Convolutional neural networks (CNNs) have been employed in visual tracking due to their rich levels of feature representation. While the learning capability of a CNN increases with its depth, unfortunately spatial information is diluted in deeper layers which hinders its important ability to localise targets. To successfully manage this trade-off, we propose a novel residual network based gating CNN architecture for object tracking. Our deep model connects the front and bottom convolutional features with a gate layer. This new network learns discriminative features while reducing the spatial information lost. This architecture is pre-trained to learn generic tracking characteristics. In online tracking, an efficient domain adaptation mechanism is used to accurately learn the target appearance with limited samples. Extensive evaluation performed on a publicly available benchmark dataset demonstrates our proposed tracker outperforms state-of-the-art approaches.
Please cite the above publication if you use the code or compare with the GNet tracker in your work. Bibtex entry:
@INPROCEEDINGS{8296753,
author={T. {Kokul} and C. {Fookes} and S. {Sridharan} and A. {Ramanan} and U. A. J. {Pinidiyaarachchi}},
booktitle={2017 IEEE International Conference on Image Processing (ICIP)},
title={Gate connected convolutional neural network for object tracking},
year={2017},
volume={},
number={},
pages={2602-2606},
keywords={feature extraction;image classification;learning (artificial intelligence);neural nets;object detection;object tracking;convolutional neural network;object tracking;visual tracking;feature representation;CNN architecture;convolutional features;discriminative features;generic tracking characteristics;online tracking;spatial information;residual network;CNN learning capability;Target tracking;Visualization;Logic gates;Adaptation models;Machine learning;Object tracking;Network architecture;object tracking;CNN;domain adaptation},
doi={10.1109/ICIP.2017.8296753},
ISSN={},
month={Sep.},}
If you have any other question, you can contact me by email: kokul1984@gmail.com, kokul@vau.jfn.ac.lk