Detection of buildings from a single airborne image using a Markov random field model

We propose an automated method for the detection of buildings from a single airborne color optical image using a dedicated Markov random field model, which describes both geometric and photometric attributes of the 3-D objects of interest. The paper presents the basic principles and some preliminary results of our approach.

[1]  Kim L. Boyer,et al.  Computer Perceptual Organization in Computer Vision , 1994, Series in Machine Perception and Artificial Intelligence.

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

[3]  Olof Henricsson,et al.  The Role of Color Attributes and Similarity Grouping in 3-D Building Reconstruction , 1998, Comput. Vis. Image Underst..

[4]  Taejung Kim,et al.  Development of a graph-based approach for building detection , 1999, Image Vis. Comput..

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

[6]  Silvano Di Zenzo,et al.  A note on the gradient of a multi-image , 1986, Comput. Vis. Graph. Image Process..

[7]  Sven Wachsmuth,et al.  Towards an integrated framework for contour-based grouping and object recognition using Markov random fields , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

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