Towards Unsupervised Sudden Group Movement Discovery for Video Surveillance

Sofia Zaidenberg 1 Piotr Bilinski 1 Francois Bremond 1
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : This paper presents a novel and unsupervised approach for discovering "sudden" movements in video surveillance videos. The proposed approach automatically detects quick motions in a video, corresponding to any action. A set of possible actions is not required and the proposed method successfully detects potentially alarm-raising actions without training or camera calibration. Moreover, the system uses a group detection and event recognition framework to relate detected sudden movements and groups of people, and provide a semantical interpretation of the scene. We have tested our approach on a dataset of nearly 8 hours of videos recorded from two cameras in the Parisian subway for a European Project. For evaluation, we annotated 1 hour of sequences containing 50 sudden movements.
Keywords : Event detection Motion estimation Anomaly estimation Situation awareness Scene Understanding Group Activity Recognition Stream Selection
Document type :
Conference papers
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download
https://hal.inria.fr/hal-00878580
Contributor : Sofia Zaidenberg <>
Submitted on : Wednesday, October 30, 2013 - 12:23:28 PM
Last modification on : Tuesday, July 24, 2018 - 3:48:03 PM
Long-term archiving on : Friday, January 31, 2014 - 9:25:27 AM

File

ZaidenbergVISAPP2014.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00878580, version 1

Collections

INRIA | UNIV-COTEDAZUR

Citation

Sofia Zaidenberg, Piotr Bilinski, Francois Bremond. Towards Unsupervised Sudden Group Movement Discovery for Video Surveillance. VISAPP - 9th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - 2014, Jose Braz, Jan 2014, Lisbon, Portugal. ⟨hal-00878580⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

426

Files downloads

409

Contact


archive-ouverte@inria.fr