Person re-identification by probabilistic relative distance comparison
Queen Mary University of London · Sun Yat-sen University
Abstract
Matching people across non-overlapping camera views, known as person re-identification, is challenging due to the lack of spatial and temporal constraints and large visual appearance changes caused by variations in view angle, lighting, background clutter and occlusion. To address these challenges, most previous approaches aim to extract visual features that are both distinctive and stable under appearance changes. However, most visual features and their combinations under realistic conditions are neither stable nor distinctive thus should not be used indiscriminately. In this paper, we propose to formulate person re-identification as a distance learning problem, which aims to learn the optimal distance that…
Citation impact
- FWCI
- 37.41
- Percentile
- 100%
- References
- 26
Authors
3Topics & keywords
- Artificial intelligence
- Computer science
- Matching (statistics)
- Boosting (machine learning)
- Probabilistic logic
- Clutter
- Identification (biology)
- Pattern recognition (psychology)
- Reduced inequalities