| 光谱学与光谱分析 |
|
|
|
|
|
| Integration of Soft and Hard Classifications Using Linear Spectral Mixture Model and Support Vector Machines |
| HU Tan-gao, PAN Yao-zhong*, ZHANG Jin-shui, LI Ling-ling, LI Le |
| State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, China |
|
|
|
|
Abstract This paper presents a new soft and hard classification. By analyzing the target objects in the image distribution, and calculating the adaptive threshold automatically, the image is divided into three regions: pure regions, non-target objects regions and mixed regions. For pure regions and non-target objects regions, hard classification method (support vector machine) is used to quickly extract classified results; For mixed regions, soft classification method (selective endmember for linear spectral mixture model) is used to extract the abundance of target objects. Finally, it generates an integrated soft and hard classification map. In order to evaluate the accuracy of this new method, it is compared with SVM and LSMM using ALOS image. The RMSE value of new method is 0.203, and total accuracy is 95.48%. Both overall accuracies and RMSE show that integration of hard and soft classification has a higher accuracy than single hard or soft classification. Experimental results prove that the new method can effectively solve the problem of mixed pixels, and can obviously improve image classification accuracy.
|
|
Received: 2010-05-17
Accepted: 2010-08-30
|
|
|
|
Corresponding Authors:
PAN Yao-zhong
E-mail: pyz@bnu.edu.cn
|
|
[1] HU Tan-gao, ZHU Wen-quan, YANG Xiao-qiong, et al(胡潭高, 朱文泉, 阳小琼，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2009, 29(10): 2703.
[2] Das S K, Singh R. IEEE Transactions on Geoscience and Remote Sensing Letters, 2009, 6 (3): 453.
[3] Brandt Tso, Mather Paul M. Classification Methods for Remotely Sensed Data (Second Edition). London: CRC Press, 2009. 54.
[4] HE Ling-min, SHENG Zhang-quan, KONG Fan-sheng(何灵敏, 沈掌泉, 孔繁胜). Journal of Image and Graphics(中国图象图形学报), 2007, 12(4): 649.
[5] ZHANG Jin-shui, HE Chun-yang, PAN Yao-zhong(张锦水, 何春阳, 潘耀忠). Journal of Remote Sensing(遥感学报), 2006, 10(1): 49.
[6] LIU Yan-fang, LAN Ze-ying, LIU Yang(刘艳芳, 兰泽英, 刘 洋). Acta Geodaetica et Cartographica Sinica(测绘学报), 2009, 38(1): 82.
[7] ZHAO Ying-shi, et al(赵英时, 等). The Principles and Methods for Analysis and Application of Remote Sensing(遥感应用分析原理与方法). Beijing: Science Press(北京: 科学出版社), 2003. 328.
[8] Ichoku C, Karnieli A. Remote Sensing Reviews, 1996，13: 161.
[9] Shanmugam P, Ahn Y, Sanjeevi S. Ecological Modelling, 2006. 194: 379.
[10] WU Ke, ZHANG Liang-pei, LI Ping-xiang(吴 柯, 张良培, 李平湘). Journal of Remote Sensing(遥感学报), 2007, 11(1): 20.
[11] Wu T. Journal of Machine Learning Research, 2004, 5: 975.
[12] CHEN Xue-hong, CHEN Jin, YANG Wei(陈学泓, 陈 晋, 杨 伟). Journal of Remote Sensing(遥感学报), 2008, 12(5): 683.
[13] YANG Wei, CHEN Jin, Matsushita Bunkei(杨 伟, 陈 晋, 松下文经). Journal of Remote Sensing(遥感学报), 2008, 12(3): 455.
[14] Verhoeye J, Wulf R De. Remote Sensing of Environment, 2002, 79(1): 96.
[15] Chang C I, Plaza A. IEEE Geoscience and Remote Sensing Letters, 2006, 3(1): 63.
[16] Song Conghe, Dickinson Matthew B, Su Lihong. Remote Sensing of Environment, 2010, 114(5): 1099.
[17] Heinl M, Walde J, Tappeiner G. International Journal of Applied Earth Observation and Geoinformation, 2009, 11: 423.
|
| [1] |
LIANG Wei*, HAO Wen, LI Xiu-xiu, WANG Ying-hui, YANG Xiu-hong. Multispectral Image LabW2P Codec for Improvement of Both Colorimetric and Spectral Accuracy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(06): 1823-1828. |
| [2] |
HU Tan-gao, XU Jun-feng*, ZHANG Deng-rong, WANG Jie, ZHANG Yu-zhou . Hard and Soft Classification Method of Multi-Spectral Remote Sensing Image Based on Adaptive Thresholds [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33(04): 1038-1042. |
| [3] |
LIANG Liang, YANG Min-hua*, LI Ying-fang . Hyperspectral Remote Sensing Image Classification Based on ICA and SVM Algorithm [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2010, 30(10): 2724-2728. |
|
|
|
|
