CN111126171A - Vehicle reverse running detection method and system - Google Patents
Vehicle reverse running detection method and system Download PDFInfo
- Publication number
- CN111126171A CN111126171A CN201911223911.XA CN201911223911A CN111126171A CN 111126171 A CN111126171 A CN 111126171A CN 201911223911 A CN201911223911 A CN 201911223911A CN 111126171 A CN111126171 A CN 111126171A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target
- module
- detection
- candidate
- 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
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
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
Abstract
A vehicle reverse running detection method comprises collecting video image information from front-end equipment, detecting position information of all vehicles in real time by deep learning technology, counting running track according to the position information of the vehicles, the driving direction of the vehicle is calculated through the driving track, and is finally compared with the preset retrograde direction to judge whether the vehicle is in retrograde motion or not, if the vehicle is found to be in retrograde motion, the voice alarm is carried out, so that the problem of autonomously setting the retrograde direction is effectively solved, meanwhile, the deep learning technology is utilized to carry out classification detection and multi-target tracking technology on the vehicle target so as to obtain the running track of the vehicle for real-time tracking, therefore, the real-time performance and the accuracy of detecting the vehicle reverse driving event are realized, the false detection rate of the reverse driving detection is effectively reduced, the illegal behaviors of the reverse driving vehicle driving person can be timely stopped within the first time of the occurrence of the event, and the occurrence of traffic accidents is prevented.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a vehicle retrograde motion detection method and system.
Background
With the development of the traffic field, the traffic safety facilities such as road traffic signs, marking lines and the like in China are improved day by day, and the consciousness that citizens obey the traffic laws and regulations is gradually strengthened. However, a few drivers of motor vehicles are biased to 'go against the way' and throw away traffic regulations. The vehicle retrograde motion is a relatively serious subjective illegal behavior in road traffic, and traffic jam is caused if the vehicle retrograde motion is slight, so that the road traffic capacity is reduced; the serious result is traffic accident and even the serious result of car damage and death. According to the statistical data analysis of the major traffic accidents which occur every year by the traffic police department in China, most of the data analysis is caused by the reverse driving of drivers.
In a traditional traffic video monitoring system, monitoring cameras are installed at important positions of main traffic roads, expressways, national roads and the like in cities, road conditions are monitored manually in real time, but under the situation of massive video big data, the defects of manual monitoring are gradually obvious, such as visual fatigue, insufficient real-time performance, large manpower consumption and the like. Therefore, intelligent traffic video monitoring technology is in force.
Along with the development of video-based intelligent analysis technology, an intelligent video monitoring system is more and more popular, can identify abnormal road conditions in real time, prevent or treat traffic accidents in time, and can reduce the labor cost of video monitoring. Therefore, application to video analysis techniques for vehicle reverse travel detection is indispensable.
Disclosure of Invention
The present invention provides a method and a system for detecting a vehicle driving in a reverse direction, so as to solve the above problems in the background art.
The technical problem solved by the invention is realized by adopting the following technical scheme:
a vehicle reverse running detection method comprises the following specific steps:
s0: acquiring a video image, decoding a video stream acquired at the front end by using a decoder, and acquiring a three-channel image in an rgb format;
s1: converting the three-channel image obtained in the step S0) through a color space to obtain a gray image of one channel;
GRAY=R×0.299+G×0.587+B×0.114 (1)
s2: setting an interested area in the monitoring camera, wherein the interested area needs to detect whether the vehicle drives in the wrong direction;
marking and dividing the one-way driving road needing to be monitored in the three-channel image obtained in the step S0) by using a left curve and a right curve in the three-channel image by adopting an artificial marking method, wherein the two dividing lines are respectively marked as Ln, left={(x1,y1),(x2,y2),......,(xn,yn)}、Ln, right={(x1,y1),(x2,y2),......,(xn,yn) And (x, y) represents the position information of the pixel, and the area between the two dividing lines is an area of interest for vehicle reverse driving detection, namely Ln, left、Ln, rightThe region in between is set as a region of interest;
s3: according to a pre-trained vehicle detection model and a multi-scale sliding window method, performing vehicle detection analysis on each region of the gray level image to obtain a vehicle target candidate set P;
collecting a large number of road vehicle sample images, cutting the road vehicle sample images to 256 multiplied by 256 sizes, marking vehicle target position information and size in the cut road vehicle sample images to obtain a vehicle sample set, and training the vehicle sample set by using a caffe tool and adopting a CNN-based deep learning technology to obtain a vehicle detection model;
when a vehicle target is detected, a multi-scale sliding window method in a CNN network is adopted to extract a candidate target region, meanwhile, a deep learning target detection technology based on CNN is adopted to classify and detect all candidate targets, all candidate targets without vehicle characteristics are removed according to classification, the vehicle target is reserved, vehicle position information at the current moment is recorded, and a vehicle candidate target set P { (x) is obtainedt,yt)}t∈{1,2,3.......∞}Wherein t represents the t-th frame image;
s4: in the step S3), vehicle targets outside the interest area in the step S1) are removed from the vehicle target candidate set P to obtain a vehicle final target candidate set Q;
judging whether the vehicle candidate target set P is located in (x)A,yA) Whether a certain vehicle is in the division curve Ln, left、Ln, rightFirst, the vehicle A is firstly connected with the vehicle Ln, leftThe curves are compared and x isAAnd Ln, leftSame position L on the curven, left(xOn the left side of the frame, the left side,yA) X of (A)Left side ofMaking a comparison while x is being comparedAAnd Ln, rightSame position L on the linen, right(xOn the right side of the frame, the left side of the frame,yA) X of (A)Right sideMaking a comparison if x is satisfiedLeft side of≤xA≤xRight sideIf the condition is met, judging that the vehicle A is in the region of interest of the segmentation curve, and reserving the candidate target, otherwise, rejecting the candidate target; all targets in the vehicle target candidate set P are judged, and finally the vehicle candidate target set Q { (x) is obtainedt,yt)}t∈{1,2,3.......∞};
S5: tracking the vehicle target according to the vehicle final target candidate set Q obtained in the step S4), and counting the position information of the target vehicle to obtain the vehicle motion track;
tracking the vehicle by adopting a particle filter algorithm, wherein each tracked target vehicle stores the position information of the previous m frames, and the track information is recorded as gammam={(x1,y1),(x2,y2),......,(xm,ym)};
S6: according to the trajectory information Γ in step S5)mAnalyzing the driving direction of the vehicle motion track, and judging whether the driving direction is consistent with the reverse driving direction according to the predefined reverse driving direction;
predefining a reverse driving direction, wherein the left upper corner of the obtained image is taken as the axis of the two-dimensional coordinate, the right side is taken as the x axis, and the downward side is taken as the y axis;
the criterion for judging the reverse running of the vehicle is that the tracked target vehicle is calculatedTrack information gammamIn { yi}i=1,2,......,mThe difference and the sum of the differences are recorded as diffsum=∑t=2,....,m(yt-yt-1) If diff issumIf the speed is more than 0, the vehicle is considered to be running in the reverse direction, otherwise, the vehicle is running normally.
Still provide a vehicle detection system that moves in reverse, this system includes video acquisition module, model training module, interesting region setting module, vehicle detection module, target tracking module, the module of judging and the audio alert module of moving in reverse, specifically as follows:
the video acquisition module comprises a monitoring camera, a switch and a service terminal, wherein the switch acquires a video stream from the network camera and then extracts a video image at the service terminal through a video decoding technology;
the monitoring camera is aligned to the tail of the vehicle running in the forward direction and the head of the vehicle running in the reverse direction during installation, and only one side of the one-way running road is monitored;
the model training module is used for training a vehicle detection model by adopting a deep learning technology after a vehicle sample set is obtained by using professional data set acquisition equipment to collect a vehicle sample;
the interesting region setting module is used for acquiring a frame of image from the monitoring camera and then setting an interesting region, namely a region needing to perform retrograde detection on vehicles on a monitored road;
the vehicle detection module extracts all vehicle targets from the region of interest of the monitoring image and stores position information and size information of the vehicle targets;
the target tracking module tracks according to the detected vehicle target position information, and counts a running path to obtain tracking track information;
the reverse driving judging module is used for judging whether the vehicle is in a reverse driving state or not, calculating the driving direction of the vehicle according to the vehicle track information, and then comparing the driving direction with the preset reverse driving direction to judge whether the vehicle is in the reverse driving state or not;
the voice alarm module is provided with a voice broadcast device or an alarm device and is used for sending out voice alarm when detecting that the vehicle runs in the wrong direction and timely reminding a driver.
