13 April 2018 Enhanced online convolutional neural networks for object tracking
Author Affiliations +
Proceedings Volume 10696, Tenth International Conference on Machine Vision (ICMV 2017); 106960A (2018) https://doi.org/10.1117/12.2310122
Event: Tenth International Conference on Machine Vision, 2017, Vienna, Austria
Abstract
In recent several years, object tracking based on convolution neural network has gained more and more attention. The initialization and update of convolution filters can directly affect the precision of object tracking effective. In this paper, a novel object tracking via an enhanced online convolution neural network without offline training is proposed, which initializes the convolution filters by a k-means++ algorithm and updates the filters by an error back-propagation. The comparative experiments of 7 trackers on 15 challenging sequences showed that our tracker can perform better than other trackers in terms of AUC and precision.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dengzhuo Zhang, Dengzhuo Zhang, Yun Gao, Yun Gao, Hao Zhou, Hao Zhou, Tianwen Li, Tianwen Li, } "Enhanced online convolutional neural networks for object tracking", Proc. SPIE 10696, Tenth International Conference on Machine Vision (ICMV 2017), 106960A (13 April 2018); doi: 10.1117/12.2310122; https://doi.org/10.1117/12.2310122
PROCEEDINGS
7 PAGES


SHARE
Back to Top