Efficient Video Summarization Using Principal Person Appearance for Video-Based Person Re-Identification

Seongro Yoon, Furqan Khan and Francois Bremond

Abstract

In video-based person re-identification, while most work has focused on problems of person signature representation and matching between different cameras, intra-sample variance is also a critical issue to be addressed. There are various factors that cause the intra-sample variance such as detection/tracking inconsistency, motion change and background. However, finding individual solutions for each factor is difficult and complicated. To deal with the problem collectively, we assume that it is more effective to represent a video with signatures based on a few of the most stable and representative features rather than extract from all video frames. In this work, we propose an efficient approach to summarize a video into a few of discriminative features given those challenges. Primarily, our algorithm learns principal person appearance over an entire video sequence, based on low-rank matrix recovery method. We design the optimizer considering temporal continuity of the person appearance as a constraint on the low-rank based manner. In addition, we introduce a simple but efficient method to represent a video as groups of similar frames using recovered principal appearance.

Session

Orals - Matching

Files

PDF iconPaper (PDF)
PDF iconSupplementary (PDF)

DOI

10.5244/C.31.187
https://dx.doi.org/10.5244/C.31.187

Citation

Seongro Yoon, Furqan Khan and Francois Bremond. Efficient Video Summarization Using Principal Person Appearance for Video-Based Person Re-Identification. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 187.1-187.13. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_187,
                title={Efficient Video Summarization Using Principal Person Appearance for Video-Based Person Re-Identification},
                author={Seongro Yoon, Furqan Khan and Francois Bremond},
                year={2017},
                month={September},
                pages={187.1-187.13},
                articleno={187},
                numpages={13},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.187},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.187}
            }