Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (9): 2705-2711.DOI: 10.11772/j.issn.1001-9081.2020111805

Special Issue: 多媒体计算与计算机仿真

• Multimedia computing and computer simulation • Previous Articles     Next Articles

Object tracking algorithm of fully-convolutional Siamese networks with rotation and scale estimation

JI Zhangjian1,2, REN Xingwang1,2   

  1. 1. School of Computer and Information Technology, Shanxi University, Taiyuan Shanxi 030006, China;
    2. Institute of Big Data Science and Industry, Shanxi University, Taiyuan Shanxi 030006, China
  • Received:2020-11-18 Revised:2021-01-16 Online:2021-09-10 Published:2021-05-12
  • Supported by:
    This work is partially supported by the Youth Program of National Natural Science Foundation of China (61602288, 61703252, 61702314), the Natural Science Foundation of Shanxi Province (201701D221102, 201901D211176, 201901D211170).

带旋转与尺度估计的全卷积孪生网络目标跟踪算法

姬张建1,2, 任兴旺1,2   

  1. 1. 山西大学 计算机与信息技术学院, 太原 030006;
    2. 山西大学 大数据科学与产业研究院, 太原 030006
  • 通讯作者: 姬张建
  • 作者简介:姬张建(1983-),男,陕西澄城人,副教授,博士,CCF会员,主要研究方向:计算机视觉、机器学习;任兴旺(1994-),男,山西河曲人,硕士研究生,主要研究方向:目标检测与跟踪。
  • 基金资助:
    国家自然科学基金青年科学基金资助项目(61602288,61703252,61702314);山西省自然科学基金资助项目(201701D221102,201901D211176,201901D211170)。

Abstract: In the object tracking task, Fully-Convolutional Siamese networks (SiamFC) tracking method has problems of tracking errors or inaccurate tracking results caused by the rotation and scale variation of objects. Therefore, a SiamFC tracking algorithm with rotation and scale estimation was proposed, which consists of location module and rotation-scale estimation module. Firstly, in the location module, the tracking position was obtained by using SiamFC algorithm, and this position was adjusted by combining the rotation and scale information. Then, in the rotation-scale estimation module, as the image rotation and scale variation were converted into translational motions in log-polar coordinate system, the object search area was transformed from Cartesian coordinate system to log-polar coordinate system, so that the scale and rotation angle of the object were estimated by using correlation filtering technology. Finally, an object tracking model which can simultaneously estimate object position, rotation angle and scale variation was obtained. In the comparison experiments, the proposed algorithm had the success rate and accuracy of 57.7% and 81.4% averagely on Visual Tracker Benchmark 2015 (OTB2015) dataset, and had the success rate and accuracy of 51.8% and 53.3% averagely on Planar Object Tracking in the wild (POT) dataset with object rotation and scale variation. Compared with the success rate and accuracy of SiamFC algorithm, those of the proposed algorithm were increased by 13.5 percentage points and 13.4 percentage points averagely. Experimental results verify that the proposed algorithm can effectively solve the tracking challenges caused by object rotation and scale variation.

Key words: object tracking, Fully-Convolutional Siamese networks (SiamFC), correlation filtering, log-polar coordinate, rotation, scale

摘要: 针对目标跟踪任务中,全卷积孪生网络(SiamFC)跟踪算法存在因目标的旋转、尺度变化而造成跟踪错误或跟踪结果不准确的问题,提出一种带旋转与尺度估计的SiamFC跟踪算法。该算法由定位模块与旋转、尺度估计模块两部分组成。首先在定位模块中,利用SiamFC算法获得跟踪位置,并结合旋转与尺度信息对该位置进行调整;其次在旋转、尺度估计模块中,鉴于图像的旋转和尺度变化在对数极坐标系下变成了平移运动,将目标搜索区域从笛卡儿坐标系变换到对数极坐标系下,由此便可利用相关滤波技术估计待跟踪目标的尺度和旋转角度;最终实现了一个能同步估计目标位置、旋转角度以及尺度变化的目标跟踪模型。在对比实验中,该算法在OTB2015数据集上的成功率与准确率分别达到57.7%和81.4%;在包含目标旋转和尺度变化的POT数据集上的成功率与准确率分别达到51.8%和53.3%。与SiamFC算法相比,所提算法的成功率和准确率分别提高了13.5个百分点和13.4个百分点。实验结果表明,所提算法能有效应对目标旋转与尺度变化带来的跟踪挑战。

关键词: 目标跟踪, 全卷积孪生网络, 相关滤波, 对数极坐标, 旋转, 尺度

CLC Number: