What question did this study set out to answer?

This research aims to develop an efficient algorithm for recognizing 3-D objects from single gray-scale images under difficult conditions like occlusion.

January 1, 1990

Affine invariant model-based object recognition

Key Points

This research aims to develop an efficient algorithm for recognizing 3-D objects from single gray-scale images under difficult conditions like occlusion.
Developed a matching algorithm based on affine approximation to view transformations.
Implemented offline model preprocessing for shape representation independent of scene data.
Tested algorithm on industrial objects in composite, occluded scenes.
Successfully recognized overlapping and partially occluded 3-D objects.
Showed effective performance using the proposed matching algorithm in various scenarios.
Achieved straightforward parallel implementation.

Abstract

New techniques are described for model-based recognition of the objects in 3-D space. The recognition is performed from single gray-scale images taken from unknown viewpoints. The objects in the scene may be overlapping and partially occluded. An efficient matching algorithm, which assumes affine approximation to the prospective viewing transformation, is proposed. The algorithm has an offline model preprocessing (shape representation) phase which is independent of the scene information and a recognition phase based on efficient indexing. It has a straightforward parallel implementation. The algorithm was successfully tested in recognition of industrial objects appearing in composite occluded scenes.>

Bookmark

Affine invariant model-based object recognition

Key Points

Abstract

Cite This Study

Also Consider

Also Consider