Fusing Crowd Density Maps and Visual Object Trackers for People Tracking in Crowd Scenes
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Title of host publication | 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 |
Subtitle of host publication | Proceedings |
Pages | 5353-5362 |
Publication status | Published - Jun 2018 |
Publication series
Name | |
---|---|
ISSN (Print) | 2575-7075 |
Conference
Title | 31st IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018) |
---|---|
Location | Calvin L. Rampton Salt Palace Convention Center |
Place | United States |
City | Salt Lake City |
Period | 18 - 22 June 2018 |
Link(s)
DOI | DOI |
---|---|
Document Link | |
Link to Scopus | https://www.scopus.com/record/display.uri?eid=2-s2.0-85062891034&origin=recordpage |
Permanent Link | https://scholars.cityu.edu.hk/en/publications/publication(83c45405-5232-42d0-a133-02383b7f97a7).html |
Abstract
While visual tracking has been greatly improved over the recent years, crowd scenes remain particularly challenging for people tracking due to heavy occlusions, high crowd density, and significant appearance variation. To address these challenges, we first design a Sparse Kernelized Correlation Filter (S-KCF) to suppress target response variations caused by occlusions and illumination changes, and spurious responses due to similar distractor objects. We then propose a people tracking framework that fuses the S-KCF response map with an estimated crowd density map using a convolutional neural network (CNN), yielding a refined response map. To train the fusion CNN, we propose a two-stage strategy to gradually optimize the parameters. The first stage is to train a preliminary model in batch mode with image patches selected around the targets, and the second stage is to fine-tune the preliminary model using the real frame-by-frame tracking process. Our density fusion framework can significantly improves people tracking in crowd scenes, and can also be combined with other trackers to improve the tracking performance. We validate our framework on two crowd video datasets.
Citation Format(s)
Fusing Crowd Density Maps and Visual Object Trackers for People Tracking in Crowd Scenes. / Ren, Weihong; Kang, Di; Tang, Yandong et al.
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018: Proceedings. 2018. p. 5353-5362 8578659.
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018: Proceedings. 2018. p. 5353-5362 8578659.
Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review