PCA-based structure refinement for reconstruction of urban scene

There is plenty of structured information (such as lines and planes) in urban scenes. Considering this, we propose a new method for making use of this information to enhance the reconstruction of urban outdoor scenes. Structured information (collinearity and coplanarity) is extracted from images by performing line detection and color image segmentation, which is used as hypothetic constraints of the 3D structure. In refining stage, we first build PCA subspaces for each structured components (collinear and coplanar point sets), during which the former hypothetic structure information is further inspected by the initial 3D structure. Then we iteratively update the structure through EM estimation. Experiments show that this method effectively improves the accuracy and robustness of reconstruction of urban scenes.

[1]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[2]  Jianxiong Xiao,et al.  Image-based façade modeling , 2008, ACM Trans. Graph..

[3]  Luc Van Gool,et al.  Procedural modeling of buildings , 2006, SIGGRAPH 2006.

[4]  Horst Bischof,et al.  Fusion of Feature- and Area-Based Information for Urban Buildings Modeling from Aerial Imagery , 2008, ECCV.

[5]  Horst Bischof,et al.  A Globally Optimal Algorithm for Robust TV-L1 Range Image Integration , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  H. Opower.  Multiple view geometry in computer vision , 2002 .

[7]  Luc Van Gool,et al.  3D Urban Scene Modeling Integrating Recognition and Reconstruction , 2008, International Journal of Computer Vision.

[8]  Roberto Cipolla,et al.  Probabilistic visibility for multi-view stereo , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Andrew Zisserman,et al.  Multiple View Geometry in Computer Vision (2nd ed) , 2003 .

[10]  Frank Nielsen,et al.  Statistical region merging , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Zhanyi Hu,et al.  MSLD: A robust descriptor for line matching , 2009, Pattern Recognit..

[12]  Long Quan,et al.  A quasi-dense approach to surface reconstruction from uncalibrated images , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Juho Kannala,et al.  Quasi-Dense Wide Baseline Matching Using Match Propagation , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.