Model-free Tracking with Deep Appearance and Motion Features Integration
arXiv:1812.06418
Abstract
Being able to track an anonymous object, a model-free tracker is comprehensively applicable regardless of the target type. However, designing such a generalized framework is challenged by the lack of object-oriented prior information. As one solution, a real-time model-free object tracking approach is designed in this work relying on Convolutional Neural Networks (CNNs). To overcome the object-centric information scarcity, both appearance and motion features are deeply integrated by the proposed AMNet, which is an end-to-end offline trained two-stream network. Between the two parallel streams, the ANet investigates appearance features with a multi-scale Siamese atrous CNN, enabling the tracking-by-matching strategy. The MNet achieves deep motion detection to localize anonymous moving objects by processing generic motion features. The final tracking result at each frame is generated by fusing the output response maps from both sub-networks. The proposed AMNet reports leading performance on both OTB and VOT benchmark datasets with favorable real-time processing speed.
arXiv comment10 pages, 10 figures. Accepted in IEEE Winter Conference on Applications of Computer Vision (WACV), 2019
References in corpus (7)
- MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
- DCFNet: Discriminant Correlation Filters Network for Visual Tracking
- Good Features to Correlate for Visual Tracking
- Siamese Instance Search for Tracking
- A Twofold Siamese Network for Real-Time Object Tracking
- CREST: Convolutional Residual Learning for Visual Tracking
- Deep Tracking: Visual Tracking Using Deep Convolutional Networks