Welcome to the InfoSci Platform
Video-Based Person Re-Identification With Unregulated Sequences

Video-Based Person Re-Identification With Unregulated Sequences

Wenjun Huang, Chao Liang, Chunxia Xiao, Zhen Han
Copyright: © 2020 |Volume: 12 |Issue: 2 |Pages: 18
ISSN: 1941-6210|EISSN: 1941-6229|EISBN13: 9781799805809|DOI: 10.4018/IJDCF.2020040104
Cite Article Cite Article

MLA

Huang, Wenjun, et al. "Video-Based Person Re-Identification With Unregulated Sequences." IJDCF vol.12, no.2 2020: pp.59-76. http://doi.org/10.4018/IJDCF.2020040104

APA

Huang, W., Liang, C., Xiao, C., & Han, Z. (2020). Video-Based Person Re-Identification With Unregulated Sequences. International Journal of Digital Crime and Forensics (IJDCF), 12(2), 59-76. http://doi.org/10.4018/IJDCF.2020040104

Chicago

Huang, Wenjun, et al. "Video-Based Person Re-Identification With Unregulated Sequences," International Journal of Digital Crime and Forensics (IJDCF) 12, no.2: 59-76. http://doi.org/10.4018/IJDCF.2020040104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Video-based person re-identification (re-id) has recently attracted widespread attentions because extra space-time information and more appearance cues in videos can be used to improve the performance of image-based person re-id. Most existing approaches equally treat person video images, ignoring their individual discrepancy. However, in real scenarios, captured images are usually contaminated by various noises, especially occlusions, resulting in a series of unregulated sequences. Through investigating the impact of unregulated sequences to feature representation of video-based person re-id, the authors find a remarkable promotion by eliminating noisy sub sequences. Based on this interesting finding, an adaptive unregulated sub sequence detection and refinement method is proposed to purify original video sequence and obtain a more effective and discriminative feature representation for video-based person re-id. Experimental results on two public datasets demonstrate that the proposed method outperforms the state-of-the-art work.