Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (3): 649-660.DOI: 10.3778/j.issn.1673-9418.2010029

• Graphics and Image • Previous Articles     Next Articles

Gradient-Guided Object Tracking Algorithm with Channel Selection

CHENG Shilong, XIE Linbo+(), PENG Li   

  1. Engineering Research Center of Internet of Things Technology Applications (School of Internet of Things Engineering, Jiangnan University), Ministry of Education, Wuxi, Jiangsu 214122, China
  • Received:2020-10-12 Revised:2020-11-30 Online:2022-03-01 Published:2020-12-08
  • About author:CHENG Shilong, born in 1995, M.S. candidate. His research interests include visual object track-ing and deep learning.
    XIE Linbo, born in 1973, Ph.D., professor, Ph.D. supervisor, member of CAA. His research interests include process modeling and control, intelligent detection and system safety.
    PENG Li, born in 1967, Ph.D., professor, Ph.D. supervisor, member of CAAI and CCF. His research interests include visual Internet of things and intelligent detection.
  • Supported by:
    National Natural Science Foundation of China(61873112)

梯度导向的通道选择目标跟踪算法

程世龙, 谢林柏+(), 彭力   

  1. 物联网技术应用教育部工程研究中心(江南大学 物联网工程学院),江苏 无锡 214122
  • 通讯作者: + E-mail: xie_linbo@jiangnan.edu.cn
  • 作者简介:程世龙(1995—),男,安徽宿州人,硕士研究生,主要研究方向为目标跟踪、深度学习。
    谢林柏(1973—),男,湖南永州人,博士,教授,博士生导师,CAA会员,主要研究方向为过程建模与控制、智能检测与系统安全性。
    彭力(1967—),男,河北唐山人,博士,教授,博士生导师,CAAI会员,CCF会员,主要研究方向为视觉物联网、智能检测。
  • 基金资助:
    国家自然科学基金(61873112)

Abstract:

In object tracking task, the target object to be tracked is arbitrary, and there may be similar distractor around the target, which often leads to the target features extracted by the pre-trained network not fully applicable to the tracked target. To solve the above-mentioned issues, the gradient-guided object tracking algorithm is proposed in the Siamese tracking framework. Firstly, the pre-trained network is used to extract the features of object. To eliminate the interference of similar objects, the switch-penalty loss function is used to impose penalty operation on similar objects in the background. Secondly, in the feature channel selection stage, the most expressive feature channels are selected according to the gradient information of back propagation in loss function. Finally, in the part of cross correlation between template branch and search branch, the accurate target position is obtained by using multi-channel cross correlation of the weighted response score map. The proposed algorithm is compared with the mainstream algorithms on OTB and VOT public datasets. Experimental results show that the proposed algorithm has good anti-background interference ability and robustness. The algorithm achieves the performance of the mainstream tracking algorithms in the main tracking indicators.

Key words: object tracking, gradient-guided network, penalty function, multi-channel cross correlation

摘要:

通常在目标跟踪任务中需要跟踪的目标物体具有任意性,同时目标周围可能有相似的干扰物体,这常常导致预训练网络提取的目标特征并不完全适用于当前需要跟踪的目标物体。针对以上问题,在Siamese孪生网络目标跟踪框架下,提出一种新型的基于梯度导向的通道选择目标跟踪算法。首先从预训练网络提取待跟踪目标特征,利用提出的开关-惩罚损失函数对背景中的相似性干扰物体施加惩罚操作,以排除相似物体对跟踪目标的干扰;其次在特征通道选择阶段,根据损失函数反向传播的梯度信息选择特征表达性最强的特征通道;最后在模板分支与搜索分支进行互相关操作部分,利用逐通道互相关方法获得加权的分数响应图以获得更精确的目标位置。在OTB和VOT公开数据集上将该算法和主流算法进行比较。实验结果表明,该算法具有良好的抗背景干扰能力和鲁棒性,在主要跟踪指标上达到了主流跟踪算法的性能。

关键词: 目标跟踪, 梯度导向网络, 惩罚函数, 逐通道互相关

CLC Number: