CN113343782A - Expressway sign plate detection method based on unmanned aerial vehicle remote sensing - Google Patents
Expressway sign plate detection method based on unmanned aerial vehicle remote sensing Download PDFInfo
- Publication number
- CN113343782A CN113343782A CN202110540468.XA CN202110540468A CN113343782A CN 113343782 A CN113343782 A CN 113343782A CN 202110540468 A CN202110540468 A CN 202110540468A CN 113343782 A CN113343782 A CN 113343782A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- sign
- detection
- remote sensing
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 238000012937 correction Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013461 design Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/14—Receivers specially adapted for specific applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a highway sign plate detection method based on unmanned aerial vehicle remote sensing, which determines the starting point and the end point of a road section needing to detect a sign plate; acquiring a list of sign signs to be laid in a detection interval; adopting an unmanned aerial vehicle carrying camera equipment and a GPS module, and carrying out rough detection on a detection area based on an image recognition technology; an unmanned aerial vehicle carrying a binocular camera and a GPS module is adopted, and the mark sign is accurately detected based on image recognition and a binocular vision algorithm; and obtaining the damage detection result of the mark label in the detection area. The invention realizes the standardized and automatic detection of the highway sign plate, reduces the life danger and traffic influence brought by the traditional manual method, and effectively eliminates the influence of subjective judgment of observers on objective evaluation standards.
Description
Technical Field
The invention belongs to the field of road engineering, and particularly relates to a method for detecting a sign plate of an expressway.
Background
With the continuous growth of national economy, road traffic, which is the infrastructure of national economy, is also developed vigorously. According to the statistical data of the department of transportation, the total mileage of the roads in China reaches 501.25 kilometers by 2019, the density of the roads is 52.21 kilometers per hundred square kilometers, and the road density is increased by 1.73 kilometers per hundred square kilometers compared with the last year. When a highway network is constructed in a large scale, people have higher and higher requirements on operation management and maintenance of high-grade roads. In recent years, the proportion of highway maintenance mileage to total highway mileage is increasing: the highway maintenance mileage accounts for 97.5% in 2014; the highway maintenance mileage of 2019 is 495.31 kilometers, and accounts for 98.8% of the total highway mileage.
In order to ensure safe, rapid, economical and comfortable operation and normal use of the highway, necessary facilities along the highway are arranged according to regulations. The facilities along the highway mainly comprise traffic safety facilities, traffic management facilities, auxiliary facilities and the like. During the operation of the expressway, facilities along the expressway are damaged, such as damage of protective facilities, damage of isolation barriers and the like, particularly the damage of the sign plate, so that the service level of the expressway within the service life is reduced, the service function of the expressway is seriously influenced, the comprehensive benefits of transportation are prevented from being brought into play, and traffic accidents are increased. Therefore, there is a need to develop an automatic detection system for the sign plate of the highway, which provides reference for the management and maintenance department of the highway.
At present, the detection method for the highway sign plate is relatively simple, mainly depends on manual observation and troubleshooting of the lacking or damaged sign plate according to the assessment standard of the highway technical condition, manual measurement or estimation of damage degree and the like, fills in a facility damage questionnaire along the line, and calculates the Technical Condition Index (TCI) of the facility along the line as the evaluation index of the facility along the line. In addition, some detection technologies based on vehicle-mounted equipment exist at present, but the technologies still depend on manual selection and screening of defective facilities by field workers in the later stage, and automatic standardized detection and evaluation cannot be realized.
Disclosure of Invention
In order to solve the technical problems mentioned in the background technology, the invention provides a highway sign plate detection method based on unmanned aerial vehicle remote sensing.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
a highway sign plate detection method based on unmanned aerial vehicle remote sensing comprises the following steps:
(1) determining a starting point and an end point of a road section needing to detect the sign plate;
(2) acquiring a list of sign signs to be laid in a detection interval;
(3) adopting an unmanned aerial vehicle carrying camera equipment and a GPS module, and carrying out rough detection on a detection area based on an image recognition technology;
(4) an unmanned aerial vehicle carrying a binocular camera and a GPS module is adopted, and the mark sign is accurately detected based on image recognition and a binocular vision algorithm;
(5) and (4) integrating the results of the steps (2) to (4) to obtain the damage detection result of the sign plate in the detection area.
