Visual tracking using Siamese convolutional neural network with region proposal and domain specific updating

This paper deals with the problem of arbitrary object tracking using Siamese convolutional neural network (CNN), which is trained to match the initial patch of the target in the first frame with candidates in a new frame. The network returns the most similar candidate with the smallest margin contrastive loss. For candidate proposals in each frame, a Siamese region proposal network is applied to identify potential targets from across the whole frame. It is also able to mine hard negative examples to make the network more discriminative for the specific sequence. The Siamese tracking network and the Siamese region proposal network share weights which are trained end-to-end. Taking advantage of the fast implementation of fully convolutional architecture, the Siamese region proposal network does not cost much spare time during online tracking. Although the network is trained to be a generic tracker that can be applied to any video sequence, we find that domain specific network updating with a short-and long-term strategy can significantly improve the tracking performance. After combining generic Siamese network training, Siamese region proposal, and domain specific updating, the proposed tracker obtains state-of-the-art tracking performance. (C) 2017 Elsevier B.V. All rights reserved.