Target tracking method based on sparse discriminant learning

Abstract

The invention discloses a target tracking method based on sparse discrimination learning. The method comprises the steps that a target appearance model is constructed for a first frame sampling target and the surrounding background; the two-dimensional image features of the target appearance model are extracted and are normalized to acquire an initial dictionary; a supervised discriminant dictionary learning method is introduced; a classification error term is added on the basis of a reconstruction error term to train a judgment dictionary; the minimum reconstruction error term is solved under sparsity constraint; an iteration switching optimization policy is used to update dictionary and sparse coding; Euclidean distance is used to measure the similarity between samples; and the most similar samples are used as a tracking target. According to the invention, when the target appearance model is established, the surrounding background in spatial correlation with the target is added as a clue template, and the processing of the target attitude change is robust.

Description

technical field [0001] The present invention relates to the field of information technology, in particular to a target tracking method based on sparse discriminant learning Background technique [0002] Object tracking is one of the important basic problems in the field of computer vision research, and it has a very wide range of applications in monitoring, motion estimation, human-computer interaction, etc. Many tracking algorithms that have emerged in recent years can better track target objects in certain scenarios, such as particle filter, Boosting algorithm, L 1 tracking algorithm, etc. However, since the video is a sequence of sequential images in a complex scene, which includes illumination changes, occlusion, motion deformation, background clutter, target scale changes, etc., an adaptive target representation model is constructed to obtain robust tracking Algorithm is currently a research hotspot in the field of tracking, and it is also a difficult problem. [000...

AI Technical Summary

Problems solved by technology

Due to the introduction of noise templates, the algorithm is more accurate and robust when dealing with occlusions, but when the target is often deformed, the base vector of the template set cannot represent the deformed target

In addition, the template set is actually a dictionary without a learning process, so the sparse coding obtained cannot guarantee the maximum sparsity, and the sample with the smallest reconstruction error is not necessarily the best candidate, and it is easy to accumulate drift errors

Images