Adaptive Shadow Detection Using a Blackbody Radiator Model

The application potential of remotely sensed optical imagery is boosted through the increase in spatial resolution, and new analysis, interpretation, classification, and change detection methods are developed. Together with all the advantages, shadows are more present in such images, particularly in urban areas. This may lead to errors during data processing. The task of automatic shadow detection is still a current research topic. Since image acquisition is influenced by many factors such as sensor type, sun elevation and acquisition time, geographical coordinates of the scene, conditions and contents of the atmosphere, etc., the acquired imagery has highly varying intensity and spectral characteristics. The variance of these characteristics often leads to errors, using standard shadow detection methods. Moreover, for some scenes, these methods are inapplicable. In this paper, we present an alternative robust method for shadow detection. The method is based on the physical properties of a blackbody radiator. Instead of static methods, this method adaptively calculates the parameters for a particular scene and allows one to work with many different sensors and images obtained with different illumination conditions. Experimental assessment illustrates significant improvement for shadow detection on typical multispectral sensors in comparison to other shadow detection methods. Examples, as well as quantitative assessment of the results, are presented for Landsat-7 Enhanced Thematic Mapper Plus, IKONOS, WorldView-2, and the German Aerospace Center (DLR) 3K Camera airborne system.

[1]  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.

[2]  Touradj Ebrahimi,et al.  Cast shadow segmentation using invariant color features , 2004, Comput. Vis. Image Underst..

[3]  Tai-Pang Wu,et al.  A Bayesian approach for shadow extraction from a single image , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[4]  Edward H. Adelson,et al.  Recovering intrinsic images from a single image , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Shugen Wang,et al.  SHADOW DETECTION OF URBAN COLOR AERIAL IMAGES BASED ON PARTIAL DIFFERENTIAL EQUATIONS , 2008 .

[6]  Theo Gevers,et al.  Classifying color edges in video into shadow-geometry, highlight, or material transitions , 2003, IEEE Trans. Multim..

[7]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[8]  Mohan M. Trivedi,et al.  Detecting Moving Shadows: Algorithms and Evaluation , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  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.

[10]  Jiandong Tian,et al.  Tricolor Attenuation Model for Shadow Detection , 2009, IEEE Transactions on Image Processing.

[11]  Mark S. Drew,et al.  Removing Shadows from Images , 2002, ECCV.

[12]  Hao Jiang,et al.  Tracking objects with shadows , 2003, IS&T/SPIE Electronic Imaging.

[13]  Takis Kasparis,et al.  Correction: Shorter, N. et al. Automatic Vegetation Identification and Building Detection from A Single Nadir Aerial Image. Remote Sens. 2009, 1, 731-757 , 2010 .

[14]  G D Finlayson,et al.  Color constancy at a pixel. , 2001, Journal of the Optical Society of America. A, Optics, image science, and vision.

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

[16]  D. Knill,et al.  Geometry of shadows. , 1997, Journal of the Optical Society of America. A, Optics, image science, and vision.

[17]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[18]  Peter Reinartz,et al.  ARGOS - Near Real Time Airborne Monitoring System for Disaster and Traffic Applications , 2010 .

[19]  Sayan Chakraborti.  Verification of the Rayleigh scattering cross section , 2007 .

[20]  Mark S. Drew,et al.  Removing Shadows From Images using Retinex , 2002, CIC.

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

[22]  J. Marchant,et al.  Spectral invariance under daylight illumination changes. , 2002, Journal of the Optical Society of America. A, Optics, image science, and vision.

[23]  K. Ikeuchi,et al.  Color constancy from blackbody illumination. , 2007, Journal of the Optical Society of America. A, Optics, image science, and vision.

[24]  Takis Kasparis,et al.  Automatic Vegetation Identification and Building Detection from a Single Nadir Aerial Image , 2009, Remote. Sens..

[25]  Irwin G. Priest,et al.  The Colorimetry and Photometry of Daylight and Incandescent Illuminants by the Method of Rotatory Dispersion , 1923 .

[26]  Zhongfei Zhang,et al.  Hierarchical shadow detection for color aerial images , 2006, Comput. Vis. Image Underst..