期刊文献+

基于稀疏性理论与子问题耦合的多目标跟踪方法 预览 被引量:2

Multi-target Tracking Method Based on Sparse Theory and Sub-problem Coupling
在线阅读 下载PDF
分享 导出
摘要 针对多数目标跟踪方法在非受控环境中稳定性不高以及检测.跟踪模块分离的缺点,提出一种稀疏性检测器与网络数据关联技术相结合的多目标跟踪方法。离散化目标的移动空间,对于3D的每个可能位置,将目标投影到图像平面,形成码字并构建字典。扩展模型至多类别跟踪情况,并根据耦合公式分配给子问题和协调局部解以实现解的最优化。使用网络单纯形算法解决最小成本流数据关联问题。在BU-Marathon,PETS2009等公开数据集上的实验结果表明,与能处理遮挡的多目标跟踪方法相比,该方法具有较高的跟踪精度,误检率和漏检率更低。 Aiming at the inherent shortcomings that many existing target tracking methods lack of stability in non controlled environment and the detecting-tracking module are separate, a multi-target tracking method based on sparseness detector and network data association technique is proposed. The moving space of the target is discretized, and the target is projected onto the image plane for each possible 3D position. The dictionary is built after formation of code. The model is extended to multiple classes. The optimal solution is achieved by assigning coupling equation to the sub problems and coordinating local solutions. The minimum cost flow problem of data association is solved by network simplex algorithm. BU-Marathon, PETS2009 and other public data sets are used in the experiments. Experimental results show that, compared with the multiple target tracking algorithms with occlusion handling, the proposed method has higher tracking accuracy and less false detection rate and missing detection rate.
作者 叶润 邓煜 YE Run,DENG Yu ( School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai 200240, China)
出处 《计算机工程》 CSCD 北大核心 2017年第6期219-224,229共7页 Computer Engineering
关键词 多目标跟踪 检测-跟踪方法 稀疏性 耦合公式 网络单纯形算法 multi-target tracking detecting-tracking method sparseness coupling equation network simplex algorithm
作者简介 叶润(1991-),男,硕士研究生,主研方向为智能算法、目标跟踪. 邓煜,硕士研究生。
  • 相关文献

参考文献7

二级参考文献66

  • 1沈红斌 ,王士同 ,吴小俊 .离群模糊核聚类算法[J].软件学报,2004,15(7):1021-1029. 被引量:34
  • 2侯志强,韩崇昭.基于像素灰度归类的背景重构算法[J].软件学报,2005,16(9):1568-1576. 被引量:89
  • 3SHEN Hong-bin, YANG Jie, WANG Shi-tong.Outlier detecting in fuzzy switching regression models [A]. AIMSA'04. LNAI3192 [C]. Varna:Springer, 2004.208- 215. 被引量:1
  • 4Hubert L J, Arabie P. Comparing partitions [J].Journal of Classification, 1985,15 (2):193- 218. 被引量:1
  • 5Xuanli Lisa Xie, Gerardo Beni. A validity measure for fuzzy clustering [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1991,13 (8):841-847. 被引量:1
  • 6Marr D. A computational investigation into the human representation[M]. San Francisco: W H Freeman,1982. 被引量:1
  • 7Romeny B M H, Florack L. A multiscale geometric model of human vision[A]. The Perception of Visual Information[C]. New York : Springer-Verlag, 1993.93-114. 被引量:1
  • 8Benedetto J J, Paulo J S, Ferreira G. Modern sampling theory: mathematics and applications [M].Boston: Birkhauser Boston, 2001. 被引量:1
  • 9Coren S, Ward L M, Enns J T. Sensation and perception[M]. 4th ed. Fort Worth, TX: Cold Spring Harcourt Brace College Publishers ,1994. 被引量:1
  • 10Poggio T. A theory of how the brain might work [M]. Torronto: Harbor Laboratory Press,1990. 被引量:1

共引文献32

同被引文献12

引证文献2

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