Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (2): 343-347.DOI: 10.11772/j.issn.1001-9081.2018061211

Previous Articles     Next Articles

Object tracking algorithm based on parallel tracking and detection framework and deep learning

YAN Ruoyi1, XIONG Dan2, YU Qinghua1, XIAO Junhao1, LU Huimin1   

  1. 1. College of Intelligence Science and Technology, National University of Defense Technology, Changsha Hunan 410073, China;
    2. Unmanned Systems Research Center, National Innovation Institute of Defense Technology, Beijing 100071, China
  • Received:2018-06-12 Revised:2018-08-27 Online:2019-02-10 Published:2019-02-15
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61773393, 61503401).

基于并行跟踪检测框架与深度学习的目标跟踪算法

闫若怡1, 熊丹2, 于清华1, 肖军浩1, 卢惠民1   

  1. 1. 国防科技大学 智能科学学院, 长沙 410073;
    2. 国防科技创新研究院 无人系统研究中心, 北京 100071
  • 通讯作者: 卢惠民
  • 作者简介:闫若怡(1993-),女,黑龙江牡丹江人,硕士研究生,主要研究方向:机器人视觉;熊丹(1986-),男,湖南岳阳人,博士,主要研究方向:机器人视觉、视觉同步定位与建图;于清华(1988-),男,辽宁海城人,博士研究生,主要研究方向:机器人视觉、视觉同步定位与建图;肖军浩(1984-),男,河北保定人,讲师,博士,主要研究方向:移动机器人三维感知、多机器人协同控制;卢惠民(1980-),男,福建南平人,副教授,博士,主要研究方向:机器人视觉、多机器人协同控制、机器人足球、机器人救援。
  • 基金资助:
    国家自然科学基金资助项目(61773393,61503401)。

Abstract: In the context of air-ground robot collaboration, the apperance of the moving ground object will change greatly from the perspective of the drone and traditional object tracking algorithms can hardly accomplish target tracking in such scenarios. In order to solve this problem, based on the Parallel Tracking And Detection (PTAD) framework and deep learning, an object detecting and tracking algorithm was proposed. Firstly, the Single Shot MultiBox detector (SSD) object detection algorithm based on Convolutional Neural Network (CNN) was used as the detector in the PTAD framework to process the keyframe to obtain the object information and provide it to the tracker. Secondly, the detector and tracker processed image frames in parallel and calculated the overlap between the detection and tracking results and the confidence level of the tracking results. Finally, the proposed algorithm determined whether the tracker or detector need to be updated according to the tracking or detection status, and realized real-time tracking of the object in image frames. Based on the comparison with the original algorithm of the PTAD on video sequences captured from the perspective of the drone, the experimental results show that the performance of the proposed algorithm is better than that of the best algorithm with the PTAD framework, its real-time performance is improved by 13%, verifying the effectiveness of the proposed algorithm.

Key words: parallel tracking and detection, object tracking, deep learning, correlation filter, drone

摘要: 在空地协同背景下,地面目标的移动导致其在无人机视角下外观会发生较大变化,传统算法很难满足此类场景的应用要求。针对这一问题,提出基于并行跟踪和检测(PTAD)框架与深度学习的目标检测与跟踪算法。首先,将基于卷积神经网络(CNN)的目标检测算法SSD作为PTAD的检测子处理关键帧获取目标信息并提供给跟踪子;其次,检测子与跟踪子并行处理图像帧并计算检测与跟踪结果框的重叠度及跟踪结果的置信度;最后,根据跟踪子与检测子的跟踪或检测状态来判断是否对跟踪子或检测子进行更新,并对图像帧中的目标进行实时跟踪。在无人机视角下的视频序列上开展实验研究和对比分析,结果表明所提算法的性能高于PTAD框架下最优算法,而且实时性提高了13%,验证了此算法的有效性。

关键词: 并行跟踪和检测, 目标跟踪, 深度学习, 相关滤波, 无人机

CLC Number: