Semantic segmentation of multispectral satellite images for land use analysis based on embedded information

Abstract

Semantic segmentation of satellite and aerial imageries has many applications including automated map making, land use analysis, urban planning and so on. This paper presents a special type of semantic segmentation. First, the boundaries of natural objects such as agricultural fields are detected and approximated by polygons. Second, texture recognition based on Digital Wavelet Transform (DWT) and Local Binary Patterns (LBPs) is implemented using a limited textural dictionary. The obtained information is embedded using DWT and Arnold’s transform. Such watermarked images can be publicly available, but semantic information after extraction and inpainting is provided only to the authorized users. Such semantic labelling is very useful in land use analysis of rural territories.