基于Siamese网络的目标跟踪研究
Research on Object Tracking Based on Siamese Network
DOI: 10.12677/CSA.2021.115150, PDF,   
作者: 方长江, 林俊杰：中南民族大学电子信息工程学院，湖北 武汉
关键词: 视觉目标跟踪；深度学习；双胞胎网络；Visual Object Tracking； Deep Learning； Siamese Networks
摘要: 视觉目标跟踪是计算机视觉领域一个重要研究方向，在自动驾驶、视频监控、人机交互、医疗诊断等众多领域有着广泛的应用。随着深度学习的崛起，基于神经网络的视觉目标跟踪已成为主流研究方向，其中基于双胞胎(Siamese)网络模型的方法在目标跟踪领域表现出了优异的性能。本文将基于Siamese网络，探究不同干扰和网络结构对目标跟踪性能的影响。
Abstract: Visual object tracking is an important research in computer vision field, with a range of applications such as autonomous driving, video surveillance, human-computer interaction, medical diagnosis, etc. With the rise of deep learning, neural networks have been employed in the mainstream frameworks for visual object tracking. Among them, the methods built on architecture of Siamese networks have shown excellent tracking performance. In this paper, we will investigate the effects of different interference and network structures on target tracking performance based on Siamese networks.
文章引用：方长江, 林俊杰. 基于Siamese网络的目标跟踪研究[J]. 计算机科学与应用, 2021, 11(5): 1468-1473. https://doi.org/10.12677/CSA.2021.115150

参考文献

[1] Wu, Y., Lim, J. and Yang, M.H. (2013) Online Object Tracking: A Benchmark. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, OR, 23-28 June 2013, 2411-2418. [Google Scholar] [CrossRef] 
[2] 黄凯奇, 陈晓棠, 康运锋, 谭铁牛. 智能视频监控技术综述[J]. 计算机学报, 2015, 38(6): 1093-1118.
[3] 高文, 朱明, 贺柏根, 吴笑天. 目标跟踪技术综述[J]. 中国光学, 2014, 7(3): 365-375.
[4] 王鑫, 徐立中. 图像目标跟踪技术[M]. 北京: 人民邮电出版社, 2012.
[5] Bertinetto, L., Valmadre, J., Henriques, J.F., et al. (2016) Fully-Convolutional Siamese Networks for Object Tracking. European Con-ference on Computer Vision (ECCV), Springer, Cham, 850-865. [Google Scholar] [CrossRef] 
[6] Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) ImageNet Classification with Deep Convolutional Neural Networks. International Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, 3-6 December 2012, 1097-1105.
[7] Girshick, R., Donahue, J., Darrell, T., et al. (2016) Region-Based Convolutional Networks for Accurate Object Detection and Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 38, 142-158. [Google Scholar] [CrossRef] 
[8] Yi, W., Lim, J. and Yang, M.H. (2013) Online Object Track-ing: A Benchmark. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, 23-28 June 2013, 2411-2418.