Hierarchical Convolutional Features for Visual Tracking
ICCV(2015)
摘要
Visual object tracking is challenging as target objects often undergo significant appearance changes caused by deformation, abrupt motion, background clutter and occlusion. In this paper, we exploit features extracted from deep convolutional neural networks trained on object recognition datasets to improve tracking accuracy and robustness. The outputs of the last convolutional layers encode the semantic information of targets and such representations are robust to significant appearance variations. However, their spatial resolution is too coarse to precisely localize targets. In contrast, earlier convolutional layers provide more precise localization but are less invariant to appearance changes. We interpret the hierarchies of convolutional layers as a nonlinear counterpart of an image pyramid representation and exploit these multiple levels of abstraction for visual tracking. Specifically, we adaptively learn correlation filters on each convolutional layer to encode the target appearance. We hierarchically infer the maximum response of each layer to locate targets. Extensive experimental results on a largescale benchmark dataset show that the proposed algorithm performs favorably against state-of-the-art methods.
更多查看译文
关键词
convolutional layer,correlation filters,image pyramid representation,spatial resolution,semantic information encoding,object recognition datasets,deep convolutional neural networks,feature extraction,visual object tracking,hierarchical convolutional features
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络