People re-identification and tracking from multiple cameras: A review
Authors:
- 1 September 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 1601-1604
Abstract
People tracking is a central and crucial point for the development of intelligent surveillance systems. When multiple cameras are used, the problem becomes more challenging as people re-identification is needed. Humans can greatly change their appearance according to posture, clothing and lighting conditions, thus defining features that describe people moving in large scenarios is a complex task. In this paper the problem of people re-identification and tracking is reviewed. The most used methodologies are discussed and insight into open problems and future research directions is provided.Keywords
This publication has 17 references indexed in Scilit:
- People re-identification across multiple non-overlapping cameras system by appearance classification and silhouette part segmentation2011
- Evaluation of local features for person re-identification in image sequences2011
- Spatial–temporal consistent labeling of tracked pedestrians across non-overlapping camera viewsPattern Recognition, 2011
- A Graph-Kernel Method for Re-identification2011
- Person Re-identification by Descriptive and Discriminative Classification2011
- Cascade of descriptors to detect and track objects across any network of camerasComputer Vision and Image Understanding, 2010
- Detection algorithm for color dynamic images by multiple surveillance cameras under low luminance conditions based on fuzzy corresponding mapApplied Soft Computing, 2008
- Modeling inter-camera space–time and appearance relationships for tracking across non-overlapping viewsComputer Vision and Image Understanding, 2008
- Person Reidentification Using Spatiotemporal Appearance2006
- Appearance Modeling for Tracking in Multiple Non-Overlapping Cameras2005