KCF tracking target loss detection method and system based on foreground detection

Abstract

The embodiment of the invention relates to the technical field of visual target tracking, and discloses a KCF tracking target loss detection method and system based on foreground detection. The KCF tracking target loss detection method based on foreground detection comprises: extracting a foreground image by adopting a foreground detection algorithm; extracting a target detection frame by using aKCF tracking algorithm; obtaining a foreground region corresponding to the target detection frame, calculating the ratio of the target contour area in the foreground area to the total area of the foreground area; judging whether a KCF tracking target is lost or not by setting a ratio threshold. According to the KCF target tracking method and device, the problems that the KCF algorithm cannot be perceived after the target is lost and the KCF tracker takes the background information as the target to continue tracking are solved, and accurate judgment when the tracking target is shielded in a large area or leaves a lens is realized on the basis of not influencing the real-time performance of KCF target tracking.

Description

technical field [0001] The invention relates to the technical field of visual target tracking, in particular to a foreground detection-based KCF tracking target loss detection method and system. Background technique [0002] Visual object tracking is one of the most challenging topics in the field of computer vision, and it is widely used in video surveillance, human-computer interaction, smart cars, medical images and other fields. Currently the most used tracker based on the correlation filtering algorithm, the main characteristics of the correlation filtering method are low algorithm complexity, fast operation speed, and meet real-time requirements, mainly including KCF tracker and its variants. At present, the loss detection methods for KCF tracking targets mainly include the KCF target loss detection method based on outlier detection and the tracking target loss detection method based on perceptual hash algorithm. [0003] When the target is affected by factors such as...

AI Technical Summary

Problems solved by technology

[0003] When the target is affected by factors such as scale change, severe occlusion, similar target interference and out of view, the KCF algorithm will still lose the target

Once the target is lost, the tracker itself cannot detect it and does not have the ability to detect target loss, which is an inherent defect of the KCF tracking algorithm

During the trajectory tracking process, the loss of the tracking target will cause the trajectory to jump or shift

Images