Learning Dynamic Siamese Network for Visual Object Tracking
Authors:
- Qing GuoQGQing Guo
- Wei FengWFWei Feng
- Ce ZhouCZCe Zhou
- Rui HuangRHRui Huang
- Liang WanLWLiang Wan
- Song WangSWSong Wang
Top Cited Papers
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1781-1789
Abstract
How to effectively learn temporal variation of target appearance, to exclude the interference of cluttered background, while maintaining real-time response, is an essential problem of visual object tracking. Recently, Siamese networks have shown great potentials of matching based trackers in achieving balanced accuracy and beyond realtime speed. However, they still have a big gap to classification & updating based trackers in tolerating the temporal changes of objects and imaging conditions. In this paper, we propose dynamic Siamese network, via a fast transformation learning model that enables effective online learning of target appearance variation and background suppression from previous frames. We then present elementwise multi-layer fusion to adaptively integrate the network outputs using multi-level deep features. Unlike state-of-theart trackers, our approach allows the usage of any feasible generally- or particularly-trained features, such as SiamFC and VGG. More importantly, the proposed dynamic Siamese network can be jointly trained as a whole directly on the labeled video sequences, thus can take full advantage of the rich spatial temporal information of moving objects. As a result, our approach achieves state-of-the-art performance on OTB-2013 and VOT-2015 benchmarks, while exhibits superiorly balanced accuracy and real-time response over state-of-the-art competitors.Keywords
This publication has 25 references indexed in Scilit:
- A Novel Performance Evaluation Methodology for Single-Target TrackersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- SPHORB: A Fast and Robust Binary Feature on the SphereInternational Journal of Computer Vision, 2014
- NestDE: generic parameters tuning for automatic story segmentationSoft Computing, 2014
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Bag of squares: A reliable model of measuring superpixel similarity2014
- Robust Visual Tracking Via Consistent Low-Rank Sparse LearningInternational Journal of Computer Vision, 2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Maximum Cohesive Grid of Superpixels for Fast Object Localization2013
- Toeplitz and Circulant Matrices: A ReviewFoundations and Trends® in Communications and Information Theory, 2006