CN113506449B - High-speed highway vehicle speed measuring method based on video compression domain - Google Patents
High-speed highway vehicle speed measuring method based on video compression domain Download PDFInfo
- Publication number
- CN113506449B CN113506449B CN202110559643.XA CN202110559643A CN113506449B CN 113506449 B CN113506449 B CN 113506449B CN 202110559643 A CN202110559643 A CN 202110559643A CN 113506449 B CN113506449 B CN 113506449B
- Authority
- CN
- China
- Prior art keywords
- frame
- motion vector
- speed
- vehicle
- macro block
- 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
- 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
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
- H04N19/176—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
- H04N19/503—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving temporal prediction
- H04N19/51—Motion estimation or motion compensation
- H04N19/513—Processing of motion vectors
Abstract
The invention provides a high-speed road vehicle speed measuring method based on a video compression domain, which comprises the following steps: step 1, extracting a motion vector MV from a video code stream; step 2, initializing the camera: extracting a region of interest ROI; mapping a camera pixel coordinate system into a road actual coordinate system; learning the maximum vehicle speed analyzable by the camera; step 3, preprocessing a motion vector MV, eliminating the motion vector MV which is not in the ROI, and only processing the macro block of the non-zero motion vector MV in the ROI; step 4, detecting a moving target in a time-space domain; step 5, marking a moving target; step 6, tracking the moving target; step 7, calculating the speed: calculating the pixel displacement of the current target frame and the tracking target frame through the tracking target frame obtained in the step 6, and obtaining time through a frame rate so as to calculate the pixel displacement speed; and (3) calculating the actual displacement speed through the pixel displacement conversion obtained in the step (2), and finally obtaining the vehicle speed.
Description
Technical Field
The invention relates to a detection method based on machine vision, in particular to a high-speed road vehicle speed measurement method based on a video compression domain.
Background
With the development of society, the expressway reaches all the way around nowadays, brings convenience to the travelers. However, the overspeed condition occurs on the expressway, and the overspeed is one of the main reasons for the accident of the expressway, which brings great potential safety hazards to the travelers on the expressway. At present, many speed measuring devices are arranged on the expressway, and are used for detecting the occurrence of the violation item of overspeed, including electromagnetic coil speed measurement, radar speed measurement, laser speed measurement and the like. These speed measuring devices need to cooperate with a camera device to detect whether the vehicle is speeding. The speed measuring methods not only need to install additional equipment, but also have higher installation and maintenance cost, so a new method for measuring the speed of the video image is generated. The method only needs the support of the camera equipment, calculates the vehicle speed by using an image processing method, and can be applied to the scenes of the traditional speed measuring method.
The current video image speed measurement methods are of two types, one is to select certain information of a vehicle as a characteristic (such as a license plate) for identification and tracking; one is to specify a certain area in the image as a monitoring point and measure the speed when a target passes through. The former needs to perform feature identification and matching, and although higher precision can be achieved, the video needs to be completely decoded, a vehicle is searched for in the whole frame of image, and the calculation complexity is high. In the latter, although the calculation amount is reduced, the time when the vehicle enters and exits the boundary is difficult to determine, an error is increased, the accuracy is reduced, and the measurement is difficult in the case where a large number of vehicles enter the area.
The current video image speed measurement method firstly finds out vehicles in each frame and records vehicle characteristics (such as license plate, vehicle type and color), then finds out the same vehicle through the characteristics, records the displacement of the vehicle between frames, and calculates the vehicle speed. Therefore, vehicles need to be searched globally in a video frame, because the existing monitoring video has higher resolution, the global search in the whole frame needs higher calculation power, the problems of high delay, instability and the like can be caused, and the speed measurement of the vehicles needs more stable real-time performance so as to achieve the purpose of warning or danger early warning of overspeed vehicles. It is therefore desirable to provide a method for fast search and tracking of vehicles and calculating their speed to solve the current delay problem due to full decoding calculations.
Disclosure of Invention
The invention aims to provide a high-speed road vehicle speed measuring method based on a video compression domain, aiming at the defects of the prior art.
In order to achieve the purpose, the invention adopts the technical scheme that:
the invention provides a high-speed road vehicle speed measuring method based on a video compression domain in a first aspect, which comprises the following steps:
1) fitting a road region function f (x) through accumulation of the extracted motion vectors MV, and taking the road region function f (x) as a region of interest ROI;
2) mapping a camera pixel coordinate system into a road actual coordinate system by a DLT method;
3) learning the maximum vehicle speed analyzable by the camera;
and 3, preprocessing a motion vector MV:
eliminating the motion vector MV not in the ROI, and only processing the macro block of the non-zero motion vector MV in the ROI;
judging whether a nonzero macro block in the ROI is a moving target or not according to the characteristic that the vehicle motion is continuous and smooth, and setting a threshold value to determine whether the current macro block MBc to be detected is a macro block MBreal of a moving vehicle or not;
step 5, marking the moving target:
merging the macro blocks MBreal marked as moving vehicles in the current frame, classifying the spatial neighbors into one class, and if the intra-class motion vector MV difference is too large, continuously subdividing the intra-class motion vector MV cluster into multiple classes;
marking the MBreal of all vehicles through a rectangular target frame, recording the length, the width and the gravity center of the target frame as the position of the vehicle in the frame, and fusing and projecting the motion vectors MV of all MBreal in the target frame to form a single motion vector MVreal capable of representing the motion condition of the vehicle in the frame;
step 6, tracking the moving target:
setting cMReal as the projection of the motion vector MV of the current frame, and setting nMReal as the projection of the motion vector MV of the next frame;
matching cMUVreal of all target frames of the current frame with nMRVreal of a target frame of the next frame, selecting the target frames with high similarity as a matching object set A, judging the length and width difference of the target frames in A, selecting the most similar target frame as a matching object set B, selecting the target frames with the most similar positions in B as tracking target frames, and simultaneously declaring the tracking success;
step 7, calculating the speed:
calculating the pixel displacement of the current target frame and the tracking target frame through the tracking target frame obtained in the step 6, and obtaining time through a frame rate so as to calculate the pixel displacement speed;
and (3) calculating the actual displacement speed through the pixel displacement conversion obtained in the step (2), and finally obtaining the vehicle speed.
Based on the above, when the motion vector MV is extracted from the video code stream, the macroblock size is normalized to 4 × 4, the macroblocks other than 4 × 4 are split into n macroblocks of 4 × 4, and the original MV size is used for the split macroblocks.
Based on the above, the maximum vehicle speed V which can be analyzed by the learning cameramaxThe method comprises the following steps: the vehicle enters the camera in the first frame and the second frameMoving out of the camera, and calculating the maximum vehicle speed V according to the distance of the shooting area of the camera and the time in one framemax。
Based on the above, the detecting the moving target in the time-space domain in the step 4 includes:
step a, spatial domain processing: determining whether the macro block is an isolated point according to whether a motion vector MV exists in an 8-neighborhood of the current macro block MBc to be detected, if more than 5 macro blocks exist in the neighborhood and have non-zero motion vectors MV, determining that the macro block is a non-isolated point, otherwise, determining that the macro block is an isolated point, and setting the motion vector MV of the macro block to be zero;
step b, time domain processing: let macroblock MBc be the macroblock to be analyzed and MVc be its motion vector MV; MBref is a macroblock MBcProjected to a macroblock in a reference frame, MVref is its motion vector MV;
and c, processing the macro block MBc processed in the step a as follows: synthesizing the macro block MBc to be analyzed and the corresponding MVc and back-projecting the synthesized macro block to the reference frame to generate MBref, wherein the MBref at most overlaps with four blocks of the reference frame, the MVref size is calculated by weighting MVs of the four overlapped blocks according to the overlapping area, the MVref size is compared with the MVc, if the MVref size is similar to the MVc, MBc and the corresponding MVc really reflect a moving vehicle, and MBc is marked as MBreal.
The invention provides a camera, which is deployed on a highway for measuring the speed of vehicles, and is characterized in that: the method for measuring the speed of the vehicle adopts the method for measuring the speed of the vehicle on the highway based on the video compression domain.
Compared with the prior art, the invention has prominent substantive characteristics and remarkable progress, and particularly has the following beneficial effects:
1. only the motion vector mv is used for analysis, other compression domain parameters are not involved, and special parameters owned by different standards are avoided;
2. the road information is learned through the motion vector MV, the non-road information is eliminated, and the processing amount is reduced;
3. the difference of the magnitude and the direction of the motion vector MV is considered, the object tracking accuracy is improved, and the corresponding weight can be changed according to the road.
4. The road area is learned in the camera initialization process, a large amount of non-road area information can be eliminated in subsequent data processing and identification, and the data volume and the processing complexity are greatly reduced.
Drawings
FIG. 1 is a schematic view of a region of interest ROI obtained by accumulating MVs in the method of the present invention.
FIG. 2 is a schematic diagram of a current frame projected onto a reference frame in the method of the present invention.
Detailed Description
The technical solution of the present invention is further described in detail by the following embodiments.
Example 1
As shown in fig. 1-2, the present embodiment provides a method for measuring speed of vehicles on a highway based on a video compression domain, including the following steps:
during extraction, the macroblock size is normalized to 4 × 4, non-4 × 4 macroblocks are split into n 4 × 4 macroblocks, and the split macroblocks use the original MV size.
1) fitting a road region function f (x) through accumulation of the extracted motion vectors MV, taking the road region function f (x) as a region of interest ROI, and removing influences brought by non-concerned objects;
2) mapping a camera pixel coordinate system into a road actual coordinate system by a DLT method;
3) learning the maximum vehicle speed analyzable by the camera;
assuming that the vehicle enters the camera in the first frame and exits the camera in the second frame, the vehicle speed is the maximum vehicle speed Vmax. The maximum vehicle speed V can be calculated according to the distance of the shooting area of the camera and the time in one framemax。All less than VmaxThe moving object can be recorded to the motion state by the camera in more than 2 frames, namely the motion speed can be estimated and the tracking can be finished by the method.
And 3, preprocessing a motion vector MV:
the motion vectors MV not in the region of interest ROI are removed and only the macroblocks of non-zero motion vectors MV in the region of interest ROI are processed.
judging whether a nonzero macro block in the ROI is a moving target according to the characteristic that the vehicle moves continuously and smoothly, and setting a threshold value to determine whether the current macro block MBc to be detected is a macro block MBreal of a moving vehicle;
specifically, the time-space domain detection of the moving target includes:
step a, spatial domain processing: determining whether the macro block is an isolated point according to whether a motion vector MV exists in an 8-neighborhood of the current macro block MBc to be detected, if more than 5 macro blocks exist in the neighborhood and have non-zero motion vectors MV, determining that the macro block is a non-isolated point, otherwise, determining that the macro block is an isolated point, and setting the motion vector MV of the macro block to be zero;
step b, time domain processing: let macroblock MBc be the macroblock to be analyzed and MVc be its motion vector MV; MBref is a macroblock MBcThe motion vector MV of the macroblock projected into the reference frame is MVref;
and c, processing the macro block MBc processed in the step a as follows: synthesizing a macro block MBc to be analyzed and a corresponding MVc, and reversely projecting the synthesized macro block MBc and the corresponding MVc onto a reference frame to generate an MBref, wherein the MBref at most overlaps with four blocks of the reference frame, the MVref size is calculated by weighting MVs of the four overlapped blocks according to the overlapped area, the MVref size is compared with the MVc, if the MBref size is similar to the MVc size, MBc and the corresponding MVc actually reflect a moving vehicle, and MBc is marked as MBreal;
the above calculation method can be expressed as follows:
MBref=MBc-MVc/k
wherein si represents the overlapping area MVi of the macroblock i in the reference frame and the projection MBref and represents the MV of the macroblock i; k is a coefficient reflecting different pixel precisions of the MVs, namely, the MVs are converted into vectors based on the pixel sizes; TH is a threshold to verify whether MVc and MVref are close.
Step 5, marking the moving target:
merging the macro blocks MBreal marked as moving vehicles in the current frame, classifying the spatial neighbors into one class, and if the intra-class motion vector MV difference is found to be overlarge, continuously subdividing into multiple classes through intra-class motion vector MV clustering;
marking the MBreal of all vehicles through a rectangular target frame, recording the length, the width and the gravity center of the target frame as the position of the vehicle in the frame, and fusing and projecting the motion vectors MV of all MBreal in the target frame to form a single motion vector MVreal capable of representing the motion condition of the vehicle in the frame;
step 6, tracking the moving target:
setting cMReal as the projection of the motion vector MV of the current frame, and setting nMReal as the projection of the motion vector MV of the next frame;
matching cMUVreal of all target frames of the current frame with nMRVreal of a target frame of the next frame, selecting the target frames with high similarity as a matching object set A, judging the length and width difference of the target frames in A, selecting the most similar target frame as a matching object set B, selecting the target frames with the most similar positions in B as tracking target frames, and simultaneously declaring the tracking success;
specifically, let S be the similarity, the calculation method for tracking the moving object is as follows:
wherein eucl is Euclidean distance and is used for judging the distance between vectors and is sensitive to absolute distance, cos is cosine similarity and is used for judging the included angle between vectors and is sensitive to change trend. The two are combined to determine the difference between the vectors in absolute distance and variation trend. Alpha and beta are weights of alpha and beta, alpha and beta can be updated through the road information obtained in the step 2, derivatives of f (x) are calculated in a segmented mode through the road fitting function f (x) obtained in the step 2, the larger the derivative is, the more curved the road curve is proved to be, the driving direction of the vehicle is changed, the cosine similarity is increased in error, at the moment, the Euclidean distance accounts for the main component of the similarity, and alpha needs to be increased to reduce beta. And vice versa.
Step 7, calculating the speed:
calculating the pixel displacement of the current target frame and the tracking target frame through the tracking target frame obtained in the step 6, and obtaining time through a frame rate so as to calculate the pixel displacement speed;
and (3) calculating the actual displacement speed through the pixel displacement conversion obtained in the step (2), and finally obtaining the vehicle speed.
Example 2
The embodiment provides a camera, which is deployed on a highway and used for vehicle speed measurement, and the method for vehicle speed measurement adopts the method for vehicle speed measurement on the highway based on the video compression domain described in embodiment 1.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention and not to limit it; although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art will understand that: modifications to the specific embodiments of the invention or equivalent substitutions for parts of the technical features may be made; without departing from the spirit of the present invention, it is intended to cover all aspects of the invention as defined by the appended claims.
Claims (5)
1. A method for measuring speed of vehicles on a highway based on a video compression domain is characterized by comprising the following steps:
step 1, extracting a motion vector MV from a video code stream;
step 2, initializing the camera:
1) fitting a road region function f (x) through accumulation of the extracted motion vectors MV, and taking the road region function f (x) as a region of interest ROI;
2) mapping a camera pixel coordinate system into a road actual coordinate system by a DLT method;
3) learning the maximum vehicle speed analyzable by the camera;
and 3, preprocessing a motion vector MV:
eliminating the motion vector MV not in the ROI, and only processing the macro block of the non-zero motion vector MV in the ROI;
step 4, detecting a moving target in a time-space domain:
judging whether a nonzero macro block in the ROI is a moving target or not according to the characteristic that the vehicle motion is continuous and smooth, and setting a threshold value to determine whether the current macro block MBc to be detected is a macro block MBreal of a moving vehicle or not;
step 5, marking a moving target:
merging the macro blocks MBreal marked as moving vehicles in the current frame, classifying the spatial neighbors into one class, and if the intra-class motion vector MV difference is too large, continuously subdividing the intra-class motion vector MV cluster into multiple classes;
marking the MBreal of all vehicles through a rectangular target frame, recording the length, the width and the gravity center of the target frame as the position of the vehicle in the frame, and fusing and projecting the motion vectors MV of all MBreal in the target frame to form a single motion vector MVreal capable of representing the motion condition of the vehicle in the frame;
step 6, tracking the moving target:
setting cMReal as the projection of the motion vector MV of the current frame, and setting nMReal as the projection of the motion vector MV of the next frame;
matching cMUVreal of all target frames of the current frame with nMRVreal of a target frame of the next frame, selecting the target frames with high similarity as a matching object set A, judging the length and width difference of the target frames in A, selecting the most similar target frame as a matching object set B, selecting the target frames with the most similar positions in B as tracking target frames, and simultaneously declaring the tracking success;
step 7, calculating speed:
calculating the pixel displacement of the current target frame and the tracking target frame through the tracking target frame obtained in the step 6, and obtaining time through a frame rate so as to calculate the pixel displacement speed;
and (3) calculating the actual displacement speed through the pixel displacement conversion obtained in the step (2), and finally obtaining the vehicle speed.
2. The method according to claim 1, wherein when the motion vector MV is extracted from the video bitstream, the macroblock size is normalized to 4 × 4, the non-4 × 4 macroblocks are split into n 4 × 4 macroblocks, and the original MV size is used for the split macroblocks.
3. The method for measuring speed of vehicles on highways based on video compression domain as claimed in claim 2, wherein the maximum vehicle speed V analyzable by the learning cameramaxThe method comprises the following steps: the vehicle enters the camera in the first frame, the vehicle exits the camera in the second frame, and the maximum vehicle speed V is calculated according to the distance of the shooting area of the camera and the time in one framemax。
4. The method for measuring the speed of vehicles on highways according to claim 3, wherein the step 4 of detecting moving targets in the space-time domain comprises:
step a, spatial domain processing: determining whether the macro block is an isolated point according to whether a motion vector MV exists in an 8-neighborhood of the current macro block MBc to be detected, if more than 5 macro blocks exist in the neighborhood and have non-zero motion vectors MV, determining that the macro block is a non-isolated point, otherwise, determining that the macro block is an isolated point, and setting the motion vector MV of the macro block to be zero;
step b, time domain processing: let macroblock MBc be the macroblock to be analyzed and MVc be its motion vector MV; MBref is the macroblock from which the macroblock MBc projects into the reference frame, and MVref is its motion vector MV;
and c, processing the macro block MBc processed in the step a as follows: synthesizing the macro block MBc to be analyzed and the corresponding MVc and back-projecting the synthesized macro block to the reference frame to generate MBref, wherein the MBref at most overlaps with four blocks of the reference frame, the MVref size is calculated by weighting MVs of the four overlapped blocks according to the overlapping area, the MVref size is compared with the MVc, if the MVref size is similar to the MVc, MBc and the corresponding MVc really reflect a moving vehicle, and MBc is marked as MBreal.
5. The utility model provides a camera, deploys and is used for the vehicle to test the speed on highway which characterized in that: the method for measuring the speed of the vehicle adopts the method for measuring the speed of the vehicle on the highway based on the video compression domain as claimed in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110559643.XA CN113506449B (en) | 2021-05-21 | 2021-05-21 | High-speed highway vehicle speed measuring method based on video compression domain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110559643.XA CN113506449B (en) | 2021-05-21 | 2021-05-21 | High-speed highway vehicle speed measuring method based on video compression domain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113506449A CN113506449A (en) | 2021-10-15 |
| CN113506449B true CN113506449B (en) | 2022-06-21 |
Family
ID=78008474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110559643.XA Active CN113506449B (en) | 2021-05-21 | 2021-05-21 | High-speed highway vehicle speed measuring method based on video compression domain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113506449B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114363562A (en) * | 2021-12-08 | 2022-04-15 | 国网河北省电力有限公司信息通信分公司 | 5G distribution network monitoring system and distribution network monitoring method based on cloud distribution |
| CN114363563A (en) * | 2021-12-08 | 2022-04-15 | 国网河北省电力有限公司信息通信分公司 | Distribution network monitoring system and method based on 5G ultra-high-definition video monitoring |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070077179A (en) * | 2007-06-28 | 2007-07-25 | 이기훈 | Car speed detector |
| JP2009129181A (en) * | 2007-11-22 | 2009-06-11 | Ikegami Tsushinki Co Ltd | Speed measurement method |
| CN101604448A (en) * | 2009-03-16 | 2009-12-16 | 北京中星微电子有限公司 | A kind of speed-measuring method of moving target and system |
| KR20100053030A (en) * | 2008-11-12 | 2010-05-20 | (주)인펙비전 | Method for vehicle image detection and speed calculation |
| CN104318782A (en) * | 2014-10-31 | 2015-01-28 | 浙江力石科技股份有限公司 | Expressway video speed measuring method and system for zone overlapping |
| CN105761504A (en) * | 2016-05-17 | 2016-07-13 | 重庆大学 | Vehicle speed real-time measuring method based on inhomogeneous video image frame collection |
