CN116503818A - Multi-lane vehicle speed detection method and system - Google Patents
Multi-lane vehicle speed detection method and system Download PDFInfo
- Publication number
- CN116503818A CN116503818A CN202310470574.4A CN202310470574A CN116503818A CN 116503818 A CN116503818 A CN 116503818A CN 202310470574 A CN202310470574 A CN 202310470574A CN 116503818 A CN116503818 A CN 116503818A
- Authority
- CN
- China
- Prior art keywords
- lane
- vehicle
- lane line
- expressway
- detection
- 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 43
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000009466 transformation Effects 0.000 claims abstract description 22
- 239000000203 mixture Substances 0.000 claims abstract description 10
- 238000013461 design Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000003708 edge detection Methods 0.000 claims description 8
- 238000003709 image segmentation Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 7
- 238000005259 measurement Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
- G06V10/36—Applying a local operator, i.e. means to operate on image points situated in the vicinity of a given point; Non-linear local filtering operations, e.g. median filtering
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- 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)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Nonlinear Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a multi-lane vehicle speed detection method and system, which belong to the technical field of vehicle speed calculation, wherein a highway video is subjected to Gaussian mixture modeling to obtain a highway background image without vehicles, then lane lines are detected, the edge coordinates of the lane lines and the distance of the lane lines are utilized to carry out coordinate transformation, virtual detection areas of different lane lines with accurate distances are obtained, the mass center of the vehicles is taken as a reference from the known vehicle track, and the speed of the vehicles passing through the detection areas is calculated. The method comprises the steps of carrying out coordinate transformation on the end point coordinates of the lane lines, dividing detection areas for a plurality of lanes in the expressway, calculating the average speed of vehicles passing through the detection areas by utilizing video frame rates, and solving the technical problem that the speed detection accuracy is reduced because the position information of the lane lines in the existing expressway scene cannot set the speed measurement areas on the lanes on the two sides of the expressway.
Description
Technical Field
The invention relates to the technical field of vehicle speed calculation, in particular to a multi-lane vehicle speed detection method and system.
Background
At present, compared with methods such as radar, laser, ground induction coil and the like, the video speed measurement method has the advantages of simple equipment, low cost, visual process, verifiable result and the like, and is mainly divided into: camera calibration and virtual coil methods.
The traditional camera calibration method mainly obtains a plurality of images by rotating, translating or carrying out plane orthogonal movement on a camera, and processes and realizes the images, the method needs to change the position or the gesture of the camera to finish parameter calibration, a plurality of camera parameters need to be calibrated, the requirement on shooting angles is strict, the calculation complexity is high, and most of road monitoring equipment at present can not meet the requirement. The virtual coil method is used for detecting the speed of the vehicle by arranging a virtual coil on a road instead of a real ground induction coil, so that the calculation complexity is low, but due to the characteristics of multiple lanes of the expressway, the traditional virtual detection line treats the multiple lanes as a single lane, so that the deviation between the actual distance and the ideal distance of the lane designs at two sides is larger, and the error is larger when the speed of the vehicle is detected through a detection area.
Therefore, designing a method and a system for detecting a multi-lane vehicle speed to improve the accuracy of detecting the multi-lane vehicle speed is a problem that needs to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the invention provides a method and a system for detecting a multi-lane vehicle speed, which are used for dividing a plurality of detection areas for a plurality of lanes by carrying out coordinate transformation on the edge vertexes of lane lines and carrying out vehicle speed detection, so that the technical problem that the vehicle speed detection accuracy is reduced because the position information of the lane lines in the existing expressway scene cannot set the speed measurement areas on the lanes at two sides of the expressway is solved.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in one aspect, the invention discloses a multi-lane vehicle speed detection method, which comprises the following steps:
carrying out Gaussian mixture modeling on the expressway video to obtain an expressway background map without vehicles;
detecting lane lines based on the expressway background map, extracting lane lines and acquiring lane line end point information; the lane line endpoint information is lane line endpoint pixel coordinates in an image coordinate system;
carrying out coordinate transformation on the lane line endpoint information to obtain virtual detection areas of different lanes;
and selecting the position of the mass center of the vehicle, detecting and tracking the obtained vehicle track by using the vehicle, and taking the mass center of the vehicle as a reference to obtain the running speed of the vehicle passing through the virtual detection area.
Preferably, the image coordinate system is an OPQ coordinate system, the origin O is the vertex of the lower left corner of the image, and the coordinates (P i ，Q i ) The inverse of the column and row numbers, respectively, of the pixel in the array.
Preferably, the detecting lane lines based on the highway background map, extracting lane lines and obtaining lane line end point information includes:
carrying out image segmentation on the expressway background map by adopting a threshold segmentation method, reserving lane line position information, and dividing lane line areas;
performing edge detection on the lane lines by using a sobel operator, and extracting the lane lines;
and acquiring endpoint information at two ends of the lane line based on probability Hough transformation.
Preferably, the coordinate transformation is performed on the lane line endpoint information to obtain virtual detection areas of different lanes, including:
a pixel coordinate (P) i ，Q i ) Transformed into coordinates in a world coordinate system, and the conversion relation between the two is shown as the following formula:
wherein the world coordinate system coordinates (X i ，Y i ，Z i ) For the pixel coordinates (P i ，Q i ) Projection coordinates on world coordinate system, S i Is a constant; m is 1 matrix 3 x 4, called projection matrix; m is m ij The j-th column element of the ith row of the projection matrix M;
neglecting Z coordinate information in the world coordinate system to obtain the following formula:
obtaining pixel coordinates (P) according to the above i ，Q i ) Coordinates in world coordinate system (X i ，Y i )。
Preferably, the virtual detection area of each lane is a rectangular area determined by four points, and the lanes comprise a middle lane and an edge lane;
the virtual detection area of the middle lane is determined by lane line edge endpoints at two sides of the middle lane;
and selecting an inner side lane line end point of the edge lane corresponding to lane line edge end points on two sides of the middle lane, respectively acquiring the perpendicular points of the inner side lane line end point and the edge lane line according to the inner side lane line end point, and determining a virtual detection area of the edge lane based on the inner side lane line end point and the perpendicular points.
Preferably, determining a vehicle centroid position, detecting and tracking an obtained vehicle track by using a vehicle and obtaining a running speed of the vehicle passing through the virtual detection area by taking the vehicle centroid as a reference, includes:
recording the video frame number t of the moment when the vehicle mass center enters the edge line of the virtual detection area 1 ；
Recording the number t of video frames at the moment when the mass center of the vehicle is driven away from the edge line of the virtual detection area 2 ；
Using velocity formulaThe vehicle speed is determined.
On the other hand, the invention also discloses a multi-lane vehicle speed detection system, which comprises a virtual area design module and a vehicle speed detection module, wherein the virtual area design module comprises:
the Gaussian mixture processing sub-module is used for carrying out Gaussian mixture modeling on the expressway video to obtain an expressway background image without vehicles;
the lane line detection sub-module is used for detecting lane lines based on the expressway background image, extracting lane lines and acquiring lane line end point information; the lane line endpoint information is lane line endpoint pixel coordinates in an image coordinate system;
the coordinate transformation submodule is used for carrying out coordinate transformation on the lane line endpoint information to obtain virtual detection areas of different lanes;
the vehicle speed detection module is used for detecting and tracking the obtained vehicle track by using the vehicle and obtaining the running speed of the vehicle passing through the virtual detection area by taking the mass center of the vehicle as a reference.
Preferably, the lane line detection submodule includes:
the image segmentation unit is used for carrying out image segmentation on the expressway background image by adopting a threshold segmentation method, reserving lane line position information and dividing lane line areas;
the edge detection unit is used for carrying out edge detection on the lane lines by utilizing a sobel operator and extracting the lane lines;
and the probability Hough transformation unit is used for acquiring the endpoint information at the two ends of the lane line based on the probability Hough transformation.
Compared with the prior art, the invention discloses a multi-lane vehicle speed detection method and a system, which are used for carrying out Gaussian mixture modeling on expressway videos to obtain an expressway background map without vehicles; detecting lane lines based on the expressway background map, extracting lane lines and acquiring lane line end point information; carrying out coordinate transformation on the lane line endpoint information to obtain virtual detection areas of different lanes; and selecting the position of the mass center of the vehicle, detecting and tracking the obtained vehicle track by using the vehicle, and calculating the running speed of the vehicle passing through the virtual detection area by taking the mass center of the vehicle as a reference. According to the invention, through carrying out coordinate transformation on the edge vertexes of the lane lines, a plurality of detection areas are divided for a plurality of lanes, and the speed detection is carried out, so that the technical problem that the speed detection precision is reduced because the speed measurement areas cannot be set for lanes on two sides of the expressway due to the position information of the lane lines in the existing expressway scene is solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a design of a virtual detection area according to an embodiment of the present invention;
fig. 2 (a) is an original map of a highway, and fig. 2 (b) is a background map of the highway obtained based on mixed gaussian modeling;
FIG. 3 is a diagram of lane line detection results according to an embodiment of the present invention;
fig. 4 (a) is a highway image graph, and fig. 4 (b) is a highway world plane graph;
fig. 5 is a block diagram of the multi-lane vehicle speed detection system of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
On the expresswayIn the calculation of the vehicle speed, a section of highway monitoring video I= { I is input 1 ,I 2 ,...,I T Using the travel path of all vehiclesBy the vehicle speed calculation formula>Obtaining the running speeds V= { V of all vehicles 1 ,v 2 ,...,v M }. Where Δt is the vehicle travel time, which can be obtained from the video frame rate, Δh is the vehicle travel distance, and generally the travel distance of the vehicle is defined by defining a virtual detection line whose distance is known. It is noted that the expressway includes a plurality of lane lines a, b, c, d, however, in the prior art, due to the influence of the video angle, the plurality of lanes of the expressway are regarded as a detection area formed by a single lane, and the image of the detection area is trapezoid, so that the virtual detection line defined in the video deviates from the actually set known distance Δh, and the running speed v= { V of each vehicle is obtained 1 ,v 2 ,...,v m The error is large.
Aiming at the problems, the embodiment of the invention discloses a multi-lane vehicle speed detection method, which comprises the following steps:
1. and (3) carrying out mixed Gaussian modeling on the image (fig. 2 (a)) in the expressway video to obtain a vehicle-free expressway background image.
The multi-vehicle speed detection model based on the lane lines firstly needs to detect the lane lines, and in order to eliminate the situation that the expressway is interfered by the detection of the lane lines due to the running of vehicles, firstly, a mixed Gaussian background modeling method is adopted to obtain a road background diagram without the running of vehicles, as shown in fig. 2 (b).
2. Detecting lane lines based on the expressway background map, extracting lane lines and acquiring lane line end point information; the lane line endpoint information is the pixel coordinates of the lane line endpoint in the image coordinate system.
In order to remove the interference of road texture features, a threshold segmentation method is adopted to separate the expressway, the image is segmented by selecting a proper threshold value according to the characteristic of high brightness of the lane lines, and only the highlighted pixel point areas of the lane lines are reserved. The lane line area is divided, interference of other environmental conditions in the image can be removed, and only the position information of the lane line is reserved in the binary image, so that the subsequent lane line detection is facilitated. And detecting the edges of the vehicles by using a sobel operator, and detecting the lane lines by using a probability Hough transformation method to obtain end point information of the line segments. For better calculation, only the near view direction in the bidirectional lane line is divided into areas, and a lane line detection result diagram is shown in fig. 3.
3. And carrying out coordinate transformation on the lane line endpoint information to obtain virtual detection areas of different lanes.
A pixel coordinate (P) in the image coordinate system i ，Q i ) Is transformed into coordinates in a world coordinate system, wherein the image coordinate system is an OPQ coordinate system, the origin O is the vertex of the lower left corner of the image, and the coordinates of a certain pixel (P i ，Q i ) The inverse of the column and row numbers, respectively, of the pixel in the array.
The conversion relation between the two is shown as follows:
wherein the world coordinate system coordinates (X i ，Y i ，Z i ) For pixel coordinates (P i ，Q i ) Projection coordinates on world coordinate system, S i Is a constant; m is 1 matrix 3 x 4, called projection matrix; m is m ij Is the j-th column element of the i-th row of the projection matrix M.
In an actual highway scenario, the vehicle is traveling on a flat road surface with substantially no change in altitude, while the altitude is negligible. Namely, neglecting Z coordinate information in a world coordinate system, and obtaining the formula:
obtaining pixel coordinates (P) according to the above i ，Q i ) Coordinates in world coordinate system (X i ，Y i )。
Wherein, calibrating the matrix P by a camera i Q i The projection matrix M is solved.
According to the lane line design specified in the highway engineering technical standard (JTGB 01-2014) (quoted), the distance between adjacent lane lines is known to be 3.75 meters, the interval between the dotted lines is 9 meters, the length of the dotted lines is 6 meters, the coordinates of at least 4 points in each plane on the image plane can be known, the coordinates of 4 corresponding points on the actual road surface can be obtained from the above, namely, the corresponding relation between one point in space and the projection point of the image coordinate system can be obtained, namely, the actual distance between any 2 points in the image coordinate system can be known, and the image coordinate system and the real world coordinate system are mapped as shown in fig. 4 (a) and 4 (b). And dividing corresponding detection areas on the lanes at two sides according to the actual distance of the middle lane, and completing the design of the virtual detection areas. The virtual detection area design flow chart is shown in fig. 1.
The virtual detection area of each lane is a rectangular area determined by four points, and the lanes comprise a middle lane and an edge lane;
the virtual detection area of the middle lane is determined by lane line edge end points at two sides of the middle lane;
and selecting an inner side lane line end point of the edge lane corresponding to the lane line edge end points on two sides of the middle lane, respectively acquiring the perpendicular points of the inner side lane line end point and the edge lane line according to the inner side lane line end point, and determining a virtual detection area of the edge lane based on the inner side lane line end point and the perpendicular points.
4. Selecting a vehicle mass center position, detecting and tracking an obtained vehicle track by using the vehicle and taking the vehicle mass center as a reference to obtain the running speed of the vehicle passing through a virtual detection area, wherein the time for the vehicle passing through the detection area is calculated by using a video frame rate of 25 frames/s, and the method comprises the following steps:
recording video frame number t of moment when vehicle centroid enters virtual detection area edge line 1 ；
Recording video frame number t of moment when vehicle centroid moves away from virtual detection area edge line 2 ；
Using velocity formulaThe vehicle speed is determined.
On the other hand, the embodiment of the invention also provides a multi-lane vehicle speed detection system, as shown in fig. 5, comprising a virtual area design module and a vehicle speed detection module, wherein the virtual area design module comprises:
the Gaussian mixture processing sub-module is used for carrying out Gaussian mixture modeling on the expressway video to obtain an expressway background image without vehicles;
the lane line detection sub-module is used for detecting lane lines based on the expressway background map, extracting lane lines and acquiring lane line end point information; the lane line endpoint information is lane line endpoint pixel coordinates in an image coordinate system;
the coordinate transformation submodule is used for carrying out coordinate transformation on the lane line end point information to obtain virtual detection areas of different lanes;
the vehicle speed detection module is used for detecting and tracking the obtained vehicle track by using the vehicle and obtaining the running speed of the vehicle passing through the virtual detection area by taking the mass center of the vehicle as a reference.
Wherein, lane line detects submodule piece includes:
the image segmentation unit is used for carrying out image segmentation on the expressway background image by adopting a threshold segmentation method, reserving lane line position information and dividing lane line areas;
the edge detection unit is used for carrying out edge detection on the lane lines by utilizing a sobel operator and extracting the lane lines;
the probability Hough transform unit is used for acquiring endpoint information of two ends of the lane line based on probability Hough transform.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method for detecting a speed of a multi-lane vehicle, comprising the steps of:
carrying out Gaussian mixture modeling on the expressway video to obtain an expressway background map without vehicles;
detecting lane lines based on the expressway background map, extracting lane lines and acquiring lane line end point information; the lane line endpoint information is lane line endpoint pixel coordinates in an image coordinate system;
carrying out coordinate transformation on the lane line endpoint information to obtain virtual detection areas of different lanes;
and selecting the position of the mass center of the vehicle, detecting and tracking the obtained vehicle track by using the vehicle, and taking the mass center of the vehicle as a reference to obtain the running speed of the vehicle passing through the virtual detection area.
2. The method according to claim 1, wherein the image coordinate system is an OPQ coordinate system, the origin O is a vertex of a lower left corner of the image, and the coordinates (P i ，Q i ) The inverse of the column and row numbers, respectively, of the pixel in the array.
3. The method for detecting a multi-lane vehicle speed according to claim 1, wherein the detecting lane lines based on the expressway background map, extracting lane lines and acquiring lane line end point information comprises:
carrying out image segmentation on the expressway background map by adopting a threshold segmentation method, reserving lane line position information, and dividing lane line areas;
performing edge detection on the lane lines by using a sobel operator, and extracting the lane lines;
and acquiring endpoint information at two ends of the lane line based on probability Hough transformation.
4. The method for detecting a multi-lane vehicle speed according to claim 2, wherein performing coordinate transformation on the lane line end point information to obtain virtual detection areas of different lanes comprises:
a pixel coordinate (P) i ，Q i ) Transformed into coordinates in a world coordinate system, and the conversion relation between the two is shown as the following formula:
wherein the world coordinate system coordinates (X i ，Y i ，Z i ) For the pixel coordinates (P i ，Q i ) Projection coordinates on world coordinate system, S i Is a constant; m is 1 matrix 3 x 4, called projection matrix; m is m ij The j-th column element of the ith row of the projection matrix M;
neglecting Z coordinate information in the world coordinate system to obtain a formula:
obtaining pixel coordinates (P) according to the above i ，Q i ) Coordinates in world coordinate system (X i ，Y i )。
5. The multi-lane vehicle speed detection method according to claim 1, wherein the virtual detection area of each lane is a rectangular area determined by four points, the lanes including a center lane and an edge lane;
the virtual detection area of the middle lane is determined by lane line edge endpoints at two sides of the middle lane;
and selecting an inner side lane line end point of the edge lane corresponding to lane line edge end points on two sides of the middle lane, respectively acquiring the perpendicular points of the inner side lane line end point and the edge lane line according to the inner side lane line end point, and determining a virtual detection area of the edge lane based on the inner side lane line end point and the perpendicular points.
6. The method according to claim 1, wherein determining a vehicle centroid position, using a vehicle trajectory obtained by vehicle detection and tracking, and taking the vehicle centroid as a reference, to obtain a running speed of the vehicle through the virtual detection area, comprises:
recording the video frame number t of the moment when the vehicle mass center enters the edge line of the virtual detection area 1 ；
Recording the number t of video frames at the moment when the mass center of the vehicle is driven away from the edge line of the virtual detection area 2 ；
Using velocity formulaThe vehicle speed is determined.
7. The utility model provides a multilane speed of a motor vehicle detecting system which characterized in that includes virtual regional design module and speed of a motor vehicle detecting module, virtual regional design module includes:
the Gaussian mixture processing sub-module is used for carrying out Gaussian mixture modeling on the expressway video to obtain an expressway background image without vehicles;
the lane line detection sub-module is used for detecting lane lines based on the expressway background image, extracting lane lines and acquiring lane line end point information; the lane line endpoint information is lane line endpoint pixel coordinates in an image coordinate system;
the coordinate transformation submodule is used for carrying out coordinate transformation on the lane line endpoint information to obtain virtual detection areas of different lanes;
the vehicle speed detection module is used for detecting and tracking the obtained vehicle track by using the vehicle and obtaining the running speed of the vehicle passing through the virtual detection area by taking the mass center of the vehicle as a reference.
8. The multi-lane vehicle speed detection system of claim 7 wherein the lane line detection submodule comprises:
the image segmentation unit is used for carrying out image segmentation on the expressway background image by adopting a threshold segmentation method, reserving lane line position information and dividing lane line areas;
the edge detection unit is used for carrying out edge detection on the lane lines by utilizing a sobel operator and extracting the lane lines;
and the probability Hough transformation unit is used for acquiring the endpoint information at the two ends of the lane line based on the probability Hough transformation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310470574.4A CN116503818A (en) | 2023-04-27 | 2023-04-27 | Multi-lane vehicle speed detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310470574.4A CN116503818A (en) | 2023-04-27 | 2023-04-27 | Multi-lane vehicle speed detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116503818A true CN116503818A (en) | 2023-07-28 |
Family
ID=87321213
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310470574.4A Pending CN116503818A (en) | 2023-04-27 | 2023-04-27 | Multi-lane vehicle speed detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503818A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116884235A (en) * | 2023-08-09 | 2023-10-13 | 广东省交通运输规划研究中心 | Video vehicle speed detection method, device and equipment based on wire collision and storage medium |
| CN117953191A (en) * | 2023-12-29 | 2024-04-30 | 广东智视云控科技有限公司 | Vehicle speed detection line generation method, system and storage medium based on video monitoring |
| CN117994741A (en) * | 2024-01-03 | 2024-05-07 | 广东智视云控科技有限公司 | Vehicle speed detection method, system and storage medium based on video monitoring |
| CN118015567A (en) * | 2024-04-07 | 2024-05-10 | 东南大学 | Lane dividing method and related device suitable for highway roadside monitoring |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160083410A (en) * | 2014-12-31 | 2016-07-12 | 가천대학교 산학협력단 | System and method for detecting lane using lane variation vector and cardinal spline |
| CN108052880A (en) * | 2017-11-29 | 2018-05-18 | 南京大学 | Traffic monitoring scene actual situation method for detecting lane lines |
| WO2018123019A1 (en) * | 2016-12-28 | 2018-07-05 | 本田技研工業株式会社 | Vehicle control system, vehicle control method, and vehicle control program |
| CN112150826A (en) * | 2020-07-29 | 2020-12-29 | 广州汽车集团股份有限公司 | Vehicle speed determination method and device and computer readable storage medium |
-
2023
- 2023-04-27 CN CN202310470574.4A patent/CN116503818A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160083410A (en) * | 2014-12-31 | 2016-07-12 | 가천대학교 산학협력단 | System and method for detecting lane using lane variation vector and cardinal spline |
| WO2018123019A1 (en) * | 2016-12-28 | 2018-07-05 | 本田技研工業株式会社 | Vehicle control system, vehicle control method, and vehicle control program |
| CN108052880A (en) * | 2017-11-29 | 2018-05-18 | 南京大学 | Traffic monitoring scene actual situation method for detecting lane lines |
| CN112150826A (en) * | 2020-07-29 | 2020-12-29 | 广州汽车集团股份有限公司 | Vehicle speed determination method and device and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 封博文: "高速公路视频测速中的距离自动标定与测距关键技术研究", 中国优秀硕士学位论文全文数据库信息科技辑, no. 06, 15 June 2016 (2016-06-15), pages 24 - 40 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116884235A (en) * | 2023-08-09 | 2023-10-13 | 广东省交通运输规划研究中心 | Video vehicle speed detection method, device and equipment based on wire collision and storage medium |
| CN116884235B (en) * | 2023-08-09 | 2024-01-30 | 广东省交通运输规划研究中心 | Video vehicle speed detection method, device and equipment based on wire collision and storage medium |
| CN117953191A (en) * | 2023-12-29 | 2024-04-30 | 广东智视云控科技有限公司 | Vehicle speed detection line generation method, system and storage medium based on video monitoring |
| CN117994741A (en) * | 2024-01-03 | 2024-05-07 | 广东智视云控科技有限公司 | Vehicle speed detection method, system and storage medium based on video monitoring |
| CN118015567A (en) * | 2024-04-07 | 2024-05-10 | 东南大学 | Lane dividing method and related device suitable for highway roadside monitoring |
| CN118015567B (en) * | 2024-04-07 | 2024-06-11 | 东南大学 | Lane dividing method and related device suitable for highway roadside monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021004548A1 (en) | Vehicle speed intelligent measurement method based on binocular stereo vision system | |
| CN116503818A (en) | Multi-lane vehicle speed detection method and system | |
| CN109059944B (en) | Motion planning method based on driving habit learning | |
| EP4191532A1 (en) | Image annotation | |
| CN103617412B (en) | Real-time lane line detection method | |
| WO2018177026A1 (en) | Device and method for determining road edge | |
| CN104217427B (en) | Lane line localization method in a kind of Traffic Surveillance Video | |
| CN104766058A (en) | Method and device for obtaining lane line | |
| CN103425764B (en) | Vehicle matching method based on videos | |
| CN110307791B (en) | Vehicle length and speed calculation method based on three-dimensional vehicle boundary frame | |
| CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
| CN104282020A (en) | Vehicle speed detection method based on target motion track | |
| Zhang et al. | A real-time curb detection and tracking method for UGVs by using a 3D-LIDAR sensor | |
| Unger et al. | Parking assistance using dense motion-stereo: Real-time parking slot detection, collision warning and augmented parking | |
| CN109101939B (en) | Method, system, terminal and readable storage medium for determining vehicle motion state | |
| CN109791607B (en) | Detection and verification of objects from a series of images of a camera by means of homography matrices | |
| CN110189363B (en) | Airport scene moving target low-visual-angle video speed measuring method | |
| Luo et al. | Multiple lane detection via combining complementary structural constraints | |
| CN103204104B (en) | Monitored control system and method are driven in a kind of full visual angle of vehicle | |
| Poggenhans et al. | A universal approach to detect and classify road surface markings | |
| CN111325187B (en) | Lane position identification method and device | |
| Xu et al. | Road lane modeling based on RANSAC algorithm and hyperbolic model | |
| Liu et al. | Towards industrial scenario lane detection: vision-based AGV navigation methods | |
| CN113516853B (en) | Multi-lane traffic flow detection method for complex monitoring scene | |
| US11904843B2 (en) | Autonomous parking systems and methods for vehicles |
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 |