为寻求一种有效的提高多源遥感数据土地覆被分类制图精度的方法，探讨了融合HJ1B和ALOS/PALSAR图像进行遥感图像分类制图的方法。在对光学图像HJ1B和雷达遥感数据ALOS/PALSAR进行离散小波融合的基础上，应用分类决策树CART(Classification and Regression Tree)算法对融合的图像进行了土地覆被分类制图，并将其分类结果与支持向量机SVM（Support Vector Machine）分类结果进行对比。研究结果表明：将光学和雷达图像数据进行离散小波融合，采用分类决策树CART和支持向量机SVM进行图像分类，CART的分类精度要优于SVM的结果。可见，在光学图像HJ1B和雷达数据ALOS/PALSAR融合的基础上，应用CART能有效进行地物识别，提高图像的分类精度。
Abstract
In order to increase the accuracy of the land use and land cover (LULC) classification via multisource remote sensing data, we explored an effective algorithm by fusion of HJ1B images from optical sensors and ALOS/PALSAR data from radar remote sensing. In the process of fusion, the discrete wavelet transform (DWT) was utilized. The landcover classification mapping was performed by using the classification and regression tree (CART) approach. The classification result by CRT approach was compared with that by support vector machine (SVM) approach. The results show that: 1) through fusing HJ1B optical images with ALOS/PALSAR radar data, we obtain an overall Kappa coefficient (0.826 9) and total accuracy(85.60 %) by CRT approach, while by SVM approach the value is 0.816 7 and 84.82 %, respectively; 2) in terms of classification accuracy, CRT approach is superior to SVM approach; 3) by means of fusing optical images with radar data , we can effectively carry out object recognition and improve classification accuracy through applying CART approach.
关键词
环境卫星 /
雷达图像 /
图像融合 /
分类决策树 /
支持向量机 /
图像分类
Key words
environmental satellite /
radar image /
image fusion /
CART /
SVM /
image classification
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] SELLERS P J, MEESON B W, HALL F G, et al. Remote Sensing of the Land Surface for Studies of Global Change: Models, Algorithms, and Experiments [J] . Remote Sensing of Environment, 1995, 51(1): 3-26.
[2] 于秀兰,钱国蕙. TM和SAR遥感图像的不同层次融合分类比较[J] .遥感技术与应用,1999, 14(3): 38-43. (YU Xiu-lan, QIAN Guo-hui. Comparison of TM and SAR Remote Sensing Image Different Level Fusion Classification [J] . Remote Sensing Technology and Application, 1999, 14(3): 38-43.(in Chinese) )
[3] KIEREIN-YOUNG K S. The Integration of Optical and Radar Data to Characterize Mineralogy and Morphology of Surfaces in Death Valley, California[J] . International Journal of Remote Sensing, 1997, 18(7): 1517-1541.
[4] LARRAAGA A, LVAREZ-MOZOS J, ALBIZUA L. Crop Classification in Rain-fed and Irrigated Agricultural Areas Using Landsat TM and ALOS/PALSAR Data[J] . Canadian Journal of Remote Sensing, 2011, 37(1): 157-120.
[5] WALKER W S, STICKLER C M, KELLNDORFER J M, et al. Large-area Classification and Mapping of Forest and Land Cover in the Brazilian Amazon: A Comparative Analysis of ALOS/PALSAR and Landsat Data Sources[J] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2010, 3(4): 594-604.
[6] FRIEDL M A, BRODLEY C E. Decision Tree Classification of Land Cover from Remotely Sensed Data[J] . Remote Sensing of Environment, 1997, 61(3): 399-409.
[7] OTUKEI J R, BLASCHKE T. Land Cover Change Assessment Decision Trees, Support Vector Machines and Maximum Likelihood Classification Algorithms[J] . International Journal of Applied Earth Observation and Geoinformation, 2010, 12(Supp.1):27-31.
[8] BRUCE L M, KOGER C H, LI J. Dimensionality Reduction of Hyperspectral Data Using Discrete Wavelet Transform Feature Extraction[J] . IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(10): 2331-2338.
[9] RANCHIN, T, WALD L. Fusion of High Spatial and Spectral Resolution Images: The ARSIS Concept and Its Implementation[J] . Photogrammetric Engineering and Remote Sensing, 2000, 66: 49-61.
[10] ALPARONE L S, BARONTI S, GARZELLI A, et al . Landsat ETM+ and SAR Image Fusion Based on Generalized Intensity Modulation[J] . IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(12): 2832-2839.
[11] CHIBANI Y. Selective Synthetic Aperture Radar and Panchromatic Image Fusion by Using the à Trous Wavelet Decomposition[J] . EURASIP Journal on Applied Signal Processing, 2005, 14: 2207-2214.
[12] CHIBANI Y. Additive Integration of SAR Features into Multispectral SPOT Images by Means of the àTrous Wavelet Decomposition[J] . ISPRS Journal of Photogrammetric & Remote Sensing, 2006, 60: 306-314.
[13] ZHOU Z S,LEHMANN E,WU X, et al . Terrain Slope Correction and Precise Registration of SAR Data for Forest Mapping and Monitoring[C] // International Symposium for Remote Sensing of the Environment, Sydney, Australia, 2011:1–4.
[14] FRIEDL M A, BRODLEY C E, STRAHLER A H. Maximizing Land Cover Classification Accuracies Produced by Decision Trees at Continental to Global Scales[J] . IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(2): 969-977.
[15] 陈云,戴锦芳,李俊杰. 基于影像多种特征的CART决策树分类方法及其应用[J] . 地理与地理信息科学,2008, 24(2): 33-36. (CHEN Yun, DAI Jin-fang, LI Jun-jie. CART-Based Decision Tree Classifier Using Multi-feature of Image and Its Application[J] . Geography and Geo-Information Science, 2008, 24(2): 33-36. (in Chinese) )
[16] 赵萍,傅云飞,郑刘根,等. 基于分类回归树分析的遥感影像土地利用/覆被分类研究[J] . 遥感学报,2005, 9(6): 708-715. (ZHAO Ping, FU Yun-fei, ZHENG Liu-gen, et al . CART-based Land Use and Cover Classification of Remote Sensing Images[J] . Journal of Remote Sensing, 2005, 9(6): 708-715.(in Chinese))
基金
国家自然科学基金项目(41261089,41201393);宁夏自然科学基金项目(NZ12146)
PDF(1270 KB)
