Robust Real-Time Visual Object Tracking via Multi-Scale Fully Convolutional Siamese Networks
Authors:
- Longchao YangLYLongchao Yang
- Peilin JiangPJPeilin Jiang
- Fei WangFWFei Wang
- Xuan WangXWXuan Wang
- 1 November 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 25, 1-7
Abstract
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.Keywords
This publication has 18 references indexed in Scilit:
- Struck: Structured Output Tracking with KernelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Real-time part-based visual tracking via adaptive correlation filters2015
- Long-term correlation tracking2015
- Fully convolutional networks for semantic segmentation2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Object Tracking BenchmarkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Partial Occlusion Handling for Visual Tracking via Robust Part Matching2014
- Part-Based Tracking with Appearance Learning and Structural Constrains2014
- Incremental Learning for Robust Visual TrackingInternational Journal of Computer Vision, 2007