CN111753797A - Vehicle speed measuring method based on video analysis - Google Patents
Vehicle speed measuring method based on video analysis Download PDFInfo
- Publication number
- CN111753797A CN111753797A CN202010626133.5A CN202010626133A CN111753797A CN 111753797 A CN111753797 A CN 111753797A CN 202010626133 A CN202010626133 A CN 202010626133A CN 111753797 A CN111753797 A CN 111753797A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target
- vehicle speed
- speed measuring
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
The invention discloses a vehicle speed measuring method based on video analysis, which comprises the following steps: carrying out vehicle target detection on a vehicle speed measuring area by using a deep convolutional neural network; starting to track the vehicle after the vehicle enters the detection area to obtain the real-time positioning of the vehicle; and after the vehicle exits the vehicle speed measuring area, fitting a nonlinear function of vehicle displacement and vehicle speed by using a deep neural network to output the vehicle speed. According to the invention, the target detection and tracking of the vehicle are realized through deep learning, and the mapping between the pixel position of the vehicle and the vehicle speed is realized through constructing a deep neural network model, so that the running speed of the vehicle can be accurately detected.
Description
Technical Field
The invention relates to the technical field of intelligent traffic, in particular to a vehicle speed measuring method based on video analysis, and specifically relates to a method for analyzing videos through a convolutional neural network to realize vehicle speed measurement.
Background
With the rapid development of the traffic industry in China, the vehicle video information collected by the road camera forms massive data storage. Traditional traffic monitoring system shoots the road through the camera equipment of installing in road top or side usually, and then cooperates modes such as pre-buried coil or radar, laser radar to detect the hypervelocity action and take a picture and collect evidence, needs the work that a plurality of systems cooperation work just can accomplish the work of testing the speed. Compared with the traditional complex installation, laying and debugging work of the sensor, the video-based vehicle speed measurement method has wider application scenes due to the flexibility. Image and video processing is widely used to solve urban traffic problems, which will make better use of existing road monitoring systems.
With the rapid development of video image processing technology, many scholars are dedicated to research on a traffic parameter detection method based on the video image technology, and a virtual coil method and a trajectory tracking method are researched in sequence and applied to vehicle speed measurement. However, measuring speed of vehicles in natural scenes is still a challenging task.
The current methods related to video-based vehicle speed measurement include: the invention patent (application number: CN201611018445.8, name: a vehicle speed measuring method based on video detection) utilizes Sobel operator to calculate edge image, and real-time speed measurement is carried out according to vehicle tail multi-frame position matching and conversion of image coordinate and world coordinate, but the detection precision of the method is easily influenced by illumination, weather environment and the like; the invention discloses a vehicle license plate recognition model (application number: CN201910608772.6, name: an intelligent vehicle speed measurement method based on a binocular stereo vision system) for detecting a vehicle license plate of an acquired video frame, carrying out stereo measurement on a matching point by using binocular vision, acquiring a position under a space coordinate and finally acquiring a vehicle running speed. But the accuracy of stereo measurement affects the real displacement accuracy of the vehicle in video processing. Under a natural scene, the complex traffic environment makes the construction of a mapping model of vehicle pixel displacement and real displacement become a difficult point of a key technology. A plurality of technical bottlenecks exist in key links such as vehicle extraction, target segmentation and stability tracking, and the detection accuracy and stability are difficult to meet practical requirements.
Disclosure of Invention
In order to overcome the above disadvantages of the prior art, the present invention provides a vehicle speed measuring method based on video analysis, which analyzes a video through a convolutional neural network to measure the vehicle speed, and can stably track a traffic vehicle and accurately measure the speed.
The invention relates to a vehicle speed measuring method based on video analysis, which comprises the following steps:
step 1: building a camera above a road, wherein the mounting height of the camera is HcThe included angle between the optical center of the camera and the vertical line is theta, the speed measuring start-stop line is calibrated in the vehicle speed measuring area, and the distance between the near-end marking line of the camera is HcTan theta, the length of the vehicle speed measuring area is l;
step 2: carrying out vehicle target detection on a vehicle speed measuring area by using a deep convolutional neural network, and judging whether a vehicle drives into the speed measuring area;
and step 3: when a vehicle drives into a speed measuring area, vehicle tracking detection is started to obtain real-time positioning of the vehicle, and the method specifically comprises the following steps:
step 3.1: detecting all targets in the current frame by using a deep convolutional neural network to obtain target positioning frames of all vehicles in the frame;
step 3.2: initializing the detected targets, creating a new tracker, labeling the identification of each detected target, and recording the category C of the target and the current time tsRecording the starting center point (x) of the target vehicles,ys) And the length and width values (l) of the bounding boxs,ws);
Step 3.3: using a Kalman filter to obtain state prediction and covariance prediction generated by a target detected in a previous frame of image, solving an IOU threshold value of all target states of a tracker and a target frame detected in a current frame, obtaining the only match with the maximum IOU threshold value through Hungarian algorithm, and removing a matching pair with a matching value smaller than the IOU threshold value;
step 3.4: updating a Kalman tracker by using the target detection frame matched in the frame, calculating Kalman gain, updating state and updating covariance, outputting the state updating value as the tracking frame of the current frame, and reinitializing the tracker for the target which is not matched in the frame;
and 4, step 4: when the vehicle exits the vehicle speed measuring area, the current time t is recordedeRecording the final center point (x) of the target vehiclee,ye) And the length and width values (l) of the current bounding boxe,we);
And 5: calculating the time difference delta t-t of the target vehiclee-tsThe center point offset Δ x ═ xe-xs,Δy=ye-ysLength and width offsets Δ l ═ le-ls,Δw=we-ws;
Step 6: fitting a nonlinear function of vehicle displacement and vehicle speed by using a deep neural network, specifically:
step 6.1: the input layer of the deep neural network model comprises the vehicle type of the target vehicle, the time difference between the target vehicle entering and exiting the speed measuring region, the offset of the center point of the target vehicle entering the speed measuring region and the center point of the target vehicle entering the speed measuring region, the length and the width of the target vehicle entering the speed measuring region and the offset of the length and the width of the target vehicle exiting the speed measuring region, and 1/1000 of the real speed is used as a predicted real value;
step 6.2: the hidden layer of the deep neural network model comprises 3 layers of neural networks which respectively comprise 16, 8 and 4 neural nodes, each node is subjected to batch normalization, a Sigmoid function is used for activation to obtain a predicted value of a network output node, and a mean square error is used as a loss function;
wherein n isIndicates the total number of training batches, i indicates the order of the training batches, yiReal value, y ', representing the ith data in the training batch'iRepresenting the predicted value of the ith data in the training batch, y representing the real value of the training batch data, and y' representing the predicted value of the network output node;
step 6.3: calculating the vehicle speed through the predicted value of the neural network;
v'=1000×y' (2)
where y 'represents the predicted value of the network output node and v' represents the predicted vehicle speed.
The invention has the advantages that: the invention realizes the target detection and tracking of the vehicle through deep learning, has better robustness to illumination and weather change, realizes the mapping of the pixel position of the vehicle and the vehicle speed through constructing a deep neural network model, and can accurately and effectively detect the running speed of the vehicle.
