基于XGBoost的机载激光雷达与高光谱影像结合的特征选择算法
|
摘要
为了解决地物分类的机载激光雷达(LiDAR)与高光谱特征构造中存在的特征维数过高的问题,提出了一种基于XGBoost与皮尔逊相关系数相结合的特征选择算法——XGB-PCCS,同时设计了XGBoost与序列后向选择相结合的特征选择算法——XGB-SBS与之对比。采用真实数据验证所设计的两种算法,结果表明:两种算法均可在保证分类结果准确率的基础上有效地减小特征集维数;XGB-SBS算法保留的特征维度为33,得到的总体分类精度为95.63%,Kappa系数为0.943;XGB-PCCS算法保留的特征维度为25,总体分类精度为95.55%,Kappa系数为0.942。XGB-PCCS算法的人为干预程度较低,运行时间较短,保留的特征集更精简。此外,对比了两种算法得到的特征子集,并总结了LiDAR点云与高光谱影像多模态特征构造中重要程度较高的24种特征。
In order to solve the problem of high feature dimension in the feature construction of airborne light detection and ranging(LiDAR) and hyperspectral images for the classification of ground objects, we propose a feature selection algorithm based on extreme gradient boosting(XGBoost) combined with Pearson correlation coefficients(PCCS), named XGB-PCCS. Meanwhile, another feature selection algorithm based on XGBoost combined with sequential backward selection(SBS), named XGB-SBS, is designed to compare with XGB-PCCS. The real data is used to verify the two algorithms designed above. The results show that both algorithms can effectively reduce the dimension of feature sets on the basis that the accuracy of classification results is ensured. As for the XGB-SBS algorithm, the retained feature dimension is 33, the overall classification accuracy is 95.63%, and the Kappa coefficient is 0.943. In contrast, as for the XGB-PCCS algorithm, the retained feature dimension is 25, the overall classification accuracy is 95.55%, and the Kappa coefficient is 0.942. The XGB-PCCS algorithm has low degree of human intervention and short running time, and the retained feature set is compact. In addition, the feature subsets obtained by the two algorithms are compared, and 24 kinds of features with high importance in the multi-modal feature construction of LiDAR point cloud and hyperspectral images are summarized.
In order to solve the problem of high feature dimension in the feature construction of airborne light detection and ranging(LiDAR) and hyperspectral images for the classification of ground objects, we propose a feature selection algorithm based on extreme gradient boosting(XGBoost) combined with Pearson correlation coefficients(PCCS), named XGB-PCCS. Meanwhile, another feature selection algorithm based on XGBoost combined with sequential backward selection(SBS), named XGB-SBS, is designed to compare with XGB-PCCS. The real data is used to verify the two algorithms designed above. The results show that both algorithms can effectively reduce the dimension of feature sets on the basis that the accuracy of classification results is ensured. As for the XGB-SBS algorithm, the retained feature dimension is 33, the overall classification accuracy is 95.63%, and the Kappa coefficient is 0.943. In contrast, as for the XGB-PCCS algorithm, the retained feature dimension is 25, the overall classification accuracy is 95.55%, and the Kappa coefficient is 0.942. The XGB-PCCS algorithm has low degree of human intervention and short running time, and the retained feature set is compact. In addition, the feature subsets obtained by the two algorithms are compared, and 24 kinds of features with high importance in the multi-modal feature construction of LiDAR point cloud and hyperspectral images are summarized.
引文
[1] Zhang B.Advancement of hyperspectral image processing and information extraction[J].Journal of Remote Sensing,2016,20(5):1062-1090.张兵.高光谱图像处理与信息提取前沿[J].遥感学报,2016,20(5):1062-1090.
[2] Zhu J T,Huang R.Feature selection and classification of hyperspectral data and LiDAR data based on Adaboost[J].Remote Sensing Information,2014,29(6):68-72.朱江涛,黄睿.基于 Adaboost 的高光谱与 LiDAR 数据特征选择与分类[J].遥感信息,2014,29(6):68-72.
[3] Dong B G.Research on classification technologies of land cover by fusing airborne LiDAR point clouds and remote sensing imagery[D].Zhengzhou:PLA Information Engineering University,2013.董保根.机载LiDAR点云与遥感影像融合的地物分类技术研究[D].郑州:解放军信息工程大学,2013.
[4] Pan S Y,Guan H Y.Object classification using airborne multispectralLiDAR data[J].Acta Geodaetica et Cartographica Sinica,2018,47(2):198-207.潘锁艳,管海燕.机载多光谱LiDAR数据的地物分类方法[J].测绘学报,2018,47(2):198-207.
[5] Cheng X J,Cheng X L,Hu M J,et al.Buildings detection and contour extraction by fusion of aerial images and LIDAR point cloud[J].Chinese Journal of Lasers,2016,43(5):0514002.程效军,程小龙,胡敏捷,等.融合航空影像和LIDAR点云的建筑物探测及轮廓提取[J].中国激光,2016,43(5):0514002.
[6] Zhang Q C,Tong G F,Li Y,et al.River detection in remote sensing images based on multi-feature fusion and soft voting[J].Acta Optica Sinica,2018,38(6):0628002.张庆春,佟国峰,李勇,等.基于多特征融合和软投票的遥感图像河流检测[J].光学学报,2018,38(6):0628002.
[7] Yao X,Wang X D,Zhang Y X,et al.Summary of feature selection algorithms[J].Control and Decision,2012,27(2):161-166,192.姚旭,王晓丹,张玉玺,等.特征选择方法综述[J].控制与决策,2012,27(2):161-166,192.
[8] Yao D J,Yang J,Zhan X J.Feature selection algorithm based on random forest[J].Journal of Jilin University (Engineering and Technology Edition),2014,44(1):137-141.姚登举,杨静,詹晓娟.基于随机森林的特征选择算法[J].吉林大学学报(工学版),2014,44(1):137-141.
[9] CHEN T,GUESTRIN C.Xgboost:a scalable tree boosting system[C].Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2016 :785-794.
[10] Liu M,Li Z R,Zhang H T,et al.Feature selection algorithm application in near-infrared spectroscopy classification based on binary search combined with random forest pruning[J].Laser & Optoelectronics Progress,2017,54(10):103001.刘明,李忠任,张海涛,等.基于二分搜索结合修剪随机森林的特征选择算法在近红外光谱分类中的应用[J].激光与光电子学进展,2017,54(10):103001.
[11] Zhang A W,Xiao T,Duan Y H.A method of adaptive feature selection for airborne LiDAR point cloud classification[J].Laser & Optoelectronics Progress,2016,53(8):082802.张爱武,肖涛,段乙好.一种机载LiDAR点云分类的自适应特征选择方法[J].激光与光电子学进展,2016,53(8):082802.
[12] Liang X W.Research on feature selection and precise classification technique from LIDAR data[D].Taiyuan:North University of China,2015.梁小伟.机载LIDAR数据特征选择与精确分类技术研究[D].太原:中北大学,2015.
[13] Ye Z,He M Y.PCA and windowed wavelet transform for hyperspectral decision fusion classification[J].Journal of Image and Graphics,2015,20(1):132-139.叶珍,何明一.PCA与移动窗小波变换的高光谱决策融合分类[J].中国图象图形学报,2015,20(1):132-139.
[14] Zang Z,Lin H,Yang M H.Comparative study on descending dimension classification of hyperspectral data between ICA algorithm and PCA algorithm[J].Journal of Central South University of Forestry & Technology,2011,31(11):18-22.臧卓,林辉,杨敏华.ICA与PCA在高光谱数据降维分类中的对比研究[J].中南林业科技大学学报,2011,31(11):18-22.
[15] Li J,Yang Y Q,Shen W,et al.Research on fabric texture based on gray level co-occurrence matrix[J].Advanced Textile Technology,2013,21(3):12-16.李静,杨玉倩,沈伟,等.基于灰度共生矩阵的织物纹理研究[J].现代纺织技术,2013,21(3):12-16.
[16] Tian Y Q,Guo P,Lu H Q.Texture feature extraction of multiband remote sensing image based on gray level co-occurrence matrix[J].Computer Science,2004,31(12):162-163,195.田艳琴,郭平,卢汉清.基于灰度共生矩阵的多波段遥感图像纹理特征的提取[J].计算机科学,2004,31(12):162-163,195.
[17] Ren G Z,Jiang T.Study on GLCM-based texture extraction methods[J].Computer Applications and Software,2014,31(11):190-192,325.任国贞,江涛.基于灰度共生矩阵的纹理提取方法研究[J].计算机应用与软件,2014,31(11):190-192,325.
[18] Bigdeli B,Samadzadegan F,Reinartz P.Fusion of hyperspectral and LIDAR data using decision template-based fuzzy multiple classifier system[J].International Journal of Applied Earth Observation and Geoinformation,2015,38:309-320.
[19] Bigdeli B,Pahlavani P.High resolution multisensor fusion of SAR,optical and LiDAR data based on crisp vs.fuzzy and feature vs.decision ensemble systems[J].International Journal of Applied Earth Observation and Geoinformation,2016,52:126-136.
[20] Jiang J W,Liu W G.Application of XGBoost algorithm in manufacturing quality prediction[J].Intelligent Computer and Applications,2017,7(6):58-60.蒋晋文,刘伟光.XGBoost算法在制造业质量预测中的应用[J].智能计算机与应用,2017,7(6):58-60.
[21] Yang C.Road network extraction from remote sensing images based on XGBoost[J].Microcomputer & Its Applications,2017,36(24):28-31.杨灿.基于XGBoost的遥感图像中道路网络的提取[J].微型机与应用,2017,36(24):28-31.
[22] Li Y Z,Wang Z Y,Zhou Y L,et al.The improvement and application of Xgboost method based on the Bayesian optimization[J].Journal of Guangdong University of Technology,2018,35(1):23-28.李叶紫,王振友,周怡璐,等.基于贝叶斯最优化的Xgboost算法的改进及应用[J].广东工业大学学报,2018,35(1):23-28.
[2] Zhu J T,Huang R.Feature selection and classification of hyperspectral data and LiDAR data based on Adaboost[J].Remote Sensing Information,2014,29(6):68-72.朱江涛,黄睿.基于 Adaboost 的高光谱与 LiDAR 数据特征选择与分类[J].遥感信息,2014,29(6):68-72.
[3] Dong B G.Research on classification technologies of land cover by fusing airborne LiDAR point clouds and remote sensing imagery[D].Zhengzhou:PLA Information Engineering University,2013.董保根.机载LiDAR点云与遥感影像融合的地物分类技术研究[D].郑州:解放军信息工程大学,2013.
[4] Pan S Y,Guan H Y.Object classification using airborne multispectralLiDAR data[J].Acta Geodaetica et Cartographica Sinica,2018,47(2):198-207.潘锁艳,管海燕.机载多光谱LiDAR数据的地物分类方法[J].测绘学报,2018,47(2):198-207.
[5] Cheng X J,Cheng X L,Hu M J,et al.Buildings detection and contour extraction by fusion of aerial images and LIDAR point cloud[J].Chinese Journal of Lasers,2016,43(5):0514002.程效军,程小龙,胡敏捷,等.融合航空影像和LIDAR点云的建筑物探测及轮廓提取[J].中国激光,2016,43(5):0514002.
[6] Zhang Q C,Tong G F,Li Y,et al.River detection in remote sensing images based on multi-feature fusion and soft voting[J].Acta Optica Sinica,2018,38(6):0628002.张庆春,佟国峰,李勇,等.基于多特征融合和软投票的遥感图像河流检测[J].光学学报,2018,38(6):0628002.
[7] Yao X,Wang X D,Zhang Y X,et al.Summary of feature selection algorithms[J].Control and Decision,2012,27(2):161-166,192.姚旭,王晓丹,张玉玺,等.特征选择方法综述[J].控制与决策,2012,27(2):161-166,192.
[8] Yao D J,Yang J,Zhan X J.Feature selection algorithm based on random forest[J].Journal of Jilin University (Engineering and Technology Edition),2014,44(1):137-141.姚登举,杨静,詹晓娟.基于随机森林的特征选择算法[J].吉林大学学报(工学版),2014,44(1):137-141.
[9] CHEN T,GUESTRIN C.Xgboost:a scalable tree boosting system[C].Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2016 :785-794.
[10] Liu M,Li Z R,Zhang H T,et al.Feature selection algorithm application in near-infrared spectroscopy classification based on binary search combined with random forest pruning[J].Laser & Optoelectronics Progress,2017,54(10):103001.刘明,李忠任,张海涛,等.基于二分搜索结合修剪随机森林的特征选择算法在近红外光谱分类中的应用[J].激光与光电子学进展,2017,54(10):103001.
[11] Zhang A W,Xiao T,Duan Y H.A method of adaptive feature selection for airborne LiDAR point cloud classification[J].Laser & Optoelectronics Progress,2016,53(8):082802.张爱武,肖涛,段乙好.一种机载LiDAR点云分类的自适应特征选择方法[J].激光与光电子学进展,2016,53(8):082802.
[12] Liang X W.Research on feature selection and precise classification technique from LIDAR data[D].Taiyuan:North University of China,2015.梁小伟.机载LIDAR数据特征选择与精确分类技术研究[D].太原:中北大学,2015.
[13] Ye Z,He M Y.PCA and windowed wavelet transform for hyperspectral decision fusion classification[J].Journal of Image and Graphics,2015,20(1):132-139.叶珍,何明一.PCA与移动窗小波变换的高光谱决策融合分类[J].中国图象图形学报,2015,20(1):132-139.
[14] Zang Z,Lin H,Yang M H.Comparative study on descending dimension classification of hyperspectral data between ICA algorithm and PCA algorithm[J].Journal of Central South University of Forestry & Technology,2011,31(11):18-22.臧卓,林辉,杨敏华.ICA与PCA在高光谱数据降维分类中的对比研究[J].中南林业科技大学学报,2011,31(11):18-22.
[15] Li J,Yang Y Q,Shen W,et al.Research on fabric texture based on gray level co-occurrence matrix[J].Advanced Textile Technology,2013,21(3):12-16.李静,杨玉倩,沈伟,等.基于灰度共生矩阵的织物纹理研究[J].现代纺织技术,2013,21(3):12-16.
[16] Tian Y Q,Guo P,Lu H Q.Texture feature extraction of multiband remote sensing image based on gray level co-occurrence matrix[J].Computer Science,2004,31(12):162-163,195.田艳琴,郭平,卢汉清.基于灰度共生矩阵的多波段遥感图像纹理特征的提取[J].计算机科学,2004,31(12):162-163,195.
[17] Ren G Z,Jiang T.Study on GLCM-based texture extraction methods[J].Computer Applications and Software,2014,31(11):190-192,325.任国贞,江涛.基于灰度共生矩阵的纹理提取方法研究[J].计算机应用与软件,2014,31(11):190-192,325.
[18] Bigdeli B,Samadzadegan F,Reinartz P.Fusion of hyperspectral and LIDAR data using decision template-based fuzzy multiple classifier system[J].International Journal of Applied Earth Observation and Geoinformation,2015,38:309-320.
[19] Bigdeli B,Pahlavani P.High resolution multisensor fusion of SAR,optical and LiDAR data based on crisp vs.fuzzy and feature vs.decision ensemble systems[J].International Journal of Applied Earth Observation and Geoinformation,2016,52:126-136.
[20] Jiang J W,Liu W G.Application of XGBoost algorithm in manufacturing quality prediction[J].Intelligent Computer and Applications,2017,7(6):58-60.蒋晋文,刘伟光.XGBoost算法在制造业质量预测中的应用[J].智能计算机与应用,2017,7(6):58-60.
[21] Yang C.Road network extraction from remote sensing images based on XGBoost[J].Microcomputer & Its Applications,2017,36(24):28-31.杨灿.基于XGBoost的遥感图像中道路网络的提取[J].微型机与应用,2017,36(24):28-31.
[22] Li Y Z,Wang Z Y,Zhou Y L,et al.The improvement and application of Xgboost method based on the Bayesian optimization[J].Journal of Guangdong University of Technology,2018,35(1):23-28.李叶紫,王振友,周怡璐,等.基于贝叶斯最优化的Xgboost算法的改进及应用[J].广东工业大学学报,2018,35(1):23-28.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |