计算机工程与应用 ›› 2018, Vol. 54 ›› Issue (14): 180-185.DOI: 10.3778/j.issn.1002-8331.1703-0236

• 图形图像处理 • 上一篇    下一篇

全局分层关联网络流在多目标跟踪中的应用

王雪琴1,蒋建国1,2,齐美彬1,2   

  1. 1.合肥工业大学 计算机与信息学院,合肥 230009
    2.安全关键工业测控技术教育部工程研究中心,合肥 230009
  • 出版日期:2018-07-15 发布日期:2018-08-06

Application of global hierarchical association network in multi-target tracking

WANG Xueqin1, JIANG Jianguo1,2, QI Meibin1,2   

  1. 1.School of Computer and Information, Hefei University of Technology, Hefei 230009, China
    2.Engineering Research Center of Safety Critical Industrial Measurement and Control Technology, Ministry of Education, Hefei 230009,China
  • Online:2018-07-15 Published:2018-08-06

摘要: 整体上将多目标跟踪问题转化为图的问题。首先采用经典的分层思想,建立两层跟踪框架,并将目标的运动特征和外观特征融入权值,可以较精确地模拟真实的跟踪场景。接着,加入虚拟结点以处理目标缺失的问题,并给出其加速版:聚合虚拟结点。最后利用最大二值整数规划求解无向图以同时获得一系列团。实验在公共数据集上进行,结果表明,该算法可以实现实时跟踪,且跟踪结果较好。

关键词: 多目标跟踪, 图, 聚合虚拟结点, 最大二值整数规划

Abstract: Translating multi-target tracking into graphs is a problem as a whole. First of all, the application of classic layered thinking is adopted, and two tracking frameworks are established, and then target movement characteristics and appearance characteristics blend into the weight, which can simulate real tracking scene more accurately. Then, the dummy node is joined to deal with missing targets problem, which gives its accelerated version: aggregated dummy nodes. Finally, the mixed-binary-integer programming is used to solve the undirected graph to obtain a series of clusters at the same time. Experimental results on common dataset show that the proposed algorithm can realize real-time tracking and the tracking result is better.

Key words: multi-target tracking, graphs, aggregated dummy nodes, mixed-binary-integer programming