Object tracking method based on Monte Carlo tree searching

Abstract

The invention provides an object tracking method based on Monte Carlo tree searching and belongs to the technical field of computer vision and figure images. The object tracking method comprises the steps of: firstly obtaining each image area of vehicle in a video monitoring range through a background modeling and foreground extracting method; initializing a Monte Carlo tree and an initial node of a predicted track, obtaining video images in a segment of time, then generating and evaluating the predicted track by means of a plurality of times of node selection, expansion and simulation and similarity calculation, and thereby updating tree node weights; and using the path having the largest node weight as a target track, completing vehicle positioning, and further realizing vehicle tracking. Finally, based on the tracking result of the vehicle target, the moving image distance of the vehicle target in the time period is calculated, the practical moving distance of the vehicle on a road is calculated according to the proportion relation between the image distance and the practical distance, the driving speed of the vehicle is further obtained, and the vehicle over-speed tracking detection is completed.

Description

Technical field: [0001] The invention belongs to the technical fields of computer vision and computer graphic images. Background technique: [0002] Visual object tracking is one of the most important components in computer vision applications, such as intelligent surveillance, human-computer interaction, automatic control systems, etc. The purpose of object tracking is to automatically determine its position and size in each subsequent frame given the position and size of the initial object. Although the research on object tracking has been carried out for decades, and a lot of important progress has been made in recent years, due to the complexity of the real world, such as background interference, appearance and illumination changes, low image quality, frame skipping, etc. Designing tracking methods that can achieve human-level performance is still very difficult. An ideal tracking method must consider the real-time performance, stability and persistence of tracking at ...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method of object tracking based on Monte Carlo tree search, which can effectively solve the problem of long-term real-time and stable target tracking, and can adapt to more complex tracking scenarios

Images