Building detection in high resolution remotely sensed images based on morphological operators

Abstract

Information retrieval from high resolution remotely sensed images is a challenging issue due to the inherent complexity and the curse of dimensionality of data under study. This paper presents an approach for building detection in high resolution remotely sensed images incorporating structural information of spatial data into spectral information. The proposed approach moves along eliminating irrelevant areas in a hierarchical manner. As a first step, pan-sharpened image is obtained from multi-spectral and panchromatic bands of Quickbird image. Vegetation and shadow regions are masked out by using Normalized Difference Vegetation Index (NDVI) and ratio of hue to intensity in YIQ model, respectively. Then, panchromatic band is filtered by mean shift filtering for smoothing structures while preserving the discontinuities near boundaries. Next, differential morphological profile (DMP) is calculated for each pixel and a relative measure of structure size is recorded as the first maximum value of DMP which generates a labeled image representing connected components according to sizes of structures. However, there appear some connected components which are irrelevant to buildings in shape. To eliminate those connected components, their skeletons are obtained via thinning to get a relative length measure along with measuring areas of connected components. These measures are compared to a threshold individually, which provides a cue for a candidate building structure.

Extracting Building Unit Number Information from High Resolution SAR Images with Regression Model

“…These bright features are important characteristic to indicate the presence of buildings [7]. So detecting buildings by thresholding the SAR intensity data is reasonable.…”

Detecting and assessment of tsunami building damage using high‐resolution satellite images with GIS data

“…The DMP was developed by feature detectors attempts to identify urban structures and it is constructed using morphological opening and closing by reconstruction operators IJDRBE 4,2 (Aytekin et al, 2009;Destival, 1986;Heijmans and Roerdink, 1998;Laporterie et al, 2001;Parape and Tamura, 2011). Mathematical morphology employs a set of image operators to extract and analyze image components based on shape and size of quasi-homogeneous regions in the image, has been used to a wide area of image processing field such as pre-processing, noise filtering, shape and target detection, segmentation, decomposition and pattern recognition (Pesaresi and Benediktsson, 2001;Soille, 2003;Shackelford and Davis, 2004).…”

Automatic reconstruction of regular buildings using a shape‐based balloon snake model

“…These methods differ according to the nature of the input data or the initial knowledge applied in the modelling. Considering the nature of the input data, building extraction methods have been developed for aerial and satellite images (Baillard and Zisserman, ; Aytekin et al., ) or the integration of image information and digital surface models (DSMs) (Paparoditis et al., ; Chen et al., ). From the applied initial knowledge approach, methods are based on using geometric constraints of building shapes (Haala and Brenner, ) and 3D building models (Scholze et al., ).…”