CN117115760A - Engineering vehicle height limit detection method and system based on video picture - Google Patents
Engineering vehicle height limit detection method and system based on video picture Download PDFInfo
- Publication number
- CN117115760A CN117115760A CN202310901884.7A CN202310901884A CN117115760A CN 117115760 A CN117115760 A CN 117115760A CN 202310901884 A CN202310901884 A CN 202310901884A CN 117115760 A CN117115760 A CN 117115760A
- Authority
- CN
- China
- Prior art keywords
- engineering vehicle
- vehicle
- identified
- straight line
- height limit
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 55
- 238000012544 monitoring process Methods 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Abstract
The application relates to the technical field of image processing, in particular to a method and a system for detecting the height limit of an engineering vehicle based on a video picture. The method comprises the following steps: s1, detecting a passing vehicle at a height limit detection point through a monitoring unit and collecting monitoring video image information in real time; s2, identifying the engineering vehicle in the monitoring video image information through an identification unit; s3, when the engineering vehicle is identified, 3D reconstruction is carried out on the engineering vehicle through a 3D reconstruction unit, and then the height of the identified engineering vehicle is obtained; s4, comparing the identified height of the engineering vehicle with the height limit at the height limit detection point through a detection unit, and further completing the height limit detection of the identified engineering vehicle. The system is used for realizing the method. The application can better realize the height limit detection of the engineering vehicle.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a method and a system for detecting the height limit of an engineering vehicle based on a video picture.
Background
With the increasing number of urban buildings and bridges, the height limiting problem of engineering vehicles on roads is increasingly prominent. The traditional detection method needs manual monitoring, consumes a great deal of manpower and material resources, and is low in detection precision and easy to make mistakes.
Disclosure of Invention
The application provides a video-picture-based engineering vehicle height limit detection method which can overcome certain or certain defects in the prior art.
The application relates to a video-picture-based engineering vehicle height limit detection method, which comprises the following steps:
s1, detecting a passing vehicle at a height limit detection point through a monitoring unit and collecting monitoring video image information in real time;
s2, identifying the engineering vehicle in the monitoring video image information through an identification unit;
s3, when the engineering vehicle is identified, 3D reconstruction is carried out on the engineering vehicle through a 3D reconstruction unit, and then the height of the identified engineering vehicle is obtained;
s4, comparing the identified height of the engineering vehicle with the height limit at the height limit detection point through a detection unit, and further completing the height limit detection of the identified engineering vehicle.
According to the method, the engineering vehicle appearing in the monitoring video image can be subjected to 3D reconstruction, so that the height information of the engineering vehicle is obtained, and whether the height of the relevant engineering vehicle exceeds the limit can be known better by comparing the obtained height information with the limit height information, so that the ultrahigh automatic detection of the engineering vehicle can be realized better.
Preferably, in step S3, a picture of the identified engineering vehicle in the monitoring video image information center area is acquired and used as a detection picture, and the 3D reconstruction is performed on the identified engineering vehicle based on the detection picture. Therefore, the 3D reconstruction precision can be improved better, and the recognized height of the engineering vehicle can be detected more accurately.
Preferably, in step S3, when the engineering vehicle is identified, coordinates of a vehicle center of the identified engineering vehicle in each frame of picture are acquired, a euclidean distance between the vehicle center and the picture center is calculated, and a picture with the minimum euclidean distance is used as a picture of the identified engineering vehicle in the monitoring video image information center region. Therefore, the method can better realize the acquisition of the pictures of the identified engineering vehicle in the monitoring video image information center area.
Preferably, in step S3, when the identified construction vehicle is 3D reconstructed, the method includes the steps of,
s31, acquiring the running direction of the identified engineering vehicle based on the identified engineering vehicle in the detection picture and the vehicle center coordinates in M frames (M is taken as 5 in the embodiment) of the detection picture; and the running direction is taken as the front-rear direction of the identified engineering vehicle, the direction orthogonal to the running direction in the monitoring video image information plane is taken as the left-right direction of the engineering vehicle, and the direction orthogonal to the front-rear direction and the left-right direction is taken as the height direction of the identified engineering vehicle;
s32, acquiring the identified vanishing point R of the engineering vehicle in the front-rear direction and the vanishing point L in the left-right direction;
s33, acquiring the vehicle contour of the identified engineering vehicle through an extraction unit, wherein the extracted vehicle contour is a circle with the smallest radius, which can cover all pixels of the engineering vehicle;
s34, acquiring three-dimensional reconstruction data of the identified engineering vehicle based on the vanishing point R, the vanishing point L and the vehicle contour, and further acquiring the height of the identified engineering vehicle.
It can be understood that the engineering vehicle can be regarded as a cuboid rigid body, so modeling of the engineering vehicle can be preferably realized through steps S31-S34.
Preferably, in step S31,
first, the recognized center coordinates (u 0, v 0) of the engineering vehicle on the inspection screen and the center coordinates (u) of the engineering vehicle on the inspection screen in the front M frames M ，v M ) T-turn based on perspective transformation matrixChanging to the world coordinate system to obtain the world coordinate (X) corresponding to the vehicle center coordinate (u 0, v 0) 0 ，Y 0 ，Z 0 ) And the vehicle center coordinates (u) M ，v M ) Corresponding world coordinates (X M ，Y M ，Z M )；
Thereafter, a unit direction vector of the identified traveling direction of the engineering vehicle in the world coordinate system is acquired
Then, the unit direction vector in the horizontal plane is obtainedPerpendicular unit vector>And +_unit vector>As a unit direction vector of the recognized left-right direction of the construction vehicle in the world coordinate system.
By the aid of the method, the direction of the identified engineering vehicle can be well positioned.
Preferably, in step S32, the vanishing point R and the vanishing point L are set at pixel coordinates (u R ，v R ) Sum (u) L ，v L ) The acquisition is based on the following formula,
where T is the perspective transformation matrix and λ is the argument.
The above can preferably achieve the acquisition of the identified vanishing point R in the front-rear direction and vanishing point L in the left-right direction of the construction vehicle.
Preferably, the vehicle profile is expressed in such a way that,
(u-u0) 2 +(v-v0) 2 ＝r 2 ；
where the coordinates (u, v) are any point on the vehicle contour and r is the radius of the vehicle contour.
The acquisition of the vehicle profile can be preferably realized.
Preferably, in step S34,
firstly, constructing straight lines R1 and R2 of a vanishing point R tangent to a vehicle contour in a detection picture, and constructing straight lines L1 and L2 of a vanishing point L tangent to the vehicle contour; simultaneously constructing straight lines p2 and p1 which extend along the width direction of the detection picture and respectively pass through the leftmost point and the rightmost point of the vehicle contour in the length direction;
then, an intersection point c of the straight line r1 and the straight line l2, an intersection point d of the straight line r1 and the straight line p2, an intersection point k of the straight line l1 and the straight line p2, an intersection point h of the straight line l1 and the straight line r2, an intersection point i of the straight line p1 and the straight line r2, and an intersection point b of the straight line p1 and the straight line l2 are obtained;
then, constructing a straight line R3 passing through the vanishing points R and b and a straight line L3 passing through the vanishing points L and d, and obtaining an intersection point a of the straight line R3 and the straight line L3;
then, constructing a straight line R4 passing through the vanishing point R and the point k and a straight line L4 passing through the vanishing point L and the point i, and obtaining an intersection point j of the straight line R4 and the straight line L4;
then, the points a, b, c, D, h, i, j and k are used as vertexes, and the 3D reconstruction model of the identified engineering vehicle can be obtained.
Therefore, all vertex information of the 3D reconstruction model of the identified engineering vehicle can be better acquired.
Preferably, in step S4, coordinates of each vertex of the 3D reconstruction model of the identified engineering vehicle in the world coordinate system are obtained, and an actual length of each edge length of the 3D reconstruction model in the height direction in the world coordinate system is obtained, and the maximum edge length value is taken as the height of the identified engineering vehicle. Therefore, the height of the engineering vehicle can be acquired better.
In addition, the application also provides a video-picture-based engineering vehicle height limit detection system, which is used for realizing any one of the above video-picture-based engineering vehicle height limit detection methods, and comprises the following steps:
the monitoring unit is used for realizing the step S1;
the identification unit is used for realizing the step S2;
the 3D reconstruction unit is used for realizing the step S3; and
and a detection unit for implementing step S4.
Therefore, the height limit detection of the engineering vehicle can be preferably realized.
Drawings
Fig. 1 is a flow chart of a method for detecting the limit height of the engineering vehicle in embodiment 1;
fig. 2 is a schematic diagram of the first processing step of step S34 in embodiment 1;
fig. 3 is a schematic diagram of a second processing step of step S34 in embodiment 1;
fig. 4 is a schematic diagram of a third processing step of step S34 in embodiment 1;
fig. 5 is a schematic diagram of a fourth processing step of step S34 in embodiment 1.
Detailed Description
For a further understanding of the present application, the present application will be described in detail with reference to examples. It is to be understood that the examples are illustrative of the present application and are not intended to be limiting.
Example 1
Referring to fig. 1, the embodiment provides a method for detecting the height limit of an engineering vehicle based on a video frame, which comprises the following steps:
s1, detecting a passing vehicle at a height limit detection point through a monitoring unit and collecting monitoring video image information in real time;
s2, identifying the engineering vehicle in the monitoring video image information through an identification unit;
s3, when the engineering vehicle is identified, 3D reconstruction is carried out on the engineering vehicle through a 3D reconstruction unit, and then the height of the identified engineering vehicle is obtained;
s4, comparing the identified height of the engineering vehicle with the height limit at the height limit detection point through a detection unit, and further completing the height limit detection of the identified engineering vehicle.
According to the method, the engineering vehicle appearing in the monitoring video image can be subjected to 3D reconstruction, so that the height information of the engineering vehicle is obtained, and whether the height of the relevant engineering vehicle exceeds the limit can be known better by comparing the obtained height information with the limit height information, so that the ultrahigh automatic detection of the engineering vehicle can be realized better.
In step S2, the recognition unit detects the engineering vehicle in the monitoring video image information based on the existing example segmentation algorithm model. Therefore, the engineering vehicle can be better identified.
The example segmentation algorithm model is an existing mature image recognition technology, and is not described in detail in this embodiment.
In step S3, a picture of the identified engineering vehicle in the monitoring video image information center area is acquired and used as a detection picture, and 3D reconstruction is performed on the identified engineering vehicle based on the detection picture. Therefore, the 3D reconstruction precision can be improved better, and the recognized height of the engineering vehicle can be detected more accurately.
In step S3, when the engineering vehicle is identified, coordinates of a vehicle center of the identified engineering vehicle in each frame of picture are obtained, a euclidean distance between the vehicle center and the picture center is calculated, and a picture with the minimum euclidean distance is used as a picture of the identified engineering vehicle in the monitoring video image information center region. Therefore, the method can better realize the acquisition of the pictures of the identified engineering vehicle in the monitoring video image information center area.
It can be understood that the maximum length coordinate u1 and the minimum length coordinate u2 of the identified engineering vehicle in the screen length direction, and the maximum width coordinate v1 and the minimum width coordinate v2 in the width direction can be acquired by the identification unit; thus, coordinates (u 0, v 0) of the vehicle center can be acquired, where u0= (u 1-u 2)/2, v0= (v 1-v 2)/2; at the same time, the coordinates (u ', v') of the picture center are fixed values, so that the method can be preferably based on a formulaThe Euclidean distance between the center of the vehicle and the center of the picture is obtained.
In step S3, when the identified engineering vehicle is 3D reconstructed, the method includes the steps of:
s31, acquiring the running direction of the identified engineering vehicle based on the identified engineering vehicle in the detection picture and the vehicle center coordinates in M frames (M is taken as 5 in the embodiment) of the detection picture; and the running direction is taken as the front-rear direction of the identified engineering vehicle, the direction orthogonal to the running direction in the monitoring video image information plane is taken as the left-right direction of the engineering vehicle, and the direction orthogonal to the front-rear direction and the left-right direction is taken as the height direction of the identified engineering vehicle;
s32, acquiring the identified vanishing point R of the engineering vehicle in the front-rear direction and the vanishing point L in the left-right direction;
s33, acquiring the vehicle contour of the identified engineering vehicle through an extraction unit, wherein the extracted vehicle contour is a circle with the smallest radius, which can cover all pixels of the engineering vehicle;
s34, acquiring three-dimensional reconstruction data of the identified engineering vehicle based on the vanishing point R, the vanishing point L and the vehicle contour, and further acquiring the height of the identified engineering vehicle.
It can be understood that the engineering vehicle can be regarded as a cuboid rigid body, so modeling of the engineering vehicle can be preferably realized through steps S31-S34.
In the step S31 of the process,
first, the identified engineering vehicle is detected on a screenVehicle center coordinates (u 0, v 0) and vehicle center coordinates (u) in M frames of images before the detected image M ，v M ) Based on the perspective transformation matrix T, the world coordinate system is converted, and then the world coordinate (X) corresponding to the central coordinates (u 0, v 0) of the vehicle is obtained 0 ，Y 0 ，Z 0 ) And the vehicle center coordinates (u) M ，v M ) Corresponding world coordinates (X M ，Y M ，Z M )；
Thereafter, a unit direction vector of the identified traveling direction of the engineering vehicle in the world coordinate system is acquired
Then, the unit direction vector in the horizontal plane is obtainedPerpendicular unit vector>And +_unit vector>As a unit direction vector of the recognized left-right direction of the construction vehicle in the world coordinate system.
By the aid of the method, the direction of the identified engineering vehicle can be well positioned.
In step S32, the pixel coordinates (u R ，v R ) Sum (u) L ，v L ) The acquisition is based on the following formula,
where T is the perspective transformation matrix and λ is the argument.
The above can preferably achieve the acquisition of the identified vanishing point R in the front-rear direction and vanishing point L in the left-right direction of the construction vehicle.
The world coordinate system can be constructed with the shooting direction of the monitoring unit as the Y axis, the direction perpendicular to the Y axis on the imaging plane as the X axis, and the direction perpendicular to the ground as the Z axis.
Wherein, the upper left corner of the picture shot by the monitoring unit can be used as an origin to construct an image coordinate system.
It can be understood that the perspective transformation matrix T can be obtained by calibrating the monitoring unit, which is a conventional technology and will not be described in detail in this embodiment.
Briefly, one expression of the perspective transformation matrix T may be expressed as,
wherein f x For monitoring the horizontal focal length of the unit, f y For the vertical focal length of the monitoring unit, (u ', v') is the coordinate of the center of the picture, R represents the rotation matrix, and H represents the translation matrix.
In step S33, the vehicle profile is expressed in such a manner that,
(u-u0) 2 +(v-v0) 2 ＝r 2 ；
where the coordinates (u, v) are any point on the vehicle contour and r is the radius of the vehicle contour.
The acquisition of the vehicle profile can be preferably realized.
It can be understood that the coordinates (u 0, v 0) of the vehicle center and the maximum value of all the identified edge pixel points of the engineering vehicle in the image are calculated, namely the radius r of the vehicle contour.
In step S34 of the process,
referring to fig. 2, first, in a detection screen, straight lines R1 and R2 are constructed in which a vanishing point R is tangent to a vehicle contour, and straight lines L1 and L2 are constructed in which a vanishing point L is tangent to the vehicle contour; simultaneously constructing straight lines p2 and p1 which extend along the width direction of the detection picture and respectively pass through the leftmost point and the rightmost point of the vehicle contour in the length direction;
then, an intersection point c of the straight line r1 and the straight line l2, an intersection point d of the straight line r1 and the straight line p2, an intersection point k of the straight line l1 and the straight line p2, an intersection point h of the straight line l1 and the straight line r2, an intersection point i of the straight line p1 and the straight line r2, and an intersection point b of the straight line p1 and the straight line l2 are obtained;
see fig. 3, and then, constructing a straight line R3 passing through the vanishing points R and b and a straight line L3 passing through the vanishing points L and d, and obtaining an intersection point a of the straight line R3 and the straight line L3;
see fig. 4, and then, constructing a straight line R4 passing through the vanishing point R and the point k and a straight line L4 passing through the vanishing point L and the point i, and obtaining an intersection j of the straight line R4 and the straight line L4;
referring to fig. 5, after that, the 3D reconstructed model of the identified engineering vehicle can be obtained by using the points a, b, c, D, h, i, j and k as vertices.
Therefore, all vertex information of the 3D reconstruction model of the identified engineering vehicle can be better acquired.
In step S4, coordinates of each vertex of the identified 3D reconstruction model of the engineering vehicle in the world coordinate system are obtained, and an actual length of each edge length of the 3D reconstruction model in the height direction in the world coordinate system is obtained, and the maximum edge length value is used as the height of the identified engineering vehicle.
Therefore, the height of the engineering vehicle can be acquired better.
In addition, the embodiment also provides a project vehicle height limit detection system based on video pictures, which comprises:
the monitoring unit is used for realizing the step S1;
the identification unit is used for realizing the step S2;
the 3D reconstruction unit is used for realizing the step S3; and
and a detection unit for implementing step S4.
Therefore, the height limit detection of the engineering vehicle can be preferably realized.
It is understood that the monitoring unit, the identification unit, the 3D reconstruction unit and the detection unit can be implemented based on actual periods or computer programs.
It is to be understood that, based on one or several embodiments provided in the present application, those skilled in the art may combine, split, reorganize, etc. the embodiments of the present application to obtain other embodiments, which do not exceed the protection scope of the present application.
The application and its embodiments have been described above by way of illustration and not limitation, and the examples are merely illustrative of embodiments of the application and the actual construction is not limited thereto. Therefore, if one of ordinary skill in the art is informed by this disclosure, the structural mode and the embodiments similar to the technical scheme are not creatively designed without departing from the gist of the present application.
Claims (10)
1. The engineering vehicle height limit detection method based on the video picture comprises the following steps:
s1, detecting a passing vehicle at a height limit detection point through a monitoring unit and collecting monitoring video image information in real time;
s2, identifying the engineering vehicle in the monitoring video image information through an identification unit;
s3, when the engineering vehicle is identified, 3D reconstruction is carried out on the engineering vehicle through a 3D reconstruction unit, and then the height of the identified engineering vehicle is obtained;
s4, comparing the identified height of the engineering vehicle with the height limit at the height limit detection point through a detection unit, and further completing the height limit detection of the identified engineering vehicle.
2. The method for detecting the height limit of the engineering vehicle based on the video picture according to claim 1, wherein the method comprises the following steps: in step S3, a picture of the identified engineering vehicle in the monitoring video image information center area is acquired and used as a detection picture, and 3D reconstruction is performed on the identified engineering vehicle based on the detection picture.
3. The method for detecting the height limit of the engineering vehicle based on the video picture according to claim 2, wherein the method comprises the following steps: in step S3, when the engineering vehicle is identified, coordinates of a vehicle center of the identified engineering vehicle in each frame of picture are obtained, a euclidean distance between the vehicle center and the picture center is calculated, and a picture with the minimum euclidean distance is used as a picture of the identified engineering vehicle in the monitoring video image information center region.
4. The method for detecting the height limit of the engineering vehicle based on the video picture according to claim 1, wherein the method comprises the following steps: in step S3, when the identified engineering vehicle is 3D reconstructed, there is a step of,
s31, acquiring the running direction of the identified engineering vehicle based on the identified engineering vehicle in the detection picture and the vehicle center coordinates in M frames (M is taken as 5 in the embodiment) of the detection picture; and the running direction is taken as the front-rear direction of the identified engineering vehicle, the direction orthogonal to the running direction in the monitoring video image information plane is taken as the left-right direction of the engineering vehicle, and the direction orthogonal to the front-rear direction and the left-right direction is taken as the height direction of the identified engineering vehicle;
s32, acquiring the identified vanishing point R of the engineering vehicle in the front-rear direction and the vanishing point L in the left-right direction;
s33, acquiring the vehicle contour of the identified engineering vehicle through an extraction unit, wherein the extracted vehicle contour is a circle with the smallest radius, which can cover all pixels of the engineering vehicle;
s34, acquiring three-dimensional reconstruction data of the identified engineering vehicle based on the vanishing point R, the vanishing point L and the vehicle contour, and further acquiring the height of the identified engineering vehicle.
5. The method for detecting the height limit of the engineering vehicle based on the video picture according to claim 4, wherein the method comprises the following steps: in the step S31 of the process,
first, the recognized center coordinates (u 0, v 0) of the engineering vehicle on the inspection screen and the center coordinates (u) of the engineering vehicle on the inspection screen in the front M frames M ，v M ) Based on the perspective transformation matrix T, the world coordinate system is converted, and then the world coordinate (X) corresponding to the central coordinates (u 0, v 0) of the vehicle is obtained 0 ，Y 0 ，Z 0 ) And the vehicle center coordinates (u) M ，v M ) Corresponding world coordinates (X M ，Y M ，Z M )；
Thereafter, a unit direction vector of the identified traveling direction of the engineering vehicle in the world coordinate system is acquired
Then, the unit direction vector in the horizontal plane is obtainedPerpendicular unit vector>And +_unit vector>As a unit direction vector of the recognized left-right direction of the construction vehicle in the world coordinate system.
6. The method for detecting the height limit of the engineering vehicle based on the video picture according to claim 5, wherein the method comprises the following steps: in step S32, the pixel coordinates (u R ，v R ) Sum (u) L ，v L ) The acquisition is based on the following formula,
where T is the perspective transformation matrix and λ is the argument.
7. The method for detecting the height limit of the engineering vehicle based on the video picture according to claim 6, wherein the method comprises the following steps: the vehicle profile is expressed in such a way that,
(u-u0) 2 +(v-v0) 2 ＝r 2 ；
where the coordinates (u, v) are any point on the vehicle contour and r is the radius of the vehicle contour.
8. The method for detecting the height limit of the engineering vehicle based on the video picture according to claim 7, wherein the method comprises the following steps: in step S34 of the process,
firstly, constructing straight lines R1 and R2 of a vanishing point R tangent to a vehicle contour in a detection picture, and constructing straight lines L1 and L2 of a vanishing point L tangent to the vehicle contour; simultaneously constructing straight lines p2 and p1 which extend along the width direction of the detection picture and respectively pass through the leftmost point and the rightmost point of the vehicle contour in the length direction;
then, an intersection point c of the straight line r1 and the straight line l2, an intersection point d of the straight line r1 and the straight line p2, an intersection point k of the straight line l1 and the straight line p2, an intersection point h of the straight line l1 and the straight line r2, an intersection point i of the straight line p1 and the straight line r2, and an intersection point b of the straight line p1 and the straight line l2 are obtained;
then, constructing a straight line R3 passing through the vanishing points R and b and a straight line L3 passing through the vanishing points L and d, and obtaining an intersection point a of the straight line R3 and the straight line L3;
then, constructing a straight line R4 passing through the vanishing point R and the point k and a straight line L4 passing through the vanishing point L and the point i, and obtaining an intersection point j of the straight line R4 and the straight line L4;
then, the points a, b, c, D, h, i, j and k are used as vertexes, and the 3D reconstruction model of the identified engineering vehicle can be obtained.
9. The method for detecting the height limit of the engineering vehicle based on the video picture according to claim 8, wherein the method comprises the following steps: in step S4, coordinates of each vertex of the identified 3D reconstruction model of the engineering vehicle in the world coordinate system are obtained, and an actual length of each edge length of the 3D reconstruction model in the height direction in the world coordinate system is obtained, and the maximum edge length value is used as the height of the identified engineering vehicle.
10. The video frame-based engineering vehicle height limit detection system is used for realizing the video frame-based engineering vehicle height limit detection method according to any one of claims 1 to 9, and comprises the following steps:
the monitoring unit is used for realizing the step S1;
the identification unit is used for realizing the step S2;
the 3D reconstruction unit is used for realizing the step S3; and
and a detection unit for implementing step S4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310901884.7A CN117115760A (en) | 2023-07-21 | 2023-07-21 | Engineering vehicle height limit detection method and system based on video picture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310901884.7A CN117115760A (en) | 2023-07-21 | 2023-07-21 | Engineering vehicle height limit detection method and system based on video picture |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117115760A true CN117115760A (en) | 2023-11-24 |
Family
ID=88810032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310901884.7A Pending CN117115760A (en) | 2023-07-21 | 2023-07-21 | Engineering vehicle height limit detection method and system based on video picture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117115760A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100322476A1 (en) * | 2007-12-13 | 2010-12-23 | Neeraj Krantiveer Kanhere | Vision based real time traffic monitoring |
| CN108550143A (en) * | 2018-04-03 | 2018-09-18 | 长安大学 | A kind of measurement method of the vehicle length, width and height size based on RGB-D cameras |
| CN109763437A (en) * | 2018-11-29 | 2019-05-17 | 深圳市赛亿科技开发有限公司 | The system and method for vehicle limit for height on a kind of highway |
| CN111008557A (en) * | 2019-10-30 | 2020-04-14 | 长安大学 | Vehicle fine granularity identification method based on geometric constraint |
| CN112489106A (en) * | 2020-12-08 | 2021-03-12 | 深圳市哈工交通电子有限公司 | Video-based vehicle size measuring method and device, terminal and storage medium |
| CN213653283U (en) * | 2020-08-28 | 2021-07-09 | 云南建设基础设施投资股份有限公司滇南分公司 | Intelligent height limiting device for road |
| CN113592888A (en) * | 2021-07-01 | 2021-11-02 | 湖北文理学院 | Height limiting frame early warning method, device, equipment and storage medium |
| CN114240895A (en) * | 2021-12-20 | 2022-03-25 | 上海交通大学 | Vehicle three-dimensional surrounding frame detection system and method based on roadside monitoring view angle |
-
2023
- 2023-07-21 CN CN202310901884.7A patent/CN117115760A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100322476A1 (en) * | 2007-12-13 | 2010-12-23 | Neeraj Krantiveer Kanhere | Vision based real time traffic monitoring |
| CN108550143A (en) * | 2018-04-03 | 2018-09-18 | 长安大学 | A kind of measurement method of the vehicle length, width and height size based on RGB-D cameras |
| CN109763437A (en) * | 2018-11-29 | 2019-05-17 | 深圳市赛亿科技开发有限公司 | The system and method for vehicle limit for height on a kind of highway |
| CN111008557A (en) * | 2019-10-30 | 2020-04-14 | 长安大学 | Vehicle fine granularity identification method based on geometric constraint |
| CN213653283U (en) * | 2020-08-28 | 2021-07-09 | 云南建设基础设施投资股份有限公司滇南分公司 | Intelligent height limiting device for road |
| CN112489106A (en) * | 2020-12-08 | 2021-03-12 | 深圳市哈工交通电子有限公司 | Video-based vehicle size measuring method and device, terminal and storage medium |
| CN113592888A (en) * | 2021-07-01 | 2021-11-02 | 湖北文理学院 | Height limiting frame early warning method, device, equipment and storage medium |
| CN114240895A (en) * | 2021-12-20 | 2022-03-25 | 上海交通大学 | Vehicle three-dimensional surrounding frame detection system and method based on roadside monitoring view angle |
Non-Patent Citations (1)
| Title |
|---|
| 武非凡等: "交通监控场景下的相机标定与车辆速度测量", 计算机应用研究, no. 08, 18 July 2019 (2019-07-18) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111462135B (en) | Semantic mapping method based on visual SLAM and two-dimensional semantic segmentation | |
| CN109615611B (en) | Inspection image-based insulator self-explosion defect detection method | |
| Uittenbogaard et al. | Privacy protection in street-view panoramas using depth and multi-view imagery | |
| Taneja et al. | City-scale change detection in cadastral 3d models using images | |
| Kang et al. | Detection and tracking of moving objects from a moving platform in presence of strong parallax | |
| Gallup et al. | Piecewise planar and non-planar stereo for urban scene reconstruction | |
| US20080232715A1 (en) | Image processing apparatus | |
| CN110956661B (en) | Method for calculating dynamic pose of visible light and infrared camera based on bidirectional homography matrix | |
| Li et al. | Automatic registration of panoramic image sequence and mobile laser scanning data using semantic features | |
| CN111160291B (en) | Human eye detection method based on depth information and CNN | |
| CN110766024B (en) | Deep learning-based visual odometer feature point extraction method and visual odometer | |
| Wang et al. | A robust approach for automatic registration of aerial images with untextured aerial lidar data | |
| JPH07336669A (en) | Stereo image corresponding method and stereo image parallax measuring method | |
| CN109544635B (en) | Camera automatic calibration method based on enumeration heuristic | |
| CN106462975A (en) | Method and apparatus for object tracking and segmentation via background tracking | |
| CN103700082B (en) | Image split-joint method based on dual quaterion relative orientation | |
| CN113763438B (en) | Point cloud registration method, device, equipment and storage medium | |
| Nouduri et al. | Deep realistic novel view generation for city-scale aerial images | |
| CN117115760A (en) | Engineering vehicle height limit detection method and system based on video picture | |
| CN115273080A (en) | Lightweight visual semantic odometer method for dynamic scene | |
| Gandhi et al. | Application of planar motion segmentation for scene text extraction | |
| KR101524074B1 (en) | Method for Image Processing | |
| van de Wouw et al. | Hierarchical 2.5-d scene alignment for change detection with large viewpoint differences | |
| CN115147344A (en) | Three-dimensional detection and tracking method for parts in augmented reality assisted automobile maintenance | |
| Fan et al. | Collaborative three-dimensional completion of color and depth in a specified area with superpixels |
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 |