Object tracking using deep convolutional neural networks and visual appearance models

Abstract : In this paper we introduce a novel single object tracking method that extends the traditional GOTURN algorithm with a visual attention model. The proposed approach returns accurate object tracks and is able to handle sudden camera and background movement, long-term occlusions and multiple moving objects that can evolve simultaneously in a same neighborhood. The process of occlusion identification is performed using image quad-tree decomposition and patch matching, based on a convolution neural network trained offline. The object appearance model is adaptively modified in time based on both visual similarity constraints and trajectory verification tests. The experimental evaluation performed on the VOT 2016 dataset demonstrates the efficiency of our method that returns high accuracy scores regardless of the scene dynamics or object shape
Type de document :
Communication dans un congrès
ACIVS2017 : International Conference on Advanced Concepts for Intelligent Vision Systems , Sep 2017, Antwerp, Belgium. Springer, Proceedings ACIVS2017 : International Conference on Advanced Concepts for Intelligent Vision Systems pp.114 - 125, 2017, 〈10.1007/978-3-319-70353-4_10〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01691189
Contributeur : Médiathèque Télécom Sudparis & Institut Mines-Télécom Business School <>
Soumis le : mardi 23 janvier 2018 - 16:53:46
Dernière modification le : jeudi 31 mai 2018 - 09:12:02

Identifiants

Citation

Bogdan Mocanu, Ruxandra Tapu, Titus Zaharia. Object tracking using deep convolutional neural networks and visual appearance models. ACIVS2017 : International Conference on Advanced Concepts for Intelligent Vision Systems , Sep 2017, Antwerp, Belgium. Springer, Proceedings ACIVS2017 : International Conference on Advanced Concepts for Intelligent Vision Systems pp.114 - 125, 2017, 〈10.1007/978-3-319-70353-4_10〉. 〈hal-01691189〉

Partager

Métriques

Consultations de la notice

49