CN105716568A - Binocular camera ranging method in automatic pilot system - Google Patents
Binocular camera ranging method in automatic pilot system Download PDFInfo
- Publication number
- CN105716568A CN105716568A CN201610058151.1A CN201610058151A CN105716568A CN 105716568 A CN105716568 A CN 105716568A CN 201610058151 A CN201610058151 A CN 201610058151A CN 105716568 A CN105716568 A CN 105716568A
- Authority
- CN
- China
- Prior art keywords
- image
- binocular camera
- point
- region
- parallax
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C3/00—Measuring distances in line of sight; Optical rangefinders
Abstract
The invention provides a binocular camera ranging method in an automatic pilot system. The binocular camera ranging method includes the specific steps of 1, determining of a feature point, wherein the same target image is collected through a binocular camera, the feature point is determined in an image collected by one of cameras, and the image area containing the feature point is selected; 2, obtaining of a parallax error point, wherein the image area containing the feature point is selected from an image collected by the other camera to serve as a 'search window', the previously selected image area serves as a 'search template', matching is conducted in the 'search window', and the parallax error point is obtained; 3, positioning of the binocular camera, wherein a parallax error is obtained through the parallax error point of the binocular camera, and the distance between the binocular camera and the target image is calculated. The binocular camera ranging method has the advantages that after the method is adopted to calculate and obtain the parallax error, the position of the automatic pilot system can be positioned through the coordinate of a signboard owned by the automatic pilot system; meanwhile, the automatic pilot system is precisely positioned to be within 2 meters in the longitudinal direction.
Description
Technical field
The present invention relates to automatic Pilot field or safety assistant driving field, specifically binocular camera distance-finding method in a kind of automated driving system.
Background technology
Binocular range finding is classic algorithm inside mapping science.Simulate two eyes of people with two photographic head, observe parallax produced by same impact point by " left eye " and " right eye ", and then calculate the eyes distance to object.Therefore, the precision of binocular range-measurement system is also dependent on the difference of the same impact point coordinate in two photographic head acquired images respectively.So, in the picture that two photographic head gather, how accurately to detect same impact point and then become the difficulties of binocular range-measurement system.
Traditional binocular location algorithm is usually used in industrial detection, and general measure distance is all within 5 meters, and object all can have gem-pure textural characteristics, is beneficial to the suitable impact point of selection and carries out accurate disparity computation.And in automated driving system, due to binocular camera to measure usually with the distance of roadside traffic marking board, its difficult point is in that distance long-range guided missile causes the picture of shooting and unintelligible, chooses and mates impact point thus giving and calculate accurate parallax and bring difficulty.
Summary of the invention
In order to overcome above-mentioned technological deficiency, the present invention provides that a kind of method is simple, calculates accurately, and realizes binocular camera distance-finding method in the automated driving system of precision location.
Binocular camera distance-finding method in a kind of automated driving system: comprise the following steps:
S1: the determination of characteristic point: gather same target image by binocular camera, determines characteristic point and the selected image-region comprising described characteristic point wherein in the image of a camera collection；
S2: the acquisition of parallax point: choose the image-region comprising described characteristic point in the image of another camera collection as " search window ", then using selected previous image region as " search pattern ", " search window " mates, it is thus achieved that parallax point；
S3: the location of binocular camera: obtain parallax by the parallax of binocular camera point, calculates the distance between binocular camera and target image.
Preferably, choosing SAD function is adaptation function；
Preferably, the area of the image-region at " search pattern " place is more than the area of the image-region at " search window " place.
Binocular camera distance-finding method in automated driving system of the present invention, its advantage is: after adopting this method to calculate acquisition parallax, the position of the coordinate setting automated driving system of Sign Board that can be gathered around with automated driving system；Meanwhile, automated driving system is accurately located within longitudinal 2 meters.
Accompanying drawing explanation
Fig. 1 is binocular camera distance-finding method flow chart in automated driving system；
Fig. 2 is step S1 flow chart；
Wherein, nameplate is traffic marking board.
Detailed description of the invention
The invention will be further described below:
According to Fig. 1, Fig. 2, binocular camera distance-finding method in a kind of automated driving system, comprise the following steps:
S1: the determination of characteristic point
1., before intelligent automobile moves, binocular camera and biocular systems being carried out binocular calibration, the internal and external orientation to guarantee photographic head is accurate；
Further, in described calibration process, keep binocular camera baseline values, if baseline cannot keep level, can be realized by the focal length of adjustment binocular camera；
2., when intelligent automobile is run at high speed, utilize the image that binocular camera is collected by traffic marking board detection algorithm to be analyzed identifying, when left and right order image pair and when all containing traffic marking board, extract corresponding image pair；
Further, the corresponding image of extraction is to the image pair for comprising traffic marking board.
3., to the image extracted to being analyzed, identify the traffic marking board of image pair, extract the minimum external square boxes comprising traffic marking board, and in selected traffic marking board, redness justifies the highest summit of vertical direction of frame as characteristic point in described square boxes.
Further, square-shaped frame is sized to: 30X30 pixel is to 100X100 pixel, if the length of side of square boxes can not meet pixel condition, then terminates present image analysis, extracts subsequent time image, then determine characteristic point；
S2: the acquisition of parallax point
1., in left order image, centered by characteristic point, pixel extracts an image-region as " search pattern ", determine the coordinate of the central pixel point of left order image, then point extracts another image-region as " search window " centered by characteristic point in right order image；
2., in " search window " of right order image, extract an image-region identical with " search pattern " size, the image-region making extraction carries out gradient of disparity constrained matching with " search pattern ", the matching value obtained chooses smallest match value, and using the image-region corresponding to smallest match value as object matching district.
Further, the central pixel point in object matching district is the parallax point with left order images match；
Further, described gradient of disparity coupling is particularly as follows: in " search window " of right order image, from left to right translate a pixel successively, mate with " search pattern "；
Further, when measuring traffic marking board in vehicle traveling process, due to the baseline values of binocular camera, then will not produce the parallax in Y-direction, be sized to 9X9 pixel when what choose " search pattern "；" search window " be sized to 25X9 pixel；Then the image-region corresponding to smallest match value be sized to 9X9 pixel, carry out altogether 25-9+1=17 coupling, obtain 17 SAD functional values, in 17 SAD functional values of acquisition, the image-region corresponding to minima is object matching district.
S3: the location of binocular camera
1., adopt the coordinate of the central pixel point in the object matching district chosen in right order image, deduct the coordinate of the central pixel point in object matching district in left order image, it is thus achieved that parallax；
2., by parallax substituting into binocular range finding formula, calculate the binocular camera distance to traffic marking board, binocular range finding formula is as follows:
Wherein, T is binocular camera spacing, and f is the focal length of binocular camera, and Δ x is parallax, and Z is the traffic marking board distance to binocular camera.
Embodiment 1:
S1: the determination of characteristic point
1., before intelligent automobile moves, binocular camera and biocular systems being demarcated, calibration result is as follows:
Binocular camera spacing T is 324.11mm, and the focal distance f of binocular camera is 1878.60mm；
2., when intelligent automobile is run at high speed, the image that binocular camera is collected by traffic marking board detection algorithm is utilized to be analyzed identifying, namely when left and right order image pair and when all containing traffic marking board, extract the image pair comprising traffic marking board, and left images resolution is 1600X1200 pixel；
3., to the image extracted to being analyzed, thus identifying the traffic marking board of image pair, extract the minimum external square boxes comprising traffic marking board, record square frame and be sized to 50X50 pixel, and in selected traffic marking board, redness justifies the highest summit of vertical direction of frame as characteristic point in described square frame, record this characteristic point coordinate in the picture for (1148,651).
S2: the acquisition of parallax point
1., in left order image, centered by characteristic point, pixel extracts and is sized to the image-region of 9X9 pixel as " search pattern ", then in right order image same centered by the redness circle the highest summit of frame vertical direction point extract another image-region of being sized to 25X9 pixel as " search window "；
2., in " search window " of right order image, from left to right translate a region being sized to 9X9 pixel successively, " search pattern " that be sized to 9X9 pixel fixing with left order image mates, adaptation function adopts most widely used SAD function in images match, when from left to right all having mated, carry out altogether 25-9+1=17 coupling, obtain 17 SAD functional values, in 17 the SAD functional values obtained, minima is 65, and its corresponding image-region is object matching district；And the central pixel point in object matching district is the parallax point with left order images match, the coordinate recording this central pixel point is (1124,651)；
S3: the location of binocular camera
1., adopt the coordinate of the central pixel point in the object matching district chosen in right order image, deduct the coordinate of the central pixel point in object matching district in left order image, it is thus achieved that parallax is 24 pixels；
2., by the parallax of above-mentioned acquisition substitute into binocular range finding formula, calculate binocular camera to the distance of traffic marking board, be calculated as follows:
Finally, recording the actual range between traffic marking board and binocular camera is 26.63m, then measurement error is 1.26 meters.
Embodiment 2:
S1: the determination of characteristic point
1., before intelligent automobile moves, binocular camera and biocular systems being demarcated, calibration result is as follows:
Recording binocular camera spacing T is 324.11mm, and the focal distance f of binocular camera is 1878.60mm；
2., when intelligent automobile is run at high speed, the image that binocular camera is collected by traffic marking board detection algorithm is utilized to be analyzed identifying, namely when left and right order image pair and when all containing traffic marking board, extract the image pair comprising traffic marking board, and left images resolution is 1600X1200 pixel；
3., to the image extracted to being analyzed, thus identifying the traffic marking board of image pair, extract the minimum external square boxes comprising traffic marking board, record square frame and be sized to 62X62 pixel, and in selected traffic marking board, redness justifies the highest summit of vertical direction of frame as characteristic point in described square frame, record this characteristic point coordinate in the picture for (1051,620).
S2: the acquisition of parallax point
1., in left order image, centered by characteristic point, pixel extracts and is sized to the image-region of 9X9 pixel as " search pattern ", then in right order image same centered by the redness circle the highest summit of frame vertical direction point extract another image-region of being sized to 25X9 pixel as " search window "；
2., in " search window " of right order image, from left to right translate a region being sized to 9X9 pixel successively, " search pattern " that be sized to 9X9 pixel fixing with left order image mates, adaptation function adopts most widely used SAD function in images match, when from left to right all having mated, carry out altogether 25-9+1=17 coupling, obtain 17 SAD functional values, in 17 the SAD functional values obtained, minima is 47, and its corresponding image-region is object matching district；And the central pixel point in object matching district is the parallax point with left order images match, the coordinate recording this central pixel point is (1018,620)；
S3: the location of binocular camera
1., adopt the coordinate of the central pixel point in the object matching district chosen in right order image, deduct the coordinate of the central pixel point in object matching district in left order image, it is thus achieved that parallax is 33 pixels；
2., by the parallax of above-mentioned acquisition substitute into binocular range finding formula, calculate binocular camera to the distance of traffic marking board, be calculated as follows:
Finally, recording the actual range between traffic marking board and binocular camera is 20.37m, then measurement error is 1.92 meters.
Embodiment 3:
S1: the determination of characteristic point
1., before intelligent automobile moves, binocular camera and biocular systems being demarcated, calibration result is as follows:
Binocular camera spacing T is 324.11mm, and the focal distance f of binocular camera is 1878.60mm；
2., when intelligent automobile is run at high speed, the image that binocular camera is collected by traffic marking board detection algorithm is utilized to be analyzed identifying, namely when left and right order image pair and when all containing traffic marking board, extract the image pair comprising traffic marking board, and left images resolution is 1600X1200 pixel；
3., to the image extracted to being analyzed, thus identifying the traffic marking board of image pair, extract the minimum external square boxes comprising traffic marking board, record square frame and be sized to 90X90 pixel, and in selected traffic marking board, redness justifies the highest summit of vertical direction of frame as characteristic point in described square frame, record this characteristic point coordinate in the picture for (1104,670).
S2: the acquisition of parallax point
1., in left order image, centered by characteristic point, pixel extracts and is sized to the image-region of 9X9 pixel as " search pattern ", then in right order image same centered by the redness circle the highest summit of frame vertical direction point extract another image-region of being sized to 25X9 pixel as " search window "；
2., in " search window " of right order image, from left to right translate a region being sized to 9X9 pixel successively, " search pattern " that be sized to 9X9 pixel fixing with left order image mates, adaptation function adopts most widely used SAD function in images match, when from left to right all having mated, carry out altogether 25-9+1=17 coupling, obtain 17 SAD functional values, in 17 the SAD functional values obtained, minima is 52, and its corresponding image-region is object matching district；And the central pixel point in object matching district is the parallax point with left order images match, the coordinate recording this central pixel point is (1058,670)；
S3: the location of binocular camera
1., adopt the coordinate of the central pixel point in the object matching district chosen in right order image, deduct the coordinate of the central pixel point in object matching district in left order image, it is thus achieved that parallax is 46 pixels；
2., by the parallax of above-mentioned acquisition substitute into binocular range finding formula, calculate binocular camera to the distance of traffic marking board, be calculated as follows:
Finally, recording the actual range between traffic marking board and binocular camera is 14.3m, then measurement error is 1.064 meters.
Wen Zhong, target image can be traffic marking board or other marker.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all within the spirit and principles in the present invention, any amendment of making, equivalent replacement, improvement etc., should be included within protection scope of the present invention.
Claims (7)
1. binocular camera distance-finding method in an automated driving system, it is characterised in that: comprise the following steps:
S1: the determination of characteristic point: gather same target image by binocular camera, determines characteristic point and the selected image-region comprising described characteristic point wherein in the image of a camera collection；
S2: the acquisition of parallax point: choose the image-region comprising described characteristic point in the image of another camera collection as " search window ", then using selected previous image region as " search pattern ", " search window " mates, it is thus achieved that parallax point；
S3: the location of binocular camera: obtain parallax by the parallax of binocular camera point, calculates the distance between binocular camera and target image.
2. binocular camera distance-finding method in automated driving system according to claim 1, it is characterised in that: the area of the image-region at described " search pattern " place is more than the area of the image-region at " search window " place.
3. binocular camera distance-finding method in automated driving system according to claim 1, it is characterised in that: include, step S1: the determination of characteristic point
1., before intelligent automobile moves, binocular camera and biocular systems are carried out binocular calibration；
2., when intelligent automobile is run at high speed, the image that binocular camera is collected is analyzed identifying, when left and right order image pair all contains traffic marking board, extracts image pair；
3., to the image extracted to being analyzed, identify the traffic marking board of image pair, extract the minimum external square boxes comprising traffic marking board, and in selected traffic marking board, redness justifies the highest summit of vertical direction of frame as characteristic point in described square boxes.
4. binocular camera distance-finding method in automated driving system according to claim 1, it is characterised in that: include, S2: the acquisition of parallax point
1., in left order image, centered by characteristic point, pixel extracts an image-region as " search pattern ", determine the coordinate of the central pixel point of left order image, then point extracts another image-region as " search window " centered by characteristic point in right order image；
2., in " search window " of right order image, extract an image-region identical with " search pattern " size, the image-region making extraction carries out gradient of disparity constrained matching with " search pattern ", the matching value obtained chooses smallest match value, and using the image-region corresponding to smallest match value as object matching district.
5. binocular camera distance-finding method in automated driving system according to claim 1, it is characterised in that: include, S3: the location of binocular camera
1., adopt the coordinate of the central pixel point in the object matching district chosen in right order image, deduct the coordinate of the central pixel point in object matching district in left order image, it is thus achieved that parallax；
2., by parallax substitute into binocular range finding formula, calculate the binocular camera distance to traffic marking board.
6. binocular camera distance-finding method in automated driving system according to claim 4, it is characterised in that: step 3. in, square-shaped frame is sized to: 30X30 pixel is to 100X100 pixel.
7. binocular camera distance-finding method in automated driving system according to claim 1 or 4, it is characterised in that: choosing SAD function is adaptation function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610058151.1A CN105716568A (en) | 2016-01-28 | 2016-01-28 | Binocular camera ranging method in automatic pilot system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610058151.1A CN105716568A (en) | 2016-01-28 | 2016-01-28 | Binocular camera ranging method in automatic pilot system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105716568A true CN105716568A (en) | 2016-06-29 |
Family
ID=56154311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610058151.1A Pending CN105716568A (en) | 2016-01-28 | 2016-01-28 | Binocular camera ranging method in automatic pilot system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105716568A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106225764A (en) * | 2016-07-01 | 2016-12-14 | 北京小米移动软件有限公司 | Based on the distance-finding method of binocular camera in terminal and terminal |
| CN107839690A (en) * | 2017-10-31 | 2018-03-27 | 珠海格力电器股份有限公司 | A kind of safety driving distance reminding method and equipment |
| CN108012143A (en) * | 2017-12-04 | 2018-05-08 | 深圳市沃特沃德股份有限公司 | Binocular camera scaling method and device |
| CN108481327A (en) * | 2018-05-31 | 2018-09-04 | 珠海市微半导体有限公司 | A kind of positioning device, localization method and the robot of enhancing vision |
| CN109141344A (en) * | 2018-06-15 | 2019-01-04 | 北京众星智联科技有限责任公司 | A kind of method and system based on the accurate ranging of binocular camera |
| CN109214988A (en) * | 2018-07-27 | 2019-01-15 | 惠州华阳通用电子有限公司 | A kind of method, system and storage medium for expanding driving vision |
| CN109407080A (en) * | 2018-11-27 | 2019-03-01 | 东风商用车有限公司 | A kind of vehicle odometry system and its distance measuring method based on binocular camera |
| CN110220500A (en) * | 2019-05-06 | 2019-09-10 | 深圳市华芯技研科技有限公司 | A kind of unmanned based on binocular camera uses distance measuring method |
| CN110796846A (en) * | 2019-11-21 | 2020-02-14 | 珠海格力电器股份有限公司 | Method, device and system for controlling intelligent device by remote control device with binocular camera |
| CN110887488A (en) * | 2019-11-18 | 2020-03-17 | 天津大学 | Unmanned rolling machine positioning method |
| CN112489104A (en) * | 2020-12-03 | 2021-03-12 | 海宁奕斯伟集成电路设计有限公司 | Distance measurement method and device, electronic equipment and readable storage medium |
| CN113155083A (en) * | 2021-04-25 | 2021-07-23 | 深圳慧源创新科技有限公司 | Binocular camera ranging method and device, ranging equipment and readable storage medium |
| CN113610901A (en) * | 2021-07-07 | 2021-11-05 | 江西科骏实业有限公司 | Binocular motion capture camera control device and all-in-one machine equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103407407A (en) * | 2013-08-28 | 2013-11-27 | 沈阳工业大学 | Automobile safety distance warning device and method based on binocular stereo vision |
| EP2803944A2 (en) * | 2013-05-14 | 2014-11-19 | Ricoh Company, Ltd. | Image Processing Apparatus, Distance Measurement Apparatus, Vehicle-Device Control System, Vehicle, and Image Processing Program |
-
2016
- 2016-01-28 CN CN201610058151.1A patent/CN105716568A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2803944A2 (en) * | 2013-05-14 | 2014-11-19 | Ricoh Company, Ltd. | Image Processing Apparatus, Distance Measurement Apparatus, Vehicle-Device Control System, Vehicle, and Image Processing Program |
| CN103407407A (en) * | 2013-08-28 | 2013-11-27 | 沈阳工业大学 | Automobile safety distance warning device and method based on binocular stereo vision |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106225764A (en) * | 2016-07-01 | 2016-12-14 | 北京小米移动软件有限公司 | Based on the distance-finding method of binocular camera in terminal and terminal |
| CN107839690A (en) * | 2017-10-31 | 2018-03-27 | 珠海格力电器股份有限公司 | A kind of safety driving distance reminding method and equipment |
| CN108012143A (en) * | 2017-12-04 | 2018-05-08 | 深圳市沃特沃德股份有限公司 | Binocular camera scaling method and device |
| CN108481327A (en) * | 2018-05-31 | 2018-09-04 | 珠海市微半导体有限公司 | A kind of positioning device, localization method and the robot of enhancing vision |
| CN108481327B (en) * | 2018-05-31 | 2023-11-07 | 珠海一微半导体股份有限公司 | Positioning device, positioning method and robot for enhancing vision |
| CN109141344A (en) * | 2018-06-15 | 2019-01-04 | 北京众星智联科技有限责任公司 | A kind of method and system based on the accurate ranging of binocular camera |
| CN109214988A (en) * | 2018-07-27 | 2019-01-15 | 惠州华阳通用电子有限公司 | A kind of method, system and storage medium for expanding driving vision |
| CN109214988B (en) * | 2018-07-27 | 2023-05-05 | 惠州华阳通用电子有限公司 | Method, system and storage medium for expanding driving vision |
| CN109407080A (en) * | 2018-11-27 | 2019-03-01 | 东风商用车有限公司 | A kind of vehicle odometry system and its distance measuring method based on binocular camera |
| CN110220500B (en) * | 2019-05-06 | 2021-12-07 | 深圳市华芯技研科技有限公司 | Binocular camera-based distance measurement method for unmanned driving |
| CN110220500A (en) * | 2019-05-06 | 2019-09-10 | 深圳市华芯技研科技有限公司 | A kind of unmanned based on binocular camera uses distance measuring method |
| CN110887488A (en) * | 2019-11-18 | 2020-03-17 | 天津大学 | Unmanned rolling machine positioning method |
| CN110796846A (en) * | 2019-11-21 | 2020-02-14 | 珠海格力电器股份有限公司 | Method, device and system for controlling intelligent device by remote control device with binocular camera |
| CN112489104A (en) * | 2020-12-03 | 2021-03-12 | 海宁奕斯伟集成电路设计有限公司 | Distance measurement method and device, electronic equipment and readable storage medium |
| CN113155083A (en) * | 2021-04-25 | 2021-07-23 | 深圳慧源创新科技有限公司 | Binocular camera ranging method and device, ranging equipment and readable storage medium |
| CN113610901A (en) * | 2021-07-07 | 2021-11-05 | 江西科骏实业有限公司 | Binocular motion capture camera control device and all-in-one machine equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105716568A (en) | Binocular camera ranging method in automatic pilot system | |
| CN110322702B (en) | Intelligent vehicle speed measuring method based on binocular stereo vision system | |
| CN110285793B (en) | Intelligent vehicle track measuring method based on binocular stereo vision system | |
| CN103575227B (en) | A kind of vision extensometer implementation method based on digital speckle | |
| WO2023124383A1 (en) | Vehicle speed measurement method, collision early-warning method, and electronic device | |
| CN103186892B (en) | Aerial Images is utilized to generate the method and system of equal proportion outdoor scene scene photo | |
| CN110332945B (en) | Vehicle navigation method and device based on traffic road marking visual identification | |
| CN108594244B (en) | Obstacle recognition transfer learning method based on stereoscopic vision and laser radar | |
| Staniek | Stereo vision method application to road inspection | |
| CN105378794A (en) | 3d recording device, method for producing 3d image, and method for setting up 3d recording device | |
| US11971961B2 (en) | Device and method for data fusion between heterogeneous sensors | |
| CN103366555B (en) | Aerial image-based traffic accident scene image rapid generation method and system | |
| CN106446785A (en) | Passable road detection method based on binocular vision | |
| CN111288890A (en) | Road sign dimension and height automatic measurement method based on binocular photogrammetry technology | |
| CN101487702A (en) | Binocular vision based traffic accident on-site photogrammetric survey method | |
| CN114359181A (en) | Intelligent traffic target fusion detection method and system based on image and point cloud | |
| WO2023240805A1 (en) | Connected vehicle overspeed early warning method and system based on filtering correction | |
| CN106183995A (en) | A kind of visual parking device method based on stereoscopic vision | |
| CN110135216B (en) | Method and device for detecting lane number change area in electronic map and storage equipment | |
| CN117111085A (en) | Automatic driving automobile road cloud fusion sensing method | |
| CN113255578B (en) | Traffic identification recognition method and device, electronic equipment and storage medium | |
| CN111126363B (en) | Object recognition method and device for automatic driving vehicle | |
| CN110516524A (en) | Vehicle number of axle recognition methods based on Mask R-CNN in a kind of traffic scene | |
| CN109345576B (en) | Vehicle running speed identification method and system | |
| CN114724104B (en) | Method, device, electronic equipment, system and medium for detecting visual recognition distance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160629 |