Long-term static object detection and tracking method with function of state marking

Abstract

The invention discloses a long-term static object detection and tracking method with a function of state marking, and the method comprises the steps: firstly constructing a long-short double-foreground model, and generating a foreground mask after fusion; secondly carrying out the classifying and marking of block masses based on the moving states of the block masses on the foreground mask, and obtaining long-term block masses; and finally updating the long-short double-foreground model of a corresponding region of the block masses in different states. The method obtains the foreground mask of an image through employing a long-short foreground detection method, carries out the classifying and marking of the block masses according to the durations of the block masses in the long-short foreground mask, the time difference of the durations of the block masses in the long-short foreground mask, the moving tracks of the block masses and the features of difference between the block masses and the surrounding pixels, obtains the probability value of the moving states of the block masses through employing a logic regression analysis method, and finally updates the long-short double-foreground model of the corresponding region of the block masses in different states, has the detection instantaneity, is better in video detection effect and robustness than other conventional methods for different scenes, and can meet the actual application demands.

Description

technical field [0001] The invention belongs to the field of computer vision object detection and tracking, and in particular relates to a long-term stationary object detection and tracking method with state marking. Background technique [0002] Object detection and tracking based on video has important applications in the fields of video processing, computer vision and pattern recognition. Illegal parking, a traffic law problem, has become increasingly prominent. Illegal parking has increased the incidence of traffic accidents and reduced traffic efficiency; burden and cannot guarantee the timeliness and objectivity of law enforcement. In contrast, if intelligent video monitoring and detection of long-term parked vehicles in traffic videos can be carried out, the purpose of illegal parking supervision can be achieved, which can not only reduce labor costs but also improve efficiency. Therefore, it is necessary to propose an accurate and fast long-term stationary object d...

AI Technical Summary

Problems solved by technology

[0021] In order to solve the problems existing in the actual application of existing long-term stationary object detection and tracking methods, the purpose of the present invention is to provide a long-term stationary object detection and tracking method with state annotation, which can quickly, accurately and robustly detect various Long-term Stationary Objects in Videos of Complex Scenes

Images