RECONSTRUCTION OF 3 D LINEAR PRIMITIVES FROM MULTIPLE VIEWS FOR URBAN AREAS MODELISATION

In this paper, a new method for reconstruction of 3D segments from multiple images in urban areas environment is presented. Compared to previous algorithms, this one performs the matching of 2D segments in the Object Space through a sweep plane technique, thus avoiding the combinatorial exploration of all possible correspondences and handling images in a symmetric way. Furthermore, a method for reconstruction of 3D line from 2D lines, which takes into account the uncertainty on the parameters that define the 2D lines is also presented. It enables to get normalized residuals, which is used as a geometric criterion usable whatever the number of images is, to assess or reject potential correspondences. This criterion along with an unicity criterion is at the heart of the algorithm to prune the set of possible correspondences and to keep only reliable matches. Promising results are presented on simulated and real data. They show the ability of the algorithm to overcome detection errors in images and its robustness to occlusions in some images.

[1]  Patrick Gros,et al.  Using Local Planar Geometric Invariants to Match and Model Images of Line Segments , 1998, Comput. Vis. Image Underst..

[2]  Armin B. Cremers,et al.  Extracting Buildings from Aerial Images Using Hierarchical Aggregation in 2D and 3D , 1998, Comput. Vis. Image Underst..

[3]  Gang Xu,et al.  Epipolar Geometry in Stereo, Motion and Object Recognition , 1996, Computational Imaging and Vision.

[4]  Robert T. Collins,et al.  A space-sweep approach to true multi-image matching , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Frank Ade,et al.  A rule-based system for house reconstruction from aerial images , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[6]  Olivier D. Faugeras,et al.  A New Characterization of the Trifocal Tensor , 1998, ECCV.

[7]  E. Baltsavias,et al.  Automatic Extraction of Man-Made Objects from Aerial and Space Images (II) , 1995 .

[8]  Andrew Zisserman,et al.  Robust parameterization and computation of the trifocal tensor , 1997, Image Vis. Comput..

[9]  Cordelia Schmid,et al.  Automatic line matching across views , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Cordelia Schmid,et al.  AUTOMATIC LINE MATCHING AND 3D RECONSTRUCTION OF BUILDINGS FROM MULTIPLE VIEWS , 1999 .

[11]  Nicholas Ayache.  Vision Stéréoscopique et Perception Multisensorielle: Application à la robotique mobile , 1989 .

[12]  Amnon Shashua,et al.  Trilinearity in Visual Recognition by Alignment , 1994, ECCV.

[13]  Rachid Deriche,et al.  Using Canny's criteria to derive a recursively implemented optimal edge detector , 1987, International Journal of Computer Vision.

[14]  Ramakant Nevatia,et al.  Detection and Modeling of Buildings from Multiple Aerial Images , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Radu Horaud,et al.  Stereo Correspondence Through Feature Grouping and Maximal Cliques , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Ramakant Nevatia,et al.  Segment-based stereo matching , 1985, Comput. Vis. Graph. Image Process..

[17]  Richard I. Hartley,et al.  A linear method for reconstruction from lines and points , 1995, Proceedings of IEEE International Conference on Computer Vision.