Generalized Pooling for Robust Object Tracking

doi:10.1109/TIP.2016.2588329

Return

Generalized Pooling for Robust Object Tracking

2016-01-01

马波 (Bo Ma)

胡宏伟 (Hongwei Hu)

沈

沈建冰 (Jianbing Shen) *

Yangbiao Liu

Ling Shao (Ling Shao)

DOI：10.1109/TIP.2016.2588329

Original

Save

View PDF

Abstract

En 中文

Feature pooling in a majority of sparse coding-based tracking algorithms computes final feature vectors only by low-order statistics or extreme responses of sparse codes. The high-order statistics and the correlations between responses to different dictionary items are neglected. We present a more generalized feature pooling method for visual tracking by utilizing the probabilistic function to model the statistical distribution of sparse codes. Since immediate matching between two distributions usually requires high computational costs, we introduce the Fisher vector to derive a more compact and discriminative representation for sparse codes of the visual target. We encode target patches by local coordinate coding, utilize Gaussian mixture model to compute Fisher vectors, and finally train semi-supervised linear kernel classifiers for visual tracking. In order to handle the drifting problem during the tracking process, these classifiers are updated online with current tracking results. The experimental results on two challenging tracking benchmarks demonstrate that the proposed approach achieves a better performance than the state-of-the-art tracking algorithms.

Keywords:

Object tracking

feature pooling

Fisher kernel

local coordinate coding

sparse coding

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.