首页 > 论文 > 光学学报 > 37卷 > 7期(pp:728003--1)

基于改进豪斯多夫距离的扩展目标形态估计评估

Shape Estimation Evaluation of Extended Objects Based on Modified Hausdorff Distance

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为了验证高精度传感器量测下某种扩展目标跟踪算法的有效性,往往需要与其它算法进行对比,并评估其估计性能。与传统的点目标不同,扩展目标跟踪的主要任务不仅仅是要估计出目标的运动状态,更重要的是要对其扩展形态进行精确估计。因此,对扩展目标的形态估计性能评估有着迫切的需求。针对基于星凸形和支撑函数这两种具有代表性的扩展目标模型,考虑到其所具有的不同的形态参数描述方式,提出了一种具有不同数学形式的改进豪斯多夫距离来解决此问题。仿真实验表明,提出的改进豪斯多夫距离能够作为一种有效的度量准则来对扩展目标的形态估计性能进行有效评估。

Abstract

In order to verify the validity of extended objects tracking algorithm under high precision sensors measurement, it is often necessary to compare with other algorithms and evaluate its estimated performance. Unlike classical point objects, the main task of extended objects tracking is not only to estimate the motion state of the objects, but also more importantly to accurately estimate their shape. As a result, there is an urgent need to the shape estimation performance evaluation of the extended objects. Aiming at the two kinds of representative extended target models based on star-convex and support functions, considering their different morphological parameters, an improved Hausdorff distance with different mathematical forms is proposed. Simulation results demonstrate that the modified Hausdorff distance can be used as an effective metrics to evaluate the shape estimation performance of the extended targets effectively.

投稿润色
补充资料

中图分类号:TP391

DOI:10.3788/aos201737.0728003

所属栏目:遥感与传感器

基金项目:国家自然科学基金(U1504619,61304144,U1404615,U1404512)、毫米波国家重点实验室开放课题基金资助项目(K201504)、河南省科技攻关项目(162102210073)、河南省产学研合作项目(142107000021)

收稿日期:2017-01-05

修改稿日期:2017-03-29

网络出版日期:--

作者单位    点击查看

孙力帆:河南科技大学信息工程学院, 河南 洛阳 471023
张 森:河南科技大学信息工程学院, 河南 洛阳 471023
冀保峰:河南科技大学信息工程学院, 河南 洛阳 471023东南大学毫米波国家重点实验室, 江苏 南京 210096
普杰信:河南科技大学信息工程学院, 河南 洛阳 471023

联系人作者:孙力帆(Lifan_sun@126.com)

备注:孙力帆(1982-),男,博士,讲师,主要从事扩展目标跟踪、信息融合方面的研究。

【1】Zhang Hui, Xu Hui, Wang Xueying, et al. A Gaussian mixture PHD filter for group targets tracking based on ellipse random hypersurface models[J]. Acta Optica Sinica, 2013, 33(9): 0904001.
张 慧, 徐 晖, 王雪莹, 等. 一种基于椭圆随机超曲面模型的群目标高斯混合PHD滤波器[J]. 光学学报, 2013, 33(9): 0904001.

【2】Li X R, Zhao Z L. Evaluation of estimation algorithms-part I: incomprehensive performance measures[J]. IEEE Transactions on Aerospace and Electronic Systems, 2006, 42(4): 1340-1358.

【3】Wu Shudong, Huang Jianyu, Zhao Zhilong, et al. Experimental demonstration of spotlight mode synthetic aperture ladar[J]. Acta Optica Sinica, 2016, 36(6): 0628001.
吴曙东, 黄建余, 赵志龙, 等. 聚束模式合成孔径激光雷达实验演示[J]. 光学学报, 2016, 36(6): 0628001.

【4】Wu Jin, Zhao Zhilong, Wu Shudong, et al. High resolution synthetic aperture ladar imaging at 12.9 m distance[J]. Acta Optica Sinica, 2015, 35(12): 1228002.
吴 谨, 赵志龙, 吴曙东, 等. 12.9 m高分辨率合成孔径激光雷达成像[J]. 光学学报, 2015, 35(12): 1228002.

【5】Gilhom K, Salmond D. Spatial distribution model for tracking extended objects[J]. IEE Proceedings-Radar, Sonar and Navigation, 2005, 152(5): 364-371.

【6】Baum M, Noack B, Hanebeck U D. Extended object and group tracking with elliptic random hypersurface model[C]. The 13th International Conference on Information Fusion, Edinburgh, United Kingdom, 2010.

【7】Baum M, Hanebeck U D. Shape tracking of extended objects and group targets with star-convex RHMs[C]. The Proceedings of the 14th International Conference on Information Fusionm, Chicago, USA, 2011.

【8】Koch W. Bayesian approach to extended object and cluster tracking using random matrices[J]. IEEE Transactions on Aerospace and Electronic Systems, 2008, 44(3): 1042-1059.

【9】Lan J, Li X R. Tracking of maneuvering non-ellipsoidal extended object or target group using random matrix[J]. IEEE Transactions on Signal Processing, 2014, 62(9): 2450-2463.

【10】Lan J, Li X R. Tracking of extended object or target group using random matrix-part I: new modeland approach[C]. The Proceedings of the 15th International Conference on Information Fusion, Singapore, 2012.

【11】Feldmann M, Franken D, Koch W. Tracking of extended objects and group targets using random matrices[J]. IEEE Transactions on Signal Processing, 2011, 59(4): 1409-1420.

【12】Koch W, van Keuk G. Multiple hypothesis trackmaintenance with possibly unresolved measurements[J]. IEEE Transactions on Aerospace and Electronic Systems, 1997, 33(3): 883-892.

【13】Sun L, Li X R, Lan J. Modeling of extended objects based on support functions and extended Gaussian images for target tracking[J]. IEEE Transactions on Aerospace and Electronic Systems, 2014, 50(4): 3021-3035.

【14】Ghosh P K, Kumar K. Support function representation of convex bodies, its application in geometric computing, and some related representations[J]. Computer Vision and Image Understanding, 1998, 72(3): 379-403.

【15】Karl W C, Verghese G C, Willsky A S. Reconstructing ellipsoids from projections[J]. CVGIP: Graphical Models and Image Processing, 1994, 56(2): 124-139.

【16】Julier S J, Uhlmann J K. A new method for the nonlinear transformation of means and covariances in filters and estimators[J]. IEEE Transactions on Automatic Control, 2000, 45(6): 477-482.

【17】Li X R, JilkovV P. Survey of maneuvering target tracking-part VI: approximation techniques for nonlinear filtering[C]. The Proceedings of the 2004 SPIE Conference on Signal and Data Processing of Small Targets, 2004, 5428: 537-550.

【18】Sim D, Kwon O, Park R. Object matching algorithms using robust Hausdorff distance measures[J]. IEEE Transactions on Image Processing, 1999, 8(3): 425-429.

【19】Li X R, Jilkov V P. Survey of maneuvering target tracking-part I: dynamic models[J]. IEEE Transactions on Aerospace and Electronic Systems, 2003, 39(4): 1333-1364.

引用该论文

Sun Lifan,Zhang Sen,Ji Baofeng,Pu Jiexin. Shape Estimation Evaluation of Extended Objects Based on Modified Hausdorff Distance[J]. Acta Optica Sinica, 2017, 37(7): 0728003

孙力帆,张 森,冀保峰,普杰信. 基于改进豪斯多夫距离的扩展目标形态估计评估[J]. 光学学报, 2017, 37(7): 0728003

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF