Reasoning with geometric constraints for generic three-dimensional object recognition in occluded environments
Abstract
Generic shape recognition is the problem of determining the pose and dimensions of objects for which only shape models are available and the object's size is unknown. One application domain for generic object recognition is the handling and sorting of postal objects. Because metrical information relating object features to one another is not available, the more common feature-based approaches are inadequate. We have developed a 3-D object recognition system, INGEN (INference engine for GENeric object recognition), which uses a data-driven approach to determine the pose and size of objects with generic shapes such as parallelepipeds and cylinders. This system successfully recognizes occluded objects in heaps. It also handles scenes which have irregularities in surfaces and edges--such irregularities are common to postal objects--as well as shadows and irregularities in the range data itself. The three most important parts of INGEN are: (1) the procedures for constructing object hypotheses, computing their attributes, and evaluating how well they fit the data given that the data are oversegmented and noisy and only generic shape models are available, (2) the geometric reasoning process which determines the size of object hypotheses by finding points of contact with other object hypotheses and also detects geometric inconsistencies in the scene interpretation due to conflicting object hypotheses, and (3) the recognition process which allows backtracking when object hypotheses are rejected due to insufficient support or geometric conflict with other object hypotheses. INGEN has been used successfully to guide a robot in removing objects from piles. The robot uses a suction gripper for postal objects and a parallel jaw gripper for other objects. We show the results of these experiments.
Degree
Ph.D.
Advisors
Kak, Purdue University.
Subject Area
Electrical engineering
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.