Robust visual target tracking method suitable for long-range tracking

Abstract

The invention discloses a robust visual target tracking method suitable for long-range tracking. The method includes: extracting positive and negative samples according to an initial frame image of avideo sequence and position information of a target in an initial frame, performing feature extraction on sample image blocks to obtain low-dimensional eigenvectors, using the linear support vector machine technique to initialize a target appearance model; performing logistic regression on the obtained support vector machine model, and estimating a target position for the target appearance model under a particle filtering framework; combining the median flow tracking algorithm and the current particle filtering algorithm to perform collaborative tracking, using the incremental reduction technique to update the appearance model online in the tracking process, and combining the original appearance model and new samples to update the appearance model online till the last frame is updated. Inthis way, the visual target tracking of the robust is achieved. The parallel complementation of the two-way tracking method with different mechanisms is achieved, and the problem of spatial redundancycaused by continuously generating new information in the tracking process can be solved.

Description

technical field [0001] The invention belongs to the technical field of optical signal processing and digital image processing, in particular to a robust visual target tracking method suitable for long-distance tracking. Background technique [0002] The research on robust target tracking algorithms in complex situations has long occupied a place in the field of optical signal processing applications (such as military target strikes, video surveillance and robot vision, etc.). Due to the hysteresis of target tracking, the information in the previous video sequence is often used to estimate the position of the target in the next frame, but in the actual scene, the appearance of the target in the two-dimensional image always changes with the interference factors. These interference factors may be from its own deformation, rotation, posture changes, etc., or from external light source disturbances, occlusions, etc. Therefore, traditional tracking methods such as optical flow tr...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a robust visual target tracking method suitable for long-distance tracking based on the collaborative operation of online target discriminative appearance model and median flow tracking, which solves the problem of robust visual target tracking in complex situations. track issue

Images