Robust visual tracking via part-based model

doi:10.1007/s00530-020-00668-3

Robust visual tracking via part-based model

2020-07-01

5

PRE

AI

DOI：10.1007/s00530-020-00668-3

Original

Original request for help

Save

Abstract

En 中文

In this paper, we propose a novel visual object tracking method using a part based appearance model. First, a local kernel feature is developed to encode edge information of patches. Next, bounding box of the target is divided into multiple parts. Then, each part uses correlation filter based tracking to predict position in the next frame. The matrix cosine similarity is utilized to measure reliabilities of the patches. Finally, optimal target location is predicted via maximizing the likelihood, which is obtained by adaptively fusing the reliable patches locations. Experimental results illustrate that our algorithm outperforms state-of-the-art tracking methods significantly in terms of accuracy and robustness.

Keywords:

Part based model

Correlation filter

Visual tracking

Local kernel feature

Matrix cosine similarity

Robust visual tracking via part-based model

Abstract

Journal

Organization