Drawings
FIG. 1 is a flow chart of a method for measuring vehicle speed according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a camera and a vehicle speed measurement area according to an embodiment of the invention;
Detailed Description
The invention is further described with reference to the drawings and examples, but the scope of protection is not limited thereto:
embodiment 1 the technical scheme of the embodiment of the application is suitable for application scenes of vehicle speed measurement under traffic roads
As shown in fig. 1-2, the method for measuring the speed of a vehicle based on video analysis of the present invention includes the following steps:
step 1: building a camera above a road, wherein the mounting height of the camera is HcThe included angle between the optical center of the camera and the vertical line is theta 45 degrees, a speed measuring starting line and a speed measuring stopping line are calibrated in a vehicle speed measuring area, the distance between the near-end marked lines of the camera is 10m, and the length l of the vehicle speed measuring area is 10 m;
step 2: carrying out vehicle target detection on a vehicle speed measuring area by using a deep convolutional neural network, and judging whether a vehicle drives into the speed measuring area;
and step 3: when a vehicle drives into a speed measuring area, vehicle tracking detection is started to obtain real-time positioning of the vehicle, and the method specifically comprises the following steps:
step 3.1: detecting all targets in the current frame by using a deep convolutional neural network to obtain target positioning frames of all vehicles in the frame;
step 3.2: initializing the detected targets, creating a new tracker, labeling the identification of each detected target, and recording the category C of the target and the current time tsRecording the starting center point (x) of the target vehicles,ys) And the length and width values (l) of the bounding boxs,ws);
Step 3.3: using a Kalman filter to obtain state prediction and covariance prediction generated by a target detected in a previous frame of image, solving an IOU threshold value of all target states of a tracker and a target frame detected in a current frame, obtaining the only match with the maximum IOU threshold value through Hungarian algorithm, and removing a matching pair with a matching value smaller than the IOU threshold value;
step 3.4: updating a Kalman tracker by using the target detection frame matched in the frame, calculating Kalman gain, updating state and updating covariance, outputting the state updating value as the tracking frame of the current frame, and reinitializing the tracker for the target which is not matched in the frame;
and 4, step 4: when the vehicle exits the vehicle speed measuring area, the current time t is recordedeRecording the final center point (x) of the target vehiclee,ye) And the length and width values (l) of the current bounding boxe,we);
And 5: calculating the time difference delta t-t of the target vehiclee-tsThe center point offset Δ x ═ xe-xs,Δy=ye-ysLength and width offsets Δ l ═ le-ls,Δw=we-ws;
Step 6: fitting a nonlinear function of vehicle displacement and vehicle speed by using a deep neural network, specifically:
step 6.1: the input layer of the deep neural network model comprises the vehicle type of the target vehicle, the time difference between the target vehicle entering and exiting the speed measuring region, the offset of the center point of the target vehicle entering the speed measuring region and the center point of the target vehicle entering the speed measuring region, the length and the width of the target vehicle entering the speed measuring region and the offset of the length and the width of the target vehicle exiting the speed measuring region, and 1/1000 of the real speed is used as a predicted real value;
step 6.2: the hidden layer of the deep neural network model comprises 3 layers of neural networks which respectively comprise 16, 8 and 4 neural nodes, each node is subjected to batch normalization, a Sigmoid function is used for activation to obtain a predicted value of a network output node, and a mean square error is used as a loss function;
where n represents the total number of training batches, i represents the order of the training batches, yiReal value, y ', representing the ith data in the training batch'iRepresenting the predicted value of the ith data in the training batch, y representing the real value of the training batch data, and y' representing the predicted value of the network output node;
step 6.3: calculating the vehicle speed through the predicted value of the neural network;
v'=1000×y' (2)
where y 'represents the predicted value of the network output node and v' represents the predicted vehicle speed.
The embodiments described in this specification are merely illustrative of implementations of the inventive concept and the scope of the present invention should not be considered limited to the specific forms set forth in the embodiments but rather by the equivalents thereof as may occur to those skilled in the art upon consideration of the present inventive concept.
Claims (3)
1. A vehicle speed measuring method based on video analysis is characterized by comprising the following steps:
step 1: building a camera above a road, wherein the mounting height of the camera is HcThe included angle between the optical center of the camera and the vertical line is theta, and the speed measurement start and stop are calibrated in the vehicle speed measurement areaThe distance between the near-end reticle of the line and the camera is HcTan theta, the length of the vehicle speed measuring area is l;
step 2: carrying out vehicle target detection on the vehicle speed measuring area by using a deep convolutional neural network, and judging whether a vehicle drives into the vehicle speed measuring area;
and step 3: starting to track and detect the vehicle after the vehicle enters the detection area, initializing the detected targets, creating a new tracker, marking the identification of each detected target, and recording the category C of the target and the current time tsRecording the starting center point (x) of the target vehicles,ys) And the length and width values (l) of the bounding boxs,ws) (ii) a And obtaining real-time positioning of the vehicle;
and 4, step 4: when the vehicle exits the vehicle speed measuring area, the current time t is recordedeRecording the final center point (x) of the target vehiclee,ye) And the length and width values (l) of the current bounding boxe,we);
And 5: calculating the time difference delta t-t of the target vehiclee-tsThe center point offset Δ x ═ xe-xs,Δy=ye-ysThe length and width offsets are respectively delta l ═ le-ls,Δw=we-ws;
Step 6: a depth neural network is used to fit a non-linear function of vehicle displacement and vehicle speed.
