3D Cognitive Map Construction by Active Stereo Vision in a Virtual World

In this study, a multi-scale phase based disparity algorithm is developed. This algorithm is then applied in a simulated world. In this world there is a virtual robot which has a stereo camera system simulated with the properties similar to human eyes and there are 3D virtual objects having predefined simple shapes. The virtual robot explores its environment intelligently based on some heuristics. Only stereo images rendered from the virtual world are supplied to the robot. The robot extracts depth information from the stereo images and when an object is seen, it investigates the object in detail and classifies the object from the estimated shapes of the object parts.

[1]  Ilkay Ulusoy,et al.  Active Stereo Vision for Object Recognition and Cognitive Map Formation in a Virtual World – A Demonstration , 2003 .

[2]  Masayuki Inaba,et al.  Visual navigation using view-sequenced route representation , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[3]  T. Sanger,et al.  Stereo disparity computation using Gabor filters , 1988, Biological Cybernetics.

[4]  Edwin R. Hancock,et al.  Disparity Using Feature Points in Multi Scale , 2002, SSPR/SPR.

[5]  Demetri Terzopoulos,et al.  Animat vision: Active vision in artificial animals , 1995, Proceedings of IEEE International Conference on Computer Vision.

[6]  Masayuki Inaba,et al.  Rapid development system for humanoid vision-based behaviors with real-virtual common interface , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Guang Li,et al.  Navigating with a Focus-Directed Mapping Network , 1999, Auton. Robots.

[8]  K. Leblebicioglu,et al.  Object recognition and cognitive map formation using active stereo vision in a virtual world , 2003, 2003 IEEE International Workshop on Computer Architectures for Machine Perception.

[9]  David F. Rogers,et al.  Mathematical elements for computer graphics , 1976 .

[10]  Pietro Perona,et al.  Towards automatic discovery of object categories , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[11]  Lkay Ulusoy,et al.  ACTIVE STEREO VISION: DEPTH PERCEPTION FOR NAVIGATION, ENVIRONMENTAL MAP FORMATION AND OBJECT RECOGNITION , 2003 .

[12]  J. Tyrrell,et al.  Analytic Geometry , 1965, Nature.

[13]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Gustavo Carneiro,et al.  Multi-scale phase-based local features , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[15]  Tony J. Prescott,et al.  Spatial Representation for Navigation in Animats , 1996, Adapt. Behav..

[16]  Tomaso A. Poggio,et al.  Finding Human Faces with a Gaussian Mixture Distribution-Based Face Model , 1995, ACCV.