A Bottom-Up/Top-Down Hybrid Algorithm for Model-Based Building Detection in Single Very High Resolution SAR Image

Building detection from high-resolution synthetic aperture radar (SAR) image is an essential issue for many SAR applications in urban areas. In this letter, we propose a novel bottom-up/top-down hybrid algorithm for model-based building detection from single very high resolution (VHR) SAR image. First, the building model is generated and described by a set of extraction criteria, which restrict the spatial layout of a building and its primitive features. Specifically, the rectangles of different intensity levels are extracted from the SAR image as primitive features. Then the bottom-up stage proposes building candidates composed by extracted rectangles, and the top-down step predicts building candidates composed by weak features omitted in the primitive extraction. After that, all candidates are verified through false alarm detection. Under this framework, the detection performances can be greatly improved especially in dense built-up areas. The effectiveness of the proposed method is verified by experimental results obtained from real VHR SAR images.

[1]  Lorenzo Bruzzone,et al.  Automatic Detection and Reconstruction of Building Radar Footprints From Single VHR SAR Images , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Ya-Qiu Jin,et al.  Automatic Reconstruction of Building Objects From Multiaspect Meter-Resolution SAR Images , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[3]  Hong Sun,et al.  Urban building density detection using high resolution SAR imagery , 2011, 2011 Joint Urban Remote Sensing Event.

[4]  Paolo Gamba,et al.  Detection and extraction of buildings from interferometric SAR data , 1999, IEEE Trans. Geosci. Remote. Sens..

[5]  Uwe Soergel,et al.  Building Recognition From Multi-Aspect High-Resolution InSAR Data in Urban Areas , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Timo Balz,et al.  Building L-shape footprint extraction from high resolution SAR image , 2011, 2011 Joint Urban Remote Sensing Event.

[7]  Lei Wang,et al.  A knowledge-based 3-D building reconstruction from single very high resolution SAR images , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[8]  Lei Lin,et al.  Building Height Estimation from High Resolution SAR Imagery via Model-Based Geometrical Structure Prediction , 2015 .

[9]  Hélène Oriot,et al.  Rectangular building extraction from stereoscopic airborne Radar images , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Uwe Soergel,et al.  Perceptual grouping for automatic detection of man-made structures in high-resolution SAR data , 2006, Pattern Recognit. Lett..

[11]  Olaf Hellwich,et al.  Building Extraction from Polarimetric SAR Data using Mean Shift and Conditional Random Fields , 2008 .

[12]  Yongfeng Cao,et al.  Detecting the number of buildings in a single high-resolution SAR image , 2014 .

[13]  Nazzareno Pierdicca,et al.  Identification of building double-bounces feature in very high resoultion SAR data for earthquake damage mapping , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[14]  Chongzhao Han,et al.  Building detection from high-resolution PolSAR data at the rectangle level by combining region and edge information , 2010, Pattern Recognit. Lett..

[15]  Xiaoxiang Zhu,et al.  Robust Reconstruction of Building Facades for Large Areas Using Spaceborne TomoSAR Point Clouds , 2015, IEEE Transactions on Geoscience and Remote Sensing.