Further, in the step (1), the detection road section is divided into a plurality of small blocks according to the interval of 1km, if the last section is less than 1km, the number of the starting point pile and the number of the terminal point pile of the ith small block are recorded as iSPAnd iEP。
Further, in the step (2), a list of the signs to be arranged in the detection interval is obtained by consulting design and construction data or expert consultation, and the list comprises the number, the type, the shape and the position information of the signs to be arranged in the detection interval.
Further, in the step (3), the unmanned aerial vehicle carrying the camera device and the GPS module performs cruise shooting from a starting point to an end point of the detection interval, the flight position is right above a road center line, the flight direction is a road driving direction, the flight height is adjusted according to actual obstacle conditions, the flight speed is adjusted according to the model and weather conditions of the unmanned aerial vehicle, the GPS information of the unmanned aerial vehicle is recorded while shooting, the shot video is identified through an image identification technology based on YOLO V3, and the rough number, type and position information of the sign signs in the detection interval is acquired.
Further, in step (4), before shooting by using the unmanned aerial vehicle carrying the binocular camera and the GPS module, the binocular camera is calibrated.
Further, in step (4), according to the position information obtained by rough detection in step (3), the unmanned aerial vehicle carrying the binocular camera and the GPS module is adopted to carry out cruising and fixed-point shooting in the detection interval, and the specific process is as follows:
after the unmanned aerial vehicle takes off, the unmanned aerial vehicle is firstly raised to a safe and spacious height of more than 30m, when the unmanned aerial vehicle cruises to be close to a certain mark sign position acquired in the step (3), the flying height is lowered, the mark sign surface content of the mark sign can be shot in a forward direction in a head-up mode and is in the center of a picture, a picture is shot by using a binocular camera and corresponding position information is recorded, after the shooting is finished, the unmanned aerial vehicle is raised to the safe height to continue to cruise to the next position, the shot picture is subjected to picture recognition and binocular vision ranging algorithm to acquire accurate mark sign type, size and position information, the coincidence rate is compared with a standard size template to judge whether the mark sign is damaged, if the coincidence rate is lower than a set threshold value, the mark sign is judged to be damaged, and if the coincidence rate is not higher than the set threshold value, the mark sign is judged to be intact.
Further, the image identification and binocular vision ranging algorithm sequentially comprises binocular calibration, distortion correction, stereo correction, image identification, stereo matching, three-dimensional coordinate back calculation and size calculation and damage detection.
Further, in the step (5), the types, positions and damage information of the sign signs obtained in the steps (3) and (4) are collected, whether the sign signs are lacked is determined by comparing the type, the positions and the damage information with the list to be laid in the step (2), and finally, a sign damage questionnaire is output.
Adopt the beneficial effect that above-mentioned technical scheme brought:
the invention realizes the standardized and automatic detection of the highway marking sign, greatly reduces the life risk and traffic influence brought by the traditional manual method, effectively eliminates the influence of subjective judgment of observers on objective evaluation standards, has innovation on the detection method and has more objective accuracy on the evaluation content.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a video screenshot of a sign rough review in an embodiment;
FIG. 3 is a schematic diagram of an unmanned aerial vehicle carrying binocular cameras in the embodiment;
fig. 4 is a binocular view of the photographing sign of the unmanned aerial vehicle in the embodiment;
fig. 5 is a diagram illustrating the binocular picture detection result of the signage in the embodiment.
Detailed Description
The technical scheme of the invention is explained in detail in the following with the accompanying drawings.
The invention designs a highway sign plate detection method based on unmanned aerial vehicle remote sensing, which comprises the following steps:
step 1: determining a starting point and an end point of a road section needing to detect the sign plate;
step 2: acquiring a list of sign signs to be laid in a detection interval;
and step 3: adopting an unmanned aerial vehicle carrying camera equipment and a GPS module, and carrying out rough detection on a detection area based on an image recognition technology;
and 4, step 4: an unmanned aerial vehicle carrying a binocular camera and a GPS module is adopted, and the mark sign is accurately detected based on image recognition and a binocular vision algorithm;
and 5: and (4) integrating the results of the steps 2-4 to obtain the damage detection result of the sign board in the detection area.
In this embodiment, it is preferable that, for step 1 above, the detection interval range is divided into n small blocks at intervals of 1km, and the last segment is less than 1km and counted as 1 km. Let the small block of the detected object be i small block, where i is 1,2,3, …, n. Recording the starting point stake number and the terminal point stake number of the ith small block as iSPAnd iEP。
In this embodiment, preferably, in step 2, the number, type and position information list of the sign signs to be laid in the detection interval is obtained by referring to design and construction data or expert consultation, and is used as the basis for detecting the absence of the sign signs. The manifest template is shown in table 1 below:
TABLE 1 List of sign plate layout
In this embodiment, preferably, in step 3, the unmanned aerial vehicle equipped with the camera and the GPS is used to perform cruise shooting from the start point to the end point of the detection section, the flight position is directly above the road centerline, the flight direction is the road driving direction, the flight height is adjusted according to the actual obstacle condition, the height is preferably 10m to 30m, the flight speed is adjusted according to the model and the weather condition of the unmanned aerial vehicle, preferably about 10m/s, the shooting mode is a forward depression angle of 45 degrees, and the GPS information of the unmanned aerial vehicle is recorded while shooting. The shot video is identified by an image identification technology based on YOLO V3, and the rough number, type and position information of the sign signs in the detection section are acquired.
In this embodiment, preferably, for step 4, the unmanned aerial vehicle carrying the calibrated binocular camera is used to perform cruising and fixed-point shooting in the detection zone according to the position information obtained in step 3, and the specific manner is as follows: after the unmanned aerial vehicle takes off, the unmanned aerial vehicle firstly rises to the safe and spacious height of more than 30m, when cruising to the position nearby a certain mark sign, the flying height drops to about 8 to 10m so as to shoot the face content of the mark sign at head view and be in the center of the picture, a binocular camera is used for shooting pictures and recording corresponding position information, and after the shooting is finished, the unmanned aerial vehicle rises to the safe height again to continue cruising to the next position. The picture obtained by shooting obtains accurate type, size and position information of the sign plate through picture recognition and a binocular vision distance measurement algorithm, whether the sign plate is damaged or not is judged through comparing the coincidence rate with a standard size template, if the coincidence rate is lower than a threshold value alpha, the sign plate is judged to be damaged, and if not, the sign plate is intact. The threshold alpha can be adjusted according to the calibration precision of the binocular camera and the actual requirement of the project, and is preferably 80% to 90%.
Before using the unmanned aerial vehicle for detection, calibration of a binocular camera is carried out. On subaerial camera with two the same models carried unmanned aerial vehicle, the position and the angle of adjustment camera after fixing, but make it take off the back and directly shoot and need not readjustment. After the relative position and angle between the cameras are guaranteed not to change any more, the unmanned aerial vehicle takes off and hovers in the air, the calibration is started by using the calibration plate, and the calibration plate should be a large-size high-precision calibration plate as far as possible, so that the calibration effect is better; and during calibration, the calibration plate is shot by using two cameras at the same time, then the calibration plate is moved and shot again, the shot picture set can contain all angles and positions of the calibration plate as far as possible while the calibration plate is kept in the range of the view-finding frame, and the picture set is used as a basis for calibration.
After a calibration picture set is obtained, starting to patrol according to the flight scheme, and after a detection picture set is obtained by shooting, processing the detection picture set by using a binocular vision ranging algorithm, wherein the method mainly comprises the following parts:
(1) and (5) binocular calibration. The mapping process from an object on an image to an object in three-dimensional space is in effect a transformation of the coordinate system. The real physical coordinate of a certain point on the image can be obtained through the conversion of the physical relation, then the image plane is mapped to a certain plane of the camera coordinate system to obtain the coordinate of the point in the camera coordinate system, and finally the actual three-dimensional coordinate of the point can be determined through the rotation translation transformation of the camera coordinate system and the world coordinate system. Based on the principle, the process of solving the transformation matrix through calculation is calibration, namely, the internal reference and the external reference of the binocular camera are obtained, the internal reference is determined by a lens and a camera photosensitive element, and the external reference is determined by the relative position angle of the two cameras and the like.
(2) And (5) distortion correction. After the picture is shot through the lens, certain deformation inevitably occurs, particularly, the edge part of the picture is distorted towards the center, which affects the precision of subsequent processing, so that the distortion correction needs to be performed by using the internal reference obtained by calibration, and the actual situation is recovered.
(3) And (5) performing stereo correction. In the installation and adjustment processes of the binocular camera, the visual angles of the two lenses cannot be guaranteed to be completely parallel and on the same horizontal line, and the precision of subsequent processing can be influenced by slight difference, so that external parameters obtained by calibration need to be used for stereo correction, and pictures shot by the two cameras are located on the same plane.
(4) And (5) image recognition. After the binocular pictures are restored to the same plane, corresponding points in the two pictures have the same line coordinates, then the plate surface part of the mark plate in the binocular pictures is extracted through an image recognition algorithm based on a fast RCNN network, parallax information of the plate surface of the mark plate in the binocular pictures can be obtained through stereo matching, and further distance, size information and the like are obtained.
(5) And (5) stereo matching. Through feature point matching, binocular pictures can be spliced together to calculate parallax. In the traditional algorithm, the SIFT algorithm is adopted for the whole picture in the feature point matching process, and a better matching effect can be realized in indoor and other closed places after parameter tuning, but the matching effect is poor for open scenes such as roads and the like due to the lack of feature points, unobvious textures and the like. After the signboard face part is extracted through image recognition, the extracted part can be subjected to feature point matching only, a quick and accurate matching effect can be obtained, and the calculated parallax is accurate.
(6) And (4) performing inverse calculation on the three-dimensional coordinates and calculating the size. After an accurate parallax result is obtained, the coordinate points in the picture can be restored to three-dimensional coordinate points in the real world through matrix inverse operation according to the conversion matrix obtained by calibration, and therefore the three-dimensional coordinates of each corner point of the outer contour of the face are calculated. And the dimension information of the card face can be obtained by directly calculating the Euclidean distance between the angular points.
(7) And (4) detecting breakage. And after the actually measured size information of the signboard surface is obtained, comparing the size information with a standard signboard surface template with the same shape according to different shapes, and calculating the coincidence rate. If the coincidence rate is higher than the set threshold value alpha, the label is considered to be in good condition; if the overlap ratio is significantly lower than the threshold α, it is determined as a breakage.
In this embodiment, preferably, for the step 5, the information on the type, position and integrity of the sign board obtained in the step 3 and the step 4 is summarized, and the information is compared with the list to be laid obtained in the step 2 to determine whether the sign board is missing, and finally, a damage questionnaire for the sign board is output. And summarizing all damage questionnaires of the n small blocks in the detection interval, and outputting the detection result of the mark label.
TABLE 2 index tag damage questionnaire
The whole process of the invention is shown in figure 1.
The following detailed description of the detection method is made in conjunction with specific application cases:
s1: a certain section of the Nanjing City Ningxuan high speed of Jiangsu province is selected as a detection interval and is divided into n small blocks at intervals of every 1 km.
S2: and counting the list of the sign plates to be laid in the detection interval according to the design data.
S3: the unmanned aerial vehicle of Dajiang imperial 2 zoom version is used for cruising, recording and shooting, the flying height is 70m, the flying speed is 7m/s, the position of the flying is right above the central separation belt, the track is forward along the driving direction, the lens faces downwards, the inclination angle is 45 degrees, and meanwhile, the GPS information is recorded. A screenshot at a certain moment of recording a video is shown in fig. 2. And preliminarily identifying the sign plate by an image identification and classification technology and outputting GPS coordinate information.
S4: the big M600 Pro unmanned aerial vehicle is used for carrying two binocular cameras formed by combining the Yu 2 zoom type small unmanned aerial vehicles, and the binocular picture of the sign is shot in a cruising and fixed-point shooting mode according to the GPS coordinate information provided by S3. The device mounting method is shown in fig. 3, and the captured binocular picture is shown in fig. 4. The signs are detected by picture recognition and binocular vision algorithm, and the output result is shown in fig. 5.
S5: and summarizing the results of S3 and S4, outputting an ith area sign damage questionnaire in the detection area, summarizing the damage questionnaire of all areas in the detection area, and outputting a sign detection result in the detection area.
The embodiments are only for illustrating the technical idea of the present invention, and the technical idea of the present invention is not limited thereto, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the scope of the present invention.
Claims (8)
1. A highway sign plate detection method based on unmanned aerial vehicle remote sensing is characterized by comprising the following steps:
(1) determining a starting point and an end point of a road section needing to detect the sign plate;
(2) acquiring a list of sign signs to be laid in a detection interval;
(3) adopting an unmanned aerial vehicle carrying camera equipment and a GPS module, and carrying out rough detection on a detection area based on an image recognition technology;
(4) an unmanned aerial vehicle carrying a binocular camera and a GPS module is adopted, and the mark sign is accurately detected based on image recognition and a binocular vision algorithm;
(5) and (4) integrating the results of the steps (2) to (4) to obtain the damage detection result of the sign plate in the detection area.
2. The method for detecting the signboard on the expressway remote sensing by using the unmanned aerial vehicle as claimed in claim 1, wherein in the step (1), the detected section is divided into a plurality of small blocks at intervals of 1km, the last section is counted by 1km if the last section is less than 1km, and the number of the starting point stake and the number of the ending point stake of the ith small block are counted as iSPAnd iEP。
3. The unmanned aerial vehicle remote sensing-based highway sign board detection method according to claim 1, wherein in step (2), a list of sign boards to be laid in the detection interval is obtained by consulting design and construction data or expert consultation, and the list contains information on the number, types, shapes and positions of the sign boards to be laid in the detection interval.
4. The unmanned aerial vehicle remote sensing-based highway sign detection method according to claim 1, wherein in step (3), the unmanned aerial vehicle carrying the camera device and the GPS module performs cruise shooting from the starting point to the end point of the detection interval, the flying position is right above the road center line, the flying direction is the road driving direction, the flying height is adjusted according to the actual obstacle condition, the flying speed is adjusted according to the model and the weather condition of the unmanned aerial vehicle, the GPS information of the unmanned aerial vehicle is recorded while shooting, the shot video is identified through an image identification technology based on YOLO V3, and the rough number, type and position information of the sign in the detection interval is obtained.
5. The unmanned aerial vehicle remote sensing-based highway sign board detection method according to claim 1, wherein in step (4), the binocular camera is calibrated before shooting by the unmanned aerial vehicle carrying the binocular camera and the GPS module.
6. The unmanned aerial vehicle remote sensing-based highway sign signboard detection method according to claim 1, wherein in step (4), according to the position information obtained by rough detection in step (3), an unmanned aerial vehicle carrying a binocular camera and a GPS module is adopted to carry out cruising and fixed-point shooting in a detection interval, and the specific process is as follows:
after the unmanned aerial vehicle takes off, the unmanned aerial vehicle is firstly raised to a safe and spacious height of more than 30m, when the unmanned aerial vehicle cruises to be close to a certain mark sign position acquired in the step (3), the flying height is lowered, the mark sign surface content of the mark sign can be shot in a forward direction in a head-up mode and is in the center of a picture, a picture is shot by using a binocular camera and corresponding position information is recorded, after the shooting is finished, the unmanned aerial vehicle is raised to the safe height to continue to cruise to the next position, the shot picture is subjected to picture recognition and binocular vision ranging algorithm to acquire accurate mark sign type, size and position information, the coincidence rate is compared with a standard size template to judge whether the mark sign is damaged, if the coincidence rate is lower than a set threshold value, the mark sign.
7. The unmanned aerial vehicle remote sensing-based highway sign signboard detection method according to claim 1, wherein the image recognition and binocular vision ranging algorithm comprises binocular calibration, distortion correction, stereo correction, image recognition, stereo matching, three-dimensional coordinate back calculation and size calculation, and breakage detection in sequence.
8. The unmanned aerial vehicle remote sensing-based highway sign detection method according to claim 1, wherein in step (5), the types, positions and damage information of the sign signs obtained in steps (3) and (4) are collected, whether the sign signs are missing or not is determined by comparing with the list to be laid in step (2), and finally, a sign damage questionnaire is output.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110540468.XA CN113343782B (en) | 2021-05-18 | 2021-05-18 | Expressway sign label detection method based on unmanned aerial vehicle remote sensing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110540468.XA CN113343782B (en) | 2021-05-18 | 2021-05-18 | Expressway sign label detection method based on unmanned aerial vehicle remote sensing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113343782A true CN113343782A (en) | 2021-09-03 |
CN113343782B CN113343782B (en) | 2024-04-23 |
Family
ID=77470866
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110540468.XA Active CN113343782B (en) | 2021-05-18 | 2021-05-18 | Expressway sign label detection method based on unmanned aerial vehicle remote sensing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113343782B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2615107A (en) * | 2022-01-28 | 2023-08-02 | Continental Autonomous Mobility Germany GmbH | System and apparatus suitable for sign recognition and/or restoration thereof, and processing method in association thereto |
WO2024087290A1 (en) * | 2022-10-26 | 2024-05-02 | 中公高科养护科技股份有限公司 | Road sign and security protection facility loss detection method and system, and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140061156A (en) * | 2012-11-13 | 2014-05-21 | 한국건설기술연구원 | Position detecting method of road traffic sign |
CN108306217A (en) * | 2018-02-11 | 2018-07-20 | 广州市极臻智能科技有限公司 | A kind of overhead high-voltage wire intelligent independent is along conducting wire flight cruising inspection system and method |
CN109297428A (en) * | 2018-11-21 | 2019-02-01 | 武汉珈鹰智能科技有限公司 | A kind of high-precision deformation based on unmanned plane patrols survey technology method |
CN111288890A (en) * | 2020-02-13 | 2020-06-16 | 福建农林大学 | Road sign dimension and height automatic measurement method based on binocular photogrammetry technology |
-
2021
- 2021-05-18 CN CN202110540468.XA patent/CN113343782B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140061156A (en) * | 2012-11-13 | 2014-05-21 | 한국건설기술연구원 | Position detecting method of road traffic sign |
CN108306217A (en) * | 2018-02-11 | 2018-07-20 | 广州市极臻智能科技有限公司 | A kind of overhead high-voltage wire intelligent independent is along conducting wire flight cruising inspection system and method |
CN109297428A (en) * | 2018-11-21 | 2019-02-01 | 武汉珈鹰智能科技有限公司 | A kind of high-precision deformation based on unmanned plane patrols survey technology method |
CN111288890A (en) * | 2020-02-13 | 2020-06-16 | 福建农林大学 | Road sign dimension and height automatic measurement method based on binocular photogrammetry technology |
Non-Patent Citations (1)
Title |
---|
刘志颖;缪希仁;陈静;江灏;: "电力架空线路巡检可见光图像智能处理研究综述", 电网技术, vol. 44, no. 03, 13 August 2019 (2019-08-13), pages 1057 - 1069 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2615107A (en) * | 2022-01-28 | 2023-08-02 | Continental Autonomous Mobility Germany GmbH | System and apparatus suitable for sign recognition and/or restoration thereof, and processing method in association thereto |
WO2024087290A1 (en) * | 2022-10-26 | 2024-05-02 | 中公高科养护科技股份有限公司 | Road sign and security protection facility loss detection method and system, and medium |
Also Published As
Publication number | Publication date |
---|---|
CN113343782B (en) | 2024-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
CN110322702B (en) | Intelligent vehicle speed measuring method based on binocular stereo vision system | |
CN105654732A (en) | Road monitoring system and method based on depth image | |
CN102867417B (en) | Taxi anti-forgery system and taxi anti-forgery method | |
CN109871776B (en) | All-weather lane line deviation early warning method | |
CN113343782B (en) | Expressway sign label detection method based on unmanned aerial vehicle remote sensing | |
CN106978774A (en) | A kind of road surface pit automatic testing method | |
CN111272139B (en) | Monocular vision-based vehicle length measuring method | |
CN106296814A (en) | Highway maintenance detection and virtual interactive interface method and system | |
CN113011283B (en) | Non-contact type rail sleeper relative displacement real-time measurement method based on video | |
CN110444043B (en) | Parking space inspection system and method based on positioning technology | |
CN113255578B (en) | Traffic identification recognition method and device, electronic equipment and storage medium | |
CN112070756B (en) | Three-dimensional road surface disease measuring method based on unmanned aerial vehicle oblique photography | |
CN109747681A (en) | A kind of train positioning device and method | |
CN111288890A (en) | Road sign dimension and height automatic measurement method based on binocular photogrammetry technology | |
CN112949479B (en) | Non-contact type rail sleeper relative displacement real-time measurement method based on deep learning and perspective transformation | |
CN115019514B (en) | Highway inspection system based on car networking | |
CN114972177A (en) | Road disease identification management method and device and intelligent terminal | |
CN112985311A (en) | Vehicle-mounted portable lightweight intelligent inspection method and system | |
CN113312987B (en) | Recognition method based on unmanned aerial vehicle road surface crack image | |
CN112949482B (en) | Non-contact type rail sleeper relative displacement real-time measurement method based on deep learning and visual positioning | |
CN117710843A (en) | Intersection dynamic signal timing scheme detection method based on unmanned aerial vehicle video | |
CN109784309A (en) | A kind of advertisement board on highway identifying system and method based on in-vehicle camera | |
CN117198057A (en) | Experimental method and system for road side perception track data quality inspection | |
CN110415299B (en) | Vehicle position estimation method based on set guideboard under motion constraint |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |