Online Appearance-Motion Coupling for Multi-Person Tracking in Videos

Bonan Cuan 1 Khalid Idrissi 1 Christophe Garcia 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Multi-person tracking in videos is a promising but challenging visual task. Recent progress in this field is introducing deep convolutional features as appearance models, which achieves robust tracking results when coupled with proper motion models. However, model failures that often cause severe tracking problems, have not been well discussed and addressed in previous work. In this paper, we propose a solution by online detecting such failures and accordingly adjusting the coupling between appearance and motion models. The strategy is letting the functional models take over when certain model faces data association ambiguity, and at the same time suppressing the influence of inappropriate observations during model update. Experimental results prove the benefit of our proposed improvement. Multiple object tracking; deep neural network; online learning; tracking-by-detection; multiple hypothesis tracking (key words)
Complete list of metadatas
Contributor : Bonan Cuan <>
Submitted on : Tuesday, January 22, 2019 - 11:17:27 AM
Last modification on : Tuesday, November 19, 2019 - 2:45:27 AM


  • HAL Id : hal-01989056, version 1


Bonan Cuan, Khalid Idrissi, Christophe Garcia. Online Appearance-Motion Coupling for Multi-Person Tracking in Videos. International Journal of Modeling and Optimization, IJMO, 2019. ⟨hal-01989056⟩



Record views