殷旺,,
刘力铭,
王耀南
1.湖南大学电气与信息工程学院 长沙 410082
2.机器人视觉感知与控制技术国家工程实验室 长沙 410082
详细信息
作者简介:谭建豪：男，1962年生，教授，硕士生导师，研究方向为计算机视觉、飞行机器人、模式识别
殷旺：男，1995年生，硕士生，研究方向为计算机视觉、目标跟踪
刘力铭：男，1996年生，硕士生，研究方向为计算机视觉、目标跟踪、图像分割
王耀南：男，1957年生，教授，博士生导师，研究方向为智能控制、模式识别技术等
通讯作者:殷旺 yinwang@hnu.edu.cn
中图分类号:TN911.73; TP391.41计量
文章访问数:783
HTML全文浏览量:272
PDF下载量:98
被引次数:0
出版历程
收稿日期:2019-10-16
修回日期:2020-11-13
网络出版日期:2020-11-19
刊出日期:2021-01-15
DenseNet-siamese Network with Global Context Feature Module for Object Tracking
Jianhao TAN,Wang YIN,,
Liming LIU,
Yaonan WANG
1. College of Electrical and Information Engineering, Hunan University, Changsha 410082, China
2. National Engineering Laboratory for Robot Visual Perception and Control Technology, Hunan University, Changsha 410082, China
摘要
摘要:近年来，采用孪生网络提取深度特征的方法由于其较好的跟踪精度和速度，成为目标跟踪领域的研究热点之一，但传统的孪生网络并未提取目标较深层特征来保持泛化性能，并且大多数孪生网络只提取局部领域特征，这使得模型对于外观变化是非鲁棒和局部的。针对此，该文提出一种引入全局上下文特征模块的DenseNet孪生网络目标跟踪算法。该文创新性地将DenseNet网络作为孪生网络骨干，采用一种新的密集型特征重用连接网络设计方案，在构建更深层网络的同时减少了层之间的参数量，提高了算法的性能，此外，为应对目标跟踪过程中的外观变化，该文将全局上下文特征模块(GC-Model)嵌入孪生网络分支，提升算法跟踪精度。在VOT2017和OTB50数据集上的实验结果表明，与当前较为主流的算法相比，该文算法在跟踪精度和鲁棒性上有明显优势，在尺度变化、低分辨率、遮挡等情况下具有良好的跟踪效果，且达到实时跟踪要求。
关键词:目标跟踪/
孪生网络/
全局上下文特征/
DenseNet网络
Abstract:In recent years, the method of extracting depth features from siamese networks has become one of the hotspots in visual tracking because of its balanced in accuracy and speed. However, the traditional siamese network does not extract the deeper features of the target to maintain generalization performance, and most siamese architecture networks usually process one local neighborhood at a time, which makes the appearance model local and non-robust to appearance changes. In view of this problem, a densenet-siamese network with global context feature module for object tracking algorithm is proposed. This paper innovatively takes densenet network as the backbone of siamese network, adopts a new design scheme of dense feature reuse connection network, which reduces the parameters between layers while constructing deeper network, and enhances the generalization performance of the algorithm. In addition, in order to cope with the appearance changes in the process of object tracking, the Global Context feature Module (GC-Model) is embedded in the siamese network branches to improve the tracking accuracy. The experimental results on the VOT2017 and OTB50 datasets show that comparing with the current mainstream tracking algorithms, the Tracker has obvious advantages in tracking accuracy and robustness, and has good tracking effect in scale change, low resolution, occlusion and so on.
Key words:Object tracking/
Siamese network/
Global context feature/
DenseNet network
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=a5e70289-7602-4a4c-9fbf-39f2d39a9845
