WO2021027944A1 - 位置合规识别方法及装置、存储介质、电子装置 - Google Patents
位置合规识别方法及装置、存储介质、电子装置 Download PDFInfo
- Publication number
- WO2021027944A1 WO2021027944A1 PCT/CN2020/109344 CN2020109344W WO2021027944A1 WO 2021027944 A1 WO2021027944 A1 WO 2021027944A1 CN 2020109344 W CN2020109344 W CN 2020109344W WO 2021027944 A1 WO2021027944 A1 WO 2021027944A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- target
- image
- parking
- location
- target vehicle
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
Definitions
- the present disclosure relates to the field of data processing technology, and in particular, to a location compliance recognition method and device, storage medium, and electronic device.
- GPS Global Positioning System
- IMU Inertial Measurement Unit
- the embodiments of the present disclosure provide a location compliance recognition method and device, a storage medium, and an electronic device, so as to at least solve the problem in the related art that it is impossible to accurately recognize whether the parking place of a shared vehicle is appropriate.
- a location compliance recognition method including: in the case of detecting a parking instruction indicating that a target vehicle has stopped, using an image capture device installed on the target vehicle Collect an image of the location of the target vehicle; identify the target parking location of the target vehicle based on the image; determine whether the target parking location is a compliant parking by judging whether the target parking location is located in a designated parking area position.
- the recognizing the target parking position of the target vehicle according to the image includes: extracting a first image feature in the image; and inputting the first image feature into a first positioning model to identify the The target docking position.
- the method further includes: recognizing environmental parameters of the target parking position according to the image, wherein the environmental parameters include at least one of the following: Whether there are buildings blocking the surrounding area, whether there are public facilities in the surrounding area, and whether it is located within the designated parking area.
- the determining whether the target parking location is a compliant parking location by determining whether the target parking location is located in a designated parking area includes: when the environmental parameters of the target parking location meet a preset rule Next, determine that the target parking position is located in the designated parking area, and then determine that the target parking position is a compliant parking position; when the environmental parameters of the target parking position do not meet the preset rules, determine the The target parking position is not located in the designated parking area, and it is determined that the target parking position is a non-compliant parking position.
- the method further includes: performing at least one of the following operations: sending the non-compliant parking position to a server; sending warning information, The warning information is used to prompt that the target parking position is a non-compliant parking position, and/or is used to prompt a designated parking area within a designated range from the target parking position.
- the collecting an image of the location of the target vehicle through an image acquisition device installed on the target vehicle includes: collecting a video image and/or a photo image of the location of the target vehicle within a predetermined time period, wherein, the target vehicle includes a shared vehicle.
- a location compliance recognition method including: in the case of detecting a parking instruction indicating that the target vehicle has stopped, using an image installed on the target vehicle
- the collection device collects an image of the location of the target vehicle; sends the image to a server so that the server can recognize the target parking position of the target vehicle according to the image; receives the target returned by the server Parking position; determining whether the target parking position is a compliant parking position by determining whether the target parking position is located in a designated parking area.
- a location compliance recognition method including: acquiring an image sent by a target vehicle, where the image is that when the target vehicle detects a stop instruction, An image of the location of the target vehicle collected by the image acquisition device installed on the target vehicle, the parking instruction is used to indicate that the target vehicle has stopped; and the image of the target vehicle is identified The target parking position; the identified target parking position is sent to the target vehicle, so that the target vehicle determines whether the target parking position is a closed area by judging whether the target parking position is located in a designated parking area Regulation docking position.
- the recognizing the target parking position of the target vehicle according to the image includes: extracting a second image feature in the image; and inputting the second image feature into a second positioning model to identify the The target docking position.
- a location compliance recognition device including: a first collection module, configured to pass the said stop instruction when the stop instruction indicating that the target vehicle has stopped is detected.
- the image acquisition device installed on the target vehicle collects an image of the location of the target vehicle; the first recognition module is used to identify the target parking position of the target vehicle according to the image; the first determination module is used to pass Determine whether the target parking position is located in a designated parking area, and determine whether the target parking position is a compliant parking position.
- the recognition module includes: a first extraction unit for extracting a first image feature in the image; a first input unit for inputting the first image feature into a first positioning model to identify The target docking position.
- the device further includes: a third recognition module for recognizing environmental parameters of the target parking position according to the image, wherein the environmental parameters include at least one of the following: whether there are buildings around, Whether there are public facilities in the surrounding area and whether they are located within the designated stopping area.
- the environmental parameters include at least one of the following: whether there are buildings around, Whether there are public facilities in the surrounding area and whether they are located within the designated stopping area.
- the first determination module is configured to determine that the target parking position is located in the designated parking area when the environmental parameters of the target parking position meet a preset rule, and then determine the target The parking location is a compliant parking location; when the environmental parameters of the target parking location do not meet the preset rules, it is determined that the target parking location is not located in the designated parking area, and then the target parking location is determined to be Non-compliant docking location.
- the device further includes: an execution module, configured to perform at least one of the following operations after determining that the target parking position is a non-compliant parking position: sending the non-compliant parking position to Server; sending warning information, wherein the warning information is used to prompt that the target parking location is a non-compliant parking location, and/or used to prompt a designated parking area within a specified range from the target parking location.
- an execution module configured to perform at least one of the following operations after determining that the target parking position is a non-compliant parking position: sending the non-compliant parking position to Server; sending warning information, wherein the warning information is used to prompt that the target parking location is a non-compliant parking location, and/or used to prompt a designated parking area within a specified range from the target parking location.
- the first collection module includes: a collection unit configured to collect a video image and/or a photo image of the location of the target vehicle within a predetermined period of time, wherein the target vehicle includes a shared vehicle.
- a location compliance recognition device including: a second acquisition module, configured to pass the said parking instruction when the parking instruction indicating that the target vehicle has stopped is detected
- the image acquisition device installed on the target vehicle collects an image of the location of the target vehicle; the first sending module is configured to send the image to the server so that the server can recognize the target vehicle based on the image
- the receiving module is used to receive the target stopping position returned by the server; the second determining module is used to determine whether the target stopping position is in the designated stopping area by judging whether the target stopping position is Compliant docking position.
- a location compliance recognition device including: an acquisition module, configured to acquire an image sent by a target vehicle, wherein the image shows that the target vehicle detects a stop
- an image of the location of the target vehicle collected by an image acquisition device installed on the target vehicle, the parking instruction is used to indicate that the target vehicle has stopped
- the second recognition module uses To identify the target parking position of the target vehicle according to the image
- the second sending module is used to send the identified target parking position to the target vehicle so that the target vehicle can pass the judgment station Whether the target parking position is located in a designated parking area is used to determine whether the target parking position is a compliant parking position.
- the second recognition module includes: a second extraction unit for extracting a second image feature in the image; a second input unit for inputting the second image feature into a second positioning model, To identify the target docking position.
- a computer-readable storage medium in which a computer program is stored, wherein the computer program is configured to execute any of the foregoing method embodiments when running A step of.
- an electronic device including a memory and a processor, the memory is stored with a computer program, and the processor is configured to run the computer program to execute any of the above Steps in the method embodiment.
- the image acquisition device installed on the target vehicle is used to collect Image of the location of the target vehicle; identify the target parking location of the target vehicle based on the image; determine whether the target parking location is a compliant parking location by judging whether the target parking location is in the designated parking area, that is, through the image that comes with the target vehicle
- the collection device collects the image of the location and then recognizes it.
- FIG. 1 is a hardware structural block diagram of a mobile terminal of an optional location compliance identification method according to an embodiment of the present disclosure
- FIG. 2 is a flowchart of an optional location compliance identification method according to an embodiment of the present disclosure
- FIG. 3 is a flowchart of another optional location compliance recognition method according to an embodiment of the present disclosure.
- FIG. 4 is a flowchart of another optional location compliance recognition method according to an embodiment of the present disclosure.
- FIG. 5 is a flowchart of another optional location compliance recognition method according to an embodiment of the present disclosure.
- FIG. 6 is a structural block diagram of an optional location compliance recognition device according to an embodiment of the present disclosure.
- Fig. 7 is a structural block diagram of another optional location compliance recognition device according to an embodiment of the present disclosure.
- Fig. 8 is a structural block diagram of another optional location compliance recognition device according to an embodiment of the present disclosure.
- FIG. 1 is a hardware structural block diagram of a mobile terminal of a location compliance identification method according to an embodiment of the present disclosure.
- the mobile terminal 10 may include one or more (only one is shown in FIG. 1) processor 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA. ) And a memory 104 for storing data.
- the above mobile terminal may also include a transmission device 106 and an input/output device 108 for communication functions.
- FIG. 1 is only for illustration, and does not limit the structure of the above-mentioned mobile terminal.
- the mobile terminal 10 may also include more or fewer components than those shown in FIG. 1, or have a different configuration from that shown in FIG.
- the memory 104 may be used to store computer programs, for example, software programs and modules of application software, such as the computer programs corresponding to the method for obtaining scheduling throughput in the embodiments of the present disclosure.
- the processor 102 runs the computer programs stored in the memory 104, Thereby, various functional applications and data processing are executed, that is, the above-mentioned method is realized.
- the memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.
- the memory 104 may further include a memory remotely provided with respect to the processor 102, and these remote memories may be connected to the mobile terminal 10 via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
- the transmission device 106 is used to receive or send data via a network.
- the above-mentioned specific example of the network may include a wireless network provided by the communication provider of the mobile terminal 10.
- the transmission device 106 includes a network adapter (Network Interface Controller, NIC for short), which can be connected to other network devices through a base station to communicate with the Internet.
- the transmission device 106 may be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet in a wireless manner.
- RF Radio Frequency
- FIG. 2 is a flowchart of an optional location compliance identification method according to an embodiment of the present disclosure. As shown in FIG. 2, the method includes:
- Step S202 in the case of detecting a parking instruction indicating that the target vehicle has stopped, collect an image of the location of the target vehicle through an image acquisition device installed on the target vehicle;
- Step S204 Identify the target stopping position of the target vehicle according to the image
- Step S206 Determine whether the target parking position is a compliant parking position by determining whether the target parking position is located in the designated parking area.
- an image of the location of the target vehicle is collected through the image acquisition device installed on the target vehicle; the target parking of the target vehicle is recognized according to the image Location: Determine whether the target parking location is a compliant parking location by judging whether the target parking location is in the designated parking area, that is, the image of the location is collected by the image capture device of the target vehicle and then recognized, based on the content displayed in the image Intuitively determine whether the current parking location meets the rules of the designated parking area, and then determine whether it is a compliant location, which solves the problem that the existing technology cannot accurately identify whether the parking location of shared vehicles is appropriate, and improves the recognition of the parking location of shared vehicles Accuracy.
- the target vehicles in the embodiments of the present disclosure may include, but are not limited to, any shared vehicles, for example, shared bicycles, shared cars, shared electric vehicles, shared scooters, and the like.
- a parking instruction is triggered.
- the parking instruction here can be automatically triggered after the user turns off or locks the target vehicle, or it can be triggered by the user.
- the single-chip microcomputer or chip set inside the target vehicle will trigger the image capture device installed on the target vehicle to take a photo or video after detecting the parking instruction.
- the lens here can be set as a wide-angle lens or a lens with a deeper depth of field, as much as possible Collect image information of the surrounding environment.
- recognizing the target stopping position of the target vehicle according to the image can be achieved through the following steps:
- S2 Input the first image feature into the first positioning model to identify the target stopping position.
- the first positioning model here can be any two classification algorithm model.
- the input is the sensor data of the target vehicle, including but not limited to the captured image and GPS data of the current stop position, and the output is a determination result between 0 and 1.
- the result output by the first positioning model can be the identified target stopping position, or the judgment result of whether the target stopping position is located in the designated stopping area, or whether the target stopping position is a compliant stopping position
- the result of the judgment can also output the probability value of the target parking location in the designated parking area, or the probability value of the target parking location being a compliant parking location, and then judging whether it is a compliant parking location based on the obtained probability value. This is not limited.
- the first positioning model here can be implemented by the Support Vector Machine (SVM) algorithm: first prepare training data, that is, known reasonable or unreasonable parking photos and their judgments, and perform features in the image Detection, using detection methods such as harris, DOG, etc., extracting feature description words from feature locations, such as SIFT, Brief, etc., construct a bag of words feature description for each image, and use svm to train regression according to the judgment result Find the correspondence between features and judgments. Every time a new picture is obtained, the picture is first extracted with features, and then the SVM classifier is used to determine whether it is a compliant parking position.
- SVM Support Vector Machine
- the principle of Harris corner detection is to use a moving window to calculate the gray change value in the image.
- the key process includes converting to gray image, calculating difference image, Gaussian smoothing, calculating local extremum, and confirming corners.
- DOG Difference of Gaussian
- SIFT Scale-invariant feature transform
- BRIEF is a 2010 article named "BRIEF: Binary Robust Independent Elementary Features”.
- BRIEF is a description of the detected feature points. It is a binary-coded descriptor that discards the use of regional gray.
- the traditional method of describing feature points with degree histogram greatly speeds up the establishment of feature descriptors, and also greatly reduces the time for feature matching.
- Bag-of-words model (Bag-of-words model) is a simplified expression model under natural language processing and information retrieval (IR).
- IR information retrieval
- Bag-of-words model assumes that for a text, its word order, grammar and syntax are ignored , Regard it as just a word set, or a combination of words, the appearance of each word in the text is independent, and it does not depend on whether other words appear or not, or it is not necessary to select a word at any position Selected independently by the influence of the previous sentence.
- Bag of words to represent the feature description of the image can be understood in this way.
- each image is first divided into patches (it can be rigid segmentation or it can be based on SIFT key Point detection), in this way, each image is represented by many patches, and each patch is represented by a feature vector.
- Sift An image may have hundreds of patches, each The dimension of the patch feature vector is 128.
- build a Bag of words model assuming that the Size of the Dictionary is 100, that is, there are 100 words.
- the first positioning model here can also be implemented by a convolutional neural network.
- recognizing the target parking position of the target vehicle according to the image can also be achieved by the following steps: sending the image to the server, so that the server recognizes the target parking position of the target vehicle in the image.
- image recognition can be done in the following three ways:
- the algorithm a0 deployed in the body of the target vehicle is used to determine whether it is a reasonable parking position, and the determination result d0 is obtained.
- the image is determined by the background user, under the auxiliary information of GPS, through naked eye observation, referring to the preset rules, and the result is d2.
- the algorithm a0 and the algorithm a1 can be implemented by using machine learning algorithms, including the above-mentioned SVM algorithm and convolutional neural network model, which is not limited in the embodiment of the present disclosure.
- the algorithm a0 can choose an algorithm with a fast operation speed and low accuracy requirements
- the algorithm a1 can choose an algorithm with a slower operation speed but higher accuracy.
- method 1 can be used to make a judgment using the result d0.
- the user parks the target vehicle unreasonably one or more times and needs statistical data to decide whether to reduce its credit, he can use the high accuracy but slower method 2 and use the result d1 to make a judgment.
- method 3 can be used for manual assistance determination, and the result d2 is used to make the determination.
- the result d2 is generally more accurate, but the quantity is small and the cost is high.
- the judgment rules need to be judged by experience. For example, the judge must first determine the area where the scooter is parked through GPS, use maps, personal experience, etc., to obtain the judgment basis for normal parking (such as a designated area on the roadside) and abnormal parking in the area, and then use the target vehicle in the image To determine the location.
- the result d2 can be used as the truth value used for verification, and machine learning training can be carried out. Through continuous data accumulation, the accuracy of d0 and d1 can be improved.
- the results of d0 and d1 in the above steps also include the degree of confidence in the judgment. You can decide whether to wait for the result of d1 according to the confidence of d0. When the confidence of d1 is also low, the result d2 can be obtained through manual judgment, which makes it easier to provide machine learning understanding of difficult scenarios.
- the target parking position of the target vehicle after recognizing the target parking position of the target vehicle according to the image, it further includes: recognizing the environmental parameter of the target parking position according to the image, wherein the environmental parameter includes at least one of the following: whether there is a building block in the surrounding area, and whether there is a surrounding area Whether the public facilities are located in the designated parking area; when the environmental parameters of the target parking location meet the preset rules, it is determined that the standard parking location is located in the designated parking area.
- the determining whether the target parking position is a compliant parking position by determining whether the target parking position is located in a designated parking area includes: determining whether the environmental parameters of the target parking position meet a preset rule , Determining whether the target parking location is located in the designated parking area; wherein, when the environmental parameters of the target parking location meet a preset rule, it is determined that the target parking location is located in the designated parking area, and then It is determined that the target parking position is a compliant parking position; when the environmental parameters of the target parking position do not meet the preset rules, it is determined that the target parking position is not located in the designated parking area, and then the The target docking position is a non-compliant docking position.
- the method further includes: performing at least one of the following operations: sending the non-compliant parking position to a server; sending warning information, The warning information is used to prompt that the target parking position is a non-compliant parking position, and/or is used to prompt a designated parking area within a designated range from the target parking position.
- the surrounding environment is dark and narrow, it may indicate that the parking location is in a relatively hidden place, which is a non-compliant parking location. If the parking area is wide and bright, but there are no public facilities around, it may indicate that the parking location is too remote and it is also an illegal parking location.
- the designated stopping area can also be pre-set, and the stopping area can be divided according to GPS data.
- the stopping area can be set with more eye-catching signs. As long as the target vehicle stops within the designated stopping area, it can be detected by GPS, even if it is not detected, It can also be identified by the logo included in the image.
- the warning information can be directly sent by the target vehicle to the user’s client.
- the client here can be a client used to connect to the target vehicle, or the target vehicle can send the warning information to the server. It is sent by the server to the user's client, which is not limited in the embodiment of the present disclosure.
- capturing an image of the location of the target vehicle through an image capture device installed on the target vehicle includes: capturing a video image and/or photo image of the location of the target vehicle within a predetermined time period, where the target vehicle includes shared Transportation.
- FIG. 3 is a flowchart of an alternative location compliance recognition method according to an embodiment of the present disclosure. As shown in FIG. 3, the method includes:
- Step S302 in the case of detecting a parking instruction indicating that the target vehicle has stopped, collect an image of the location of the target vehicle through an image acquisition device installed on the target vehicle;
- Step S304 Send the image to the server, so that the server recognizes the target parking position of the target vehicle according to the image;
- Step S306 receiving the target parking position returned by the server
- step S308 it is determined whether the target parking position is a compliant parking position by determining whether the target parking position is located in the designated parking area.
- FIG. 4 is a flowchart of another optional location compliance recognition method according to an embodiment of the present disclosure. As shown in FIG. 4, the method includes:
- Step S402 Acquire an image sent by the target vehicle, where the image is an image of the location of the target vehicle collected by the image acquisition device installed on the target vehicle when the parking instruction is detected by the target vehicle.
- the image acquisition device installed on the target vehicle when the parking instruction is detected by the target vehicle.
- Step S404 Identify the target stopping position of the target vehicle according to the image
- Step S406 Send the identified target parking location to the target vehicle, so that the target vehicle determines whether the target parking location is a compliant parking location by judging whether the target parking location is located in the designated parking area.
- recognizing the target stopping position of the target vehicle according to the image includes: extracting a second image feature in the image; and inputting the second image characteristic into a second positioning model to identify the target stopping position.
- the second positioning model here can use the same algorithm as the first positioning model, and the content already described will not be repeated here.
- the result output by the second positioning model can be the identified target stopping position, or the judgment result of whether the target stopping position is located in the designated stopping area, or whether the target stopping position is a compliant stopping position
- the result of the judgment that is, the image recognition process and the judgment process of the compliant parking position can be executed on the server side, which is not limited in the embodiment of the present disclosure.
- the second positioning model can also output the probability value of the target stopping position in the designated stopping area, or the probability value of the target stopping position being a compliant stopping position, and then output the probability Send the value to the target vehicle.
- Fig. 5 is a flowchart of another optional location compliance recognition method according to an embodiment of the present disclosure. As shown in Fig. 5, the method includes:
- the user 50 triggers a parking instruction for the target vehicle 52;
- the target vehicle 52 After receiving the parking instruction, the target vehicle 52 uses its own installed image acquisition device to collect an image of the location of the target vehicle;
- S503 The target vehicle 52 sends the image to the server 54;
- S504 The server 54 recognizes the target stopping position of the target vehicle 52 according to the image
- S505 The server 54 sends the identified target stopping position to the target vehicle 52;
- the target vehicle 52 determines whether the target parking position is a compliant parking position by judging whether the target parking position is located in the designated parking area;
- the target vehicle 52 After the target vehicle 52 recognizes the result, it can give the user 50 a feedback. If it is a compliant parking location, execute the parking instruction, complete the parking and end the use process of the target vehicle, if it is a non-compliant parking location, no The execution of the parking instruction does not end the use process of the target vehicle, and can send a prompt message to the user to remind the user that the current parking location is not compliant, and provide a designated parking area nearby.
- the embodiments of the present disclosure also provide a location compliance recognition device, which is used to implement the foregoing location compliance recognition method embodiments and preferred implementations, and those that have been described will not be repeated.
- the term "module” can implement a combination of software and/or hardware with predetermined functions.
- the devices described in the following embodiments are preferably implemented by software, hardware or a combination of software and hardware is also possible and conceived.
- Fig. 6 is a structural block diagram of an optional location compliance recognition device according to an embodiment of the present disclosure. As shown in Fig. 6, the device includes:
- the first collection module 602 is configured to collect an image of the location of the target vehicle through an image collection device installed on the target vehicle in the case of detecting a parking instruction indicating that the target vehicle has stopped;
- the first recognition module 604 is configured to recognize the target parking position of the target vehicle according to the image
- the first determining module 606 is used to determine whether the target parking position is a compliant parking position by determining whether the target parking position is located in the designated parking area.
- the first recognition module 604 includes: a first extraction unit for extracting the first image feature in the image; a first input unit for inputting the first image feature into the first positioning model to identify the target stopping position .
- the first recognition module 604 includes: a sending unit, configured to send the image to the server, so that the server recognizes the target parking position of the target vehicle in the image.
- the device further includes: a third recognition module for recognizing the environmental parameters of the target parking position according to the image, wherein the environmental parameters include at least one of the following: whether there are buildings obstructing the surrounding area, whether there are public facilities nearby, Whether it is located in the designated parking area; the third determining module is used to determine that the target parking location is located in the designated parking area when the environmental parameters of the target parking location meet the preset rules.
- the environmental parameters include at least one of the following: whether there are buildings obstructing the surrounding area, whether there are public facilities nearby, Whether it is located in the designated parking area; the third determining module is used to determine that the target parking location is located in the designated parking area when the environmental parameters of the target parking location meet the preset rules.
- the first determining module 606 is further configured to determine that the target parking position is located in the designated parking area when the environmental parameters of the target parking position meet a preset rule, and then determine the target parking position The parking location is a compliant parking location; when the environmental parameters of the target parking location do not meet the preset rules, it is determined that the target parking location is not located in the designated parking area, and then the target parking location is determined to be Non-compliant docking location.
- the device further includes: an execution module configured to perform at least one of the following operations: sending the non-compliant parking location to the server; sending warning information, wherein the warning information is used to prompt the target
- the docking position is a non-compliant docking position, and/or used to prompt a designated docking area within a designated range from the target docking position.
- the first collection module 602 includes: a collection unit configured to collect a video image and/or a photo image of the location of the target vehicle within a predetermined time period, where the target vehicle includes a shared vehicle.
- Fig. 7 is a structural block diagram of another optional location compliance recognition device according to an embodiment of the present disclosure. As shown in Fig. 7, the device includes:
- the second acquisition module 702 is configured to collect an image of the location of the target vehicle through an image acquisition device installed on the target vehicle in the case of detecting a parking instruction indicating that the target vehicle has stopped;
- the first sending module 704 is configured to send the image to the server, so that the server can recognize the target parking position of the target vehicle according to the image;
- the receiving module 706 is used to receive the target parking position returned by the server
- the second determining module 708 is used for determining whether the target parking position is a compliant parking position by determining whether the target parking position is located in the designated parking area.
- Fig. 8 is a structural block diagram of an optional location compliance recognition device according to an embodiment of the present disclosure. As shown in Fig. 8, the device includes:
- the acquisition module 802 is used to acquire the image sent by the target vehicle, where the image is the image of the location of the target vehicle collected by the image acquisition device installed on the target vehicle when the target vehicle detects the parking instruction,
- the stop instruction is used to indicate that the target vehicle has stopped;
- the second recognition module 804 is configured to recognize the target stopping position of the target vehicle according to the image
- the second sending module 806 is configured to send the identified target parking location to the target vehicle, so that the target vehicle determines whether the target parking location is a compliant parking by judging whether the target parking location is in a designated parking area position.
- the second recognition module 804 includes: a second extraction unit for extracting the second image feature in the image; a second input unit for inputting the second image feature into the second positioning model to identify the target stopping position .
- the second positioning model here can use the same algorithm as the first positioning model, and the content already described will not be repeated here.
- the embodiments of the present disclosure also provide a computer-readable storage medium in which a computer program is stored, wherein the computer program is configured to execute the steps in any one of the foregoing method embodiments when running.
- the computer-readable storage medium is a non-volatile computer-readable storage medium.
- the foregoing storage medium may be configured to store a computer program for executing the following steps:
- S1 in the case of detecting a parking instruction indicating that the target vehicle has stopped, collect an image of the location of the target vehicle through an image acquisition device installed on the target vehicle;
- S3 Determine whether the target parking position is a compliant parking position by judging whether the target parking position is located in the designated parking area.
- the foregoing storage medium may also be configured to store a computer program for executing the following steps:
- S11 in the case of detecting a parking instruction indicating that the target vehicle has stopped, collect an image of the location of the target vehicle through an image acquisition device installed on the target vehicle;
- S14 Determine whether the target parking position is a compliant parking position by judging whether the target parking position is located in a designated parking area.
- the foregoing storage medium may also be configured to store a computer program for executing the following steps:
- S21 Acquire an image sent by the target vehicle, where the image is an image of the location of the target vehicle collected by an image acquisition device installed on the target vehicle when the target vehicle detects a parking instruction, and the parking instruction is used for Indicate that the target vehicle has stopped;
- S23 Send the identified target parking location to the target vehicle, so that the target vehicle determines whether the target parking location is a compliant parking by judging whether the target parking location is located in a designated parking area. position.
- the above-mentioned storage medium may include, but is not limited to: U disk, read-only memory (Read-Only Memory, ROM for short), Random Access Memory (RAM for short), Various media that can store computer programs, such as mobile hard disks, magnetic disks, or optical disks.
- An embodiment of the present disclosure also provides an electronic device, including a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the foregoing method embodiments.
- the aforementioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the aforementioned processor, and the input-output device is connected to the aforementioned processor.
- the foregoing processor may be configured to execute the following steps through a computer program:
- S1 in the case of detecting a parking instruction indicating that the target vehicle has stopped, collect an image of the location of the target vehicle through an image acquisition device installed on the target vehicle;
- S3 Determine whether the target parking position is a compliant parking position by judging whether the target parking position is located in the designated parking area.
- the foregoing processor may be configured to execute the following steps through a computer program:
- S11 in the case of detecting a parking instruction indicating that the target vehicle has stopped, collect an image of the location of the target vehicle through an image acquisition device installed on the target vehicle;
- S12 Send an image to a server, so that the server recognizes the target parking position of the target vehicle according to the image;
- S14 Determine whether the target parking position is a compliant parking position by judging whether the target parking position is located in the designated parking area.
- the foregoing processor may be configured to execute the following steps through a computer program:
- S21 Acquire an image sent by the target vehicle, where the image is an image of the location of the target vehicle collected by the image acquisition device installed on the target vehicle when the target vehicle detects the parking instruction, and the parking instruction is used for Indicate that the target vehicle has stopped;
- S23 Send the identified target parking location to the target vehicle, so that the target vehicle determines whether the target parking location is a compliant parking location by determining whether the target parking location is located in a designated parking area.
- modules or steps of the present disclosure can be implemented by a general computing device, and they can be concentrated on a single computing device or distributed in a network composed of multiple computing devices.
- they can be implemented with program codes executable by the computing device, so that they can be stored in the storage device for execution by the computing device, and in some cases, can be executed in a different order than here.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (20)
- 一种位置合规识别方法,其特征在于,包括:在检测到用于指示目标交通工具已停靠的停靠指令的情况下,通过所述目标交通工具上安装的图像采集设备采集所述目标交通工具所在位置的图像;根据所述图像识别所述目标交通工具的目标停靠位置;通过判断所述目标停靠位置是否位于指定停靠区域,确定所述目标停靠位置是否为合规停靠位置。
- 根据权利要求1所述的方法,其特征在于,所述根据所述图像识别所述目标交通工具的目标停靠位置包括:提取所述图像中的第一图像特征;将所述第一图像特征输入第一定位模型,以识别所述目标停靠位置。
- 根据权利要求1所述的方法,其特征在于,在根据所述图像识别所述目标交通工具的目标停靠位置之后,还包括:根据所述图像识别所述目标停靠位置的环境参数,其中,所述环境参数至少包括以下之一:周边是否存在建筑物遮挡、周边是否存在公共设施、是否位于所述指定停靠区域的范围内。
- 根据权利要求3所述的方法,其特征在于,所述通过判断所述目标停靠位置是否位于指定停靠区域,确定所述目标停靠位置是否为合规停靠位置包括:当所述目标停靠位置的环境参数满足预先设定的规则的情况下,确定所述目标停靠位置位于所述指定停靠区域,进而确定所述目标停 靠位置为合规停靠位置;当所述目标停靠位置的环境参数不满足预先设定的规则的情况下,确定所述目标停靠位置不位于所述指定停靠区域,进而确定所述目标停靠位置为不合规停靠位置。
- 根据权利要求4所述的方法,其特征在于,所述确定所述目标停靠位置为不合规停靠位置之后,所述方法还包括:执行以下至少之一的操作:将所述不合规停靠位置发送给服务器;发送警示信息,其中所述警示信息用于提示所述目标停靠位置为不合规停靠位置,和/或,用于提示距离所述目标停靠位置指定范围内的指定停靠区域。
- 根据权利要求1至5任一项所述的方法,其特征在于,所述通过所述目标交通工具上安装的图像采集设备采集所述目标交通工具所在位置的图像包括:在预定时间段内采集目标交通工具所在位置的视频图像和/或照片图像,其中,所述目标交通工具包括共享交通工具。
- 一种位置合规识别方法,其特征在于,包括:在检测到用于指示目标交通工具已停靠的停靠指令的情况下,通过所述目标交通工具上安装的图像采集设备采集所述目标交通工具所在位置的图像;将所述图像发送给服务器,以使所述服务器根据所述图像识别所述目标交通工具的目标停靠位置;接收所述服务器返回的所述目标停靠位置;通过判断所述目标停靠位置是否位于指定停靠区域,确定所述目标停靠位置是否为合规停靠位置。
- 一种位置合规识别方法,其特征在于,包括:获取目标交通工具发送的图像,其中,所述图像为所述目标交通工具在检测到停靠指令的情况下,通过所述目标交通工具上安装的图像采集设备采集的所述目标交通工具所在位置的图像,所述停靠指令用于指示所述目标交通工具已停靠;根据所述图像识别所述目标交通工具的目标停靠位置;将识别出的所述目标停靠位置发送给所述目标交通工具,以使所述目标交通工具通过判断所述目标停靠位置是否位于指定停靠区域来确定所述目标停靠位置是否为合规停靠位置。
- 根据权利要求8所述的方法,其特征在于,所述根据所述图像识别所述目标交通工具的目标停靠位置包括:提取所述图像中的第二图像特征;将所述第二图像特征输入第二定位模型,以识别所述目标停靠位置。
- 一种位置合规识别装置,其特征在于,包括:第一采集模块,用于在检测到用于指示目标交通工具已停靠的停靠指令的情况下,通过所述目标交通工具上安装的图像采集设备采集所述目标交通工具所在位置的图像;第一识别模块,用于根据所述图像识别所述目标交通工具的目标停靠位置;第一确定模块,用于通过判断所述目标停靠位置是否位于指定停靠区域,确定所述目标停靠位置是否为合规停靠位置。
- 根据权利要求10所述的装置,其特征在于,所述识别模块包括:第一提取单元,用于提取所述图像中的第一图像特征;第一输入单元,用于将所述第一图像特征输入第一定位模型,以识别所述目标停靠位置。
- 根据权利要求10所述的装置,其特征在于,所述装置还包括:第三识别模块,用于在根据所述图像识别所述目标交通工具的目标停靠位置之后,根据所述图像识别所述目标停靠位置的环境参数,其中,所述环境参数至少包括以下之一:周边是否存在建筑物遮挡、周边是否存在公共设施、是否位于所述指定停靠区域的范围内。
- 根据权利要求12所述的装置,其特征在于,所述第一确定模块用于:当所述目标停靠位置的环境参数满足预先设定的规则的情况下,确定所述目标停靠位置位于所述指定停靠区域,进而确定所述目标停靠位置为合规停靠位置;当所述目标停靠位置的环境参数不满足预先设定的规则的情况下,确定所述目标停靠位置不位于所述指定停靠区域,进而确定所述目标停靠位置为不合规停靠位置。
- 根据权利要求13所述的装置,其特征在于,所述装置还包括:执行模块,用于在所述确定所述目标停靠位置为不合规停靠位置 之后,执行以下至少之一的操作:将所述不合规停靠位置发送给服务器;发送警示信息,其中所述警示信息用于提示所述目标停靠位置为不合规停靠位置,和/或,用于提示距离所述目标停靠位置指定范围内的指定停靠区域。
- 根据权利要求10至14任一项所述的装置,其特征在于,所述第一采集模块包括:采集单元,用于在预定时间段内采集目标交通工具所在位置的视频图像和/或照片图像,其中,所述目标交通工具包括共享交通工具。
- 一种位置合规识别装置,其特征在于,包括:第二采集模块,用于在检测到用于指示目标交通工具已停靠的停靠指令的情况下,通过所述目标交通工具上安装的图像采集设备采集所述目标交通工具所在位置的图像;第一发送模块,用于将所述图像发送给服务器,以使所述服务器根据所述图像识别所述目标交通工具的目标停靠位置;接收模块,用于接收所述服务器返回的所述目标停靠位置;第二确定模块,用于通过判断所述目标停靠位置是否位于指定停靠区域,确定所述目标停靠位置是否为合规停靠位置。
- 一种位置合规识别装置,其特征在于,包括:获取模块,用于获取目标交通工具发送的图像,其中,所述图像为所述目标交通工具在检测到停靠指令的情况下,通过所述目标交通工具上安装的图像采集设备采集的所述目标交通工具所在位置的图 像,所述停靠指令用于指示所述目标交通工具已停靠;第二识别模块,用于根据所述图像识别所述目标交通工具的目标停靠位置;第二发送模块,用于将识别出的所述目标停靠位置发送给所述目标交通工具,以使所述目标交通工具通过判断所述目标停靠位置是否位于指定停靠区域来确定所述目标停靠位置是否为合规停靠位置。
- 根据权利要求17所述的装置,其特征在于,所述第二识别模块包括:第二提取单元,用于提取所述图像中的第二图像特征;第二输入单元,用于将所述第二图像特征输入第二定位模型,以识别所述目标停靠位置。
- 一种计算机可读存储介质,其特征在于,所述存储介质中存储有计算机程序,其中,所述计算机程序被设置为运行时执行所述权利要求1至9任一项中所述的方法。
- 一种电子装置,包括存储器和处理器,其特征在于,所述存储器中存储有计算机程序,所述处理器被设置为运行所述计算机程序以执行所述权利要求1至9任一项中所述的方法。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910755330.4 | 2019-08-15 | ||
CN201910755330.4A CN110490127A (zh) | 2019-08-15 | 2019-08-15 | 位置合规识别方法及装置、存储介质、电子装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021027944A1 true WO2021027944A1 (zh) | 2021-02-18 |
Family
ID=68551311
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/109344 WO2021027944A1 (zh) | 2019-08-15 | 2020-08-14 | 位置合规识别方法及装置、存储介质、电子装置 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110490127A (zh) |
WO (1) | WO2021027944A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114463632A (zh) * | 2022-01-14 | 2022-05-10 | 摩拜(北京)信息技术有限公司 | 一种共享车辆的还车处理方法、装置及共享车辆 |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110490127A (zh) * | 2019-08-15 | 2019-11-22 | 北京致行慕远科技有限公司 | 位置合规识别方法及装置、存储介质、电子装置 |
CN111559732A (zh) * | 2020-04-28 | 2020-08-21 | 哈工大机器人(中山)有限公司 | 一种基于2d视觉的汽车油箱位置和角度识别方法及*** |
CN113781792B (zh) * | 2021-09-06 | 2023-11-24 | 腾讯科技(深圳)有限公司 | 停放检测***、方法及相关设备 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9076060B2 (en) * | 2011-12-13 | 2015-07-07 | Electronics And Telecommunications Research Institute | Parking lot management system in working cooperation with intelligent cameras |
CN106601011A (zh) * | 2017-01-03 | 2017-04-26 | 上海量明科技发展有限公司 | 共享车辆及其停靠位置的判定方法、装置和*** |
CN106781445A (zh) * | 2017-02-13 | 2017-05-31 | 上海量明科技发展有限公司 | 共享车辆的信息输出方法、客户端及*** |
CN106779971A (zh) * | 2017-01-03 | 2017-05-31 | 上海量明科技发展有限公司 | 共享车辆协助状态下的计费方法、客户端及*** |
CN106871860A (zh) * | 2017-04-12 | 2017-06-20 | 上海量明科技发展有限公司 | 共享单车停靠方向的判定方法、***与共享单车 |
CN107067357A (zh) * | 2017-04-12 | 2017-08-18 | 上海量明科技发展有限公司 | 共享车辆停靠监管方法、***与共享车辆 |
CN110490127A (zh) * | 2019-08-15 | 2019-11-22 | 北京致行慕远科技有限公司 | 位置合规识别方法及装置、存储介质、电子装置 |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103366598B (zh) * | 2013-07-15 | 2016-01-20 | 广州市浩云安防科技股份有限公司 | 一种车辆停靠到位检测***及检测方法 |
JP6761708B2 (ja) * | 2016-09-05 | 2020-09-30 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカPanasonic Intellectual Property Corporation of America | 駐車位置特定方法、駐車位置学習方法、駐車位置特定システム、駐車位置学習装置およびプログラム |
KR101915167B1 (ko) * | 2016-12-30 | 2018-11-06 | 현대자동차주식회사 | 자동 주차 시스템 및 자동 주차 방법 |
CN106504565B (zh) * | 2017-01-03 | 2023-06-20 | 上海量明科技发展有限公司 | 共享车辆停靠位置的判定方法、装置及*** |
CN106898024A (zh) * | 2017-04-12 | 2017-06-27 | 上海量明科技发展有限公司 | 共享车辆停靠监管方法、***与装置 |
CN107491765A (zh) * | 2017-08-29 | 2017-12-19 | 张羽 | 一种共享单车及其停车识别装置和*** |
CN109993789B (zh) * | 2017-12-29 | 2021-05-25 | 杭州海康威视数字技术股份有限公司 | 一种共享单车的违停判定方法、装置及相机 |
-
2019
- 2019-08-15 CN CN201910755330.4A patent/CN110490127A/zh active Pending
-
2020
- 2020-08-14 WO PCT/CN2020/109344 patent/WO2021027944A1/zh active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9076060B2 (en) * | 2011-12-13 | 2015-07-07 | Electronics And Telecommunications Research Institute | Parking lot management system in working cooperation with intelligent cameras |
CN106601011A (zh) * | 2017-01-03 | 2017-04-26 | 上海量明科技发展有限公司 | 共享车辆及其停靠位置的判定方法、装置和*** |
CN106779971A (zh) * | 2017-01-03 | 2017-05-31 | 上海量明科技发展有限公司 | 共享车辆协助状态下的计费方法、客户端及*** |
CN106781445A (zh) * | 2017-02-13 | 2017-05-31 | 上海量明科技发展有限公司 | 共享车辆的信息输出方法、客户端及*** |
CN106871860A (zh) * | 2017-04-12 | 2017-06-20 | 上海量明科技发展有限公司 | 共享单车停靠方向的判定方法、***与共享单车 |
CN107067357A (zh) * | 2017-04-12 | 2017-08-18 | 上海量明科技发展有限公司 | 共享车辆停靠监管方法、***与共享车辆 |
CN110490127A (zh) * | 2019-08-15 | 2019-11-22 | 北京致行慕远科技有限公司 | 位置合规识别方法及装置、存储介质、电子装置 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114463632A (zh) * | 2022-01-14 | 2022-05-10 | 摩拜(北京)信息技术有限公司 | 一种共享车辆的还车处理方法、装置及共享车辆 |
Also Published As
Publication number | Publication date |
---|---|
CN110490127A (zh) | 2019-11-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021027944A1 (zh) | 位置合规识别方法及装置、存储介质、电子装置 | |
US11144786B2 (en) | Information processing apparatus, method for controlling information processing apparatus, and storage medium | |
CN109063768B (zh) | 车辆重识别方法、装置及*** | |
Montazzolli et al. | Real-time brazilian license plate detection and recognition using deep convolutional neural networks | |
CN109886222B (zh) | 人脸识别方法、神经网络训练方法、装置及电子设备 | |
WO2020042984A1 (zh) | 一种车辆行为检测方法及装置 | |
WO2021051601A1 (zh) | 利用Mask R-CNN选择检测框的方法及***、电子装置及存储介质 | |
CN105321350B (zh) | ***检测方法及装置 | |
US20170323452A1 (en) | Method and device for traffic sign recognition | |
CN112085952B (zh) | 监控车辆数据方法、装置、计算机设备及存储介质 | |
JP2016062610A (ja) | 特徴モデル生成方法及び特徴モデル生成装置 | |
US20150286884A1 (en) | Machine learning approach for detecting mobile phone usage by a driver | |
CN109993032B (zh) | 一种共享单车目标识别方法、装置及相机 | |
CN112052815B (zh) | 一种行为检测方法、装置及电子设备 | |
WO2020155790A1 (zh) | 理赔信息提取方法和装置、电子设备 | |
Varghese et al. | An efficient algorithm for detection of vacant spaces in delimited and non-delimited parking lots | |
US11250279B2 (en) | Generative adversarial network models for small roadway object detection | |
WO2023231991A1 (zh) | 交通信号灯感知方法、装置、设备及存储介质 | |
CN112329881A (zh) | 车牌识别模型训练方法、车牌识别方法及装置 | |
CN109063790B (zh) | 对象识别模型优化方法、装置和电子设备 | |
Buhus et al. | Automatic parking access using openalpr on raspberry pi3 | |
CN110826415A (zh) | 一种场景图像中车辆的重识别方法及设备 | |
Aneesh et al. | Real-time traffic light detection and recognition based on deep retinanet for self driving cars | |
Sikirić et al. | Image representations on a budget: Traffic scene classification in a restricted bandwidth scenario | |
CN111444911B (zh) | 车牌识别模型的训练方法及装置、车牌识别方法及装置 |
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: 20851562 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20851562 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20851562 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 07/11/2022) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20851562 Country of ref document: EP Kind code of ref document: A1 |