Robust Visual Tracking with Hierarchical Deep Features Weighted Fusion  

作　　者：Dianwei Wang Chunxiang Xu Daxiang Li Ying Liu Zhijie Xu Jing Wang 

机构地区：[1]School of Telecommunication and Information Engineering,Xi'an University of Posts and Telecommunications,Xi'an 710121,China [2]Key Laboratory of Electronic Information Application Technology for Scene Investigation,Ministry of Public Security,People's Republic of China,Xi'an 710121,China [3]School of Computing and Engineering,University of Huddersfield,Huddersfield,HD13DH,UK

出　　处：《Journal of Beijing Institute of Technology》2019年第4期770-776,共7页北京理工大学学报（英文版）

摘　　要：To solve the problem of low robustness of trackers under significant appearance changes in complex background,a novel moving target tracking method based on hierarchical deep features weighted fusion and correlation filter is proposed.Firstly,multi-layer features are extracted by a deep model pre-trained on massive object recognition datasets.The linearly separable features of Relu3-1,Relu4-1 and Relu5-4 layers from VGG-Net-19 are especially suitable for target tracking.Then,correlation filters over hierarchical convolutional features are learned to generate their correlation response maps.Finally,a novel approach of weight adjustment is presented to fuse response maps.The maximum value of the final response map is just the location of the target.Extensive experiments on the object tracking benchmark datasets demonstrate the high robustness and recognition precision compared with several state-of-the-art trackers under the different conditions.

关 键 词：visual tracking convolution neural network correlation filter feature fusion 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]