Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (8): 2214-2218.DOI: 10.11772/j.issn.1001-9081.2019122195

• Artificial intelligence • Previous Articles     Next Articles

Dynamic weighted siamese network tracking algorithm

XIONG Changzhen, LI Yan   

  1. Beijing Key Laboratory of Urban Road Transportation Intelligent Control Technology(North China University of Technology), Beijing 100144, China
  • Received:2019-12-31 Revised:2020-03-10 Online:2020-08-10 Published:2020-05-13
  • Supported by:
    This work is partially supported by the National Key Research and Development Program of China (2017YFC0821102).


熊昌镇, 李言   

  1. 城市道路交通智能控制技术北京市重点实验室(北方工业大学), 北京 100144
  • 通讯作者: 熊昌镇(1979-),男,福建建宁人,副教授,博士,主要研究方向:深度学习、视频分析,
  • 作者简介:李言(1994-),男,北京人,硕士研究生,主要研究方向:目标跟踪。
  • 基金资助:

Abstract: In order to improve the tracking accuracy of fast online target tracking and segmentation algorithm, a dynamic weighted siamese network tracking algorithm was proposed. First, the template features extracted from the initial frame and the template features extracted from each frame were learned and fused to improve the generalization ability of the tracker. Second, in the process of obtaining the target mask by the mask branch, the features were fused in a weighting method, so as to reduce the interference caused by redundant features and improve the tracking accuracy. The algorithm was evaluated on the VOT2016 and VOT2018 datasets. The results show that the proposed algorithm has the expected average overlap rate of 0.450 and 0.390 respectively, the accuracy of 0.649 and 0.618 respectively, and the robustness of 0.205 and 0.267 respectively, all of which are higher than those of baseline algorithm. The tracking speed of the proposed algorithm is 34 frame/s, which meets the requirements of real-time tracking. The proposed algorithm effectively improves the tracking accuracy, and completes the tracking task well in a complex tracking environment.

Key words: visual tracking, siamese network, Convolutional Neural Network (CNN), template update, weighted fusion

摘要: 为提升快速在线目标跟踪与分割算法的跟踪精度,提出了一种动态的加权孪生网络跟踪算法。首先,对初始帧提取的模板特征与每帧提取的模板特征进行学习融合,提高跟踪器的泛化能力;其次,在掩膜分支产生目标掩膜的过程中用加权的方式融合特征,减少冗余特征带来的干扰,提高跟踪的精度。在数据集VOT2016和VOT2018上进行测试,所提算法的预期平均重叠率分别为0.450和0.390,精确性分别为0.649和0.618,鲁棒性分别为0.205和0.267,均高于基准算法,跟踪速度为34帧/s,达到了实时跟踪的要求。所提算法有效地提高了跟踪的准确性,能在复杂的跟踪环境下较好地完成跟踪任务。

关键词: 视觉跟踪, 孪生网络, 卷积神经网络, 模板更新, 加权融合

CLC Number: