Robust real-time visual object tracking via multi-scale fully convolutional Siamese networks

L Yang, P Jiang, F Wang… - … Conference on Digital …, 2017 - ieeexplore.ieee.org
L Yang, P Jiang, F Wang, X Wang
2017 International Conference on Digital Image Computing …, 2017ieeexplore.ieee.org
Robust visual object tracking against occlusions and deformations is still very challenging
task. To tackle these issues, existing Convolutional Neural Networks (CNNs) based trackers
either fail to handle them or can just run in low speed. In this paper, we present a realtime
tracker which is robust to occlusions and deformations based on a Region-based, Multi-
Scale Fully Convolutional Siamese Network (R-MSFCN). In the proposed R-MSFCN, the
information of regions is extracted separately by the proposition of position-sensitive score …
Robust visual object tracking against occlusions and deformations is still very challenging task. To tackle these issues, existing Convolutional Neural Networks (CNNs) based trackers either fail to handle them or can just run in low speed. In this paper, we present a realtime tracker which is robust to occlusions and deformations based on a Region-based, Multi-Scale Fully Convolutional Siamese Network (R- MSFCN). In the proposed R-MSFCN, the information of regions is extracted separately by the proposition of position-sensitive score maps on multiple convolutional layers. Combining these score maps via adaptive weights leads to accurate location of the target on a new frame. The experiments illustrate that our method outperforms state-of-the-art approaches, and can handle the cases of object deformation and occlusion at about 31 FPS.
ieeexplore.ieee.org
Showing the best result for this search. See all results