Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (10): 2822-2830.DOI: 10.11772/j.issn.1001-9081.2020030297

• Artificial intelligence • Previous Articles     Next Articles

Object tracking algorithm based on jointly-optimized strong-coupled Siamese region proposal network

SHI Guoqiang, ZHAO Xia   

  1. College of Electronic and Information Engineering, Tongji University, Shanghai 201804, China
  • Received:2020-03-18 Revised:2020-05-19 Online:2020-10-10 Published:2020-05-29


石国强, 赵霞   

  1. 同济大学 电子与信息工程学院, 上海 201804
  • 通讯作者: 赵霞
  • 作者简介:石国强(1996-),男,安徽宣城人,硕士研究生,主要研究方向:深度学习、目标跟踪;赵霞(1974-),女,内蒙古包头人,副教授,博士,主要研究方向:语义分割、深度学习。

Abstract: For the mismatch between the maximum classification score and the best border in Region Proposal Network (RPN) during the object tracking task, a object tracking algorithm based on Strong-Coupled Siamese Region Proposal Network (SCSiamRPN) was proposed. Firstly, the Bounded IoU method was adopted to optimize the calculation of Intersection over Union (IoU) value of positive samples, and the calculation process was simplified by decomposing formulas, fixing variables, substituting differences, and constraining approximation values. Then, the loss function structures were optimized. A coupling factor with the IoU value as bound was added to the classification loss function to combine the classification task and the border regression task, so as to increase the loss values of high IoU samples. A weighted coefficient with the IoU value as main variable was added to the border regression loss function to increase the contributions of the target center samples, so as to improve the border localization precision. Simulation results showed that the proposed algorithm had the tracking precision and success rate reached 0.86 and 0.64 respectively on OTB100 dataset, both of which were improved by 3% in the comparison with those of high performance visual tracking with Siamese Region Proposal Network (SiamRPN). It is found that the proposed algorithm solves the mismatch between the maximum classification score, enhances the coupling between the classification task and the border regression task, greatly improves the tracking precision without slowing down the tracking speed.

Key words: Region Proposal Network (RPN), joint optimization, object tracking, convolutional neural network, Intersection over Union (IoU)

摘要: 针对区域推荐网络(RPN)在目标跟踪任务中出现的最大分类分数与最佳边框不匹配的问题,提出一种基于联合优化的强耦合孪生区域推荐跟踪算法(SCSiamRPN)。首先,采用Bounded IoU方法来优化正样本交并比(IoU)值的计算,通过分解公式、固定变量、替换差值和约束近似的操作来简化计算过程。然后,优化损失函数结构,通过在分类损失函数中添加以IoU值为纽带的耦合因子来联合分类任务和边框回归任务,以提升高IoU样本的损失值;通过在边框回归损失函数中添加以IoU为主变量的加权系数来提高目标中心样本的贡献,以提升边框定位精度。仿真结果显示:SCSiamRPN算法在OTB100数据集上的精度和成功率为0.86和0.64;同基于孪生区域推荐候选网络的高性能单目标跟踪(SiamRPN)算法相比,均有3%的提升。实验结果表明:SCSiamRPN算法解决了最大分类分数与最佳边框不匹配的问题,增强了分类和边框回归任务的耦合性,且在不损失跟踪速度的前提下实现了跟踪精度的较大幅度提升。

关键词: 区域推荐网络, 联合优化, 目标跟踪, 卷积神经网络, 交并比

CLC Number: