路を走行中であれば、交通掲示物２０３の種別に応じたテンプレート画像のマッチングの優先順位の変更を行い、車両３０１が交通掲示物２０３の対象道路を走行中でなければ、デフォルトの優先順位に沿ってテンプレート画像を撮影画像とマッチングする。 If the vehicle 301 is traveling on the target road of the traffic bulletin board 203, the recognition unit 14 of this embodiment changes the priority order of template image matching according to the type of the traffic bulletin board 203, and If the vehicle is not traveling on the target road of the traffic bulletin board 203, the template image is matched with the photographed image according to the default priority order.
　＜Ｃ－２．動作＞
　図１２は、掲示物認識装置１０３の動作を示すフローチャートである。図１２のフローは、例えば車両３０１の走行開始と共に開始する。図１２のフローは、実施の形態２で説明した図９のフローのステップＳ２０２とステップＳ１０４との間にステップＳ３０１，Ｓ３０２，Ｓ３０３を追加したものである。 <C-2. Operation>
FIG. 12 is a flowchart showing the operation of the notice recognition device 103. The flow in FIG. 12 starts, for example, when the vehicle 301 starts traveling. The flow in FIG. 12 is obtained by adding steps S301, S302, and S303 between step S202 and step S104 in the flow in FIG. 9 described in the second embodiment.
　ステップＳ３０１において車両位置判断部１７は、受信部１２が受信した識別信号に対象道路情報２３２が含まれるか否かを判断する。ステップＳ３０１において識別信号に対象道路情報２３２が含まれる場合、掲示物認識装置１０３の処理はステップＳ３０２に移行する。 In step S301, the vehicle position determining unit 17 determines whether the target road information 232 is included in the identification signal received by the receiving unit 12. If the target road information 232 is included in the identification signal in step S301, the process of the notice recognition device 103 moves to step S302.
　ステップ３０２において車両位置判断部１７は、ＧＰＳセンサ５２から取得したＧＰＳ信号と、受信部１２から取得した対象道路情報２３２とに基づき、車両３０１が対象道路を走行中であるか否かを判断する。 In step 302, the vehicle position determination unit 17 determines whether the vehicle 301 is traveling on the target road based on the GPS signal acquired from the GPS sensor 52 and the target road information 232 acquired from the reception unit 12. .
　ステップＳ３０２において車両３０１が対象道路を走行中であれば、掲示物認識装置１０３の処理はステップＳ１０４に進む。 If the vehicle 301 is traveling on the target road in step S302, the processing of the notice recognition device 103 proceeds to step S104.
　ステップＳ３０２において車両３０１が対象道路を走行中でなければ、掲示物認識装置１０３の処理はステップＳ３０３に進む。 If the vehicle 301 is not traveling on the target road in step S302, the processing of the notice recognition device 103 proceeds to step S303.
　ステップＳ３０３において認識部１４は、ステップＳ２０２において変更したテンプレート画像の撮影画像とのマッチングの優先順位を、デフォルトに戻す。 In step S303, the recognition unit 14 returns the priority order of matching of the template image with the photographed image changed in step S202 to the default.
　＜Ｃ－３．効果＞
　実施の形態３において、掲示物認識装置１０３が交通掲示物２０３から受信する識別信号には、交通掲示物２０３の対象道路を表す対象道路情報２３２が含まれる。認識部１４は、対象道路情報２３２に表された対象道路が車両３０１の走行する道路でない場合に、テンプレート画像のパターンマッチングの優先順位の変更を行わない。従って、掲示物認識装置１０３によれば、車両３０１とは無関係な交通掲示物２０３からの識別情報を受信しても、当該交通掲示物２０３にあわせたパターンマッチング処理を行うことを避けることができる。 <C-3. Effect>
In the third embodiment, the identification signal that the bulletin board recognition device 103 receives from the traffic bulletin board 203 includes target road information 232 representing the target road of the traffic bulletin board 203. If the target road represented in the target road information 232 is not the road on which the vehicle 301 is traveling, the recognition unit 14 does not change the priority order of pattern matching of the template image. Therefore, according to the notice recognition device 103, even if identification information is received from a traffic notice 203 unrelated to the vehicle 301, it is possible to avoid performing pattern matching processing tailored to the traffic notice 203. .
　＜Ｄ．ハードウェア構成＞
　上述した掲示物認識装置１０１－１０３および交通掲示物２０１－２０３はいずれも、図１３に示すプロセッサ８１、メモリ８２、および通信装置８３により実現される。 <D. Hardware configuration>
The above-described notice recognition devices 101-103 and traffic notices 201-203 are both realized by the processor 81, memory 82, and communication device 83 shown in FIG.
　掲示物認識装置１０１－１０３において、受信部１２は通信装置８３により実現され、テンプレート格納部１５はメモリ８２により実現され、画像取得部１１、掲示位置判断部１３、認識部１４および出力制御部１６は、メモリ８２に格納されたプログラムをプロセッサ８１が実行することにより、実現される。 In the bulletin board recognition devices 101-103, the reception section 12 is realized by the communication device 83, the template storage section 15 is realized by the memory 82, the image acquisition section 11, the bulletin position judgment section 13, the recognition section 14, and the output control section 16. is realized by the processor 81 executing a program stored in the memory 82.
　交通掲示物２０１－２０３において、送信部２１は通信装置８３により実現され、識別信号格納部２３はメモリ８２により実現され、制御部２２は、メモリ８２に格納されたプログラムをプロセッサ８１が実行することにより、実現される。 In the traffic bulletin boards 201-203, the transmitter 21 is implemented by the communication device 83, the identification signal storage unit 23 is implemented by the memory 82, and the controller 22 is implemented by the processor 81 executing a program stored in the memory 82. This is realized by
　プロセッサ８１は、例えば中央処理装置、処理装置、演算装置、マイクロプロセッサ、マイクロコンピュータ、ＤＳＰ（Digital Signal Processor）等である。 The processor 81 is, for example, a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, a DSP (Digital Signal Processor), or the like.
　メモリ８２に格納されたプログラムは、掲示物認識装置１０１－１０３、または交通掲示物２０１－２０３の各部の方法をコンピュータに実行させるものである。ここで、メモリ８２は、例えば、ＲＡＭ（Random Access Memory）、ＲＯＭ（Read Only Memory）、フラッシュメモリ、ＥＰＲＯＭ（Erasable Programmable Read Only Memory）、ＥＥＰＲＯＭ（Electrically Erasable Programmable Read Only Memory）などの、不揮発性または揮発性の半導体メモリ、ＨＤＤ（Hard Disk Drive）、磁気ディスク、フレキシブルディスク、光ディスク、コンパクトディスク、ミニディスク、ＤＶＤ（Digital Versatile Disk）及びそのドライブ装置等、または、今後使用されるあらゆる記憶媒体であってもよい。 The program stored in the memory 82 causes the computer to execute the method of each part of the bulletin board recognition devices 101-103 or the traffic bulletin boards 201-203. Here, the memory 82 is a nonvolatile or Volatile semiconductor memory, HDD (Hard Disk Drive), magnetic disk, flexible disk, optical disk, compact disk, mini disk, DVD (Digital Versatile Disk) and its drive device, etc., or any storage media that will be used in the future. It's okay.
　また、上記では掲示物認識装置１０１－１０３を車載装置として説明したが、ＰＮＤ（Portable Navigation Device）、通信端末（例えば携帯電話、スマートフォン、およびタブレットなどの携帯端末）、およびこれらにインストールされるアプリケーションの機能、並びにサーバなどを適宜に組み合わせて構築されるシステムにも適用することができる。この場合、以上で説明した掲示物認識装置１０１－１０３の各機能または各構成要素は、システムを構築する各機器に分散して配置されてもよいし、いずれかの機器に集中して配置されてもよい。 In addition, although the bulletin board recognition devices 101-103 have been described above as in-vehicle devices, PNDs (Portable Navigation Devices), communication terminals (for example, mobile terminals such as mobile phones, smartphones, and tablets), and applications installed on these devices It can also be applied to a system constructed by appropriately combining the functions of , servers, etc. In this case, each function or each component of the bulletin board recognition devices 101-103 explained above may be distributed and arranged in each device constructing the system, or may be arranged centrally in one of the devices. It's okay.
　なお、各実施の形態を自由に組み合わせたり、各実施の形態を適宜、変形、省略したりすることが可能である。上記の説明は、すべての態様において、例示である。例示されていない無数の変形例が想定され得るものと解される。 Note that it is possible to freely combine each embodiment, or to modify or omit each embodiment as appropriate. The above description is in all aspects exemplary. It is understood that countless variations not illustrated may be envisioned.
　１１　画像取得部、１２　受信部、１３　掲示位置判断部、１４　認識部、１５　テンプレート格納部、１６　出力制御部、１７　車両位置判断部、２１　送信部、２２　制御部、２３　識別信号格納部、５１　カメラ、５２　ＧＰＳセンサ、５３　ディスプレイ、５４　スピーカ、６１　対象範囲、８１　プロセッサ、８２　メモリ、８３　通信装置、１０１－１０３　掲示物認識装置、２０１－２０３　交通掲示物、２３１　種別情報、２３２　対象道路情報、３０１　車両、１００１－１００３　掲示物認識システム。 11 Image acquisition unit, 12 Receiving unit, 13 Notice position determination unit, 14 Recognition unit, 15 Template storage unit, 16 Output control unit, 17 Vehicle position determination unit, 21 Transmission unit, 22 Control unit, 23 Identification signal storage unit, 51 Camera, 52 GPS sensor, 53 Display, 54 Speaker, 61 Target range, 81 Processor, 82 Memory, 83 Communication device, 101-103 Bulletin board recognition device, 201-203 Traffic bulletin board, 231 Type information, 232 Target road information, 301 Vehicle, 1001-1003 Postage recognition system.

Claims (8)

  1. 　車両の周辺の撮影画像を取得する画像取得部と、
    　前記車両に搭載され、道路上に設置された交通掲示物から送信される識別信号を受信する受信部と、
    　前記識別信号に基づき、前記交通掲示物の前記車両に対する位置を表す前記交通掲示物の位置情報を推定する掲示位置判断部と、
    　前記交通掲示物の種類別に用意された複数のテンプレート画像を予め定められた優先順位に従い前記撮影画像とパターンマッチングすることにより、前記撮影画像に映った前記交通掲示物を認識する認識部と、を備え、
    　前記認識部は、前記掲示位置判断部が推定した前記交通掲示物の位置情報に基づき、前記撮影画像の一部の範囲を前記交通掲示物が撮影された対象範囲と特定し、前記対象範囲を前記パターンマッチングの対象とする、
    掲示物認識装置。     an image acquisition unit that acquires captured images of the surroundings of the vehicle;
    a receiving unit mounted on the vehicle and receiving an identification signal transmitted from a traffic bulletin board installed on the road;
    a notice position determination unit that estimates position information of the traffic notice indicating the position of the traffic notice with respect to the vehicle based on the identification signal;
    a recognition unit that recognizes the traffic bulletin board appearing in the photographed image by pattern matching a plurality of template images prepared for each type of traffic bulletin board with the photographed image according to a predetermined priority order; Prepare,
    The recognition unit identifies a part of the photographed image as a target range in which the traffic bulletin was photographed, based on the position information of the traffic bulletin estimated by the bulletin position determination unit, and determines the target range. The target of the pattern matching,
    Postage recognition device.
  2. 　前記受信部が受信する前記識別信号は、前記車両の異なる３か所以上の走行位置において受信された３つ以上の前記識別信号を含む、
    請求項１に記載の掲示物認識装置。     The identification signal received by the receiving unit includes three or more identification signals received at three or more different driving positions of the vehicle.
    The notice recognition device according to claim 1.
  3. 　前記交通掲示物から前記識別信号を送信する際に用いられる電波は、前記交通掲示物の対象道路に対する指向性を有する、
    請求項１または請求項２に記載の掲示物認識装置。     The radio waves used when transmitting the identification signal from the traffic bulletin board have directionality with respect to the target road of the traffic bulletin board,
    The notice recognition device according to claim 1 or claim 2.
  4. 　前記識別信号は前記交通掲示物の種別を表す種別情報を含み、
    　前記認識部は、前記種別情報に表された種別の前記交通掲示物の前記テンプレート画像が最優先になるよう前記テンプレート画像のパターンマッチングの優先順位を変更する、
    請求項１から請求項３のいずれか１項に記載の掲示物認識装置。     The identification signal includes type information indicating the type of the traffic sign,
    The recognition unit changes the priority order of pattern matching of the template images so that the template image of the traffic bulletin board of the type represented by the type information has the highest priority.
    A notice board recognition device according to any one of claims 1 to 3.
  5. 　前記識別信号は前記交通掲示物の対象道路を表す対象道路情報を含み、
    　前記認識部は、前記対象道路情報に表された前記対象道路が前記車両の走行する道路でない場合に、前記テンプレート画像のパターンマッチングの優先順位の変更を行わない、
    請求項４に記載の掲示物認識装置。     The identification signal includes target road information representing the target road of the traffic bulletin,
    The recognition unit does not change the priority order of pattern matching of the template image when the target road represented in the target road information is not a road on which the vehicle runs.
    The notice recognition device according to claim 4.
  6. 　前記認識部が認識した前記交通掲示物の情報を前記車両に搭載された出力装置に出力させる出力制御部をさらに備える、
    請求項１に記載の掲示物認識装置。     further comprising an output control unit that causes an output device mounted on the vehicle to output information on the traffic bulletin board recognized by the recognition unit;
    The notice recognition device according to claim 1.
  7. 　道路上に設置され識別信号を送信する交通掲示物と、
    　車両の周辺の前記交通掲示物を認識する掲示物認識装置と、を備える掲示物認識システムであって、
    　前記掲示物認識装置は、
    　前記車両の周辺の撮影画像を取得する画像取得部と、
    　前記車両に搭載され、前記交通掲示物から送信される前記識別信号を受信する受信部と、
    　前記識別信号に基づき、前記交通掲示物の前記車両に対する位置を表す前記交通掲示物の位置情報を推定する掲示位置判断部と、
    　前記交通掲示物の種類別に用意された複数のテンプレート画像を予め定められた優先順位に従い前記撮影画像とパターンマッチングすることにより、前記撮影画像に映った前記交通掲示物を認識する認識部と、を備え、
    　前記認識部は、前記掲示位置判断部が推定した前記交通掲示物の位置情報に基づき、前記撮影画像の一部の範囲を対象範囲と特定し、前記対象範囲を前記パターンマッチングの対象とする、
    掲示物認識システム。     A traffic bulletin board installed on the road and transmitting an identification signal;
    A notice recognition system comprising: a notice recognition device that recognizes the traffic notices around a vehicle;
    The notice recognition device includes:
    an image acquisition unit that acquires a captured image of the surroundings of the vehicle;
    a receiving unit that is mounted on the vehicle and receives the identification signal transmitted from the traffic bulletin board;
    a notice position determination unit that estimates position information of the traffic notice indicating the position of the traffic notice with respect to the vehicle based on the identification signal;
    a recognition unit that recognizes the traffic bulletin board appearing in the photographed image by pattern matching a plurality of template images prepared for each type of traffic bulletin board with the photographed image according to a predetermined priority order; Prepare,
    The recognition unit identifies a partial range of the photographed image as a target range based on the position information of the traffic bulletin board estimated by the bulletin position determination unit, and sets the target range as a target of the pattern matching.
    Postage recognition system.
  8. 　画像取得部が、車両の周辺の撮影画像を取得し、
    　前記車両に搭載された受信部が、道路上に設置された交通掲示物から送信される識別信号を受信し、
    　掲示位置判断部が、前記識別信号に基づき、前記交通掲示物の前記車両に対する位置を表す前記交通掲示物の位置情報を推定し、
    　認識部が、前記交通掲示物の種類別に用意された複数のテンプレート画像を予め定められた優先順位に従い前記撮影画像とパターンマッチングすることにより、前記撮影画像に映った前記交通掲示物を認識し、
    　前記掲示位置判断部が推定した前記交通掲示物の位置情報に基づき、前記認識部が前記撮影画像の一部の範囲を前記交通掲示物が撮影された対象範囲と特定し、前記対象範囲を前記パターンマッチングの対象とする、
    掲示物認識方法。     The image acquisition unit acquires captured images of the surroundings of the vehicle,
    a receiving unit mounted on the vehicle receives an identification signal transmitted from a traffic bulletin board installed on the road;
    a bulletin board position determination unit estimates position information of the traffic bulletin board representing a position of the traffic bulletin board with respect to the vehicle based on the identification signal;
    a recognition unit recognizes the traffic bulletin board appearing in the photographed image by pattern matching a plurality of template images prepared for each type of traffic bulletin board with the photographed image according to a predetermined priority order;
    Based on the position information of the traffic bulletin board estimated by the bulletin position determination unit, the recognition unit identifies a part of the photographed image as the target range in which the traffic bulletin board was photographed, and converts the target range into the target range. Targeted for pattern matching,
    Postage recognition method.
PCT/JP2022/028750 2022-07-26 2022-07-26 Sign recognition device, sign recognition system, and sign recognition method WO2024023921A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2022/028750 WO2024023921A1 (en) 2022-07-26 2022-07-26 Sign recognition device, sign recognition system, and sign recognition method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2022/028750 WO2024023921A1 (en) 2022-07-26 2022-07-26 Sign recognition device, sign recognition system, and sign recognition method