2. The video analysis-based vehicle speed measuring method according to claim 1, wherein in step 3, vehicle tracking detection is started after the vehicle enters the detection area to obtain real-time positioning of the vehicle, and the method specifically comprises the following steps:
step 3.1: detecting all targets in the current frame by using a deep convolutional neural network to obtain target positioning frames of all vehicles in the frame;
step 3.2: initializing each detected target, creating a new tracker, marking the identification of each detected target, and recording the category C of the target and the current time tsRecording the start of the target vehicleCenter point (x)s,ys) And the length and width values (l) of the bounding boxs,ws);
Step 3.3: using a Kalman filter to obtain state prediction and covariance prediction generated by a target detected in a previous frame of image, solving an IOU threshold value of all target states of a tracker and a target frame detected in a current frame, obtaining the only match with the maximum IOU threshold value through Hungarian algorithm, and removing a matching pair with a matching value smaller than the IOU threshold value;
step 3.4: and updating the Kalman tracker by using the target detection frame matched in the frame, calculating Kalman gain, updating the state and updating the covariance, outputting the state updating value as the tracking frame of the current frame, and reinitializing the tracker for the target which is not matched in the frame.
3. The video analysis-based vehicle speed measurement method according to claim 1, wherein in step 6, a depth neural network is used to fit a nonlinear function of vehicle displacement and vehicle speed, and the method specifically comprises the following steps:
step 6.1: the input layer of the deep neural network model comprises the vehicle type of the target vehicle, the time difference between the target vehicle entering and exiting the vehicle speed measuring area, the offset of the center point of the target vehicle entering the speed measuring area and the center point of the target vehicle entering the speed measuring area, the length and width of the target vehicle entering the speed measuring area and the offset of the length and width of the target vehicle exiting the speed measuring area, and 1/1000 of the real speed is used as a predicted real value;
step 6.2: the hidden layer of the deep neural network model comprises 3 layers of neural networks which respectively comprise 16, 8 and 4 neural nodes, each node is subjected to batch normalization, a Sigmoid function is used for activation to obtain a predicted value of a network output node, and a mean square error is used as a loss function;
where n represents the total number of training batches, i represents the order of the training batches, yiReal value, y ', representing the ith data in the training batch'iExpressing trainingThe predicted value of the ith data in the training batch, y represents the true value of the training batch data, and y' represents the predicted value of the network output node;
step 6.3: calculating the vehicle speed through the predicted value of the neural network;
v'=1000×y' (2)
where y 'represents the predicted value of the network output node and v' represents the predicted vehicle speed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010626133.5A CN111753797B (en) | 2020-07-02 | 2020-07-02 | Vehicle speed measuring method based on video analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010626133.5A CN111753797B (en) | 2020-07-02 | 2020-07-02 | Vehicle speed measuring method based on video analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111753797A true CN111753797A (en) | 2020-10-09 |
CN111753797B CN111753797B (en) | 2022-02-22 |
Family
ID=72678588
