Abnormal road condition quick-finding method based on road monitoring videos
A technology for monitoring video and discovering methods, which is applied in the directions of instruments, calculations, and traffic flow detection. It can solve the problems of large amount of calculation, difficulty in achieving traffic management efficiency, a large amount of manpower, energy and labor intensity, and achieve the effect of small amount of calculation.
Active Publication Date: 2018-02-27
TRAFFIC MANAGEMENT RES INST OF THE MIN OF PUBLIC SECURITY
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The former can only extract ordinary road conditions, and still requires manual inspection by video patrol personnel, which requires a lot of manpower, energy and labor intensity, and it is difficult to achieve the goal of improving traffic management efficiency through technological informationization
[0005] The latter can more accurately identify abnormal road conditions through traffic parameter detection, and the amount of calculation required for rapid discovery is very large, which can only be achieved by deploying a large number of high-performance servers, and the cost is too high to be fully promoted
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042] The present invention will be further described below in conjunction with specific drawings and embodiments.
[0043] The present invention comprehensively applies image processing technologies such as image rasterization and image difference, and automatically extracts the image difference matrix for each road monitoring video, and obtains the normal road condition difference degree by analyzing a series of positive difference degree matrices obtained from the normal road condition video for many times. index. Compare the difference degree matrix of the actual road condition with the difference degree index of the normal road condition to evaluate whether the road condition is abnormal.
[0044] The difference degree of pictures is to use the principle of higher similarity and continuity of images in the same surveillance video in a similar time period, intercept two successive pictures at shorter intervals, calculate the difference degree of the two pictures, and obta...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides an abnormal road condition quick-finding method based on road monitoring videos. Aiming at the monitoring videos, the method comprises two indicators, namely a normal road condition difference range indicator and a normal road condition motion area difference frequency indicator. When a diversity matrix calculated according to monitored real-time road conditions is out of anormal road condition difference range, it is judged that the road conditions are abnormal; when a motion area difference frequency calculated according to monitored real-time road conditions is out of a normal road condition motion area difference frequency range, it is judged that the road conditions are abnormal. By means of the abnormal road condition quick-finding method based on the road monitoring videos, the abnormal road conditions can be quickly found in real time from the monitoring videos, the calculation amount is small, and the method is suitable for front-end embedding equipmentand large-scale parallel computing.
Description
technical field [0001] The invention relates to a method for quickly discovering abnormal road conditions, is aimed at road monitoring video, and belongs to the technical field of video monitoring. Background technique [0002] In recent years, local public security traffic control departments, transportation departments and other public departments have installed and deployed a large number of video surveillance equipment on expressways, national and provincial highways, urban roads, and rural roads as necessary facilities for road control and traffic management. One of the important applications is to determine road traffic conditions (referred to as road conditions) through video patrolling. Real-time road conditions, especially abnormal road conditions, are important reference information for scientifically organizing and directing traffic, and are also important information for guiding the traffic behavior of traffic participants. [0003] At present, the method for ex...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G08G1/04G06K9/00
CPCG08G1/04G06V20/42
Inventor 杨卓敏蔡岗张森李小武张慧辰尤东海
Owner TRAFFIC MANAGEMENT RES INST OF THE MIN OF PUBLIC SECURITY