期刊文献+

基于EM的多目标跟踪算法 被引量:4

Multi-target tracking algorithm based on EM method
下载PDF
导出
摘要 为了提高多目标跟踪的鲁棒性,增强目标之间的区别性,使用了一种基于能量最小化(energy minimization,EM)的多目标跟踪算法,不同于现有算法,本算法专注于将多目标跟踪中的复杂问题表示为能量函数的模型,模型中包括了更优的目标区分策略(相似度模型)。通过将每个能量函数成本值对应一个多目标的跟踪轨迹方案,算法将多目标跟踪问题转化为能量最小化的问题。在能量函数模型的优化方法上,算法采用共轭梯度算法和一系列的跳转运动来找到能量最小的值。公开数据集的实验结果证明了本算法的有效性,而且定量分析结果证明了本算法提高了目标与背景、目标之间的相互区别性从而与其他算法相比能获得更好的鲁棒性能。 In order to improve the multi-target tracking robustness and enhance the difference between the targets, this paper uses an energy minimization method for muhi-target tracking. Different to the existing algorithm, the algorithm focuses on the representation of the complex problem in multi-target tracking as energy function model, which includes a better target segmentation strategy ( similarity model). By assigns every possible solutions a cost ( the "energy" ), the algorithm transforms the multiple target tracking problem into an energy minimization problem. In the energy minimization optimization method, the algorithm uses the conjugate gradient algorithm and a series of jump moves to find the minimum energy value. The experimental results of open data demonstrate the effectiveness. And the quantitative analysis results show that this algorithm can improve the difference between targets or between target and background so as to obtain better robust performance compared with other algorithms.
作者 周娜 鲁昌华 徐婷佳 蒋薇薇 杜雲 Zhou Na Lu Changhua Xu Tingjia Jiang Weiwei Du Yun(School of Computer and Information, Hefei University of Technology, Hefei 230031, China)
出处 《电子测量与仪器学报》 CSCD 北大核心 2017年第1期139-143,共5页 Journal of Electronic Measurement and Instrumentation
基金 公安网视频云计算平台应用支撑系统研制(1401b042002) 安徽省科技攻关计划资助项目
关键词 多目标跟踪 目标区分策略 能量最小化 multi-target tracking target discrimination strategy energy minimization
  • 相关文献

参考文献4

二级参考文献34

  • 1ANTONINI G,MARTINEZ S V,BIERLAIRE M,et al.Behavioral priors for detection and tracking of pedestriansin video sequences[J].International Journal on Comput-er Vision,2006,69(2):159-180. 被引量:1
  • 2WANG C,KOMODAKIS N,PAR AGIOS N. Markovrandom field modeling,inference learning in computervision 8-- image understanding: A survey [J]. ComputerVision and Image Understanding,2013, 117 (11):1610-1627. 被引量:1
  • 3OJHA S, SAKHARE S. Image processing techniques for object tracking in video surveillance: A survey [C]. IEEE International Conference on Pervasive Computing, 2015 : 1-6. 被引量:1
  • 4ANDREAS E, BASTIAN L. Robust muhiperson tracking from a mobile platform [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31(10) : 1831-1846. 被引量:1
  • 5LIU T, YUAN Z J. Learning to detect a salient object[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(2): 353-367. 被引量:1
  • 6COLEMAN G B, ANDREWS H C. Image segmentation by clustering [ J]. Proceedings of the IEEE, 1979, 67(5) :773-785. 被引量:1
  • 7ANDREAS E, BASTIAN L. Robust multiperson tracking from a mobile platform[ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31(10) : 1831-1846. 被引量:1
  • 8LUCAS B D, KANADE T. An iterative image registration technique with an application to stereo vision[C]. IJCAI, 1981: 674-679. 被引量:1
  • 9VISHWANATHAN S V N, SCHRAUDOLPH N N, SCHMI'DT M W, et al. Accelerated training of conditional random fields methods[C]. Proceedings Conference on Machine 969-976. with stochastic gradient of the 23rd International Learning, ACM, 2006. 被引量:1
  • 10于海滨,刘济林.应用于公交客流统计的机器视觉方法[J].中国图象图形学报,2008,13(4):716-722. 被引量:26

共引文献57

同被引文献28

引证文献4

二级引证文献15

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