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010626133.5A Active CN111753797B (en) | 2020-07-02 | 2020-07-02 | Vehicle speed measuring method based on video analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111753797B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112466121A (en) * | 2020-12-12 | 2021-03-09 | 江西洪都航空工业集团有限责任公司 | Speed measuring method based on video |
CN112487908A (en) * | 2020-11-23 | 2021-03-12 | 东南大学 | Front vehicle line pressing behavior detection and dynamic tracking method based on vehicle-mounted video |
CN112491999A (en) * | 2020-11-18 | 2021-03-12 | 成都佳华物链云科技有限公司 | Data reporting method and device |
CN112634344A (en) * | 2020-12-15 | 2021-04-09 | 西安理工大学 | Method for detecting center position of cold-rolled strip coil shaft hole based on machine vision |
CN112785855A (en) * | 2021-01-26 | 2021-05-11 | 张俊峰 | Method for acquiring vehicle speed from road monitoring video |
CN112990128A (en) * | 2021-04-27 | 2021-06-18 | 电子科技大学 | Multi-vehicle speed measuring method based on video tracking |
CN113506449A (en) * | 2021-05-21 | 2021-10-15 | 郑州大学 | High-speed highway vehicle speed measuring method based on video compression domain |
CN114758511A (en) * | 2022-06-14 | 2022-07-15 | 深圳市城市交通规划设计研究中心股份有限公司 | Sports car overspeed detection system, method, electronic equipment and storage medium |
JP7411771B1 (en) | 2022-12-01 | 2024-01-11 | セイコーソリューションズ株式会社 | Vehicle speed detection device, vehicle speed detection method and program |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102592454A (en) * | 2012-02-29 | 2012-07-18 | 北京航空航天大学 | Intersection vehicle movement parameter measuring method based on detection of vehicle side face and road intersection line |
CN102622895A (en) * | 2012-03-23 | 2012-08-01 | 长安大学 | Video-based vehicle speed detecting method |
CN105654060A (en) * | 2016-01-04 | 2016-06-08 | 中海网络科技股份有限公司 | Method for acquiring vehicle speed from road monitoring video |
US20160232410A1 (en) * | 2015-02-06 | 2016-08-11 | Michael F. Kelly | Vehicle speed detection |
CN108091142A (en) * | 2017-12-12 | 2018-05-29 | 公安部交通管理科学研究所 | For vehicle illegal activities Tracking Recognition under highway large scene and the method captured automatically |
CN110033479A (en) * | 2019-04-15 | 2019-07-19 | 四川九洲视讯科技有限责任公司 | Traffic flow parameter real-time detection method based on Traffic Surveillance Video |
CN110490156A (en) * | 2019-08-23 | 2019-11-22 | 哈尔滨理工大学 | A kind of fast vehicle detection method based on convolutional neural networks |
CN110738690A (en) * | 2019-09-16 | 2020-01-31 | 南京理工大学 | unmanned aerial vehicle video middle vehicle speed correction method based on multi-target tracking framework |
-
2020
- 2020-07-02 CN CN202010626133.5A patent/CN111753797B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102592454A (en) * | 2012-02-29 | 2012-07-18 | 北京航空航天大学 | Intersection vehicle movement parameter measuring method based on detection of vehicle side face and road intersection line |
CN102622895A (en) * | 2012-03-23 | 2012-08-01 | 长安大学 | Video-based vehicle speed detecting method |
US20160232410A1 (en) * | 2015-02-06 | 2016-08-11 | Michael F. Kelly | Vehicle speed detection |
CN105654060A (en) * | 2016-01-04 | 2016-06-08 | 中海网络科技股份有限公司 | Method for acquiring vehicle speed from road monitoring video |
CN108091142A (en) * | 2017-12-12 | 2018-05-29 | 公安部交通管理科学研究所 | For vehicle illegal activities Tracking Recognition under highway large scene and the method captured automatically |
CN110033479A (en) * | 2019-04-15 | 2019-07-19 | 四川九洲视讯科技有限责任公司 | Traffic flow parameter real-time detection method based on Traffic Surveillance Video |
CN110490156A (en) * | 2019-08-23 | 2019-11-22 | 哈尔滨理工大学 | A kind of fast vehicle detection method based on convolutional neural networks |
CN110738690A (en) * | 2019-09-16 | 2020-01-31 | 南京理工大学 | unmanned aerial vehicle video middle vehicle speed correction method based on multi-target tracking framework |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112491999A (en) * | 2020-11-18 | 2021-03-12 | 成都佳华物链云科技有限公司 | Data reporting method and device |
CN112487908A (en) * | 2020-11-23 | 2021-03-12 | 东南大学 | Front vehicle line pressing behavior detection and dynamic tracking method based on vehicle-mounted video |
CN112466121A (en) * | 2020-12-12 | 2021-03-09 | 江西洪都航空工业集团有限责任公司 | Speed measuring method based on video |
CN112634344A (en) * | 2020-12-15 | 2021-04-09 | 西安理工大学 | Method for detecting center position of cold-rolled strip coil shaft hole based on machine vision |
CN112634344B (en) * | 2020-12-15 | 2022-08-30 | 西安理工大学 | Method for detecting center position of cold-rolled strip coil shaft hole based on machine vision |
CN112785855A (en) * | 2021-01-26 | 2021-05-11 | 张俊峰 | Method for acquiring vehicle speed from road monitoring video |
CN112990128A (en) * | 2021-04-27 | 2021-06-18 | 电子科技大学 | Multi-vehicle speed measuring method based on video tracking |
CN113506449A (en) * | 2021-05-21 | 2021-10-15 | 郑州大学 | High-speed highway vehicle speed measuring method based on video compression domain |
CN113506449B (en) * | 2021-05-21 | 2022-06-21 | 郑州大学 | High-speed highway vehicle speed measuring method based on video compression domain |
CN114758511A (en) * | 2022-06-14 | 2022-07-15 | 深圳市城市交通规划设计研究中心股份有限公司 | Sports car overspeed detection system, method, electronic equipment and storage medium |
CN114758511B (en) * | 2022-06-14 | 2022-11-25 | 深圳市城市交通规划设计研究中心股份有限公司 | Sports car overspeed detection system, method, electronic equipment and storage medium |
JP7411771B1 (en) | 2022-12-01 | 2024-01-11 | セイコーソリューションズ株式会社 | Vehicle speed detection device, vehicle speed detection method and program |
Also Published As
Publication number | Publication date |
---|---|
CN111753797B (en) | 2022-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111753797B (en) | Vehicle speed measuring method based on video analysis | |
Dhiman et al. | Pothole detection using computer vision and learning | |
CN112700470B (en) | Target detection and track extraction method based on traffic video stream | |
CN111429484B (en) | Multi-target vehicle track real-time construction method based on traffic monitoring video | |
CN110619279B (en) | Road traffic sign instance segmentation method based on tracking | |
CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
US20130100286A1 (en) | System and method for predicting vehicle location | |
CN104378582A (en) | Intelligent video analysis system and method based on PTZ video camera cruising | |
KR20200064873A (en) | Method for detecting a speed employing difference of distance between an object and a monitoring camera | |
CN112329747B (en) | Vehicle parameter detection method based on video identification and deep learning and related device | |
CN110348332B (en) | Method for extracting multi-target real-time trajectories of non-human machines in traffic video scene | |
Ji et al. | RGB-D SLAM using vanishing point and door plate information in corridor environment | |
KR20150049529A (en) | Apparatus and method for estimating the location of the vehicle | |
Liu et al. | Vehicle detection and ranging using two different focal length cameras | |
Quach et al. | Real-time lane marker detection using template matching with RGB-D camera | |
CN111160132B (en) | Method and device for determining lane where obstacle is located, electronic equipment and storage medium | |
Diego et al. | Vision-based road detection via on-line video registration | |
Vuong et al. | Toward Planet-Wide Traffic Camera Calibration | |
CN110555423A (en) | Multi-dimensional motion camera-based traffic parameter extraction method for aerial video | |
CN115629385A (en) | Vehicle queuing length real-time detection method based on correlation of millimeter wave radar and camera | |
CN113409588B (en) | Multi-vehicle speed measurement method based on video compression domain | |
Chandorkar et al. | Vehicle detection and speed tracking | |
Khosravi et al. | Vehicle speed and dimensions estimation using on-road cameras by identifying popular vehicles | |
Yuan et al. | Real-time long-range road estimation in unknown environments | |
Sun et al. | Embedded vehicle lane-marking tracking system |
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 |