Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (5): 1466-1470.DOI: 10.11772/j.issn.1001-9081.2017.05.1466

Previous Articles     Next Articles

Long-term visual object tracking algorithm based on correlation filter

ZHU Mingmin, HU Maohai   

  1. School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing Jiangsu 210094, China
  • Received:2016-10-17 Revised:2016-12-21 Online:2017-05-10 Published:2017-05-16


朱明敏, 胡茂海   

  1. 南京理工大学 电子工程与光电技术学院, 南京 210094
  • 通讯作者: 胡茂海
  • 作者简介:朱明敏(1990-),男,江苏句容人,硕士研究生,主要研究方向:手势识别、目标检测、目标跟踪;胡茂海(1967-),男,安徽马鞍山人,副教授,博士,主要研究方向:图像处理、光学模式识别、生物显微成像。

Abstract: Focusing on the issue that the Correlation Filter (CF) has poor performance in tracking fast motion object, a Long-term Kernelized Correlation Filter (LKCF) tracking algorithm based on optical flow combining with Kernel Correlation Filter (KCF) was proposed. Firstly, while tracking with the tracker, a value of Peak-to-Sidelobe Ratio (PSR) was calculated. Secondly, the position was achieved in the last frame, optical flow was used to calculate coarse position when the value of PSR less than a threshold in the current frame, which means tracking failure. Finally, accurate position was calculated using the tracker again according to the coarse position. The results of experiment compared with four kinds of tracking algorithms such as Compressive Tracking (CT), Tracking-Learning-Detection (TLD), KCF and Spatio-Temporal Context (STC) show that the proposed algorithm is optimal in distance accuracy and success rate which are 6.2 percentage points and 5.1 percentage points higher than those of KCF. In other words, the proposed algorithm is robust to the tracking of fast motion object.

Key words: correlation filter, optical flow, long-term object tracking, fast motion, object redetection

摘要: 为解决相关滤波器(CF)在跟踪快速运动目标时存在跟踪失败的问题,提出一种结合了核相关滤波(KCF)跟踪器和基于光流法的检测器的长时核相关滤波(LKCF)跟踪算法。首先,使用跟踪器跟踪目标,并计算所得跟踪目标的峰值响应强度(PSR);然后,通过比较峰值响应强度(PSR)与经验阈值大小判断目标是否跟踪丢失,当目标跟踪丢失时,在上一帧所得目标附近运用光流法检测运动目标,得到目标在当前帧中的粗略位置;最后,在此粗略位置处再次运用跟踪器得到精确位置。与核相关滤波(KCF)、跟踪-学习-检测(TLD)、压缩跟踪(CT)、时空上下文(STC)等4种跟踪算法进行对比实验,实验结果表明,所提算法在距离精确度和成功率上都表现最优,且分别比核相关滤波(KCF)跟踪算法高6.2个百分点和5.1个百分点,表明所提算法对跟踪快速运动目标有很强的适应能力。

关键词: 相关滤波, 光流法, 长时目标跟踪, 快速运动, 目标再检测

CLC Number: