Person Re-identification Using Haar-based and DCD-based Signature

Abstract : In many surveillance systems there is a requirement to determine whether a given person of interest has already been observed over a network of cameras. This paper presents two approaches for this person re-identification problem. In general the human appearance obtained in one camera is usually different from the ones obtained in another camera. In order to re-identify people the human signature should handle difference in illumination, pose and camera parameters. Our appearance models are based on haar-like features and dominant color descriptors. The AdaBoost scheme is applied to both descriptors to achieve the most invariant and discriminative signature. The methods are evaluated using benchmark video sequences with different camera views where people are automatically detected using Histograms of Oriented Gradients (HOG). The reidentification performance is presented using the cumulative matching characteristic (CMC) curve.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/inria-00496051
Contributor : Slawomir Bak <>
Submitted on : Tuesday, June 29, 2010 - 3:31:16 PM
Last modification on : Tuesday, July 24, 2018 - 3:48:06 PM
Long-term archiving on : Monday, October 22, 2012 - 4:40:33 PM

File

avss2010_workshop_bak.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : inria-00496051, version 1

Collections

Citation

Slawomir Bak, Etienne Corvee, François Bremond, Monique Thonnat. Person Re-identification Using Haar-based and DCD-based Signature. 2nd Workshop on Activity Monitoring by Multi-Camera Surveillance Systems, AMMCSS 2010, in conjunction with 7th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS - 2010, Aug 2010, Boston, United States. ⟨inria-00496051⟩

Share

Metrics

Record views

384

Files downloads

1060