Rectangular building extraction from stereoscopic airborne Radar images

From the recent availability of images recorded by synthetic aperture radar (SAR) airborne systems, automatic results of digital elevation models (DEMs) on urban structures have been published lately. This paper deals with automatic extraction of three-dimensional (3-D) buildings from stereoscopic high-resolution images recorded by the SAR airborne RAMSES sensor from the French Aerospace Research Center (ONERA). On these images, roofs are not very textured whereas typical strong L-shaped echoes are visible. These returns generally result from dihedral corners between ground and structures. They provide a part of the building footprints and the ground altitude, but not the building heights. Thus, we present an adapted processing scheme in two steps. First is stereoscopic structure extraction from L-shaped echoes. Buildings are detected on each image using the Hough transform. Then they are recognized during a stereoscopic refinement stage based on a criterion optimization. Second, is height measurement. As most of previous extracted footprints indicate the ground altitude, building heights are found by monoscopic and stereoscopic measures. Between structures, ground altitudes are obtained by a dense matching process. Experiments are performed on images representing an industrial area. Results are compared with a ground truth. Advantages and limitations of the method are brought out.

[1]  Alfred M. Bruckstein,et al.  Antialiasing the Hough transform , 1991, CVGIP Graph. Model. Image Process..

[2]  U. Sörgel,et al.  3D-VISUALIZATION OF INTERFEROMETRIC SAR DATA , 2000 .

[3]  E. Jakeman,et al.  A model for non-Rayleigh sea echo , 1976 .

[4]  Mihai Datcu,et al.  Stochastic geometrical modeling for built-up area understanding from a single SAR intensity image with meter resolution , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Uwe Soergel,et al.  Grouping salient scatterers in InSAR data for recognition of industrial buildings , 2002, Object recognition supported by user interaction for service robots.

[6]  R. Bolter.  Reconstruction of man-made objects from high resolution SAR images , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[7]  G L Laprade,et al.  ELEVATIONS FROM RADAR IMAGERY , 1969 .

[8]  J. R. Fellerhoff,et al.  Elevation correction and building extraction from interferometric SAR imagery , 1996, IGARSS '96. 1996 International Geoscience and Remote Sensing Symposium.

[9]  Helene Oriot,et al.  Potentiality of High-Resolution SAR Images for Radargrammetric Applications , 2000 .

[10]  Franz Leberl,et al.  Radargrammetric image processing , 1990 .

[11]  O DudaRichard,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972 .

[12]  Richard Barakat,et al.  Weak-scatterer generalization of the K-density function with application to laser scattering in atmospheric turbulence , 1986 .

[13]  Yves Delignon,et al.  Etude statistique d'images SAR de la surface de la mer , 1991 .

[14]  Martin Kirscht,et al.  3D Reconstruction of Buildings and Vegetation from Synthetic Aperture Radar (SAR) Images , 1998, MVA.

[15]  H. Laur.  Analyse d'images radar en teledetection : discriminateurs radiometriques et texturaux , 1989 .

[16]  Stuart E. Dreyfus,et al.  Applied Dynamic Programming , 1965 .

[17]  Franz Leberl,et al.  Detection and reconstruction of human scale features from high resolution interferometric SAR data , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[18]  Jean-Marc Le Caillec,et al.  Unsupervised classification of radar images based on hidden Markov models and generalized mixture estimation , 2000, SPIE Remote Sensing.

[19]  Florence Tupin,et al.  Detection of building outlines based on the fusion of SAR and optical features , 2003 .

[20]  Frans C. A. Groen,et al.  Discretization errors in the Hough transform , 1981, Pattern Recognit..

[21]  S. F. George,et al.  Detection of Targets in Non-Gaussian Sea Clutter , 1970, IEEE Transactions on Aerospace and Electronic Systems.

[22]  Rodenas Navas,et al.  Detection et caracterisation des signatures d'ondes internes de la surface de l'ocean dans les images ros utilisation des methodes d'analyse en ondelettes , 1999 .

[23]  Pascale Dubois-Fernandez,et al.  The ONERA RAMSES SAR system , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[24]  A. Lopes,et al.  A statistical and geometrical edge detector for SAR images , 1988 .

[25]  V. F. Leavers,et al.  Which Hough transform , 1993 .

[26]  Elisabeth Simonetto.  Extraction 3-D de structures industrielles sur des images RAMSES haute résolution par radargrammétrie. (3-D extraction of industrial structures from high-resolution RAMSES images by radargrammetry) , 2002 .

[27]  Jean-Marie Nicolas,et al.  Accuracy of fisher distributions and log-moment estimation to describe amplitude distributions of high resolution SAR images over urban areas , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

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

[29]  Erkki Oja,et al.  A new curve detection method: Randomized Hough transform (RHT) , 1990, Pattern Recognit. Lett..

[30]  Philippe Réfrégier,et al.  Optimal snake segmentation of target and background with independent Gamma density probabilities, application to speckled and preprocessed images , 1997 .

[31]  Wojciech Pieczynski,et al.  Estimation of Generalized Multisensor Hidden Markov Chains and Unsupervised Image Segmentation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Helene Oriot,et al.  Extraction of industrial buildings from stereoscopic airborne radar images , 2002, SPIE Remote Sensing.

[33]  Florence Tupin.  Reconnaissance des formes et analyse de scenes en imagerie radar a ouverture synthetique , 1997 .