Fitting multiple models to multiple images with minimal user interaction

Utilising the broad range of information which human observers bring to bear when interpreting their visual environment is currently infeasible for artificial vision systems. We propose instead a method for modelling compound structures which intelligently divides this prior information into that which may be applied by the system and that which may not. Models are fitted to the input data on the basis of 2D and 3D image-based measures, but also as directed by a prior which is split between the human and the system. Importantly this split is carried out in a manner which minimises the human input required. ? The authors would like to acknowledge The Australian Research Council Discovery Grant scheme and EPSRC grant EP/C006631/1(P) for support

[1]  Ian D. Reid,et al.  Single View Metrology , 2000, International Journal of Computer Vision.

[2]  Thorsten Thormählen,et al.  Zuverlässige Schätzung der Kamerabewegung aus einer Bildfolge , 2006 .

[3]  Peter F. Sturm,et al.  Using geometric constraints through parallelepipeds for calibration and 3D modeling , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Robert B. Fisher,et al.  Recognition of Complex 3-D Objects from Range Data , 1993 .

[5]  Toby Howard,et al.  Interactive reconstruction of virtual environments from video sequences , 2003, Computers & graphics.

[6]  David L. Waltz,et al.  Understanding Line drawings of Scenes with Shadows , 1975 .

[7]  Geoffrey D. Sullivan,et al.  A Generic Deformable Model for Vehicle Recognition , 1995, BMVC.

[8]  Roberto Cipolla,et al.  An Interactive System for Constraint-Based Modelling , 2000, British Machine Vision Conference.

[9]  Michel Dhome,et al.  Modelled Object Pose Estimation and Tracking by Monocular Vision , 1993, BMVC.

[10]  Jitendra Malik,et al.  Modeling and Rendering Architecture from Photographs: A hybrid geometry- and image-based approach , 1996, SIGGRAPH.

[11]  Anton van den Hengel,et al.  Computing Surface-Based Photo-Consistency on Graphics Hardware , 2005, Digital Image Computing: Techniques and Applications (DICTA'05).

[12]  Roberto Cipolla,et al.  Application of Lie Algebras to Visual Servoing , 2000, International Journal of Computer Vision.

[13]  Paul Smith,et al.  Motion Segmentation by Tracking Edge Information over Multiple Frames , 2000, ECCV.

[14]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .

[15]  Roberto Cipolla,et al.  Modelling and Interpretation of Architecture from Several Images , 2004, International Journal of Computer Vision.

[16]  Stephen J. Maybank,et al.  A Method for Interactive 3D Reconstruction of Piecewise Planar Objects from Single Images , 1999, BMVC.

[17]  Richard Szeliski,et al.  A layered approach to stereo reconstruction , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[18]  K. S. Arun,et al.  Least-Squares Fitting of Two 3-D Point Sets , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Mei Han,et al.  Interactive construction of 3D models from panoramic mosaics , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).