| CN111753797A (en) * | 2020-07-02 | 2020-10-09 | 浙江工业大学 | Vehicle speed measuring method based on video analysis |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9582722B2 (en) * | 2012-08-31 | 2017-02-28 | Xerox Corporation | Video-based vehicle speed estimation from motion vectors in video streams |
-
2021
- 2021-05-21 CN CN202110559643.XA patent/CN113506449B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070077179A (en) * | 2007-06-28 | 2007-07-25 | 이기훈 | Car speed detector |
| JP2009129181A (en) * | 2007-11-22 | 2009-06-11 | Ikegami Tsushinki Co Ltd | Speed measurement method |
| KR20100053030A (en) * | 2008-11-12 | 2010-05-20 | (주)인펙비전 | Method for vehicle image detection and speed calculation |
| CN101604448A (en) * | 2009-03-16 | 2009-12-16 | 北京中星微电子有限公司 | A kind of speed-measuring method of moving target and system |
| CN104318782A (en) * | 2014-10-31 | 2015-01-28 | 浙江力石科技股份有限公司 | Expressway video speed measuring method and system for zone overlapping |
| CN105761504A (en) * | 2016-05-17 | 2016-07-13 | 重庆大学 | Vehicle speed real-time measuring method based on inhomogeneous video image frame collection |
| CN111753797A (en) * | 2020-07-02 | 2020-10-09 | 浙江工业大学 | Vehicle speed measuring method based on video analysis |
Non-Patent Citations (4)
| Title |
|---|
| An algorithm for automatic vehicle speed detection using video camera;Jianping Wu;《2009 4th International Conference on Computer Science & Education》;20090901;第193-196页 * |
| The Speed Detection Algorithm Based on Video Sequences;Wang Liang;《2012 International Conference on Computer Science and Service System》;20121231;第217-220页 * |
| 基于3D目标检测的车辆测速算法及性能分析;李圣杰 等;《中国集成电路》;20210505(第264期);第54-60页 * |
| 基于视频的车辆速度估计方法;宋涛等;《河南大学学报(自然科学版)》;20130116;第43卷(第01期);第91-95页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113506449A (en) | 2021-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111753797B (en) | Vehicle speed measuring method based on video analysis | |
| CN113506449B (en) | High-speed highway vehicle speed measuring method based on video compression domain | |
| CN100545867C (en) | Aerial shooting traffic video frequency vehicle rapid checking method | |
| CN108846854B (en) | Vehicle tracking method based on motion prediction and multi-feature fusion | |
| CN102609720B (en) | Pedestrian detection method based on position correction model | |
| US20140348390A1 (en) | Method and apparatus for detecting traffic monitoring video | |
| Nguyen et al. | Compensating background for noise due to camera vibration in uncalibrated-camera-based vehicle speed measurement system | |
| CN102855758A (en) | Detection method for vehicle in breach of traffic rules | |
| CN111160220B (en) | Deep learning-based parcel detection method and device and storage medium | |
| Börcs et al. | Fast 3-D urban object detection on streaming point clouds | |
| CN114170580A (en) | Highway-oriented abnormal event detection method | |
| Swathy et al. | Survey on vehicle detection and tracking techniques in video surveillance | |
| CN113313012B (en) | Dangerous driving behavior identification method based on convolution generation countermeasure network | |
| Xia et al. | Automatic multi-vehicle tracking using video cameras: An improved CAMShift approach | |
| CN113409588B (en) | Multi-vehicle speed measurement method based on video compression domain | |
| Lee et al. | Vehicle counting based on a stereo vision depth maps for parking management | |
| Qui et al. | The study of the detection of pedestrian and bicycle using image processing | |
| Špaňhel et al. | Detection of traffic violations of road users based on convolutional neural networks | |
| CN113313008B (en) | Target and identification tracking method based on YOLOv3 network and mean shift | |
| CN106056926B (en) | Video vehicle speed detection method based on dynamic virtual coil | |
| Tourani et al. | Challenges of video-based vehicle detection and tracking in intelligent transportation systems | |
| Lu et al. | Target detection algorithm based on mmw radar and camera fusion | |
| Candradewi et al. | Intelligent traffic monitoring systems: Vehicle type classification using support vector machine | |
| Yang et al. | A robust vehicle queuing and dissipation detection method based on two cameras | |
| CN112037536A (en) | Vehicle speed measuring method and device based on video feature recognition |
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 |