Traffic jam event automatic detecting method based on videos

Abstract

The invention discloses a traffic jam event automatic detecting method based on videos. The method includes steps that (1) real-time traffic parameter information of monitoring points is obtained based on a video detecting device, the parameter information is transmitted to a background server to store in a real-time mode; (2) obliterated data are identified, abnormal data are filtered, and data normalization processing is implemented by using a z-score method; (3) historical data are extracted to conduct clustering analysis by using a automatic detecting processing device, road traffic state foundation clustering centers are generated by utilizing a clustering analysis method; (4) euclidean distances to each clustering center are calculated according to the real-time traffic information, a present traffic jam event is automatically judged, and processed data are released through a release terminal device; (5) the clustering centers of each traffic state are recalculated, iteration is repeated, and traffic jam event automatic detection is achieved. The traffic jam event automatic detecting method based on the videos is mainly used for collecting traffic information, reduces cost of traffic information collection and improves veracity and response speed of the traffic jam event automatic detecting.

Description

technical field [0001] The invention relates to the fields of traffic information collection and traffic state perception, which can reduce the labor cost of traffic information collection and improve the accuracy and response efficiency of automatic detection of traffic congestion events. Background technique [0002] The road traffic operation state can be described by different traffic parameters. The video detection device can use the detected image to compare the difference between the image background and the device to obtain the entry and departure information of the vehicle target, so as to obtain the vehicle passing, presence, and vehicle information. Various traffic parameters can be obtained in real time through periodic statistical protocol analysis, and various parameter information is transmitted back to the background server in real time through the network and stored. However, the use methods of video detection devices in existing traffic events are mostly bas...

AI Technical Summary

Problems solved by technology

[0002] The road traffic operation state can be described by different traffic parameters. The video detection device can use the detected image to compare the difference between the image background and the device to obtain the entry and departure information of the vehicle target, so as to obtain the vehicle passing, presence, and vehicle information. Various traffic parameters can be obtained in real time through periodic statistical protocol analysis, and various parameter information is transmitted back to the background server in real time through the network and stored. However, the use methods of video detection devices in existing traffic events are mostly based on a single Traffic parameters, such as traffic flow, speed, density, etc., have not comprehensively set and detected multiple parameters for comprehensive analysis and processing, but the dynamic changes of traffic phenomena are extremely complex, and it is difficult to use a single parameter to reflect its characteristics. Causes inaccuracy in discrimination, and at present, video monitoring is performed manually when using video detection devices, which wastes manpower and is inefficient

[0003] The accuracy of the traffic condition discrimination algorithm directly affects the traffic flow operation of the urban road network. Setting multiple traffic parameters directly on the currently used video detection device will cause the system to misjudge the state, and wrong judgment may lead to traffic load on the road section. , forming a stagnation. Commonly used state discrimination algorithms, such as California algorithm, exponential smoothing method, standard deviation method, etc., are too blunt to classify traffic states by setting thresholds based on changes in individual traffic parameters. Urban road traffic flow is extremely complex. Simply relying on a certain traffic parameter to describe it cannot obtain accurate state discrimination, which will easily affect the accuracy of traffic flow detection and affect the handling of emergency events, resulting in a waste of public management resources

Images