CN111709938B - Pavement defect and casting detection method based on depth map - Google Patents
Pavement defect and casting detection method based on depth map Download PDFInfo
- Publication number
- CN111709938B CN111709938B CN202010562540.4A CN202010562540A CN111709938B CN 111709938 B CN111709938 B CN 111709938B CN 202010562540 A CN202010562540 A CN 202010562540A CN 111709938 B CN111709938 B CN 111709938B
- Authority
- CN
- China
- Prior art keywords
- depth
- map
- pavement
- image
- equation
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a pavement defect and casting object detection method based on a depth map, which comprises the following steps: s1: acquiring an RGB image and a depth image of a sensor, and converting the RGB image and the depth image into a parallax image only comprising a pavement area; s2: flattening the parallax map into 3 groups of vectors, and establishing a road plane equation; s3: introducing a camera baseline and a ground inclination angle to obtain a mapping relation and establishing an optimized road plane parameter equation; s4: constructing and solving a loss function, and calculating an optimal inclination angle; s5: calculating optimal road plane equation parameters; s6: detecting pavement defects and sprinkles according to the optimized pavement parameter equation and the parallax map; s7: the road surface defect and the object throwing result are visualized, the road surface equation is constructed according to the depth map, the road surface equation parameters are optimized by calculating the inclination angle of the camera baseline and the ground, the parallax map and the road surface residual error are calculated, the road surface defect and the object throwing are detected, and the result is visualized.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a pavement defect and casting object detection method based on a depth image.
Background
Roads are the infrastructure for passing various trackless vehicles and pedestrians in word sense; according to the use characteristics, the road is divided into a highway, an urban road, a rural road, a factory and mine road, a forestry road, an examination road, a competition road, an automobile test road, a workshop channel, a school road and the like, and the ancient China also has a post road. In addition, the way to achieve a certain goal, the way for things to develop and change;
road inspection is an important ring in municipal traffic, wherein the detection of pavement defects and sprinklers is a main purpose, the occurrence of accidents can be reduced by timely finding out the sprinklers and the pavement defects, in the existing road inspection, the pavement defects and the sprinklers are usually distinguished manually, in the common automatic method, the sprinklers are usually detected based on the relation between front and back frames for application in a fixed scene, and some methods based on target detection technology only can give out rectangular frames of defects or sprinklers, but cannot obtain specific information such as length and width.
Disclosure of Invention
The invention provides a pavement defect and sprinkle object detection method based on a depth map, which can effectively solve the problems that in the common automatic method provided in the background technology, the sprinkle object detection is usually based on the relation between front and back frames and is applied to a fixed scene, and some methods based on the target detection technology only can give out a rectangular frame of a defect or sprinkle object and cannot obtain specific information such as length and width.
In order to achieve the above purpose, the present invention provides the following technical solutions: a pavement defect and casting detection method based on a depth map comprises the following steps:
s1: acquiring an RGB image and a depth image of a sensor, and converting the RGB image and the depth image into a parallax image only comprising a pavement area;
s2: flattening the parallax map into 3 groups of vectors, and establishing a road plane equation;
s3: introducing a camera baseline and a ground inclination angle to obtain a mapping relation and establishing an optimized road plane parameter equation;
s4: constructing and solving a loss function, and calculating an optimal inclination angle;
s5: calculating optimal road plane equation parameters;
s6: detecting pavement defects and sprinkles according to the optimized pavement parameter equation and the parallax map;
s7: and visualizing pavement defects and casting results.
According to the above technical solution, the step S1 includes the following steps:
s101: acquiring an RGB image and a depth image of a camera, wherein the depth image can be acquired by a sensor such as a depth camera or a binocular camera;
s102: obtaining a Mask (Mask) of a road surface area in an RGB image, wherein the Mask can be obtained through manual selection or an image processing technology;
s103: converting the depth map in step S101 into a disparity map:
baseline is the binocular camera baseline length, depth is depth;
s104: the mask in step S102 is multiplied by each element of the disparity map in step S103, and a disparity map including only road surface information can be obtained.
According to the above technical solution, the step S2 includes the following steps:
s201: performing flattening (flat) operations on depth values, row coordinates and column coordinates of elements which are not NaN in the disparity map containing only the road surface information in the step S104, and storing the depth values, the row coordinates and the column coordinates in vectors d, u and v;
s202: establishing a road plane equation:
f(p)＝p T a,with p＝[u v 1] T ,a＝[0 a 1 a 2 ]a is a parameter vector.
According to the above technical solution, the step S3 includes the following steps:
s301: since the camera is not parallel to the ground during measurement, the introduction angle θ describes the inclination angle of the camera with respect to the road plane, acting on p in step S202:
r is a rotation matrix;
s302: using q in step S301, the plane equation in step S202 is rewritten to obtain: g (q, θ) =q T a；
S303: and traversing each point q corresponding to d, and storing coordinate information s and t of the point q into vectors s and t.
According to the above technical solution, the step S4 includes the following steps:
s401: establishing a loss function:
with Q＝[s t 1]；
s402: minimizing the loss function C (a) is equivalent to minimizing the loss function:
L(θ)＝d T Q(θ)(Q(θ) T Q(θ)) -1 Q(θ) T d is the largest;
s402: constructing an Optimizer (Optimizer) using a random problem gradient descent (SGD) method;
s403: bringing the loss function L (θ) in step S402 to the optimizer in step S402, solving the parameter vector when-L (θ) is minimized:
according to the above technical solution, the step S5 includes the following steps:
s501: θ in step S404 * Substitution a= (Q (θ) T Q(θ)) -1 Q(θ) T d solving for a * ；
S502: will step S501 a * Substituting into step S302, the road surface equation is obtained:
f(p)＝q T a＝a 2 +a 1 (-usinθ+vsinθ)。
according to the above technical solution, the step S6 includes the following steps:
s601: substituting disp in step S103 and the road surface equation in step S502:
fault (p) =disp (p) -f (p) +δ; delta is a bias term to obtain a new parallax image;
s602: setting a threshold t 1 ，t 2 (t 1 ＜t 2 ) The new disparity map fault (p) in step S601 is binarized,
s603: selecting a 5x5 full 1 matrix as a core, and performing corrosion operation on the new parallax map binary (p) in the step S602;
s604: performing expansion operation on the follow-up operation in the step S603, wherein the core is unchanged;
s605: then the subsequent communication area is calculated in step S604, and the communication area is filtered out to be smaller than the threshold t 3 Obtaining a filtered disparity map filter (p);
s606: view of the filtering operation performed in step S602Difference map filter (p), if the parallax value d corresponding to the parallax map fault (p) at step S605 at point p is greater than the threshold t at step S602 2 Then is a throwing object, if less than t 1 Then it is a road surface defect.
According to the above technical solution, the step S7 includes the following steps:
s701: the RGB diagram in step S101 shows the binary image binary (p) corresponding to the region in step S603.
Compared with the prior art, the invention has the beneficial effects that: the invention has scientific and reasonable structure, safe and convenient use, builds the pavement equation according to the depth map, optimizes the pavement equation parameters by calculating the inclination angle of the camera baseline and the ground, calculates the parallax map and the pavement residual error, detects the pavement defect and the throwing object, and visualizes the result.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
In the drawings:
FIG. 1 is a schematic flow diagram of an example of the present invention;
FIG. 2 is an RGB map collected in an example of the invention;
FIG. 3 is a depth map acquired in an example of the invention;
FIG. 4 is a mask of a pavement surface in an example of the invention;
FIG. 5 is a disparity map generated from a depth map in an example of the present invention;
FIG. 6 is a disparity map generated from a disparity map and a mask that includes only road surface areas in an example of the present invention;
FIG. 7 is a schematic diagram illustrating an example of the present invention in which the camera baseline is not parallel to the road plane;
FIG. 8 is a new view of the invention after optimization;
FIG. 9 is a diagram of the new disparity map binarized in an embodiment of the present invention;
FIG. 10 is a binary image of an example of the present invention after an etching operation;
FIG. 11 is a binary image after an expansion operation in an example of the present invention;
FIG. 12 is a binary image of a communication area filtered in an example of the present invention;
FIG. 13 is a schematic diagram of a visual defect in an example of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Examples: as shown in fig. 1, the invention provides a technical scheme, namely a pavement defect and casting detection method based on a depth map, which comprises the following steps:
s1: acquiring an RGB image and a depth image of a sensor, and converting the RGB image and the depth image into a parallax image only comprising a pavement area;
s2: flattening the parallax map into 3 groups of vectors, and establishing a road plane equation;
s3: introducing a camera baseline and a ground inclination angle to obtain a mapping relation and establishing an optimized road plane parameter equation;
s4: constructing and solving a loss function, and calculating an optimal inclination angle;
s5: calculating optimal road plane equation parameters;
s6: detecting pavement defects and sprinkles according to the optimized pavement parameter equation and the parallax map;
s7: and visualizing pavement defects and casting results.
According to the technical scheme, the step S1 comprises the following steps:
s101: acquiring an RGB image and a depth image of a camera, as shown in FIG. 2 and FIG. 3, wherein the depth image can be acquired by a sensor such as a depth camera or a binocular camera, and in the embodiment, the depth image is acquired by the binocular camera;
s102: obtaining a Mask (Mask) of a road surface area in the RGB image, wherein the Mask can be obtained through manual selection or an image processing technology, as shown in FIG. 4;
s103: the depth map in step S101 is converted into a disparity map as shown in fig. 5:
baseline is the binocular camera baseline length, depth is depth;
s104: the mask in step S102 is multiplied by each element of the disparity map in step S103, and a disparity map including only road surface information can be obtained.
According to the technical scheme, the S2 comprises the following steps:
s201: performing flattening (flat) operations on depth values, row coordinates and column coordinates of elements which are not NaN in the disparity map containing only the road surface information in the step S104, and storing the depth values, the row coordinates and the column coordinates in vectors d, u and v;
s202: establishing a road plane equation:
f(p)＝p T a,with p＝[u v 1] T ,a＝[0 a 1 a 2 ]a is a parameter vector.
According to the technical scheme, the step S3 comprises the following steps:
s301: as shown in fig. 7, since the camera is not parallel to the ground during measurement, the introduction angle θ describes the inclination angle of the camera with respect to the road plane, acting on p in step S202:
r is a rotation matrix;
s302: using q in step S301, the plane equation in step S202 is rewritten to obtain: g (q, θ) =q T a；
S303: and traversing each point q corresponding to d, and storing coordinate information s and t of the point q into vectors s and t.
According to the technical scheme, the step S4 comprises the following steps:
s401: establishing a loss function:
with Q＝[s t 1]；
s402: minimizing the loss function C (a) is equivalent to minimizing the loss function:
L(θ)＝d T Q(θ)(Q(θ) T Q(θ)) -1 Q(θ) T d is the largest;
s402: constructing an Optimizer (Optimizer) using a random problem gradient descent (SGD) method;
s403: bringing the loss function L (θ) in step S402 to the optimizer in step S402, solving the parameter vector when-L (θ) is minimized:
according to the technical scheme, the step S5 comprises the following steps:
s501: θ in step S404 * Substitution a= (Q (θ) T Q(θ)) -1 Q(θ) T d solving for a * ；
S502: will step S501 a * Substituting into step S302, the road surface equation is obtained:
f(p)＝q T a＝a 2 +a 1 (-usinθ+vsinθ)。
according to the technical scheme, S6 includes the following steps:
s601: substituting disp in step S103 and the road surface equation in step S502:
fault (p) =disp (p) -f (p) +δ; delta is a bias term to obtain a new disparity map, as shown in fig. 8;
s602: setting a threshold t 1 ，t 2 (t 1 ＜t 2 ) The new disparity map fault (p) in step S601 is binarized,
as shown in fig. 9;
s603: selecting a 5x5 full 1 matrix as a core, and performing corrosion operation on the new parallax map binary (p) in the step S602, as shown in FIG. 10;
s604: the expansion operation is performed after step S603, and the core is unchanged, as shown in fig. 11;
s605: then the subsequent communication area is obtained in step S604, and the communication area is filteredLess than threshold t 3 Obtaining a filtered disparity map filter (p), as shown in fig. 12;
s606: for the disparity map filter (p) subjected to the filtering operation in step S602, if the disparity value d corresponding to the disparity map fault (p) at step S605 for the point p is greater than the threshold t in step S602 2 Then is a throwing object, if less than t 1 Then it is a road surface defect.
According to the technical scheme, S7 includes the following steps:
s701: the RGB diagram in step S101 shows the binary image binary (p) corresponding to the region in step S603.
Compared with the prior art, the invention has the beneficial effects that: the invention has scientific and reasonable structure, safe and convenient use, builds the pavement equation according to the depth map, optimizes the pavement equation parameters by calculating the inclination angle of the camera baseline and the ground, calculates the parallax map and the pavement residual error, detects the pavement defect and the throwing object, and visualizes the result.
