Skip to Main content Skip to Navigation

Représenter pour suivre : exploitation de représentations parcimonieuses pour le suivi multi-objets

Loïc Pierre Fagot-Bouquet 1
1 LAAS-RAP - Équipe Robotique, Action et Perception
LAAS - Laboratoire d'analyse et d'architecture des systèmes
Abstract : Despite recent advances in object detection, multi-object tracking still raises some specific issues and therefore remains a challenging problem. In this thesis, we propose to investigate the use of sparse representations within multi-object tracking approaches in order to gain in performances. The first contribution of this thesis consists in designing an online tracking approach that takes advantage of collaborative sparse representations to better distinguish between the targets. Then, structured sparse representations are considered in order to be more suited to traking approaches based on a sliding window. In order to rely less on the object detector quality, we consider for the last contribution of this thesis to use dense dictionaries that are taking into account a large number of undetected locations inside each frame.
Document type :
Complete list of metadata

Cited literature [137 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Friday, May 4, 2018 - 4:09:06 PM
Last modification on : Thursday, June 10, 2021 - 3:04:23 AM
Long-term archiving on: : Tuesday, September 25, 2018 - 5:21:23 AM


Version validated by the jury (STAR)


  • HAL Id : tel-01516921, version 2


Loïc Pierre Fagot-Bouquet. Représenter pour suivre : exploitation de représentations parcimonieuses pour le suivi multi-objets. Automatique. Université Paul Sabatier - Toulouse III, 2017. Français. ⟨NNT : 2017TOU30030⟩. ⟨tel-01516921v2⟩



Record views


Files downloads