Viewpoint selection - a classifier independent learning approach

This paper deals with an aspect of active object recognition for improving the classification and localization results by choosing optimal next views at an object. The knowledge of "good" next views at an object is learned automatically and unsupervised from the results of the used classifier. For that purpose methods of reinforcement learning are used in combination with numerical optimization. The major advantages of the presented approach are its classifier-independence and that the approach does not require a priori assumptions about the objects. The presented results for synthetically generated images show that our approach is well suited for choosing optimal views at objects.

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

[2]  Heinrich Niemann,et al.  Wavelet features for statistical object localization without segmentation , 1997, Proceedings of International Conference on Image Processing.

[3]  Aimo A. Törn,et al.  Global Optimization , 1999, Science.

[4]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[5]  H. Niemann,et al.  Knowledge based image and speech analysis for service robots , 1999, Proceedings Integration of Speech and Image Understanding.

[6]  Lucas Paletta,et al.  A Comparison of Probabilistic, Possibilistic and Evidence Theoretic Fusion Schemes for Active Object Recognition , 1999, Computing.

[7]  Ashwin Ram,et al.  Experiments with Reinforcement Learning in Problems with Continuous State and Action Spaces , 1997, Adapt. Behav..

[8]  Richard S. Sutton,et al.  Dimensions of Reinforcement Learning , 1998 .