A Visual Object Tracking Algorithm Based on Features Extracted by Deep Residual Network

被引：0
作者：
Ma S.-G. [1 ,2 ]
Zhao X.-M. [1 ]
Hou Z.-Q. [2 ]
Wang Z.-M. [2 ,3 ]
Sun H.-L. [2 ]
机构：
[1] School of Information Engineering, Chang'an University, Xi'an
[2] School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an
[3] Shanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an University of Posts and Telecommunications, Xi'an
来源：
Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications | 2020年 / 43卷 / 02期
关键词：
Deep learning; Deep residual network; Kernelized correlation filter; Scale estimation; Visual object tracking;
D O I：
10.13190/j.jbupt.2019-071
中图分类号：
学科分类号：
摘要：
Because the objects are easy to be lost in complex scenes, a scale adaptive visual object tracking algorithm based on deep residual network (ResNet) features is proposed. Firstly, the ResNet is used to extract the multi-layer deep features of the image region of interest. Considering the restraining effect of rectified linear units (ReLU) activation function on target features, only the convolutional layers before ReLU function are selected. Secondly, the translation filters based on kernelized correlation filter are constructed in the extracted multi-layer features, and then the weighted fusion of the multiple response maps is carried out to obtain the target position with the largest response value. After the target location is determined, the target is sampled at multiple scales, and the felzenszwalb histogram of oriented gradients (fHOG) features of different scale images are extracted separately. On this basis, a scale correlation filter is constructed to estimate the target scale accurately. Comparing with six related algorithms in OTB100, an experiment is carried. It is shown that the proposed algorithm achieves high tracking success rate and accuracy, and can adapt to scale variation, background clutter and other complex scenes. © 2020, Editorial Department of Journal of Beijing University of Posts and Telecommunications. All right reserved.
引用
收藏
页码：129 / 134
页数：5
相关论文
共 9 条
[1]  
Lu Huchuan, Li Peixia, Wang Dong, Visual object tracking: a surey, Pattern Recognition and Artificial Intelligence, 31, 1, pp. 61-76, (2018)
[2]  
Henriques J F, Caseiro R, Martins P, Et al., High-speed tracking with kernelized correlation filters, IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 3, pp. 583-596, (2015)
[3]  
Ma C, Huang J B, Yang X K, Et al., Hierarchical convolutional features for visual tracking, ICCV 2015, pp. 3074-3082, (2015)
[4]  
Danelljan M, Hoger G, Khan F S, Et al., Accurate scale estimation for robust visual tracking, BMVC 2014, (2014)
[5]  
Li Y, Zhu J., A scale adaptive kernel correlation filter tracker with feature integration, ECCV 2014, pp. 254-265, (2014)
[6]  
Hong S, You T, Kwak S, Et al., Online tracking by learning discriminative saliency map with convolutional neural network, ICML 2015, pp. 597-606, (2015)
[7]  
Bertinetto L, Valmadre J, Henriques J F, Et al., Fully-convolutional siamese networks for object tracking, ECCV 2016, pp. 850-865, (2016)
[8]  
He K M, Zhang X Y, Ren S Q, Et al., Deep residual learning for image recognition, CVPR 2016, pp. 770-778, (2016)
[9]  
Tian Lang, Huang Pingmu, Lu Tiejun, SA-Siam++: the two-branch siamese network-based object tracking algorithm, Journal of Beijing University of Posts and Telecommunications, 42, 6, pp. 105-110, (2019)
1