Merged Airborne LiDAR and Hyperspectral Data for Tree Species Classification in Puer's Mountainous Area

LIU Yi-jun; PANG Yong; LIAO Sheng-xi; JIA Wen; CHEN Bo-wei; LIU Lu-xia

[Objective] To classify the tree species in Puer's mountainous area by remote sensing image, and to search an efficient way to forest management planning.[Method] The AISA Eagle II hyperspectral data and airborne LiDAR taken in April of 2014 were merged, and based on Canopy Height Model (CHM) derived from airborne LiDAR point cloud data, the vertical structure data of target species were obtained. Then, the Principal Component Analysis (PCA) transformation was used to reduce the noise and dimension of hyperspectral image. Finally, the Support Vector Machine (SVM) approach was used to classify the main tree species of Pu'er city.[Result] (1) The main tree species of Puer are Pinus kesiya Royle ex Gord. var. langbianensis (A.Chev.) Gaussen, Betula alnoides Buch.-Ham. ex D. Don, Castanopsis hystrix A.DC, Schima superba Gardn. et Champ and so on. (2) It showed that the total accuracy and kappa coefficient are 80.54%, and 0.78, which are 6.55% and 0.08 higher compared with the classification accuracies without CHM. The mapping accuracy of the main tree species reached as high as 90.24%.[Conclusion] It is proved that this method is feasible for the identification of tree species in mountainous areas, and is a feasible way to improve total accuracy with merged LiDAR and hyperspectral data.

1. Research Institute of Resource Insects, Chinese Academy of Forestry, Kunming 650224, Yunnan, China

2. Research Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, China

Received Date: 2015-12-21

Abstract: [Objective] To classify the tree species in Puer's mountainous area by remote sensing image, and to search an efficient way to forest management planning.[Method] The AISA Eagle II hyperspectral data and airborne LiDAR taken in April of 2014 were merged, and based on Canopy Height Model (CHM) derived from airborne LiDAR point cloud data, the vertical structure data of target species were obtained. Then, the Principal Component Analysis (PCA) transformation was used to reduce the noise and dimension of hyperspectral image. Finally, the Support Vector Machine (SVM) approach was used to classify the main tree species of Pu'er city.[Result] (1) The main tree species of Puer are Pinus kesiya Royle ex Gord. var. langbianensis (A.Chev.) Gaussen, Betula alnoides Buch.-Ham. ex D. Don, Castanopsis hystrix A.DC, Schima superba Gardn. et Champ and so on. (2) It showed that the total accuracy and kappa coefficient are 80.54%, and 0.78, which are 6.55% and 0.08 higher compared with the classification accuracies without CHM. The mapping accuracy of the main tree species reached as high as 90.24%.[Conclusion] It is proved that this method is feasible for the identification of tree species in mountainous areas, and is a feasible way to improve total accuracy with merged LiDAR and hyperspectral data.

HTML

Reference (20)

[1]	薛东艳. 遥感技术在林业中的应用现状与展望[J]. 科技视界, 2014(21):309-311.
[2]	贾坤, 李强子, 田亦陈, 等. 遥感影像分类方法研究进展[J]. 光谱学与光谱分析, 2011, 31(10):2618-2623.
[3]	李海涛, 顾海燕, 张兵, 等. 基于MNF和SVM的高光谱遥感影像分类研究[J]. 遥感信息, 200729(5):12-15.
[4]	李雪松. 机载激光LiDAR原理及应用[J]. 测绘与空间地理信息, 2015, 38(2):221-224.
[5]	Charaniya A P, Manduchi R, Lodha S K. Supervised parametric classification of aerial lidar data[C]//Computer Vision and Pattern Recognition Workshop, 2004. CVPRW'04. Conference on. IEEE, 2004:30-30.
[6]	余柏蒗, 刘红星,吴健平.一种应用机载LiDAR数据和高分辨率遥感影像提取城市绿地信息的方法[J].中国图象图形学报, 2010, 15(5):782-789.
[7]	董彦芳, 庞勇, 许丽娜, 等. 高光谱遥感影像与机载LiDAR数据融合的地物提取方法研究[J]. 遥感信息, 2014,29(6):73-76.
[8]	刘丽娟,庞勇,范文义,等.机载LiDAR和高光谱融合实现温带天然林树种识别[J].遥感学报, 2013,17(3):679-695.
[9]	刘万德, 苏建荣, 李帅锋, 等. 云南普洱季风常绿阔叶林优势物种不同生长阶段叶片碳, 氮, 磷化学计量特征[J]. 植物生态学报, 2015, 39(1):52-62.
[10]	吴征镒, 朱彦丞, 姜汉侨. 云南植被[M].北京:科学出版社, 1987.
[11]	荚文, 庞勇, 岳彩荣, 等. 基于AISA Eagle II机载高光谱数据的普洱市山区森林分类[J]. 林业调查规划, 2015, 40(1):9-14.
[12]	张东东, 杜培军. 机载LiDAR数据处理与地物提取[J]. 测绘信息与工程, 2011, 36(1):5-7.
[13]	刘美爽,邢艳秋,吴红波,等.基于ICESat-GLAS波形估测平均树高的研究[J]. 林业科学研究, 2014, 27(3):309-315.
[14]	赵时英. 遥感应用分析原理与方法[M].北京:科学出版社, 2003.
[15]	Kobayashi § S, Sanga-Ngoie K. A comparative study of radiometric correction methods for optical remote sensing imagery:the IRC vs. other image-based C-correction methods[J]. International Journal of Remote Sensing, 2009, 30(2):285-314.
[16]	Mountrakis G, Im J, Ogole C. Support vector machines in remote sensing:A review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(3):247-259.
[17]	Goodenough D G, Chen H, Dyk A, et al. Data fusion study between polarimetric SAR, hyperspectral and LiDAR data for forest information[C]//Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International. IEEE, 2008, 2:II-281-284.
[18]	Sasaki T, Imanishi J, Ioki K, et al. Object-based classification of land cover and tree species by integrating airborne LiDAR and high spatial resolution imagery data[J]. Landscape and Ecological Engineering, 2012, 8(2):157-171.
[19]	管海燕, 邓非, 张剑清, 等. 面向对象的航空影像与机载LiDAR数据融合分类[J]. 武汉大学学报:信息科学版, 2009, 34(7):830-833.
[20]	巩翼龙, 闫利. 结合机载LiDAR数据与航空可见光影像多层次规则分类建筑物变化检测[J]. 光谱学与光谱分析, 2015,35(5):1325-1330.

Merged Airborne LiDAR and Hyperspectral Data for Tree Species Classification in Puer's Mountainous Area

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views