Improvement of Building's Roof Detection using Spectral-Spatial Information in Hyperspectral Images

Precise and update information of urban features are being increasingly demanded for various applications of modeling and planning of urban environment.Hyperspectral imagery is one of the most efficient tools to obtain the physical and spatial information in such a complex area. Indeed, the hyperspectral systems are able to collect the valuable image data, which can be used for detection, classification,identification and quantification of manmade or natural phenomena. Target detection technique is one of the reliable and efficient approach aims to extract information about class (es) of interest.In this paper, we propose an analytical framework to produce the accurate landcover map of building roof print from high spatial, hyperspectral imagery. The proposed approach consists of several steps. The first step attempts to reduce the undesirable noise and spectral correlation of hyperspectral images by using the MNF (Minimum Noise Fraction) algorithm. In second step, different spectral matching techniques are employed to obtain the target maps. Spatial information is also used to improve the detection accuracy. Finally, ANFIS (Adaptive Neuro-Fuzzy Inference System) method is used to fuse the detection results and arrive to land-cover map of building roofs’ materials. The results of quantitative and qualitative assessments of experiments show that the proposed algorithm can lead to acceptable accuracy for mapping of urban features.