Advances in object tracking algorithm based on siamese network

被引：0
作者：
Jin G. [1 ]
Xue Y. [1 ]
Tan L. [1 ]
Xu J. [1 ]
机构：
[1] School of Nuclear Engineering, Rocket Force University of Engineering, Xi'an
来源：
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2022年 / 44卷 / 06期
关键词：
Cross correlation; Deep learning; Object tracking; Region proposal network (RPN); Siamese neural network;
D O I：
10.12305/j.issn.1001-506X.2022.06.06
中图分类号：
学科分类号：
摘要：
Object tracking, as a key topic in the field of computer vision, is widely used in fields such as intelligent video surveillance. With the rapid development of deep learning, the siamese neural network-based tracking algorithm (referred to as siamese tracking algorithm) becomes the mainstream algorithm due to its balanced advantages of speed and accuracy. Despite a large number of studies, there is still a lack of systematic analysis of siamese tracking algorithms from the level of the tracking framework. In order to sort out the current research progress of siamese tracking algorithms, the common challenges, main components, tracking process, common datasets and evaluation indexes of siamese tracking algorithms are firstly introduced. Secondly, the algorithms are divided into algorithms for improving feature extraction, algorithms for optimizing similarity calculation, and algorithms for optimizing tracking results according to the improvement direction of the tracking framework, and they are introduced in detail respectively. Then 20 mainstream tracking algorithms are tested and analyzed. Finally, we summarize the problems of current siamese tracking algorithms and future research directions. © 2022, Editorial Office of Systems Engineering and Electronics. All right reserved.
引用
收藏
页码：1805 / 1822
页数：17
相关论文
共 132 条
[1]  
YANG H X, SHAO L, ZHENG F, Et al., Recent advances and trends in visual tracking: a review, Neurocomputing, 74, 18, pp. 3823-3831, (2011)
[2]  
PEI Q N., Moving objects detection and tracking techniques based optical flow, (2009)
[3]  
LI Y S., Ground target tracking with UAV based on Kalman filter, (2012)
[4]  
LI G B, WU H F., Weighted fragments-based meanshift tracking using color-texture histogram, Journal of Computer-Aided Design and Computer Graphics, 23, 12, pp. 2059-2066, (2011)
[5]  
DU K, JU Y F, JIN Y L, Et al., Object tracking based on improved MeanShift and SIFT, Proc.of the 2nd International Conference on Consumer Electronics, Communications and Networks, pp. 2716-2719, (2012)
[6]  
EXNER D, BRUNS E, KURZ D, Et al., Fast and robust CAMShift tracking, Proc.of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 9-16, (2010)
[7]  
MENG L, YANG X., A survey of object tracking algorithms, Acta Automatica Sinica, 45, 7, pp. 1244-1260, (2019)
[8]  
BOLME D S, BEVERIDGE J R, DRAPER B A, Et al., Visual object tracking using adaptive correlation filters, Proc.of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2544-2550, (2010)
[9]  
HENRIQUES J F, CASEIRO R, MARTINS P, Et al., High-speed tracking with kernelized correlation filters, IEEE Trans.on Pattern Analysis and Machine Intelligence, 37, 3, pp. 583-596, (2015)
[10]  
LI Y, ZHU J K., A scale adaptive kernel correlation filter tracker with feature integration, Proc.of the European Conference on Computer Vision, pp. 254-265, (2015)
12345678910