FUSION OF MOTION SEGMENTATION WITH ONLINE ADAPTIVE NEURAL CLASSIFIER FOR ROBUST TRACKING

Slawomir Bak 1 Sundaram Suresh 2 François Bremond 2 Monique Thonnat 2
1 ICS-UT-POZNAN - Institute of Computer Science
2 PULSAR - Perception Understanding Learning Systems for Activity Recognition
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : This paper presents a method to fuse the information from motion segmentation with online adaptive neural classifier for robust object tracking. The motion segmentation with object classification identify new objects present in the video sequence. This information is used to initialize the online adaptive neural classifier which is learned to differentiate the object from its local background. The neural classifier can adapt to illumination variations and changes in appearance. Initialized objects are tracked in following frames using the fusion of their neural classifiers with the feedback from the motion segmentation. Fusion is used to avoid drifting problems due to similar appearance in the local background region. We demonstrate the approach in several experiments using benchmark video sequences with different level of complexity.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download
https://hal.inria.fr/inria-00496120
Contributor : Slawomir Bak <>
Submitted on : Friday, July 16, 2010 - 12:13:10 PM
Last modification on : Tuesday, July 24, 2018 - 3:48:06 PM
Long-term archiving on : Thursday, December 1, 2016 - 4:39:38 PM

File

neuraltracking.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00496120, version 2

Collections

INRIA

Citation

Slawomir Bak, Sundaram Suresh, François Bremond, Monique Thonnat. FUSION OF MOTION SEGMENTATION WITH ONLINE ADAPTIVE NEURAL CLASSIFIER FOR ROBUST TRACKING. Int. Joint Conf. on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), Feb 2009, Lisbon, Portugal. ⟨inria-00496120v2⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

280

Files downloads

205

Contact


archive-ouverte@inria.fr