Appearance-based object recognition using multiple views

Object recognition from a single view fails when the available features are not sufficient to determine the identity of a single object, either because of similarity with another object or because of feature corruption due to clutter and occlusion. Active object recognition systems have addressed this problem successfully, but they require complicated systems with adjustable viewpoints that are not always available. In this paper we investigate the performance gain available by combining the results of a single view object recognition system applied to imagery obtained from multiple fixed cameras. In particular, we address performance in cluttered scenes with varying degrees of information about relative camera pose. We argue that a property common to many computer vision recognition systems, which we term a weak target error, is responsible for two interesting limitations of multi-view performance enhancement: the lack of significant improvement in systems whose single-view performance is weak, and the plateauing of performance improvement as additional multi-view constraints are added.

[1]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[2]  John E. Howland,et al.  Computer graphics , 1990, IEEE Potentials.

[3]  Anil K. Jain,et al.  Integration of Multiple Feature Groups and Multiple Views into a 3D Object Recognition System , 1993, Applications of Invariance in Computer Vision.

[4]  Rajesh P. N. Rao,et al.  An Active Vision Architecture Based on Iconic Representations , 1995, Artif. Intell..

[5]  M. Pauline Baker,et al.  Computer Graphics, C Version , 1996 .

[6]  Bernt Schiele,et al.  Object Recognition Using Multidimensional Receptive Field Histograms , 1996, ECCV.

[7]  Cordelia Schmid,et al.  Combining greyvalue invariants with local constraints for object recognition , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Bernt Schiele,et al.  Probabilistic object recognition using multidimensional receptive field histograms , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[9]  Bartlett W. Mel.  SEEMORE: Combining Color, Shape, and Texture Histogramming in a Neurally Inspired Approach to Visual Object Recognition , 1997, Neural Computation.

[10]  Tapas Kanungo,et al.  Object recognition using appearance-based parts and relations , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Bernt Schiele,et al.  Transinformation for active object recognition , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[12]  R. Nelson,et al.  Large-scale tests of a keyed, appearance-based 3-D object recognition system , 1998, Vision Research.

[13]  Andrea Salgian,et al.  A Perceptual Grouping Hierarchy for Appearance-Based 3D Object Recognition , 1999, Comput. Vis. Image Underst..

[14]  Bruce A. Draper,et al.  ADORE: Adaptive Object Recognition , 1999, ICVS.

[15]  Lucas Paletta,et al.  Appearance-based active object recognition , 2000, Image Vis. Comput..