Publications (1)

Publication Number Publication Date
WO2024023921A1 true WO2024023921A1 (en) 2024-02-01

Family

ID=89705850

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/028750 WO2024023921A1 (en) 2022-07-26 2022-07-26 Sign recognition device, sign recognition system, and sign recognition method

Country Status (1)

Country Link
WO (1) WO2024023921A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000222687A (en) * 1999-01-28 2000-08-11 Internatl Business Mach Corp <Ibm> System for acquiring traffic signal information and display method
WO2018025566A1 (en) * 2016-08-03 2018-02-08 パナソニックＩｐマネジメント株式会社 Roadside device, on-board device, and vehicle
JP2018163667A (en) * 2018-05-08 2018-10-18 株式会社ユピテル On-vehicle electronic equipment and program
WO2020095567A1 (en) * 2018-11-06 2020-05-14 本田技研工業株式会社 Saddled vehicle
JP2021076884A (en) * 2019-11-05 2021-05-20 三菱スペース・ソフトウエア株式会社 Automatic detection system and automatic detection program

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000222687A (en) * 1999-01-28 2000-08-11 Internatl Business Mach Corp <Ibm> System for acquiring traffic signal information and display method
WO2018025566A1 (en) * 2016-08-03 2018-02-08 パナソニックＩｐマネジメント株式会社 Roadside device, on-board device, and vehicle
JP2018163667A (en) * 2018-05-08 2018-10-18 株式会社ユピテル On-vehicle electronic equipment and program
WO2020095567A1 (en) * 2018-11-06 2020-05-14 本田技研工業株式会社 Saddled vehicle
JP2021076884A (en) * 2019-11-05 2021-05-20 三菱スペース・ソフトウエア株式会社 Automatic detection system and automatic detection program

Similar Documents

Publication Publication Date Title
CN107390219B (en) Approaching vehicle notification device
US20190126942A1 (en) Assistance system, portable terminal, and vehicular device
JP6241422B2 (en) Driving support device, driving support method, and recording medium for storing driving support program
JP5461065B2 (en) Current position specifying device and current position specifying method
CN108053690B (en) Method for identifying driving lane, curve early warning method, device, medium and equipment
JP6468062B2 (en) Object recognition system
JP2008242844A (en) Running support on-vehicle device
JP2009230390A (en) Recognition system
CN109427213B (en) Collision avoidance apparatus, method and non-transitory storage medium for vehicle
JP6952778B2 (en) Driving support device and driving support method
CN110956847B (en) Parking space identification method and device and storage medium
JP2019109707A (en) Display control device, display control method and vehicle
CN111361550B (en) Parking space identification method and device and storage medium
JP6262618B2 (en) Driving support system, data structure
JP4692898B2 (en) Vehicle guidance device
JP2024052899A (en) Communication device and communication method
JPH09218265A (en) Apparatus for automatically correcting center axis of radar
WO2024023921A1 (en) Sign recognition device, sign recognition system, and sign recognition method
JP2011209849A (en) Driving support method and driving support device
JP2012220259A (en) In-vehicle apparatus and vehicle azimuth correction method thereof
JP2021043861A (en) Driving support control device, determination support control device, driving support system, driving support control method and determination support control method
JP4798549B2 (en) Car navigation system
JP2013160735A (en) Apparatus and method for identifying road on which vehicle travels
JP7449206B2 (en) Communication control device, vehicle, program, and communication control method
JP7518708B2 (en) COMMUNICATION CONTROL DEVICE, VEHICLE, PROGRAM, AND COMMUNICATION CONTROL METH

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22953018

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2024536587

Country of ref document: JP