A Compressive Tracking Method Combined with Local Structured Information

Abstract

The present invention proposes a compression tracking method combined with local structured information, adding information structured preprocessing steps in the compression tracking, and aggregating adjacent pixels with similar texture, color, brightness and other characteristics into a different visually significant Regular pixel blocks, extracting HSV color features on the basis of pixel blocks, constructing a color confidence map for rough estimation of the target position in the first stage, and then combining random projection of local structured information of pixel blocks and random projection at the pixel level to form a new measurement matrix, The measurement matrix is ​​used to reduce the dimensionality of the haar-like features, and the two-stage accurate position estimation of the target is completed according to the naive Bayesian classifier, so as to realize accurate tracking of the target. Compared with the existing tracking technology, the present invention combines the local structured information of the middle-level clues and the haar-like features of the low-level clues to characterize the appearance of the target, effectively improving the accuracy and robustness of target tracking, and ensuring Real-time performance of target tracking.

Description

technical field [0001] The invention relates to a compression tracking technology, in particular to a compression tracking method combined with local structured information, which belongs to the video analysis technology in the field of video data processing or generation, and belongs to the field of video analysis technology. Background technique [0002] With the application of video surveillance technology in the field of security more and more widely, target tracking plays an important role in computer vision systems, and has broad prospects in many fields such as intelligent transportation and security monitoring. In recent years, target tracking technology has also been a hot research topic for many scholars. However, due to the complexity of targets and backgrounds, such as illumination changes, target occlusion, background blur, etc., how to update the appearance model correctly and in real time, and estimate accurately and efficiently The location of the target is s...

AI Technical Summary

Problems solved by technology

This method applies multi-feature fusion to compressed tracking, which improves the accuracy of tracking, but the computational complexity it brings is more than doubled.

[0005] The above-mentioned methods have improved the accuracy of tracking, but still stay at the image pixel level for processing, lack of higher-level feature utilization, and the tracking efficiency is still not ideal. Yang introduced superpixels into tracking in 2014 and proposed Robust Superpixel Tracking algorithm (Robust Superpixel Tracking), which uses superpixels to maintain most of the boundaries of the target object in the image, and contains more local information than pixels, transforms the tracking problem into a computational goal- Background Confidence Map Problems for Accurate and Robust Tracking

However, the algorithm uses meanshift clustering, the entire frame structure is lengthy, and the tracking takes too long to meet the real-time requirements

Images