Bright line detection in COSMO-SkyMed SAR images of urban areas

Bright lines are a characteristic feature of synthetic aperture radar (SAR) amplitude images of urban areas, and are commonly associated with man-made structures. In order to aid in the development of SAR applications using these features, an automated approach to bright line detection is proposed, based on scale-space ridge detection at a single scale, and using a naïve Bayesian classification step to select the ridge points corresponding to bright lines. The effectiveness of the technique is demonstrated by applying it to a COSMO-SkyMed image of L'Aquila, Italy.

[1]  David D. Lewis,et al.  Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval , 1998, ECML.

[2]  H. Siegfried Stiehl,et al.  A Generalized Discrete Scale-Space Formulation for 2-D and 3-D Signals , 2003, Scale-Space.

[3]  Henri Maître,et al.  A new statistical model for Markovian classification of urban areas in high-resolution SAR images , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Uwe Stilla,et al.  Building feature extraction via a deterministic approach: application to real high resolution SAR images , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[5]  Tony Lindeberg,et al.  Edge Detection and Ridge Detection with Automatic Scale Selection , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  David H. Eberly,et al.  Ridges for image analysis , 1994, Journal of Mathematical Imaging and Vision.

[7]  Giorgio Franceschetti,et al.  A canonical problem in electromagnetic backscattering from buildings , 2002, IEEE Trans. Geosci. Remote. Sens..

[8]  Antonio Iodice,et al.  Height Retrieval of Isolated Buildings From Single High-Resolution SAR Images , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Jean-Francois Mangin,et al.  Detection of linear features in SAR images: application to road network extraction , 1998, IEEE Trans. Geosci. Remote. Sens..

[10]  Paolo Gamba,et al.  Improving urban road extraction in high-resolution images exploiting directional filtering, perceptual grouping, and simple topological concepts , 2006, IEEE Geoscience and Remote Sensing Letters.

[11]  Antonio Iodice,et al.  Assessment of TerraSAR-X Products with a New Feature Extraction Application: Monitoring of Cylindrical Tanks , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[13]  W. Clem Karl,et al.  Line detection in images through regularized hough transform , 2006, IEEE Transactions on Image Processing.

[14]  Corina da Costa Freitas,et al.  A model for extremely heterogeneous clutter , 1997, IEEE Trans. Geosci. Remote. Sens..