Has the advantages that: the invention analyzes the actual position and direction of the vehicle running on the road monitored by the monitoring camera, effectively solves the problem of automatically setting the reverse running direction, and simultaneously utilizes the deep learning technology to carry out classification detection and multi-target tracking technology on the vehicle target so as to obtain the running track of the vehicle for real-time tracking, thereby realizing the real-time and accuracy of detecting the reverse running event of the vehicle, effectively reducing the false detection rate of the reverse running detection, and also being capable of timely stopping the violation of the vehicle driver in the first time of the occurrence of the event and preventing the occurrence of traffic accidents.
Drawings
FIG. 1 is a flow chart illustrating a preferred embodiment of the present invention.
Fig. 2 is a schematic diagram illustrating the reverse driving direction definition according to the preferred embodiment of the present invention.
FIG. 3 is a schematic diagram of the connection of the vehicle reverse driving detection system in the preferred embodiment of the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further explained below by combining the specific drawings.
Referring to fig. 1, the method for detecting the vehicle driving in the wrong direction includes the following steps:
s0: acquiring a video image, decoding a video stream acquired at the front end by using a decoder, and acquiring a three-channel image in an rgb format;
s1: converting the three-channel image obtained in the step S0) through a color space to obtain a gray image of one channel;
GRAY=R×0.299+G×0.587+B×0.114 (1)
s2: setting an interested area in the monitoring camera, wherein the interested area needs to detect whether the vehicle drives in the wrong direction;
marking and dividing the one-way driving road needing to be monitored in the three-channel image obtained in the step S0) by using a left curve and a right curve in the three-channel image by adopting an artificial marking method, wherein the two dividing lines are respectively marked as Ln, left={(x1,y1),(x2,y2),......,(xn,yn)}、Ln, right={(x1,y1),(x2,y2),......,(xn,yn) And (x, y) represents the position information of the pixel, and the area between the two dividing lines is an area of interest for vehicle reverse driving detection, namely Ln, left、Ln, rightThe region in between is set as a region of interest;
s3: according to a pre-trained vehicle detection model and a multi-scale sliding window method, performing vehicle detection analysis on each region of the gray level image to obtain a vehicle target candidate set P;
in the embodiment, firstly, a large amount of road vehicle sample images are acquired, the road vehicle sample images are cut to 256 multiplied by 256, then vehicle target position information and size are marked in the cut road vehicle sample images to obtain a vehicle sample set, and then a caffe tool is utilized to train the vehicle sample set by adopting a CNN-based deep learning technology to obtain a vehicle detection model;
when a vehicle target is detected, a multi-scale sliding window method in a CNN network is adopted to extract a candidate target region, meanwhile, a deep learning target detection technology based on CNN is adopted to classify and detect all candidate targets, all candidate targets without vehicle characteristics are removed according to classification, the vehicle target is reserved, vehicle position information at the current moment is recorded, and a vehicle candidate target set P { (x) is obtainedt,yt)}t∈{1,2,3.......∞}Wherein t represents the t-th frame image;
s4: in the step S3), vehicle targets outside the interest area in the step S1) are removed from the vehicle target candidate set P to obtain a vehicle final target candidate set Q;
judging whether the vehicle candidate target set P is located in (x)A,yA) Whether a certain vehicle is in the division curve Ln, left、Ln, rightFirst, the vehicle A is firstly connected with the vehicle Ln, leftThe curves are compared and x isAAnd Ln, leftSame position L on the curven, left(xOn the left side of the frame, the left side,yA) X of (A)Left side ofMaking a comparison while x is being comparedAAnd Ln, rightSame position L on the linen, right(xOn the right side of the frame, the left side of the frame,yA) X of (A)Right sideMaking a comparison if x is satisfiedLeft side of≤xA≤xRight sideAnd if the condition is satisfied, judging that the vehicle A is in the region of interest of the segmentation curve, reserving the candidate target, and otherwise, rejecting the candidate target. All the targets in the vehicle candidate target set P are judged, and finally the vehicle candidate target set Q { (x) is obtainedt,yt)}t∈{1,2,3.......∞};
S5: tracking the vehicle target according to the vehicle final target candidate set Q obtained in the step S4), and counting the position information of the target vehicle to obtain the vehicle motion track;
tracking the vehicle by adopting a particle filter algorithm, wherein each tracked target vehicle stores the position information of the previous m frames, and the track information is recorded as gammam={(x1,y1),(x2,y2),......,(xm,ym)};
S6: according to the trajectory information Γ in step S5)mAnalyzing the driving direction of the vehicle motion track, and judging whether the driving direction is consistent with the reverse driving direction according to the predefined reverse driving direction;
