Title :
Sensor modeling, probabilistic hypothesis generation, and robust localization for object recognition
Author :
Wheeler, Mark D. ; Ikeuchi, Katsushi
Author_Institution :
Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA
fDate :
3/1/1995 12:00:00 AM
Abstract :
In an effort to make object recognition efficient and accurate enough for real applications; we have developed three probabilistic techniques-sensor modeling, probabilistic hypothesis generation, and robust localization-which form the basis of a promising paradigm for object recognition. Our techniques effectively exploit prior knowledge to reduce the number of hypotheses that must be tested during recognition. Our recognition approach utilizes statistical constraints on the matches between image and model features. These statistical constraints are computed using a model of the entire sensing process-resulting in more realistic and tighter constraints on matches. The candidate hypotheses are pruned by probabilistic constraint satisfaction to select likely matches based on the image evidence and prior statistical constraints. The resulting hypotheses are ordered most-likely first for verification. Thus minimizing unnecessary verifications. The reliability of the verification decision is significantly increased by the use of a robust localization algorithm
Keywords :
Markov processes; computer vision; image sensors; object recognition; probability; statistical analysis; stereo image processing; 3D object recognition; Markov random field; computer vision; pose estimation; probabilistic constraint satisfaction; probabilistic hypothesis generation; robust localization; sensor modeling; statistical constraints; Application software; Computer errors; Computer vision; Image recognition; Intelligent robots; Markov random fields; Object recognition; Photometry; Robustness; Testing;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on