Efficient Video Summarization Using Principal Person Appearance for Video-Based Person Re-Identification
| Autor: | Seongro Yoon, Furqan M. Khan, Francois Bremond |
|---|---|
| Přispěvatelé: | Spatio-Temporal Activity Recognition Systems (STARS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), YOON, SEONGRO |
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Matching (statistics)
business.industry Principal (computer security) [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] 0102 computer and information sciences 02 engineering and technology Variance (accounting) 01 natural sciences Automatic summarization Constraint (information theory) [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] Discriminative model 010201 computation theory & mathematics Video tracking 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Representation (mathematics) Mathematics |
| Zdroj: | The British Machine Vision Conference (BMVC) The British Machine Vision Conference (BMVC), Sep 2017, London, United Kingdom BMVC |
| Popis: | International audience; 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. Experimental results show that our algorithm combined with conventional matching methods outper-forms state-of-the-arts on publicly available datasets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|