Feature-based pattern recognition and object identification for telerobotics

This paper presents a method to efficiently recognize 3D objects from 2D images based on feature-based indexing. Object recognition is the identification of correspondences between parts of a current scene and stored views of known objects, using chains of segments or indexing vectors. To create indexed object models, characteristic model image features are extracted during preprocessing. Feature vectors representing model object contours from several points of view around each object are acquired and stored. At recognition time, the indexing vectors with the highest match probability are retrieved from the model image database, using a search strategy that employs knowledge-base (KB) search criteria. The knowledge-based simplifies the recognition process and minimizes the number of iterations and memory usage. Candidate objects in camera images are matched with the stored set of reference views by probabilistic viewing interpolation. The experimental results indicate that feature-based indexing in combination with a knowledge-based system will be a useful methodology for automatic target recognition (ATR).