Open AccessAdaptive convolutional layer selection based on historical retrospect for visual tracking
Author(s) -
Tang Fuhui,
Lu Xiankai,
Zhang Xiaoyu,
Luo Lingkun,
Hu Shiqiang,
Zhang Huanlong
Publication year - 2019
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2018.5194
Subject(s) - computer science , artificial intelligence , convolutional neural network , bittorrent tracker , correctness , pattern recognition (psychology) , eye tracking , layer (electronics) , representation (politics) , video tracking , computer vision , object detection , selection (genetic algorithm) , object (grammar) , algorithm , chemistry , organic chemistry , politics , political science , law
Visual tracking has recently gained a great advance with the use of the convolutional neural network (CNN). Usually, existing CNN‐based trackers exploit the features from a single layer or a certain combination of multiple layers. However, these features only characterise an object from an invariable aspect and cannot adapt to scene variation, which limits the performance of such trackers. To overcome this limitation, the authors study the problem from a new perspective and propose a novel convolutional layer selection method. To obtain robust appearance representation, they investigate the advantages of features extracted from different convolutional layers. To determine the correctness of the tracking prediction and updated model, they design a verification mechanism based on historical retrospect, which can estimate the deviation for each layer by bidirectionally locating the target. Meanwhile, the deviation works as the layer‐wise selection criteria. Extensive evaluations on the OTB‐2013, visual object tracking (VOT)‐2016 and VOT‐2017 benchmarks demonstrate that the proposed tracker performs favourably against several state‐of‐the‐art trackers.