The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Articles | Volume XL-8
28 Nov 2014
 | 28 Nov 2014

Land use land cover classification using local multiple pattern from very high resolution satellite imagery

R. Suresh Kumar and A. R. Mahesh Balaji

Keywords: LULC classification, Local Multiple patterns WorldView-2, Texture, Neural network classifier

Abstract. The recent development in satellite sensors provide images with very high spatial resolution that aids detailed mapping of Land Use Land Cover (LULC). But the heterogeneity in the landscapes often results in spectral variation within the same and spectral confusion among different LU/LC classes at finer spatial resolution. This leads to poor classification performances based on traditional spectral-based classification. Many studies have been addressed to improve this classification by incorporating texture information with multispectral images. Although different methods are available to extract textures from the satellite images, only a limited number of studies compared their performance in classification. The major problem with the existing texture measures is either scale/orientation/illumination variant (Haralick textures) or computationally difficult (Gabor textures) or less informative (Local binary pattern). This paper explores the use of texture information captured by Local Multiple Patterns (LMP) for LULC classification in a spectral-spatial classifier framework. LMP preserve more structural information and involves less computational efforts. Thus LMP is expected to be more promising for capturing spatial information from very high spatial resolution images. The proposed method is implemented with spectral bands and LMP derived from WorldView-2 multispectral imagery acquired for Madurai, India study area. The Multi-Layer-Perceptron neural network is used as a classifier. The proposed classification method is compared with LBP and conventional Maximum Likelihood Classification (MLC) separately. The classification results with 89.5% clarify the improvement offered by the LMP for LULC classification in comparison with the conventional approaches.