Towards automatically learning an implicit model from 2D-images based on a local similarity analysis of contours

The article deals with enabling an intelligent system to autonomously learn an implicit model of its environment. An unsupervised learning method is presented which learns the topological connections of different object views. Moreover, the method is able to distinguish between different objects. Based on a systematic local analysis of the objects' contours, the method unites learning a topology (i.e. navigation) and object recognition into one framework.

[1]  Ales Leonardis,et al.  Panoramic Eigenimages for Spatial Localisation , 1999, CAIP.

[2]  Olivier D. Faugeras,et al.  Autonomous navigation of a mobile robot using inertial and visual cues , 1993, Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '93).

[3]  Theodosios Pavlidis,et al.  Structural pattern recognition , 1977 .

[4]  Kaleem Siddiqi,et al.  Parts of visual form: computational aspects , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Donald D. Hoffman,et al.  Salience of visual parts , 1997, Cognition.

[6]  Klaus-Dieter Kuhnert,et al.  Automatic generation of significant and local feature groups of complex and deformed objects , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[7]  Peter Corke,et al.  3D perception for mining robotics , 1998 .