Single object tracking using offline trained deep regression networks

Abstract : In this paper we introduce a novel single object tracker based on two convolutional neural networks (CNNs) trained offline using data from large videos repositories. The key principle consists of alternating between tracking using motion information and adjusting the predicted location based on visual similarity. First, we construct a deep regression network architecture able to learn generic relations between the object appearance models and its associated motion patterns. Then, based on visual similarity constraints, the objects bounding box position, size and shape are continuously updated in order to maximize a patch similarity function designed using CNN. Finally, a multi-resolution fusion between the outputs of the two CNNs is performed for accurate object localization. The experimental evaluation performed on challenging datasets, proposed in the visual object tracking (VOT) international contest, validates the proposed method when compared with state-of-theart systems. In terms of computational speed our tracker runs at 20fps
Document type :
Conference papers
Complete list of metadatas
Contributor : Médiathèque Télécom Sudparis & Institut Mines-Télécom Business School <>
Submitted on : Wednesday, March 28, 2018 - 3:06:19 PM
Last modification on : Thursday, October 17, 2019 - 12:36:52 PM



Ruxandra Tapu, Bogdan Mocanu, Titus Zaharia. Single object tracking using offline trained deep regression networks. IPTA 2017 : 7th International Conference on Image Processing Theory, Tools and Applications , Nov 2017, Montreal, Canada. pp.1 - 6, ⟨10.1109/IPTA.2017.8310091⟩. ⟨hal-01745758⟩



Record views