Finally, it should be noted that: the foregoing is merely a preferred example of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A pavement defect and casting detection method based on a depth map is characterized by comprising the following steps of: the method comprises the following steps:
s1: acquiring an RGB image and a depth image of a sensor, and converting the RGB image and the depth image into a parallax image only comprising a pavement area;
s2: flattening the parallax map into 3 groups of vectors, and establishing a road plane equation;
s3: introducing a camera baseline and a ground inclination angle to obtain a mapping relation and establishing an optimized road plane parameter equation;
s4: constructing and solving a loss function, and calculating an optimal inclination angle;
s5: calculating optimal road plane equation parameters;
s6: detecting pavement defects and sprinkles according to the optimized pavement parameter equation and the parallax map;
s7: visualizing pavement defects and casting results;
the step S1 comprises the following steps:
s101: acquiring an RGB image and a depth image of a camera, wherein the depth image can be acquired by a binocular camera sensor;
s102: the mask of the road surface area in the RGB image is obtained through manual selection or an image processing technology;
s103: converting the depth map in step S101 into a disparity map:
baseline is the binocular camera baseline length, depth is depth;
s104: multiplying the mask in the step S102 by each element of the disparity map in the step S103 to obtain a disparity map only containing road surface information;
the step S2 comprises the following steps:
s201: performing flattening operation on depth values, row coordinates and column coordinates of elements which are not NaN in the disparity map only containing the pavement information in the step S104, and storing the depth values, the row coordinates and the column coordinates into vectors d, u and v;
s202: establishing a road plane equation:
f(p)＝p T a,with p＝[u v 1] T ,a＝[0 a 1 a 2 ]a is a parameter vector;
the step S3 comprises the following steps:
s301: since the camera is not parallel to the ground during measurement, the introduction angle θ describes the inclination angle of the camera with respect to the road plane, acting on p in step S202:
r is a rotation matrix;
s302: using q in step S301, the plane equation in step S202 is rewritten to obtain: g (q, θ) =q T a；
S303: and traversing each point q corresponding to d, and storing coordinate information s and t of the point q into vectors s and t.
2. The method for detecting pavement defects and sprinkles based on a depth map according to claim 1, wherein the step S4 comprises the following steps:
s401: establishing a loss function:
s402: minimizing the loss function C (a) is equivalent to minimizing the loss function:
L(θ)＝d T q(θ)(q(θ) T q(θ)) -1 q(θ) T d is the largest;
s403: constructing an optimizer using a random gradient descent method;
s404: bringing the loss function L (θ) in step S402 to the optimizer in step S403, solving the parameter vector when-L (θ) is minimized:
3. the method for detecting pavement defects and sprinkles based on a depth map according to claim 2, wherein the step S5 comprises the following steps:
s501: θ in step S404 * Substitution a= (q (θ) T q(θ)0 -1 q(θ) T d solving for a * ；
S502: will step S501 a * Substituting into step S302, the road surface equation is obtained:
g(q,θ)＝q T a＝a 2 +a 1 (-usinθ+vsinθ)。
4. a depth map-based pavement defect and sprinkle detection method according to claim 3, wherein S6 comprises the steps of:
s601: substituting disp in step S103 and the road surface equation in step S502:
fault (p) =disp (p) -g (q, θ) +δ; delta is a bias term to obtain a new parallax image;
s602: setting a threshold t 1 ，t 2 (t 1 ＜t 2 ) The new disparity map fault (p) in step S601 is binarized,
s603: selecting a full 1 matrix of 5x5 as a core, and performing corrosion operation on the binary parallax map binary (p) obtained in the step S602;
s604: performing expansion operation on the follow-up operation in the step S603, wherein the core is unchanged;
s605: then the subsequent communication area is calculated in step S604, and the communication area is filtered out to be smaller than the threshold t 3 Obtaining a filtered disparity map filter (p);
s606: for the disparity map filter (p) subjected to the filtering operation in step S605, if the disparity value corresponding to the new disparity map fault (p) of the point p in step S602 is greater than the threshold t in step S602 2 Then is a throwing object, if less than t 1 Then it is a road surface defect.
5. The method for detecting pavement defects and sprinkles based on a depth map according to claim 4, wherein the step S7 comprises the following steps:
s701: the RGB diagram in step S101 is drawn into the corresponding area of the binarized parallax map binary (p) in step S603.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010562540.4A CN111709938B (en) | 2020-06-18 | 2020-06-18 | Pavement defect and casting detection method based on depth map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010562540.4A CN111709938B (en) | 2020-06-18 | 2020-06-18 | Pavement defect and casting detection method based on depth map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111709938A CN111709938A (en) | 2020-09-25 |
| CN111709938B true CN111709938B (en) | 2023-07-07 |
Family
ID=72542074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010562540.4A Active CN111709938B (en) | 2020-06-18 | 2020-06-18 | Pavement defect and casting detection method based on depth map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111709938B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2720193A2 (en) * | 2012-09-11 | 2014-04-16 | Ricoh Company, Ltd. | Method and system for detecting uneven road surface |
| GB201622014D0 (en) * | 2016-12-22 | 2017-02-08 | Canon Kk | Method and corresponding device for digital 3D reconstruction |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101208647B1 (en) * | 2010-10-28 | 2012-12-06 | 재단법인대구경북과학기술원 | Method and apparatus for detecting obstacle on road |
| CN103123722B (en) * | 2011-11-18 | 2016-04-27 | 株式会社理光 | Road object detection method and system |
| CN104217208B (en) * | 2013-06-03 | 2018-01-16 | 株式会社理光 | Object detection method and device |
| US9571819B1 (en) * | 2014-09-16 | 2017-02-14 | Google Inc. | Efficient dense stereo computation |
| CN104639933A (en) * | 2015-01-07 | 2015-05-20 | 前海艾道隆科技（深圳）有限公司 | Real-time acquisition method and real-time acquisition system for depth maps of three-dimensional views |
| CN107909009B (en) * | 2017-10-27 | 2021-09-17 | 北京中科慧眼科技有限公司 | Obstacle detection method and device based on road surface learning |
| CN108230392A (en) * | 2018-01-23 | 2018-06-29 | 北京易智能科技有限公司 | A kind of dysopia analyte detection false-alarm elimination method based on IMU |
| RU2698402C1 (en) * | 2018-08-30 | 2019-08-26 | Самсунг Электроникс Ко., Лтд. | Method of training a convolutional neural network for image reconstruction and a system for forming an image depth map (versions) |
| CN110189294B (en) * | 2019-04-15 | 2021-05-07 | 杭州电子科技大学 | RGB-D image significance detection method based on depth reliability analysis |
| CN110148179A (en) * | 2019-04-19 | 2019-08-20 | 北京地平线机器人技术研发有限公司 | A kind of training is used to estimate the neural net model method, device and medium of image parallactic figure |
| CN111079675A (en) * | 2019-12-23 | 2020-04-28 | 武汉唯理科技有限公司 | Driving behavior analysis method based on target detection and target tracking |
-
2020
- 2020-06-18 CN CN202010562540.4A patent/CN111709938B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2720193A2 (en) * | 2012-09-11 | 2014-04-16 | Ricoh Company, Ltd. | Method and system for detecting uneven road surface |
| GB201622014D0 (en) * | 2016-12-22 | 2017-02-08 | Canon Kk | Method and corresponding device for digital 3D reconstruction |
Non-Patent Citations (1)
| Title |
|---|
| 基于无人机双目图像的线目标测量的研究;王祖武;丁健;魏文力;韩军;;计算机测量与控制(01);正文全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111709938A (en) | 2020-09-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111551958B (en) | Mining area unmanned high-precision map manufacturing method | |
| CN111260615B (en) | Laser and machine vision fusion-based method for detecting apparent diseases of unmanned aerial vehicle bridge | |
| CN108845569A (en) | Generate semi-automatic cloud method of the horizontal bend lane of three-dimensional high-definition mileage chart | |
| CN112836633A (en) | Parking space detection method and parking space detection system | |
| CN102915532A (en) | Method of determining extrinsic parameters of a vehicle vision system and vehicle vision system | |
| CN110766760B (en) | Method, device, equipment and storage medium for camera calibration | |
| CN103938531B (en) | Laser road faulting of slab ends detecting system and method | |
| KR101847944B1 (en) | Device and method for detecting road crack by using unmaned aerial vehicle | |
| CN109919856B (en) | Asphalt pavement structure depth detection method based on binocular vision | |
| JP7203586B2 (en) | Image processing device and image processing method | |
| CN107644538B (en) | Traffic signal lamp identification method and device | |
| CN110728720B (en) | Method, apparatus, device and storage medium for camera calibration | |
| CN103913121B (en) | A kind of vehicle's contour size automatic measuring method | |
| CN111460986A (en) | Lane line processing method and device | |
| CN113554646A (en) | Intelligent urban road pavement detection method and system based on computer vision | |
| CN115482295A (en) | External parameter calibration method for camera of vehicle-mounted panoramic looking-around system | |
| CN111709938B (en) | Pavement defect and casting detection method based on depth map | |
| CN111476062A (en) | Lane line detection method and device, electronic equipment and driving system | |
| CN110415299B (en) | Vehicle position estimation method based on set guideboard under motion constraint | |
| CN111429430B (en) | Tunnel detection vehicle size mapping relation calculation method based on machine vision | |
| CN110543612B (en) | Card collection positioning method based on monocular vision measurement | |
| CN113012239B (en) | Quantitative calculation method for focal length change of vehicle-road cooperative roadside perception camera | |
| CN113744393B (en) | Multi-level slope landslide change monitoring method | |
| CN110963409B (en) | Method for measuring automatic deviation rectification deviation of tire crane machine vision | |
| CN113221883A (en) | Real-time correction method for flight navigation route of unmanned aerial vehicle |
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 |