Automatic building detection in aerial and satellite images

Automatic creation of 3D urban city maps could be an innovative way for providing geometric data for varieties of applications such as civilian emergency situations, natural disaster management, military situations, and urban planning. Reliable and consistent extraction of quantitative information from remotely sensed imagery is crucial to the success of any of the above applications. This paper describes the development of an automated roof detection system from single monocular electro-optic satellite imagery. The system employs a fresh approach in which each input image is segmented at several levels. The border line definition of such segments combined with line segments detected on the original image are used to generate a set of quadrilateral rooftop hypotheses. For each hypothesis a probability score is computed that represents the evidence of true building according to the image gradient field and line segment definitions. The presented results demonstrate that the system is capable of detecting small gabled residential rooftops with variant light reflection properties with high positional accuracies.

[1]  Ramakant Nevatia,et al.  Building Detection and Description from a Single Intensity Image , 1998, Comput. Vis. Image Underst..

[2]  R. Bruce Irvin,et al.  Methods for exploiting the relationship between buildings and their shadows in aerial imagery , 1989, IEEE Trans. Syst. Man Cybern..

[3]  Allen R. Hanson,et al.  Recognition and reconstruction of buildings from multiple aerial images , 2003, Comput. Vis. Image Underst..

[4]  Clive S. Fraser,et al.  Processing of Ikonos imagery for submetre 3D positioning and building extraction , 2002 .

[5]  Allen R. Hanson,et al.  Extracting Straight Lines , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Rama Chellappa,et al.  Delineating buildings by grouping lines with MRFs , 1996, IEEE Trans. Image Process..

[7]  Jefferey A. Shufelt,et al.  Performance Evaluation and Analysis of Monocular Building Extraction From Aerial Imagery , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Thomas H. Kolbe,et al.  Building Reconstruction: The Dilemma of Generic Versus Specific Models , 2001, Künstliche Intell..

[9]  Helmut Mayer,et al.  Automatic Object Extraction from Aerial Imagery - A Survey Focusing on Buildings , 1999, Comput. Vis. Image Underst..

[10]  Parvaneh Saeedi,et al.  Automatic building detection and 3D shape recovery from single monocular electro-optic imagery , 2007, SPIE Defense + Commercial Sensing.

[11]  J. Peng,et al.  Model and context‐driven building extraction in dense urban aerial images , 2005 .

[12]  Wolfgang Förstner,et al.  Towards automatic building extraction from high-resolution digital elevation models , 1995 .

[13]  H. D. Cheng,et al.  Thresholding using two-dimensional histogram and fuzzy entropy principle , 2000, IEEE Trans. Image Process..

[14]  Ansgar Brunn,et al.  Hierarchical Bayesian nets for building extraction using dense digital surface models , 1998 .

[15]  T. H. Kolbe,et al.  Integration of 2D and 3D reasoning for building reconstruction using a generic hierarchical model , 1997 .

[16]  Larry S. Davis,et al.  Hierarchical generalized Hough transforms and line-segment based generalized H ugh transforms , 1982, Pattern Recognit..

[17]  G. Vosselman,et al.  3D RECONSTRUCTION OF BUILDING MODELS , 2000 .

[18]  Luc Van Gool,et al.  A Probabilistic Approach to Building Roof Reconstruction Using Semantic Labelling , 2002, DAGM-Symposium.

[19]  G. Sohn,et al.  Extraction of buildings from high-resolution satellite data and airborne Lidar , 2000 .