Journal
MULTIMEDIA TOOLS AND APPLICATIONS
Volume 77, Issue 17, Pages 22131-22143Publisher
SPRINGER
DOI: 10.1007/s11042-018-5664-7
Keywords
Visual tracking; Region-based; Fully convolutional; Siamese-network; Deep learning
Categories
Funding
- Natural Science Foundation of China [61231018]
- National Science and Technology Support Program [2015BAH31F01]
- Program of Introducing Talents of Discipline to University [B13043]
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available