Land Use Classification of Gaofen‐2 Remote Sensing Image Based on Maximum Likelihood Method

Dan Wu ； Tingting Meng

《World Scientific Research Journal》 7卷9期 (2021/09) Pp. 345-350

https://doi.org/10.6911/WSRJ.202109_7(9).0047

摘要

Using the gaofEN‐2 remote sensing image as the basic experimental data, the real surface information was restored through the pre‐processing operation of the image, and the high‐precision experimental data was obtained. Based on the image spectral information, the normalized vegetation index (NDVI) and the texture information, a composite image containing the original image, NDVI and all the features of the image was formed, and the maximum likelihood method was used to study the land use classification of high resolution remote sensing image. The research results show that the maximum likelihood method is used in the original image when land classification, the classification accuracy is not high, confusion between feature is more, but used to fusion the texture information, vegetation index and the spectral information of multiple features of image fusion, its obvious improved its classification accuracy, overall classification accuracy reached 87.4%, the Kappa coefficient is 0.83.

關鍵字

Maximum likelihood method ； Land use classification ； Precision evaluation

參考文獻

Chen Y, Su W, Li J, et al. Hierarchical object oriented classification using very high resolution imagery and LIDAR data over urban areas[J]. Advances in Space Research, 2009, 43(7):1101-1110.

Oza N C , Tumer K . Classifier ensembles: Select real-world applications[J]. Information Fusion, 9(1) (2008),4-20.

Zhao Jing, Wang Chongchang, Wang Jiahai, Chen Yanling. Remote sensing image classification based on cloud theory. Engineering of Surveying and Mapping,23(12) (2014),21-24+30.]

Du Guoming, KUANG Wenhui, Meng Fanhao, et al. Spatial and temporal patterns and driving factors of land use/cover change in Brazil. Progress in Geography,34(1) (2015),73-82.]

Wu Jiansheng, Pan Kuanyi, Peng Jian, et al. Land use classification of Remote sensing image based on QUEST decision Tree: A case study of Lijiang City in Yunnan Province [J]. Geographical Research,31(11) (2012),1973-1980.]