CN105809143A - Vehicle alignment checking method based on image recognition cross drone - Google Patents
Vehicle alignment checking method based on image recognition cross drone Download PDFInfo
- Publication number
- CN105809143A CN105809143A CN201610177108.7A CN201610177108A CN105809143A CN 105809143 A CN105809143 A CN 105809143A CN 201610177108 A CN201610177108 A CN 201610177108A CN 105809143 A CN105809143 A CN 105809143A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- cross
- width
- drone
- 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
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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/09—Recognition of logos
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/10—Recognition assisted with metadata
Abstract
The invention discloses a vehicle alignment checking method based on an image recognition cross drone.The method includes the steps that a camera on the side face of an associate vehicle is aligned to the cross drone on the side face of a reference vehicle to obtain a drone template, the position of the cross drone in the current image can be accurately recognized by matching drone patterns in the current image with the drone template, the longitudinal separation difference between the associate vehicle and the reference vehicle in the advancing direction is obtained, and the vehicle alignment project is accurately checked.
Description
Technical field
The present invention relates to image procossing, field of photoelectric technology, particularly relate to the neat wire examination method of vehicle mark based on image recognition cross drone.
Background technology
Hereinafter the background of related of the present invention is illustrated, but these prior aries illustrating to constitute the present invention.
In vehicle training and examination system, vehicle is divided into control vehicle and official's car, for ensureing that whole fleet keeps array constant between advancing, official car driver needs in traveling process and the control vehicle position of left (right side) side carries out mark together, to keep this car relative position in formation, and adjust travel direction and the speed of this car in real time, to ensure that whole fleet is in running neat and consistent.
Therefore, prior art needs a kind of method that vehicle mark can carry out accurately examination together.
Summary of the invention
It is an object of the invention to propose a kind of neat wire examination method of vehicle mark based on image recognition cross drone, it is possible to obtain official's car longitudinal separation with control vehicle on direct of travel poor, it is achieved accurately examining the neat project of vehicle mark.
The neat wire examination method of vehicle mark based on image recognition cross drone according to the present invention, including:
S1, make the video camera of official's car side be directed at the cross drone of control vehicle side, obtain target image, from target image, extract target template, obtain the first width w of cross drone based on target template1, first height h1With the white point quantity in cross drone；
S2, from present image extract target pattern, based on target pattern obtain cross drone the second width w2With the second height h2, determine that match width compares r according to following relational expression3, match height compare r4, coupling the ratio of width to height ratio r5And comprehensive matching value r6:
r3=min (w1,w2)/max(w1,w2), r4=min (h1,h2)/max(h1,h2),
r6=r2+r3+r4+r5；
If S3 match width compares r3More than default match width than threshold value, match height compares r4More than default match height than threshold value, the ratio r of coupling the ratio of width to height5More than the ratio threshold value of default coupling the ratio of width to height, and at r3、r4、r5And r6Middle r6Maximum, it is believed that the target pattern in present image and the target template matching in target image, and the horizontal center position x according to present imagec, picture traverse imgWidth and cross drone physical length W ', calculate offset error d.
Preferably, offset error d meets following relation:
Wherein, xcFor cross drone center in present image to the distance of image left side, unit is: mm；ImgWidth is the width of present image, and unit is: mm；W ' is cross drone physical length, and unit is: mm；D is offset error, and unit is: mm.
Preferably, step S1 farther includes after extraction target template from target image: judge whether target template meets cross characteristics, when the target in target image meets cross characteristics, it is believed that target template is cross drone.
Preferably, step S2 farther includes after extraction target pattern from present image: whether the target pattern judging in present image meets cross characteristics, when target pattern meets cross characteristics, it is believed that the target in present image is cross drone.
Preferably, described cross characteristics includes: the ratio of width to height r1, dutycycle r2White point quantity with four angles of target:
Wherein, r1=min (w, h)/max (w, h), r2=sum/ (w1·h1), sum is the white point quantity on target；
In formula, w is the width of target, and unit is: mm；H is the height of target, and unit is: mm.
Preferably, when the white point quantity at the ratio of width to height of target, dutycycle and four angles of target meets following relation, it is believed that it meets cross characteristics:
r1>0.8、And the white point quantity at four angles of target is respectively less than 5.
Preferably, four angles of target refer respectively to image and hit four right angles of target, and the width at each right angle is w/5, highly for h/5.
Preferably, step S1 extracts target template from target image to include: target image is carried out binary conversion treatment, obtains binary image；Start region growing from the center of bianry image, obtain cross drone agglomerate；Using cross drone agglomerate as target template.
Preferably, step S2 extracts target pattern from present image to include: present image is carried out binary conversion treatment, obtains the binary image of present image；Start region growing from the center of the bianry image of present image, obtain the target agglomerate of present image；Using the target agglomerate of present image as target pattern.
Preferably, binary conversion treatment is carried out as follows:
Wherein, (x, y) is image midpoint (x before binary conversion treatment to Y, y) gray value at place, (x, y) for the image midpoint (x after binary conversion treatment for M, y) gray value at place, Th is the average gray of image center location.
The neat wire examination method of vehicle mark based on image recognition cross drone according to the present invention, the video camera of official's car side is made to be directed at acquisition target template with the cross drone of control vehicle side, the position of cross drone in present image can be accurately identified out by carrying out mating with target template by the target pattern in present image, thus it is poor to obtain official's car longitudinal separation with control vehicle on direct of travel, it is achieved the accurate examination to the neat project of vehicle mark.
Accompanying drawing explanation
By the detailed description of the invention part provided referring to accompanying drawing, the features and advantages of the present invention will become better understood by, in the accompanying drawings:
Fig. 1 is the schematic flow sheet of the neat wire examination method of vehicle according to the invention mark；
Fig. 2 is the neat form schematic diagram of vehicle according to the invention mark；
Fig. 3 is video camera and cross drone installation site schematic diagram；
Fig. 4 is the cross drone schematic diagram according to the present invention；
Fig. 5 is the image schematic diagram before binary conversion treatment of the present invention；
Fig. 6 is the image schematic diagram after binary conversion treatment of the present invention；
Fig. 7 is the target agglomerate schematic diagram according to the present invention.
Detailed description of the invention
With reference to the accompanying drawings the illustrative embodiments of the present invention is described in detail.To the description of illustrative embodiments merely for the sake of demonstration purpose, and it is definitely not the restriction to the present invention and application or usage.
In the neat process of vehicle mark, official's car and control vehicle must travel along white line, and white line spacing is fixed, and two following distances are maintained within 3 to 5 meters, and therefore the image algorithm of the present invention is affected less by the change of the depth of field.Single vehicle examination distance only 200 meters, the examination time, therefore the image recognition of the present invention was affected less by the change of light and environment less than 80 seconds.The present invention can select the video camera that processing accuracy is high, and result of appraisal accuracy is high, for instance the image that the 8mm analog video camera of selection obtains over this distance, processing accuracy can reach mm level.The neat wire examination method of vehicle mark of the present invention belongs to contactless, travels without influence between vehicle, and equipment is easily installed, with low cost.In sum, it is reasonable, feasible that the neat wire examination method of vehicle mark adopting the present invention solves the examination neat problem of vehicle mark.
According to embodiments of the present invention, it is provided that based on the neat wire examination method of vehicle mark of image recognition cross drone.As shown in Figures 2 and 3, the side vehicle body at control vehicle 20 installs cross drone 21, and the corresponding side surface at official's car 10 installs video camera 11.It is poor that the present invention adopts image-recognizing method to obtain official's car longitudinal separation with control vehicle on direct of travel, and in actual vehicle mark training process together, light and environmental factors are continually changing, and measurement result is affected bigger by the change of this light and environmental factors.In order to reduce the impact of this factor as far as possible, the present invention in step sl, first makes the video camera 11 of official's car 10 side be directed at the cross drone 21 of control vehicle 20 side, obtains target image, then extracts target template from target image.By the target pattern in successive image is mated with target template, it is possible to identify whether this target pattern is cross drone, and poor according to the longitudinal separation with control vehicle on direct of travel of position acquisition official's car of target pattern in successive image.Fig. 1 illustrates the schematic flow sheet of the neat wire examination method of vehicle according to the invention mark, in actual vehicle mark examination process together, it is possible to carry out marking neat examination using the first two field picture as target image.
Step S1 is additionally based upon target template and obtains the first width w of cross drone1, first height h1With the white point quantity in cross drone.
In order to ensure that the target template extracted from target image is mounted in the cross drone of control vehicle side vehicle body, may further include after step S1 extracts target template from target image: judge whether target template meets cross characteristics, when the target in target image meets cross characteristics, it is believed that target template is cross drone.
In the present invention, the cross of cross drone is white, and the background color of cross drone is green, adds background color and can reduce the impact on the result of appraisal of the color around target or pattern in cross drone.Fig. 4 illustrates the cross drone schematic diagram according to the present invention.When obtaining target image, the white portion of cross drone is positioned at target image center.In target image except comprising cross drone, it is also possible to comprise other scenes.In order to prevent other sights impact on the result of appraisal in target image, improving the accuracy of the result of appraisal, step S1 can extract target template in the following way from target image and include: target image is carried out binary conversion treatment, obtains binary image；Start region growing from the center of bianry image, obtain cross drone agglomerate；Using cross drone agglomerate as target template.
Cross drone central point is white, carries out binary conversion treatment with the gray value of central spot for average gray, for instance carry out binary conversion treatment with the average gray in 10 × 10 scopes near central point.Preferably, it is possible to carry out binary conversion treatment as follows:
Wherein, (x, y) is image midpoint (x before binary conversion treatment to Y, y) gray value at place, (x, y) for the image midpoint (x after binary conversion treatment for M, y) gray value at place, Th is the average gray of image center location.
Fig. 5 illustrates the image in the preferred embodiment of the present invention before binary conversion treatment, and Fig. 6 illustrates the image in the preferred embodiment of the present invention after binary conversion treatment.
S2, from present image extract target pattern, based on target pattern obtain cross drone the second width w2With the second height h2, determine that match width compares r according to following relational expression3, match height compare r4, coupling the ratio of width to height ratio r5And comprehensive matching value r6:
r3=min (w1,w2)/max(w1,w2), r4=min (h1,h2)/max(h1,h2),
r6=r2+r3+r4+r5。
In present image except comprising target pattern, it is also possible to comprise other scenes.In order to prevent other sights impact on the result of appraisal in present image, improve the accuracy of the result of appraisal, step S2 can extract target pattern as follows from present image and include: present image is carried out binary conversion treatment, obtains the binary image of present image；Start region growing from the center of the bianry image of present image, obtain the target agglomerate of present image；Using the target agglomerate of present image as target pattern, referring to Fig. 7.
Those skilled in the art according to the requirement to result of appraisal accuracy or according to Practical Calculation needs, can select binary processing method.In this step, binary processing method can be identical or different with the binary processing method in step S1.
In order to ensure that extracting target pattern from present image is mounted in the cross drone of control vehicle side vehicle body, may further include after step S2 extracts target pattern from present image:
Judge whether the target pattern in present image meets cross characteristics, when target pattern meets cross characteristics, it is believed that the target in present image is cross drone.
