基于相对平均误差的高分辨距离像目标识别算法

周诺; 陈炜

doi:10.3724/SP.J.1146.2009.00599

基于相对平均误差的高分辨距离像目标识别算法

doi: 10.3724/SP.J.1146.2009.00599

周诺,
陈炜

计量
- 文章访问数: 4516
- HTML全文浏览量: 52
- PDF下载量: 1120
- 被引次数: 0
出版历程
- 收稿日期: 2009-04-24
- 修回日期: 2009-09-23
- 刊出日期: 2010-05-19

A Relative-Average-Error Based HRRP Target Recognition Algorithm

Zhou Nuo,
Chen Wei

摘要

摘要: 相似度计算是基于模板匹配的高分辨距离像自动目标识别研究中的核心问题之一。该文从误差计算方法和相似度测量准则两方面对相似度计算方法的选取进行了深入的讨论，提出一种基于相对平均误差的相似度计算方法。实验结果证明，与目前普遍使用的基于绝对均方误差的模板匹配方法相比，基于相对平均误差的模板匹配方法具有更强的目标识别能力、更好的识别鲁棒性，以及在模板角域增大、模板数量明显降低的情况下，仍具备较高的识别能力，为工程上处理高识别率与低模板数量之间的矛盾问题提供了一种有效的解决方法。
- 目标识别; 高分辨距离像; 相似度计算; 误差计算; 相似度测量准则
Abstract: Similarity computation is one of the significant issue in Template-Matching-Method (TMM) based high range resolution automatic target recognition. This paper demonstrates error computation and similarity measurement metrics in similarity computation, and proposes a Relative-Average-Error (RAE) based similarity algorithm employed in TMM. The experiment result shows that, comparing with the widely used Absolute-Mean-Square-Error (AMSE) based TMM, RAE based TMM obtains higher probability of correct classification (Pcc) and more robust recognition ability. Meanwhile, in application, RAE could be an effective solution to take the tradeoff of higher Pcc and less saving memory space for templates.

HTML全文

参考文献(1)

Westerkamp J J, Williams R L, and Palomino A P, et al.. Synthetic moving target HRR profile generation using measured and modeled target data. Algorithms for Synthetic Aperture Radar Imagery VII. Proceedings of SPIE. Orlando, FL, USA, 24 April, 2000, Vol. 4053: 631-641.[2]Blasch E. Modeling intent for a target tracking and identification scenario. Signal and Data Processing of Small Targets 2004, Proceedings of SPIE. Orlando, FL, USA, 13 April 2004, Vol. 5428: 260-269.[3]Nguyen D H, Kay J H, and Orchard B J, et al.. Classification and tracking of moving ground vehicles. Lincoln Laboratory Journal, 2002, 13(2): 275-308.[4]刘宏伟，杜兰，袁莉等. 雷达高分辨距离像目标识别研究进展[J].电子与信息学报.2005, 27(8):1328-1334浏览Liu Hong-wei, Du Lan, and Yuan Li, et al.. Progress in radar automatic target recognition based on high range resolution profile[J].Journal of Electronics Information Technology.2005, 27(8):1328-1334[5]陈凤，杜兰，保铮等. 雷达高分辨距离像自动目标识别方法的改进[J].电子与信息学报.2007, 29(6):1450-1454浏览Chen Feng, Du Lan, and Bao Zheng, et al.. Improvement on radar automatic target recognition using HRRPs[J].Journal of Electronics Information Technology.2007, 29(6):1450-1454[6]刘敬，张军英，赵峰. 一种新的雷达高分辨距离像平移不变特征[J].电子与信息学报.2008, 30(8):1949-1953浏览Liu Jing, Zhang Jun-ying, and Zhao Feng. A new time-shift invariant feature of radar HRRPs[J].Journal of Electronics Information Technology.2008, 30(8):1949-1953[7]黄培康，殷红成，许小剑. 雷达目标特性. 北京：电子工业出版社，2005: 229-274.[8]袁莉. 基于高分辨距离像的雷达目标识别方法研究. [博士论文], 西安电子科技大学，2007.[9]Yuan Li. Study of radar target recognition method based on high range resolution profile. [Ph.D. dissertation], Xidian University, 2007.[10]杜兰. 雷达高分辨距离像目标识别方法研究. [博士论文], 西安电子科技大学，2007.[11]Du Lan. Study on radar HRRP target recognition. [Ph.D. dissertation], Xidian University, 2007.[12]Nguyen D, Benitz G, and Kay J, et al.. Superresolution HRR ATR with high definition vector imaging[J].IEEE Transactions on Aerospace and Electronic Systems.2001, 37(4):1267-1286[13]付耀文，贾宇平，庄钊文. 基于一维散射中心匹配的雷达目标识别. 电子学报，2006, 34(3): 404-408.Fu Yao-wen, Jia Yu-ping, and Zhuang Zhao-wen. Radar target classification based on one dimensional scattering centers matching. Acta Electronica Sinica, 2006, 34(3): 404-408.[14]刘敬，张军英，杜兰. 基于相关系数的雷达高分辨距离像分帧方法[J].电子与信息学报.2008, 30(9):2060-2064浏览Liu Jing, Zhang Jun-ying, and Du Lan. A frame segmentation method for radar HRRPs based on correlation coefficient[J].Journal of Electronics Information Technology.2008, 30(9):2060-2064[15]Li Hsueh Jyh and Yang Sheng Hui. Using range profiles as feature vectors to identify aerospace targets[J].IEEE Transactions on Antennas and Propagation.1993, 41(3):261-268[16]Li Hsueh Jyh, Wang Yung Deh, and Wang Long-Huai. Matching score properties between range profiles of high-resolution radar targets[J].IEEE Transactions on Antennas and Propagation.1996, 44(4):444-452[17]Li X R and Zhao Zhan-lue. Evaluation of estimation algorithms part I: incomprehensive measures of performance[J].IEEE Transactions on Aerospace and Electronic Systems.2006, 42(4):1340-1358[18]Willianms R, Westerkamp J, and Gross D, et al.. Automatic target recognition of time critical moving targets using 1D high range resolution (HRR) radar. IEEE Transactions on Aerospace and Electronic Systems Magazine, 2000, 15(4): 37-43.

施引文献

资源附件(0)

访问统计