Mapping of coastal cities using Optimized Spectral-Spatial features based multi-scale superpixel classification

Abstract

The high interior heterogeneity of land surface covers in high-resolution image of coastal cities makes classification challenging. To meet this challenge, a Multi-Scale Superpixels-based Classification method using Optimized Spectral-Spatial features, denoted as OSS-MSSC, is proposed in this paper. In the proposed method, the multi-scale superpixels are firstly generated to capture the local spatial structures of the ground objects with various sizes. Then, the normalized difference vegetation index and extend multi-attribute profiles are introduced to extract the spectral-spatial features from the multi-spectral bands of the image. To reduce the redundancy of the spectral-spatial features, the crossover-based search algorithm is utilized for feature optimization. The pre-classification results at each single scale are, therefore, obtained based on the optimized spectral-spatial features and random forest classifier. Finally, the ultimate classification is generated via the majority voting of those pre-classification results in each scale. Experimental results on the Gaofen-2 image of Qingdao and WorldView-2 image of Hong Kong, China confirmed the effectiveness of the proposed method. The experiments verify that the OSS-MSSC method not only works effectively on the homogeneous regions, but also is able to preserve the small local spatial structures in the high-resolution remote sensing images of coastal cities.