It will be appreciated by those skilled in the art that and any can reflect that information characteristics that cross drone identifies all can as confirming that whether target template is the cross characteristics of cross drone, in some embodiments of the invention, cross characteristics includes: the ratio of width to height r1, dutycycle r2White point quantity with four angles of target: wherein, r1=min (w, h)/max (w, h), r2=sum/ (w1·h1), sum is the white point quantity on target；In formula, w is the width of target, and unit is: mm；H is the height of target, and unit is: mm.Preferably, when the white point quantity at the ratio of width to height of target, dutycycle and four angles of target meets following relation, it is believed that it meets cross characteristics:
r1>0.8、And the white point quantity at four angles of target is respectively less than 5.
Four angles of target refer respectively to image and hit four right angles of target.Target image four right angles of target that hit go out not have white point in theory.Therefore, it can by judging whether four angles of target exist white point and determine whether this target is cross drone.Due to flating or imaging error, image there may exist white point, in order to avoid the impact on the result of the factor such as flating or imaging error, the white point threshold value at four angles of target can be preset, when the white point quantity at four angles of target is not less than default white point threshold value, think that this target does not meet cross characteristics, be not cross drone.In some embodiments of the invention, the width at each right angle be w/5, highly for h/5.
If S3 match width compares r3More than default match width than threshold value, match height compares r4More than default match height than threshold value, the ratio r of coupling the ratio of width to height5More than the ratio threshold value of default coupling the ratio of width to height, and at r3、r4、r5And r6Middle r6Maximum, it is believed that the target pattern in present image and the target template matching in target image, and the horizontal center position x according to present imagec, picture traverse imgWidth and cross drone physical length W ', calculate offset error d.
Preferably, offset error d meets following relation:
Wherein, xcFor cross drone center in present image to the distance of image left side, unit is: mm；ImgWidth is the width of present image, and unit is: mm；W ' is cross drone physical length, and unit is: mm；D is offset error, and unit is: mm.
Fig. 1 illustrates according to the neat wire examination method flow chart of the vehicle mark in the preferred embodiment of the present invention.Side vehicle body installation cross drone at control vehicle, the corresponding side surface at official's car are installed video camera, and are made video camera bornb sight center, obtain luminance component image, then judge whether this image is the first two field picture.If, then extract target template with this image for target image, specifically, first target image is carried out binary conversion treatment, then pass through region growing image is split, obtain target agglomerate, extract target template according to this target agglomerate, when this target template meets cross characteristics, continue to obtain next frame image.If this image is not the first two field picture, then using this image as the present image in the present invention, present image is carried out binary conversion treatment, then pass through region growing and the present image after binaryzation is split, obtain target agglomerate, extract target template according to this target agglomerate；When this target template meets cross characteristics, it is mated with target template, if the match is successful, then calculate the side-play amount of official's car according to from present image with the information of extraction target image.
The present invention can overcome the identification problem under the slight rotational case of target, even if target profile is imperfect or deviates from camera lens, without missing inspection or flase drop occur.Compared with prior art, the present invention is high to the discrimination of target, false drop rate is low, and the accuracy that vehicle mark is examined together is good.
Although with reference to illustrative embodiments, invention has been described, it is to be understood that, the invention is not limited in the detailed description of the invention being described in detail in literary composition and illustrating, when not necessarily departing from claims limited range, described illustrative embodiments can be made various change by those skilled in the art.
Claims (10)
1. the neat wire examination method of vehicle mark based on image recognition cross drone, it is characterised in that including:
S1, make the video camera of official's car side be directed at the cross drone of control vehicle side, obtain target image, from target image, extract target template, obtain the first width w of cross drone based on target template1, first height h1With the white point quantity in cross drone；
S2, from present image extract target pattern, based on target pattern obtain cross drone the second width w2With the second height h2, determine that match width compares r according to following relational expression3, match height compare r4, coupling the ratio of width to height ratio r5And comprehensive matching value r6:
r3=min (w1,w2)/max(w1,w2), r4=min (h1,h2)/max(h1,h2),
r6=r2+r3+r4+r5；
If S3 match width compares r3More than default match width than threshold value, match height compares r4More than default match height than threshold value, the ratio r of coupling the ratio of width to height5More than the ratio threshold value of default coupling the ratio of width to height, and at r3、r4、r5And r6Middle r6Maximum, it is believed that the target pattern in present image and the target template matching in target image, and the horizontal center position x according to present imagec, picture traverse imgWidth and cross drone physical length W ', calculate offset error d.
2. the neat wire examination method of vehicle mark as claimed in claim 1, it is characterised in that offset error d meets following relation:
Wherein, xcFor cross drone center in present image to the distance of image left side, unit is: mm；ImgWidth is the width of present image, and unit is: mm；W ' is cross drone physical length, and unit is: mm；D is offset error, and unit is: mm.
3. the neat wire examination method of vehicle mark as claimed in claim 2, it is characterised in that farther include after extracting target template from target image in step S1:
Judge whether target template meets cross characteristics, when the target in target image meets cross characteristics, it is believed that target template is cross drone.
4. the neat wire examination method of vehicle mark as claimed in claim 3, it is characterised in that farther include after extracting target pattern from present image in step S2:
Judge whether the target pattern in present image meets cross characteristics, when target pattern meets cross characteristics, it is believed that the target in present image is cross drone.
5. the neat wire examination method of vehicle mark as described in claim 3 or 4, it is characterised in that described cross characteristics includes: the ratio of width to height r1, dutycycle r2White point quantity with four angles of target:
Wherein, r1=min (w, h)/max (w, h), r2=sum/ (w1·h1), sum is the white point quantity on target；
In formula, w is the width of target, and unit is: mm；H is the height of target, and unit is: mm.
6. the neat wire examination method of vehicle mark as claimed in claim 5, it is characterised in that when the white point quantity at the ratio of width to height of target, dutycycle and four angles of target meets following relation, it is believed that it meets cross characteristics:
r1>0.8、And the white point quantity at four angles of target is respectively less than 5.
7. the neat wire examination method of vehicle mark as claimed in claim 6, it is characterised in that four angles of target refer respectively to image and hit four right angles of target, the width at each right angle is w/5, highly is h/5.
8. the neat wire examination method of vehicle mark as claimed in claim 7, it is characterised in that extract target template in step S1 from target image and include:
Target image is carried out binary conversion treatment, obtains binary image；
Start region growing from the center of bianry image, obtain cross drone agglomerate；
Using cross drone agglomerate as target template.
9. the neat wire examination method of vehicle mark as claimed in claim 8, it is characterised in that extract target pattern in step S2 from present image and include:
Present image is carried out binary conversion treatment, obtains the binary image of present image；
Start region growing from the center of the bianry image of present image, obtain the target agglomerate of present image；
Using the target agglomerate of present image as target pattern.
10. the neat wire examination method of vehicle mark as claimed in claim 8 or 9, it is characterised in that carry out binary conversion treatment as follows:
Wherein, (x, y) is image midpoint (x before binary conversion treatment to Y, y) gray value at place, (x, y) for the image midpoint (x after binary conversion treatment for M, y) gray value at place, Th is the average gray of image center location.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610177108.7A CN105809143B (en) | 2016-03-25 | 2016-03-25 | The neat wire examination method of vehicle mark based on image recognition cross drone |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610177108.7A CN105809143B (en) | 2016-03-25 | 2016-03-25 | The neat wire examination method of vehicle mark based on image recognition cross drone |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105809143A true CN105809143A (en) | 2016-07-27 |
| CN105809143B CN105809143B (en) | 2018-12-04 |
Family
ID=56454836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610177108.7A Active CN105809143B (en) | 2016-03-25 | 2016-03-25 | The neat wire examination method of vehicle mark based on image recognition cross drone |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105809143B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108398946A (en) * | 2018-01-25 | 2018-08-14 | 成都图灵智控科技有限公司 | Intelligent tracking accurate positioning device and method |
| CN112712551A (en) * | 2020-12-29 | 2021-04-27 | 合肥联宝信息技术有限公司 | Screw detection method, device and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299240A (en) * | 2014-10-24 | 2015-01-21 | 惠州市德赛西威汽车电子有限公司 | Method and system for calibrating camera for lane offset early warning |
| CN105182320A (en) * | 2015-07-14 | 2015-12-23 | 安徽清新互联信息科技有限公司 | Depth measurement-based vehicle distance detection method |
-
2016
- 2016-03-25 CN CN201610177108.7A patent/CN105809143B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299240A (en) * | 2014-10-24 | 2015-01-21 | 惠州市德赛西威汽车电子有限公司 | Method and system for calibrating camera for lane offset early warning |
| CN105182320A (en) * | 2015-07-14 | 2015-12-23 | 安徽清新互联信息科技有限公司 | Depth measurement-based vehicle distance detection method |
Non-Patent Citations (2)
| Title |
|---|
| 朱战霞 等: "无人机编队飞行控制器设计", 《飞行力学》 * |
| 袁杰波 等: "无人机编队飞行导航方法及其仿真研究", 《计算机仿真》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108398946A (en) * | 2018-01-25 | 2018-08-14 | 成都图灵智控科技有限公司 | Intelligent tracking accurate positioning device and method |
| CN112712551A (en) * | 2020-12-29 | 2021-04-27 | 合肥联宝信息技术有限公司 | Screw detection method, device and storage medium |
| CN112712551B (en) * | 2020-12-29 | 2022-02-08 | 合肥联宝信息技术有限公司 | Screw detection method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105809143B (en) | 2018-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105674880B (en) | Contact net geometric parameter measurement method and system based on binocular principle | |
| US20210264176A1 (en) | Hazard detection from a camera in a scene with moving shadows | |
| US11958197B2 (en) | Visual navigation inspection and obstacle avoidance method for line inspection robot | |
| US9141870B2 (en) | Three-dimensional object detection device and three-dimensional object detection method | |
| CN105488454B (en) | Front vehicles detection and ranging based on monocular vision | |
| US10891738B2 (en) | Boundary line recognition apparatus and branch road determination apparatus | |
| EP2426642A1 (en) | Method, device and system for motion detection | |
| CN105373135A (en) | Method and system for guiding airplane docking and identifying airplane type based on machine vision | |
| CN111079589B (en) | Automatic height detection method based on depth camera shooting and height threshold value pixel calibration | |
| CN108257137A (en) | A kind of angle measurement method and system of the automatic interpretation of view-based access control model hot spot | |
| CN103196418A (en) | Measuring method of vehicle distance at curves | |
| CN113624225B (en) | Pose resolving method for mounting engine positioning pins | |
| CN111067530B (en) | Subway passenger height automatic detection method and system based on depth camera shooting | |
| CN103234542B (en) | The truck combination negotiation of bends trajectory measurement method of view-based access control model | |
| US20150262020A1 (en) | Marking line detection system | |
| CN105444741A (en) | Double view window based route characteristic identifying, deviation measuring, and accurate positioning method | |
| CN109447062A (en) | Pointer-type gauges recognition methods based on crusing robot | |
| CN110705485A (en) | Traffic signal lamp identification method and device | |
| CN102095370B (en) | Detection identification method for three-X combined mark | |
| CN105809143A (en) | Vehicle alignment checking method based on image recognition cross drone | |
| JP2010224918A (en) | Environment recognition device | |
| CN110889874A (en) | Error evaluation method for calibration result of binocular camera | |
| CN205711654U (en) | A kind of detection device of the road surface breakage information of three-dimensional visualization | |
| JP3589293B2 (en) | Road white line detection method | |
| CN105424059B (en) | Wide baseline near infrared camera position and orientation estimation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |