SiamRPN Target Tracking Based on Kalman Filter and Template Updating

被引：0

作者：

Gong, Chang ^{[2
]}

Shan, Yugang ^{[2
]}

Yuan, Jie ^{[1
]}

机构：

[1] School of Electrical Engineering, Xinjiang University, Urumqi

[2] School of Education, Hubei University of Arts and Science, Hubei, Xiangyang

来源：

Computer Engineering and Applications | 2023年 / 59卷 / 08期

关键词：

Kalman filter; siamese network; target tracking; template update;

D O I：

10.3778/j.issn.1002-8331.2202-0038

中图分类号：

学科分类号：

摘要：

Aiming at the problem that SiamRPN tracking algorithm is easy to lose the tracking target when the target is moving fast and the tracking effect is affected when the template is not updated, a SiamRPN target tracking method is proposed in combination Kalman filtering and template updating. Firstly, the trained SiamRPN tracking algorithm is used to track the target, and the center point position and speed of last frame of the target object are input into Kalman filter. When the tracking frame response score obtained by the RPN network is low, the Kalman filter is used to predict the target position again, and the new tracking frame is searched. And according to the speed of the target in the last frame, the search area is adaptively expanded. Secondly, the template update network is redesigned and trained, and a channel attention mechanism is added to update the target template iteratively during tracking. Experimental results show that the success rate and accuracy rate of the proposed algorithm in OTB2015 datasets are 67.2% and 89.1% respectively, and the EAO of the proposed algorithm in VOT2016 is improved by 24.3%. Compared with other algorithms, the proposed algorithm has obvious advantages in solving target deformation and motion ambiguity problems. © 2023 Journal of Computer Engineering and Applications Beijing Co., Ltd.; Science Press. All rights reserved.

引用

页码：200 / 207

页数：7

共 17 条

[1]

SHAN Y G, HU W G., Review of visual object tracking algorithms of adaptive direction and scale[J], Computer Engineering and Applications, 56, 9, pp. 13-23, (2020)

[2]

BERTINETTO L, VALMADRE J, HENRIQUES J F, Et al., Fully-convolutional siamese networks for object tracking[C], European Conference on Computer Vision, pp. 850-865, (2016)

[3]

LI B, YAN J, WU W, Et al., High performance visual tracking with siamese region proposal network[C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8971-8980, (2018)

[4]

LI B, WU W, WANG Q, Et al., Evolution of siamese visual tracking with very deep networks[C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16-20, (2019)

[5]

GUO D, WANG J, Et al., SiamCAR：siamese fully convolutional classification and regression for visual tracking[C], Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6269-6277, (2020)

[6]

CHEN X, YAN B, Et al., Transformer tracking[C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2021)

[7]

ZHANG Z L, WANG Y X., SiamRPN target tracking method based on Kalman filter[J], Intelligent Computers and Applications, 10, 3, pp. 44-50, (2020)

[8]

YANG T, CHAN A B., Learning dynamic memory networks for object tracking[C], Proceedings of the European Conference on Computer Vision（ECCV）, pp. 152-167, (2018)

[9]

LI P, CHEN B, Et al., Gradnet：gradient-guided network for visual object tracking[C], Proceedings of the International Conference on Computer Vision（ICCV）, pp. 6162-6171, (2019)

[10]

ZHU Z, WANG Q, LI B, Et al., Distractoraware siamese networks for visual object tracking[C], The 15th European Conference on Computer Vision, (2018)

← 1 2 →