Online target tracking method based on increment bilateral two-dimensional principal component analysis (Bi-2DPCA) learning and sparse representation

Abstract

The invention relates to an online target tracking method based on increment bilateral two-dimensional principal component analysis (Bi-2DPCA) learning and sparse representation, and provides an increment Bi-2DPCA learning algorithm capable of rapidly and accurately updating a target sub-space model to reflect an appearance change of a target in a tracking process. Aiming at the problem that the target is frequently blocked and polluted by noise in the tracking process to cause that the tracking effect becomes worse, according to the method disclosed by the invention, a Bi-2DPCA-based sub-space model is embedded below a sparse representation frame, so that interferences to target positioning and target sub-space model updating caused by blocking and noise are furthest removed. Meanwhile, a novel method for calculating visual similarity is used. By adopting the method, energy distribution of Bi-2DPCA when an image is presented is considered, and is more accurate in comparison with a classical reconstruction error; tracking is achieved under a Bayesian inference framework; the target state is estimated by using a particle filtering algorithm.

Description

technical field [0001] The invention relates to an online target tracking method based on incremental Bi-2DPCA learning and sparse representation, which is a subspace representation model combined with Bilateral two-dimensional Principal Component Analysis (Bi-2DPCA) and sparse representations for online object tracking. Background technique [0002] Object tracking is a fundamental problem in the field of computer vision. It has a wide range of applications: including video surveillance, behavior analysis, motion event detection, and video retrieval. Although many scholars have made a lot of efforts in this field, visual tracking is still a challenging research field. Because the appearance of the target often faces changes caused by illumination changes, occlusion, deformation, complex moving background, etc. during the tracking process. Therefore, a good target appearance model will play a decisive role in the robustness of the tracking algorithm. [0003] As a classi...

AI Technical Summary

Problems solved by technology

This method can handle noise and occlusion problems well, but the real-time performance is not high, and this method directly uses the target template as the basis of the sparse dictionary, which cannot describe the structure and changes of the target feature space well.

Images