Bayesian GOETHE Tracking

Abstract : Occlusions are serious challenges when tracking multiple targets. By greatly changing the measurement, they imply strong inter-target dependencies. Exact computation of these dependencies is not feasible. The approximations made by GOETHE preserve much of the information while staying computationally affordable.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01381502
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Friday, October 14, 2016 - 2:47:10 PM
Last modification on : Thursday, November 21, 2019 - 2:14:19 AM

Identifiers

Citation

Sebastian Wirkert, Emmanuel Dellandréa, Liming Chen. Bayesian GOETHE Tracking. International Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. pp.2077-2080, ⟨10.1109/ICPR.2010.511⟩. ⟨hal-01381502⟩

Share

Metrics

Record views

164