Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning
- 1 July 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1349-1358
- https://doi.org/10.1109/cvpr.2017.148
Abstract
This paper proposes a novel tracker which is controlled by sequentially pursuing actions learned by deep reinforcement learning. In contrast to the existing trackers using deep networks, the proposed tracker is designed to achieve a light computation as well as satisfactory tracking accuracy in both location and scale. The deep network to control actions is pre-trained using various training sequences and fine-tuned during tracking for online adaptation to target and background changes. The pre-training is done by utilizing deep reinforcement learning as well as supervised learning. The use of reinforcement learning enables even partially labeled data to be successfully utilized for semi-supervised learning. Through evaluation of the OTB dataset, the proposed tracker is validated to achieve a competitive performance that is three times faster than state-of-the-art, deep network-based trackers. The fast version of the proposed method, which operates in real-time on GPU, outperforms the state-of-the-art real-time trackers.Keywords
This publication has 23 references indexed in Scilit:
- Siamese Instance Search for TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Look-Ahead Before You Leap: End-to-End Active Recognition by Forecasting the Effect of MotionPublished by Springer Science and Business Media LLC ,2016
- Visual Tracking with Fully Convolutional NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- MatConvNetPublished by Association for Computing Machinery (ACM) ,2015
- MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,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
- Online Object Tracking: A BenchmarkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Tracking-Learning-DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992