Long-term correlation tracking using multi-layer hybrid features in dense environments

BAISA, Nathanael L., BHOWMIK, Deepayan and WALLACE, Andrew (2018). Long-term correlation tracking using multi-layer hybrid features in dense environments. In: IMAI, Francisco, TREMEAU, Alain and BRAZ, Jose, (eds.) Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. Science and Technology Publications, Lda., 464-476.

Full text not available from this repository.

Abstract

Tracking a target of interest in crowded environments is a challenging problem, not yet successfully addressed in the literature. In this paper, we propose a new long-term algorithm, learning a discriminative correlation filter and using an online classifier, to track a target of interest in dense video sequences. First, we learn a translational correlation filter using a multi-layer hybrid of convolutional neural networks (CNN) and traditional hand-crafted features. We combine the advantages of both the lower convolutional layer which retains better spatial detail for precise localization, and the higher convolutional layer which encodes semantic information for handling appearance variations. This is integrated with traditional features formed from a histogram of oriented gradients (HOG) and color-naming. Second, we include a re-detection module for overcoming tracking failures due to long-term occlusions by training an incremental (online) SVM on the most confident frames using hand-engineered features. This re-detection module is activated only when the correlation response of the object is below some pre-defined threshold to generate high score detection proposals. Finally, we incorporate a Gaussian mixture probability hypothesis density (GM-PHD) filter to temporally filter high score detection proposals generated from the learned online SVM to find the detection proposal with the maximum weight as the target position estimate by removing the other detection proposals as clutter. Extensive experiments on dense data sets show that our method significantly outperforms state-of-the-art methods.

Item Type:	Book Section
Additional Information:	Paper presented at the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP) 2017, Porto, Portugal
Research Institute, Centre or Group - Does NOT include content added after October 2018:	Cultural Communication and Computing Research Institute > Communication and Computing Research Centre
Departments - Does NOT include content added after October 2018:	Faculty of Science, Technology and Arts > Department of Computing
Identification Number:	https://doi.org/10.1016/j.jvcir.2018.06.027
Page Range:	464-476
Depositing User:	Deepayan Bhowmik
Date Deposited:	20 Apr 2017 15:53
Last Modified:	18 Mar 2021 11:35
URI:	https://shura.shu.ac.uk/id/eprint/15423

Actions (login required)

View Item

Downloads

Publication Metrics