Occlusion‐robust object tracking based on the confidence of online selected hierarchical features

• DOI: 10.1049/iet-ipr.2018.5454
• Publication Date: 2018-07-18T14:09:52Z
• Authors: Mingjie Liu; Cheng‐Bin Jin; Bin Yang; Xuenan Cui; Hakil Kim
• Keywords: Tracking (education)

In recent years, convolutional neural networks (CNNs) have been widely used for visual object tracking, especially in combination with correlation filters (CFs). However, the increasing complex CNN models introduce more useless information, which may decrease tracking performance. This study proposes an online feature map selection method to remove noisy and irrelevant maps from different layers of CNN, can reduce computation redundancy improve accuracy. Furthermore, a novel appearance model update strategy, exploits feedback peak value response maps, is developed avoid corruption. Finally, extensive evaluation proposed was conducted over OTB‐2013 OTB‐2015 datasets, compared kinds trackers, including deep learning‐based trackers CF‐based trackers. The results demonstrate that achieves highly satisfactory