Generalized Pooling for Robust Object Tracking

Bo Ma, Hongwei Hu, Jianbing Shen, Yangbiao Liu, Ling Shao

Research output: Contribution to journalArticlepeer-review

48 Citations (Scopus)

Abstract

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.
Original languageEnglish
Pages (from-to)4199-4208
JournalIEEE Transactions on Image Processing
Volume25
Issue number9
DOIs
Publication statusPublished - 7 Jul 2016

Fingerprint

Dive into the research topics of 'Generalized Pooling for Robust Object Tracking'. Together they form a unique fingerprint.

Cite this