Adaptive Threshold-Based Shadow Masking for Across-Date Settlement Classification of Panchromatic QuickBird Images

Abstract

Abstract-Multitemporal land-use analysis is becoming increasingly important for the effective management of earth resources. Despite that, consistent differences in the viewingand illumination geometry in satellite-borne imagery introduce some issues in the creation of land-use classification maps. The focus of this study is settlement classification with high-resolution panchromatic acquisitions, using texture features to distinguish between settlement classes. The important multitemporal variance component of shadow is effectively removed before feature determination, which allows for minimum-supervision acrossdate classification. Shadow detection based on local adaptive thresholding is employed and experimentally shown to outperform existing fixed threshold shadow detectors in increasing settlement classification accuracy. Both same and across-date settlement accuracies are significantly improved with shadow masking during feature calculation. A statistical study was performed and found to support the hypothesis that the increased accuracy is due to shadow masking specifically.Index Terms-Image texture analysis, feature extraction, urban areas, remote sensing.

An Effective Approach of Shadow Detection and Removal using Edge Detection and Bilateral Filtering

“…Song et al [5], Luus et al [9], Kuo et al [10] proposed a new Threshold based scheme for the Shadow Detection. Predefined entrance height based on bimodal histogram used to conclude silhouette and non outline pixels.…”

A survey on shadow detection and removal based on single light source

“…Several relative algorithm and the techniques which are implemented earlier and also the advantages and disadvantages of each algorithm is described briefly. According to the survey of the earlier algorithms, it finds that the current algorithms have more advantages [7]provides adaptive threshold hold based shadow masking in which threshold based method is used which is based on bimodal histogram used to determine shadow and non-shadow pixels. The advantage of this method is that it is simple and fast, but the disadvantage is that it requires post-processing as results might be incoherent or blurred and may have holes, noise.…”

Object-oriented detection of building shadow in TripleSat-2 remote sensing imagery

“…Some examples of the method are simple histogram thresholding, invariant color model, and object-oriented algorithm. The used features include the image spectrum, 13,25,26 texture, 11,[27][28][29][30] edge, [31][32][33][34][35] spatial context, 14,36,37 etc. Typical spectral features include the C3 component; 38 the difference between intensity and saturation of the hue, saturation, and intensity (HSI) model; 39 the normalized index; 40 the hue and brightness in color spaces such as HSI, hue, saturation, and value (HSV), hue, chroma, and value (HCV), luminance, hue, and saturation (YIQ), and luma, blue-difference chroma, and red-difference chroma (YCbCr); 40,41 the CIELCh color space.…”

“…Typical spectral features include the C3 component; 38 the difference between intensity and saturation of the hue, saturation, and intensity (HSI) model; 39 the normalized index; 40 the hue and brightness in color spaces such as HSI, hue, saturation, and value (HSV), hue, chroma, and value (HCV), luminance, hue, and saturation (YIQ), and luma, blue-difference chroma, and red-difference chroma (YCbCr); 40,41 the CIELCh color space. 42 Texture features include the gray level co-occurrence matrix, 27,29 local binary pattern, 29 edge, 28 and Gabor filter. 30 Edge features include the ratio edge 32 and weighted edge gradient ratio.…”