Interest points harvesting in video sequences for efficient person identification

Abstract : We propose and evaluate a new approach for identification of persons, based on harvesting of interest point descriptors in video sequences. By accumulating interest points on several sufficiently time-spaced images during person silhouette or face tracking within each camera, the collected interest points capture appearance variability. Our method can in particular be applied to global person re-identification in a network of cameras. We present a first experimental evaluation conducted on a publicly available set of videos in a commercial mall, with very promising inter-camera pedestrian reidentification performances (a precision of 82% for a recall of 78%). Our matching method is very fast: ~ 1/8s for re-identification of one target person among 10 previously seen persons, and a logarithmic dependence with the number of stored person models, making re-identification among hundreds of persons computationally feasible in less than ~ 1/5s second. Finally, we also present a first feasibility test for on-the-fly face recognition, with encouraging results.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/inria-00325767
Contributor : Peter Sturm <>
Submitted on : Tuesday, September 30, 2008 - 11:20:52 AM
Last modification on : Monday, November 12, 2018 - 10:58:00 AM
Document(s) archivé(s) le : Thursday, June 3, 2010 - 8:15:31 PM

File

VS2008-Poster-e.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00325767, version 1

Citation

Omar Hamdoun, Fabien Moutarde, Bogdan Stanciulescu, Bruno Steux. Interest points harvesting in video sequences for efficient person identification. The Eighth International Workshop on Visual Surveillance - VS2008, Graeme Jones and Tieniu Tan and Steve Maybank and Dimitrios Makris, Oct 2008, Marseille, France. ⟨inria-00325767⟩

Share

Metrics

Record views

343

Files downloads

332