Subset Selection for Active Object Recognition

This paper presents an algorithm for constructing object representations suitable for recognition. The system automatically selects a representative subset of the views of the object while constructing the eigenspace basis. These views are actively located for object identification and pose determination. All processing is performed on-line. The camera is actively positioned during both representation and recognition. When tested with 240 views for each of seven objects, the system achieves 100% accurate object recognition and pose determination. These results are shown to degrade gracefully as conditions deteriorate.

• Type: Conference
• Year: 1999
• Where: CVPR
• Authors: Jay Winkeler, B. S. Manjunath, Shivkumar Chandrasekaran
• Keywords: Accurate Object Recognition, Computer Vision, CVPR 1999, Object Representations