predefining a reverse driving direction, as shown in fig. 2, taking the upper left corner of the acquired image as the axis of the two-dimensional coordinate, the right side as the x axis, and the downward side as the y axis, wherein the vehicle in the image drives in reverse direction towards the front-end camera device, that is, the vehicle drives in the positive direction towards the-y axis, and the reverse direction is defined as the y axis;
the criterion for judging the vehicle is as follows: calculating tracked target vehicle track information gammamIn { yi}i=1,2,......,mThe difference and the sum of the differences are recorded as diffsum=∑t=2,....,m(yt-yt-1) If diff issumIf the speed is more than 0, the vehicle is considered to be running in the reverse direction, otherwise, the vehicle is running normally.
The embodiment provides a vehicle retrograde motion detection system, which comprises a video acquisition module, a model training module, an interested region setting module, a vehicle detection module, a target tracking module, a retrograde motion judgment module and a voice alarm module, and specifically comprises the following steps:
the video acquisition module comprises a monitoring camera, a switch and a service terminal, wherein the monitoring camera carries out network transmission on video information through the switch and then transmits video stream information to the server terminal, and the service terminal extracts video images through a video decoding technology;
the monitoring camera is arranged on a vertical rod of a road, is not too high or too low, aims at a monitoring probe at the tail of a vehicle running in the forward direction and the head of the vehicle running in the reverse direction when being arranged, and monitors only one-way running road on one side;
the model training module is used for training a vehicle detection model by adopting a deep learning technology after a large number of vehicle samples are collected by using professional data set collection equipment to obtain a vehicle sample set;
the interesting region setting module is used for acquiring a frame of image from the monitoring camera and then setting an interesting region, namely a region needing to perform retrograde detection on vehicles on a monitored road;
the vehicle detection module extracts all vehicle targets from the region of interest of the monitoring image and stores position information and size information of the vehicle targets;
the target tracking module tracks according to the detected vehicle target position information, and counts a running path to obtain tracking track information;
the reverse driving judging module is used for judging whether the vehicle is in a reverse driving state or not, calculating the driving direction of the vehicle according to the vehicle track information, and then comparing the driving direction with the preset reverse driving direction to judge whether the vehicle is in the reverse driving state or not;
and the voice alarm module is used for sending out a voice alarm when detecting that the vehicle runs in the wrong direction and timely reminding a driver.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. A vehicle reverse running detection method is characterized by comprising the following specific steps:
s0: acquiring a video image, decoding a video stream acquired at the front end by using a decoder, and acquiring a three-channel image in an rgb format;
s1: converting the three-channel image obtained in the step S0) through a color space to obtain a gray image of one channel;
s2: setting an interested area in the monitoring camera, wherein the interested area needs to detect whether the vehicle drives in the wrong direction;
marking and dividing the one-way driving road needing to be monitored in the three-channel image obtained in the step S0) by using a left curve and a right curve in the three-channel image by adopting an artificial marking method, wherein the two dividing lines are respectively marked as Ln, left={(x1,y1),(x2,y2),......,(xn,yn)}、Ln, right={(x1,y1),(x2,y2),......,(xn,yn) And (x, y) represents the position information of the pixel, and the area between the two dividing lines is an area of interest for vehicle reverse driving detection, namely Ln, left、Ln, rightThe region in between is set as a region of interest;
s3: according to a pre-trained vehicle detection model and a multi-scale sliding window method, performing vehicle detection analysis on each region of the gray level image to obtain a vehicle target candidate set P;
s4: in the step S3), vehicle targets outside the interest area in the step S1) are removed from the vehicle target candidate set P to obtain a vehicle final target candidate set Q;
s5: tracking the vehicle target according to the vehicle final target candidate set Q obtained in the step S4), and counting the position information of the target vehicle to obtain the vehicle motion track;
tracking the vehicle by adopting a particle filter algorithm, wherein each tracked target vehicle stores the position information of the previous m frames, and the track information is recorded as gammam={(x1,y1),(x2,y2),......,(xm,ym)};
S6: according to the trajectory information Γ in step S5)mAnd analyzing the driving direction of the vehicle motion track, and judging whether the driving direction of the vehicle has reverse driving according to the predefined reverse driving direction.
2. The vehicle reverse running detection method according to claim 1, wherein in step S1), the color space conversion formula: GRAY ═ R × 0.299+ G × 0.587+ B × 0.114.
3. The method according to claim 1, wherein in step S3), the process of obtaining the vehicle target candidate set P comprises:
firstly, collecting a large number of road vehicle sample images, cutting the road vehicle sample images to 256 multiplied by 256 sizes, then marking vehicle target position information and size in the cut road vehicle sample images to obtain a vehicle sample set, and then training the vehicle sample set by utilizing a caffe tool and adopting a CNN-based deep learning technology to obtain a vehicle detection model;
when a vehicle target is detected, a multi-scale sliding window method in a CNN network is adopted to extract a candidate target region, meanwhile, a deep learning target detection technology based on CNN is adopted to classify and detect all candidate targets, all candidate targets without vehicle characteristics are removed according to classification, the vehicle target is reserved, vehicle position information at the current moment is recorded, and a vehicle candidate target set P { (x) is obtainedt,yt)}t∈{1,2,3.......∞}Where t denotes the t-th frame image.
4. The method for detecting the reverse driving of the vehicle according to claim 1, wherein in the step S4), the procedure for obtaining the final target candidate set Q of the vehicle is as follows:
judging whether the vehicle candidate target set P is located in (x)A,yA) Whether a certain vehicle is in the division curve Ln, left、Ln, rightFirst, the vehicle A is firstly connected with the vehicle Ln, leftThe curves are compared and x isAAnd Ln, leftSame position L on the curven, left(xLeft side of,yA) X of (A)Left side ofMaking a comparison while x is being comparedAAnd Ln, rightSame position L on the linen, right(xRight side,yA) X of (A)Right sideMaking a comparison if x is satisfiedLeft side of≤xA≤xRight sideIf the condition is satisfied, judging that the vehicle A is in the region of interest of the segmentation curve, reserving the candidate target, otherwise, rejecting the candidate target; all targets in the vehicle candidate target set P are judged, and finally the vehicle candidate target set Q { (x) is obtainedt,yt)}t∈{1,2,3.......∞}。
5. The method for detecting the reverse running of the vehicle according to claim 1, wherein the step of determining that the vehicle has the reverse running process in step S6) comprises:
predefining a reverse driving direction, wherein the left upper corner of the obtained image is taken as the axis of the two-dimensional coordinate, the right side is taken as the x axis, and the downward side is taken as the y axis;
the criterion for judging the vehicle is as follows: calculating tracked target vehicle track information gammamIn { yi}i=1,2,......,mThe difference and the sum of the differences are recorded as diffsum=∑t=2,....,m(yt-yt-1),If it is diffsumIf the speed is more than 0, the vehicle is considered to be running in the reverse direction, otherwise, the vehicle is running normally.
6. The vehicle retrograde motion detection system is characterized by comprising a video acquisition module, a model training module, an interested region setting module, a vehicle detection module, a target tracking module and a retrograde motion judgment module, wherein the video acquisition module is connected with the model training module, the model training module and the interested region setting module are connected with the vehicle detection module, the vehicle detection module is connected with the target tracking module, and the target tracking module is connected with the retrograde motion judgment module.
7. The system of claim 6, further comprising a voice alarm module, wherein the voice alarm module is connected to the reverse driving determination module.
8. The system according to claim 7, wherein the voice alarm module is provided with a voice broadcaster.
9. The system of claim 7, wherein the voice alarm module is provided with an alarm.
10. The system of claim 6, wherein the video capture module comprises a monitoring camera, a switch and a service terminal, the monitoring camera for monitoring only one-way driving road is connected with the switch, and the switch is connected with the service terminal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911223911.XA CN111126171A (en) | 2019-12-04 | 2019-12-04 | Vehicle reverse running detection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911223911.XA CN111126171A (en) | 2019-12-04 | 2019-12-04 | Vehicle reverse running detection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111126171A true CN111126171A (en) | 2020-05-08 |
Family
ID=70497410
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911223911.XA Pending CN111126171A (en) | 2019-12-04 | 2019-12-04 | Vehicle reverse running detection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111126171A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111611901A (en) * | 2020-05-15 | 2020-09-01 | 北京百度网讯科技有限公司 | Vehicle reverse running detection method, device, equipment and storage medium |
CN112233442A (en) * | 2020-09-11 | 2021-01-15 | 浙江吉利控股集团有限公司 | Backward running early warning method and system applied to vehicle |
CN112364794A (en) * | 2020-11-18 | 2021-02-12 | 合肥湛达智能科技有限公司 | Deep learning retrograde detection method based on embedded terminal |
CN112804411A (en) * | 2020-10-29 | 2021-05-14 | 泰州程顺制冷设备有限公司 | Data compression platform using object detection |
CN113420748A (en) * | 2021-08-25 | 2021-09-21 | 深圳市城市交通规划设计研究中心股份有限公司 | Method and device for detecting illegal driving of vehicle, electronic equipment and storage medium |
CN113570877A (en) * | 2021-06-22 | 2021-10-29 | 淮阴工学院 | Non-motor vehicle retrograde detection device and detection method |
CN113706891A (en) * | 2020-05-20 | 2021-11-26 | 阿里巴巴集团控股有限公司 | Traffic data transmission method, traffic data transmission device, electronic equipment and storage medium |
CN114446062A (en) * | 2022-01-28 | 2022-05-06 | 刘银环 | Dynamic allocation system and method based on big data service |
CN114882393A (en) * | 2022-03-29 | 2022-08-09 | 华南理工大学 | Road reverse running and traffic accident event detection method based on target detection |
US20220297685A1 (en) * | 2021-03-18 | 2022-09-22 | Hyundai Mobis Co., Ltd. | Vehicle control system and method |
Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080100473A1 (en) * | 2006-10-25 | 2008-05-01 | Siemens Corporate Research, Inc. | Spatial-temporal Image Analysis in Vehicle Detection Systems |
CN101593422A (en) * | 2009-06-15 | 2009-12-02 | 无锡骏聿科技有限公司 | A kind of traffic violation detection method based on video frequency tracking and pattern-recognition |
CN102902955A (en) * | 2012-08-30 | 2013-01-30 | 中国科学技术大学 | Method and system for intelligently analyzing vehicle behaviour |
CN104200490A (en) * | 2014-08-14 | 2014-12-10 | 华南理工大学 | Rapid retrograde detecting and tracking monitoring method under complex environment |
CN106845424A (en) * | 2017-01-24 | 2017-06-13 | 南京大学 | Road surface remnant object detection method based on depth convolutional network |
CN106874863A (en) * | 2017-01-24 | 2017-06-20 | 南京大学 | Vehicle based on depth convolutional neural networks is disobeyed and stops detection method of driving in the wrong direction |
CN107886055A (en) * | 2017-10-27 | 2018-04-06 | 中国科学院声学研究所 | A kind of retrograde detection method judged for direction of vehicle movement |
CN108073690A (en) * | 2017-11-30 | 2018-05-25 | 江西洪都航空工业集团有限责任公司 | A kind of video object search method |
CN109074739A (en) * | 2016-03-01 | 2018-12-21 | 三菱电机株式会社 | It drives in the wrong direction and inhibits device, retrograde suppressing method and inverse row suppression system |
CN109326124A (en) * | 2018-10-17 | 2019-02-12 | 江西洪都航空工业集团有限责任公司 | A kind of urban environment based on machine vision parks cars Activity recognition system |
CN109661667A (en) * | 2016-10-14 | 2019-04-19 | 富士通株式会社 | The retrograde detection device of vehicle and method, electronic equipment |
CN109887281A (en) * | 2019-03-01 | 2019-06-14 | 北京云星宇交通科技股份有限公司 | A kind of method and system monitoring traffic events |
CN109948582A (en) * | 2019-03-28 | 2019-06-28 | 湖南大学 | A kind of retrograde intelligent detecting method of vehicle based on pursuit path analysis |
AU2019100914A4 (en) * | 2019-08-16 | 2019-09-26 | Weifang University | Method for identifying an intersection violation video based on camera cooperative relay |
CN110415272A (en) * | 2019-07-08 | 2019-11-05 | 东华大学 | A kind of battery truck drives in the wrong direction detection system and method |
-
2019
- 2019-12-04 CN CN201911223911.XA patent/CN111126171A/en active Pending
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080100473A1 (en) * | 2006-10-25 | 2008-05-01 | Siemens Corporate Research, Inc. | Spatial-temporal Image Analysis in Vehicle Detection Systems |
CN101593422A (en) * | 2009-06-15 | 2009-12-02 | 无锡骏聿科技有限公司 | A kind of traffic violation detection method based on video frequency tracking and pattern-recognition |
CN102902955A (en) * | 2012-08-30 | 2013-01-30 | 中国科学技术大学 | Method and system for intelligently analyzing vehicle behaviour |
CN104200490A (en) * | 2014-08-14 | 2014-12-10 | 华南理工大学 | Rapid retrograde detecting and tracking monitoring method under complex environment |
CN109074739A (en) * | 2016-03-01 | 2018-12-21 | 三菱电机株式会社 | It drives in the wrong direction and inhibits device, retrograde suppressing method and inverse row suppression system |
CN109661667A (en) * | 2016-10-14 | 2019-04-19 | 富士通株式会社 | The retrograde detection device of vehicle and method, electronic equipment |
CN106845424A (en) * | 2017-01-24 | 2017-06-13 | 南京大学 | Road surface remnant object detection method based on depth convolutional network |
CN106874863A (en) * | 2017-01-24 | 2017-06-20 | 南京大学 | Vehicle based on depth convolutional neural networks is disobeyed and stops detection method of driving in the wrong direction |
CN107886055A (en) * | 2017-10-27 | 2018-04-06 | 中国科学院声学研究所 | A kind of retrograde detection method judged for direction of vehicle movement |
CN108073690A (en) * | 2017-11-30 | 2018-05-25 | 江西洪都航空工业集团有限责任公司 | A kind of video object search method |
CN109326124A (en) * | 2018-10-17 | 2019-02-12 | 江西洪都航空工业集团有限责任公司 | A kind of urban environment based on machine vision parks cars Activity recognition system |
CN109887281A (en) * | 2019-03-01 | 2019-06-14 | 北京云星宇交通科技股份有限公司 | A kind of method and system monitoring traffic events |
CN109948582A (en) * | 2019-03-28 | 2019-06-28 | 湖南大学 | A kind of retrograde intelligent detecting method of vehicle based on pursuit path analysis |
CN110415272A (en) * | 2019-07-08 | 2019-11-05 | 东华大学 | A kind of battery truck drives in the wrong direction detection system and method |
AU2019100914A4 (en) * | 2019-08-16 | 2019-09-26 | Weifang University | Method for identifying an intersection violation video based on camera cooperative relay |
Non-Patent Citations (5)
Title |
---|
QING YE 等: "Vehicle Statistics and Retrograde Detection Based on Characteristic Analysis", 《APPLIED MECHANICS AND MATERIALS VOLS 556-562》 * |
YINGHONG LI 等: "Video-based Intelligent Multi-drive Vehicle Retrograde Detection", 《2010 3RD INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING (CISP2010)》 * |
王鹏 等: "基于视频的夜间高速公路车辆事件检测", 《中国图象图形学报》 * |
许宏科 等: "基于视频的单车道车辆逆行检测方法", 《交通信息与安全》 * |
郭锋: "基于目标跟踪的交通逆行事件检测算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111611901B (en) * | 2020-05-15 | 2023-10-03 | 北京百度网讯科技有限公司 | Vehicle reverse running detection method, device, equipment and storage medium |
CN111611901A (en) * | 2020-05-15 | 2020-09-01 | 北京百度网讯科技有限公司 | Vehicle reverse running detection method, device, equipment and storage medium |
CN113706891A (en) * | 2020-05-20 | 2021-11-26 | 阿里巴巴集团控股有限公司 | Traffic data transmission method, traffic data transmission device, electronic equipment and storage medium |
CN112233442A (en) * | 2020-09-11 | 2021-01-15 | 浙江吉利控股集团有限公司 | Backward running early warning method and system applied to vehicle |
CN112804411A (en) * | 2020-10-29 | 2021-05-14 | 泰州程顺制冷设备有限公司 | Data compression platform using object detection |
CN112364794A (en) * | 2020-11-18 | 2021-02-12 | 合肥湛达智能科技有限公司 | Deep learning retrograde detection method based on embedded terminal |
US20220297685A1 (en) * | 2021-03-18 | 2022-09-22 | Hyundai Mobis Co., Ltd. | Vehicle control system and method |
CN113570877A (en) * | 2021-06-22 | 2021-10-29 | 淮阴工学院 | Non-motor vehicle retrograde detection device and detection method |
CN113420748A (en) * | 2021-08-25 | 2021-09-21 | 深圳市城市交通规划设计研究中心股份有限公司 | Method and device for detecting illegal driving of vehicle, electronic equipment and storage medium |
CN113420748B (en) * | 2021-08-25 | 2022-02-01 | 深圳市城市交通规划设计研究中心股份有限公司 | Method and device for detecting illegal driving of vehicle, electronic equipment and storage medium |
CN114446062A (en) * | 2022-01-28 | 2022-05-06 | 刘银环 | Dynamic allocation system and method based on big data service |
CN114446062B (en) * | 2022-01-28 | 2022-09-27 | 深圳市八度云计算信息技术有限公司 | Dynamic allocation system and method based on big data service |
CN114882393A (en) * | 2022-03-29 | 2022-08-09 | 华南理工大学 | Road reverse running and traffic accident event detection method based on target detection |
CN114882393B (en) * | 2022-03-29 | 2023-04-07 | 华南理工大学 | Road reverse running and traffic accident event detection method based on target detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111126171A (en) | Vehicle reverse running detection method and system | |
CN109948582B (en) | Intelligent vehicle reverse running detection method based on tracking trajectory analysis | |
CN105744232B (en) | A kind of method of the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology | |
CN104751634B (en) | The integrated application method of freeway tunnel driving image acquisition information | |
CN108986472B (en) | Method and device for monitoring vehicle turning round | |
CN106530831A (en) | System and method for monitoring and early warning of high-threat vehicles | |
CN104809887B (en) | A kind of retrograde detection method of vehicle on expressway and autoalarm | |
CN103226891B (en) | Video-based vehicle collision accident detection method and system | |
CN110796862B (en) | Highway traffic condition detection system and method based on artificial intelligence | |
CN109448365A (en) | Across the scale space base land regions road traffic system integrated supervision method of one kind | |
CN110930723B (en) | Illegal parking detection implementation method | |
CN113676702B (en) | Video stream-based target tracking and monitoring method, system, device and storage medium | |
CN110738857A (en) | vehicle violation evidence obtaining method, device and equipment | |
KR20160141226A (en) | System for inspecting vehicle in violation by intervention and the method thereof | |
CN113033275B (en) | Vehicle lane-changing non-turn signal lamp analysis system based on deep learning | |
CN111754786A (en) | System for identifying traffic vehicle passing events on highway | |
CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
CN105574502A (en) | Automatic detection method for violation behaviors of self-service card sender | |
CN110070729A (en) | It is a kind of that vehicle detecting system and method are stopped based on the separated of mist calculating | |
CN102496275A (en) | Method for detecting overload of coach or not | |
WO2018209470A1 (en) | License plate identification method and system | |
CN112991769A (en) | Traffic volume investigation method and device based on video | |
CN116311166A (en) | Traffic obstacle recognition method and device and electronic equipment | |
CN107038870A (en) | A kind of vehicle peccancy detection method | |
CN114898309A (en) | City intelligent inspection vehicle system and inspection method based on visual AI technology |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |