An Object-Based Shadow Detection Method for Building Delineation in High-Resolution Satellite Images

In satellite image analysis, detection of shadow plays a critical role in the precise object detection applications. The size and intensity of shadow vary with solar illumination angle and miscellaneous building attributes, which may lead to their misclassification. Hence, there is a need for an accurate and robust shadow detection method. In this paper, an object-based shadow detection method is proposed to extract building shadows and subsequently used to delineate buildings from high-resolution satellite images. In the presented method, a shadow mask is generated at pixel level using a fused ratio map of a visible and a false colour image in HSI colour space. Then, the building shadow map is delineated by an automatic thresholding process on an object level. The results of a qualitative and quantitative analysis reveal the effectiveness and stability of the proposed approach for shadow detection and building delineation in high-resolution satellite images. These satellite images are taken at a different solar illumination angle and for different building attributes. Experimental results show that the proposed method achieves average improvement in F score by 21%, IOU (Intersection over Union) by 16%, and accuracy by 9% as compared to some of the state-of-the-art shadow detection methods.

[1]  Martin D. Levine,et al.  Removing shadows , 2005, Pattern Recognit. Lett..

[2]  Arzu Erener,et al.  Unsupervised building detection in complex urban environments from multispectral satellite imagery , 2012 .

[3]  Çaglar Senaras,et al.  Automated Detection of Arbitrarily Shaped Buildings in Complex Environments From Monocular VHR Optical Satellite Imagery , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Ashok Samal,et al.  Automatic Building Detection From High-Resolution Satellite Images Based on Morphology and Internal Gray Variance , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[5]  Michele Volpi,et al.  Semantic segmentation of urban scenes by learning local class interactions , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[6]  Liang Tang,et al.  Detection of and compensation for shadows in colored urban aerial images , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[7]  Vladimir Kolmogorov,et al.  "GrabCut": interactive foreground extraction using iterated graph cuts , 2004, ACM Trans. Graph..

[8]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[9]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[10]  Liangpei Zhang,et al.  A New Building Extraction Postprocessing Framework for High-Spatial-Resolution Remote-Sensing Imagery , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[11]  Mohammad Saadatseresht,et al.  A robust object-based shadow detection method for cloud-free high resolution satellite images over urban areas and water bodies , 2018, Advances in Space Research.

[12]  Ben Gorte,et al.  SHADOWDETECTION FROM VHR AERIAL IMAGES IN URBAN AREA BY USING 3DCITY MODELS AND A DECISION FUSION APPROACH , 2017 .

[13]  Emre Baseski,et al.  Multi-spectral False Color Shadow Detection , 2011, PIA.

[14]  Javier Gonzalez,et al.  Shadow detection in colour high‐resolution satellite images , 2008 .

[15]  Kuo-Liang Chung,et al.  Efficient Shadow Detection of Color Aerial Images Based on Successive Thresholding Scheme , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[17]  Ilkay Ulusoy,et al.  Building detection in high resolution remotely sensed images based on morphological operators , 2009, 2009 4th International Conference on Recent Advances in Space Technologies.

[18]  Robert A. Leathers,et al.  A novel method for illumination suppression in hyperspectral images , 2008, SPIE Defense + Commercial Sensing.

[19]  Saman Ghaffarian,et al.  Automatic building detection based on Purposive FastICA (PFICA) algorithm using monocular high resolution Google Earth images , 2014 .

[20]  Ali Ozgun Ok,et al.  Automated detection of buildings from single VHR multispectral images using shadow information and graph cuts , 2013 .

[21]  Xiaopeng Zhang,et al.  Robust Rooftop Extraction From Visible Band Images Using Higher Order CRF , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Andrea Manno-Kovacs,et al.  Building Detection From Monocular VHR Images by Integrated Urban Area Knowledge , 2015, IEEE Geoscience and Remote Sensing Letters.

[23]  Fabio Crosilla,et al.  Shadow detection and removal in RGB VHR images for land use unsupervised classification , 2016 .

[24]  Jiejie Zhu,et al.  Learning to recognize shadows in monochromatic natural images , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[25]  Franklin César Flores,et al.  Automatic shadow segmentation in aerial color images , 2003, 16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003).

[26]  R. Richter,et al.  De‐shadowing of satellite/airborne imagery , 2005 .

[27]  Dario F. G. de Azevedo,et al.  Near real-time shadow detection and removal in aerial motion imagery application , 2017, ISPRS Journal of Photogrammetry and Remote Sensing.

[28]  Vincent Mazet,et al.  Shape-Based Building Detection in Visible Band Images Using Shadow Information , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[29]  Fatos T. Yarman-Vural,et al.  Building Detection With Decision Fusion , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[30]  Jiangye Yuan,et al.  Building Extraction at Scale Using Convolutional Neural Network: Mapping of the United States , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[31]  X. Briottet,et al.  Shadow detection in very high spatial resolution aerial images: A comparative study , 2013 .

[32]  Stavros Stavrou,et al.  Satellite images analysis for shadow detection and building height estimation , 2016 .

[33]  Zhengyuan Mao,et al.  Building extraction from panchromatic high-resolution remotely sensed imagery based on potential histogram and neighborhood Total variation , 2016, Earth Science Informatics.

[34]  P. Dare.  Shadow Analysis in High-Resolution Satellite Imagery of Urban Areas , 2005 .

[35]  Deren Li,et al.  Development of a multi-scale object-based shadow detection method for high spatial resolution image , 2015 .

[36]  Xiaopeng Zhang,et al.  Building Extraction from Remotely Sensed Images by Integrating Saliency Cue , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[37]  Peter Reinartz,et al.  Adaptive Shadow Detection Using a Blackbody Radiator Model , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[38]  O. Aytekin,et al.  Automatic and unsupervised building extraction in complex urban environments from multi spectral satellite imagery , 2009, 2009 4th International Conference on Recent Advances in Space Technologies.

[39]  Makoto Nagao,et al.  Region extraction and shape analysis in aerial photographs , 1979 .

[40]  Fatos T. Yarman-Vural,et al.  A Self-Supervised Decision Fusion Framework for Building Detection , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[41]  Victor J. D. Tsai,et al.  A comparative study on shadow compensation of color aerial images in invariant color models , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[42]  B. Yang,et al.  Shadow detection from VHR aerial images in urban area by using 3 D city models and a decision fusion approach , 2018 .

[43]  Michal Shimoni,et al.  A shadow detection method for remote sensing images using VHR hyperspectral and LIDAR data , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.