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.
|Title of host publication||2015 International Conference on Computer Vision, ICCV 2015|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||9|
|Publication status||Published - 2015 Feb 17|
|Event||15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile|
Duration: 2015 Dec 11 → 2015 Dec 18
|Name||Proceedings of the IEEE International Conference on Computer Vision|
|Volume||2015 International Conference on Computer Vision, ICCV 2015|
|Other||15th IEEE International Conference on Computer Vision, ICCV 2015|
|Period||15/12/11 → 15/12/18|
Bibliographical notePublisher Copyright:
© 2015 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition