Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (8): 2175-2179.DOI: 10.11772/j.issn.1001-9081.2017123030

Previous Articles     Next Articles

Real-time visual tracking algorithm based on correlation filters and sparse convolutional features

XIONG Changzhen1, CHE Manqiang1, WANG Runling2   

  1. 1. Beijing Key Laboratory of Urban Road Transportation Intelligent Control Technology(North China University of Technology), Beijing 100144, China;
    2. College of Science, North China University of Technology, Beijing 100144, China
  • Received:2017-12-20 Revised:2018-03-08 Online:2018-08-10 Published:2018-08-11
  • Supported by:
    This work is partially supported by the National Key Research and Development Program of China (2016YFB1200402).

基于稀疏卷积特征和相关滤波的实时视觉跟踪算法

熊昌镇1, 车满强1, 王润玲2   

  1. 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;
    2. 北方工业大学 理学院, 北京 100144
  • 通讯作者: 熊昌镇
  • 作者简介:熊昌镇(1979-),男,福建建宁人,副教授,博士,主要研究方向:视频分析、深度学习;车满强(1994-),男,甘肃定西人,硕士研究生,主要研究方向:视频图像处理;王润玲(1991-),女,河北沧州人,硕士研究生,主要研究方向:图像处理。
  • 基金资助:
    国家重点研发计划项目(2016YFB1200402)。

Abstract: Concerning the real-time performance of the hierarchical convolutional features for visual tracking, a real-time object tracking algorithm based on sparse convolution features was proposed. By analyzing the characteristics of different convolution layers, the equidistant interval sampling method was adopted to extract the sparse convolutional features of each layer. Then the correlation filter response values of each convolutional feature were combined to estimate the location of target object. Finally, a sparse update strategy was applied to improve the computing speed. Experimental results on benchmark dataset OTB-2015 show that the average distance precision of the proposed algorithm is 82.2%, which is 5.25 percentage points higher than that of the original hierarchical convolutional feature tracking algorithm; furthermore, it has better robustness to appearance changes and occlusions. The average tracking speed of the proposed algorithm is 32.6 frames per second, which is nearly 2 times faster than before, which can achieve real-time performance.

Key words: object tracking, Convolutional Neural Network (CNN), correlation filter, model updating, sparse feature

摘要: 为提高分层卷积相关滤波视觉跟踪算法的实时性能,提出一种稀疏卷积特征的实时目标跟踪算法。首先,在分析不同层卷积特征的基础上,采用等间隔采样的方式提取每个卷积层的稀疏卷积特征;然后,对每个卷积层特征的相关滤波响应值进行加权组合,得到目标预测的位置;最后,采用稀疏的模型更新策略进一步提高算法的运行速度。在OTB-2015新增的50组数据上对所提算法进行测试,实验结果表明,该算法的平均距离精度为82.2%,比原分层卷积特征跟踪算法提高了5.25个百分点,对目标姿态以及遮挡等变化具有较好的鲁棒性。该算法的平均跟踪速度为32.6帧/s,是原分层卷积特征跟踪算法的近3倍,能达到实时跟踪的效果。

关键词: 目标跟踪, 卷积神经网络, 相关滤波, 模型更新, 稀疏特征

CLC Number: