基于稳健最小二乘支持向量机的测深激光信号处理

doi:10.11772/j.issn.1001-9081.2016.04.1173

计算机应用 ›› 2016, Vol. 36 ›› Issue (4): 1173-1178.DOI: 10.11772/j.issn.1001-9081.2016.04.1173

• 行业与领域应用 • 上一篇

基于稳健最小二乘支持向量机的测深激光信号处理

王勇¹, 赵现立², 付成群¹, 谢立军¹

1. 解放军理工大学野战工程学院, 南京 210007;
2. 总装备部工程兵驻无锡军代室, 江苏无锡 214037

收稿日期:2015-09-17 修回日期:2015-10-28 出版日期:2016-04-10 发布日期:2016-04-08
通讯作者: 王勇
作者简介:王勇(1984-),男,重庆人,博士研究生,主要研究方向:激光数据处理、支持向量机、智能识别; 赵现立(1981-),男,河南濮阳人,工程师,硕士,主要研究方向:装备器质量管理、数据分析; 付成群(1975-),男,河南辉县人,副教授,博士,主要研究方向:战场环境数字化; 谢立军(1974-),湖南新邵人,高级工程师,博士,主要研究方向:工程侦察。
基金资助:
国家863计划项目(2014AA7042011)。

Laser bathymetry waveform processing based on robust least square support vector machine

WANG Yong¹, ZHAO Xianli², FU Chengqun¹, XIE Lijun¹

1. College of Field Engineering, PLA University of Science and Technology, Nanjing Jiangsu 210007, China;
2. Engineer Military Representative Office of the General Armaments Department in Wuxi Area, Wuxi Jiangsu 214037, China

Received:2015-09-17 Revised:2015-10-28 Online:2016-04-10 Published:2016-04-08
Supported by:
This work is partially supported by the National High Technology Research and Development Program (863 Program) of China (2014AA7042011).

摘要/Abstract

摘要： 针对浅海探测中激光回波噪声源多、信噪比低,传统非加权最小二乘支持向量机和加权最小二乘支持向量机对低信噪比信号滤波不足的问题,提出将稳健最小二乘法与加权最小二乘支持向量机相结合的滤波方法(HW-LS-SVM)。首先采用强淘汰权函数计算先验权值、残差和均方误差,然后采用权函数模型计算最小二乘支持向量机的权值,最后通过迭代计算实现回波信号滤波。通过仿真实验结果表明, HW-LS-SVM方法较最小二乘支持向量机、贝叶斯最小二乘支持向量机和传统加权最小二乘支持向量机滤波效果更加稳健,在噪声率为45%的情况下,滤波效果较为理想,水面和水底回波提取正确率为100%;对实测4组深水区和4组浅水区数据滤波后提取的海水深度均与背景资料的深度吻合。由此表明, HW-LS-SVM方法具有更好的抗噪性,更适合于对信噪比低的测深激光信号的滤波处理。

关键词: 支持向量机, 稳健最小二乘, 激光测深, 高崩溃污染率, 权函数

Abstract: The traditional nonweighted least squares Support Vector Machine (SVM) and weighted least square SVM have a few disadvantages of processing low Signal-to-Noise Ratio (SNR) laser echo in the field of lidar bathymetry, a filtering method named HW-LS-SVM was proposed by combining robust least square and weighted least square SVM. Firstly, strong prior weight function, residual error and mean square error were calculated by elimination weight function, then the weight of least square SVM was computed by weight function. Finally, the echo signal was filtered by iterative computation. The simulation results show that HW-LS-SVM algorithm is more robust than least square SVM, Bayes least square SVM and the traditional weighted least square SVM. The results were satisfactory when the noise rate reached to 45%, and the correct rate of the extracted water surface and bottom was 100%. The extracted water depths from 4 groups of laser echoes in deep area and 4 groups in shallow area all agree with the background data. The proposed method has better anti-noise performance and is more suitable for the filtering processing of the low SNR lidar bathymetry signal.

Key words: Support Vector Machine (SVM), robust least square, laser bathymetry, high breakdown contamination rate, weight function

中图分类号:

TP301.6

王勇, 赵现立, 付成群, 谢立军. 基于稳健最小二乘支持向量机的测深激光信号处理[J]. 计算机应用, 2016, 36(4): 1173-1178.

WANG Yong, ZHAO Xianli, FU Chengqun, XIE Lijun. Laser bathymetry waveform processing based on robust least square support vector machine[J]. Journal of Computer Applications, 2016, 36(4): 1173-1178.

参考文献

[1] MALLET C, BRETAR F. Full-waveform topographic lidar:state-of-the-art[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2008, 64(1):1-16.
[2] HOFTON M A, MINSTER J B, BLAIR J B. Decomposition of laser altimeter waveforms[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000, 38(4):1989-1996.
[3] WAGNER W, ULLRICH A, DUCIC V, et al. Gaussian decomposition and calibration of a novel small-footprint full-waveform digitising airborne laser scanner[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2005, 60(2):100-112.
[4] JUTZI B, STILLA U. Range determination with waveform recording laser systems using a Wiener filter[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2006, 61(2):95-107.
[5] RONCAT A, BERGAUER G, PFEIFER N. B-spline deconvolution for differential target cross-section determination in full-waveform laser scanning data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(4):418-428.
[6] BELINA F, LRVING J, ERNST J, et al. Analysis of an iterative deconvolution approach for estimating the source wavelet during waveform inversion of crosshole georadar data[J]. Journal of Applied Geophysics, 2012, 78:20-30.
[7] WAGNER W, RONCAT A, MELZER T, et al. Waveform analysis techniques in airborne laser scanning[J]. International Archives of Photogrammetry and Remote Sensing, 2007, 36(3):413-418.
[8] BRETAR F, CHAUVE A, MALLET C, et al. Managing full waveform lidar data:a challenging task for the forthcoming years[EB/OL].[2015-02-10]. http://www.isprs.org/proceedings/XXXVII/congress/1_pdf/69.pdf.
[9] WANG C, LI Q, LIU Y, et al. A comparison of waveform processing algorithms for single-wavelength LiDAR bathymetry[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 101:22-35.
[10] 邓小英, 刘涛, 罗勇.Ricker子波核最小二乘支持向量回归滤波方法的稳健性研究[J]. 地球物理学报, 2011, 54(3):845-853.(DENG X Y, LIU T, LUO Y. Robustness of least squares support vector regression filtering method with Ricker wavelet kernel[J]. Chinese Journal of Geophysics, 2011, 54(3):845-853.)
[11] 邴萍萍, 曹思远, 路交通.基于支持向量机的非线性AVO反演[J]. 地球物理学报, 2012, 55(3):1025-1032.(BING P P, CAO S Y, LU J T. Non-linear AVO inversion based on support vector machine[J]. Chinese Journal of Geophysics, 2012, 55(3):1025-1032.)
[12] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[13] SUYKENS J A K, DE BRABANTER J, LUKAD L, et al. Weighted least squares support vector machines:robustness and sparse approximation[J]. Neurocomputing, 2002, 48(1/2/3/4):85-105.
[14] ROUSSEEUW P J, LEROY A M. Robust Regression and Outlier Detection[M]. New York:Wiley, 2005:158-174.
[15] ARCE G R. Nonlinear Signal Processing:a Statistical Approach[M]. New York:Wiley, 2005:303-346.
[16] ABDALLAH H, BAGHDADI N, BAILLY J S, et al. Wa-LiD:a new LiDAR simulator for waters[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(4):744-748.
[17] GESTEL V T, SUYKENS J A K, LANCKRIET A, et al. Bayesian framework for least-squares support vector machine classifiers, Gaussian processes, and kernel Fisher discriminant analysis[J]. Neural Computation, 2002, 15(5):1115-1147.
[18] GESTEL V T, SUYKENS J A K, MOOR D B, et al. Bayesian inference for LS-SVMs on larger datasets using the Nystrom method[C]//IJCNN 2002:Proceedings of the 2002 International Joint Conference on Neural Networks. Piscataway, NJ:IEEE, 2002:2779-2784.
[19] VONG C M, WONG P K, LI Y P. Prediction of automotive engine power and torque using least squares support vector machines and Bayesian inference[J]. Engineering Applications of Artificial Intelligence, 2006, 19(3):277-287.
[20] LI G P, YAN W W, SHAO H H. Iterative optimal control based on support vector machine modeling within the Bayesian evidence framework[J]. Journal of Shanghai University (English Edition),2007, 11(6):591-596.
[21] 杨元喜. 抗差估计理论及其应用[M].北京:八一出版社, 1993:71-89.(YANG Y X. Robust Estimation Theory and its Application[M]. Beijing:Bayi Press, 1993:71-89.)
[22] 杨元喜, 宋立杰, 徐天河. 大地测量相关观测抗差估计理论[J]. 测绘学报, 2002, 31(2):95-99.(YANG Y X, SONG L J, XU T H. Robust parameter estimation for geodetic correlated observations[J]. Acta Geodaetica et Cartographica Sinica, 2002, 31(2):95-99.)
[23] BRABANTER D K, PELCKMANS K, BRABANTER D J, et al. Robustness of kernel based regression:a comparison of iterative schemes[C]//ICANN 2009:Proceedings of the 19th International Conference on Artificial Neural Networks. Berlin:Springer, 2009:100-110.
[24] COLLIN A, LONG B, ARCHAMBAULT P. Benthic classification using bathymetric LIDAR waveforms and integration of local spatial statistics and textural features[J]. Journal of Coastal Research, 2011, 27(62):86-98.

基于稳健最小二乘支持向量机的测深激光信号处理

Laser bathymetry waveform processing based on robust least square support vector machine

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	贾鹤鸣, 姜子超, 李瑶, 孙康健. 基于改进斑点鬣狗优化算法的同步优化特征选择[J]. 计算机应用, 2021, 41(5): 1290-1298.
[2]	袁芊芊, 邓洪敏, 王晓航. 基于超像素快速模糊C均值聚类与支持向量机的柑橘病虫害区域分割[J]. 计算机应用, 2021, 41(2): 563-570.
[3]	李凯, 李洁. 基于pinball损失的结构模糊多分类支持向量机算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3104-3112.
[4]	童林, 官铮. 改进鲸鱼优化支持向量机的交通流量模糊粒化预测[J]. 计算机应用, 2021, 41(10): 2919-2927.
[5]	陆荣秀, 陈明明, 杨辉, 朱建勇. 基于溶液图像时序特征的元素组分含量动态监测系统[J]. 计算机应用, 2021, 41(10): 3075-3081.
[6]	张健铭, 施元昊, 徐正蓺, 魏建明. 基于误差预测的自适应UWB/PDR融合定位算法[J]. 计算机应用, 2020, 40(6): 1755-1762.
[7]	黄功, 赵永平, 谢云龙. 基于局部密度的加权一类支持向量机算法及其在涡轴发动机故障检测中的应用[J]. 计算机应用, 2020, 40(3): 917-924.
[8]	王杨, 赵红东. 基于改进粒子群优化的支持向量机与情景感知的人体活动识别[J]. 计算机应用, 2020, 40(3): 665-671.
[9]	赵一, 段兴, 谢仕义, 梁春林. 面向特定目标自识别的交通图像语义检索方法[J]. 计算机应用, 2020, 40(2): 553-560.
[10]	李卉, 杨志霞. 基于Rescaled Hinge损失函数的多子支持向量机[J]. 计算机应用, 2020, 40(11): 3139-3145.
[11]	牛晓可, 黄伊鑫, 徐华兴, 蒋震阳. 基于听皮层神经元感受野的强噪声环境下说话人识别[J]. 计算机应用, 2020, 40(10): 3034-3040.
[12]	白东颖, 易亚星, 王庆超, 余志勇. 面向概念漂移问题的渐进多核学习方法[J]. 计算机应用, 2019, 39(9): 2494-2498.
[13]	何海琳, 郑建彬, 余方利, 余烈, 詹恩奇. 基于改进鲸鱼优化算法的外骨骼机器人步态检测[J]. 计算机应用, 2019, 39(7): 1905-1911.
[14]	孔菁, 郭渊博, 刘春辉, 王一丰. 基于智能手机运动传感器的步态特征身份识别方法[J]. 计算机应用, 2019, 39(6): 1747-1752.
[15]	潘建国, 李豪. 基于实用拜占庭容错的物联网入侵检测方法[J]. 计算机应用, 2019, 39(6): 1742-1746.