A Constraint-Satisfaction Approach for 3-D Object Recognition by Integrating 2-D and 3-D Data,

We present a framework for recognition of 3-D objects by integrating 2-D and 3-D sensory data. The major thrust of this work is to e ciently utilize all relevant data, both 2-D and 3-D, in the early stages of recognition, in order to reduce the computational requirements of the recognition process. To achieve this goal, we formulate the problem as a Constraint-Satisfaction problem (CSP). Rather than directly solving the CSP, a problem of exponential complexity, we only enforce local consistency in low-order polynomial time. This step of local-consistency enforcement can signi cantly decrease the computational load on subsequent recognition modules by 1) signi cantly reducing the uncertainty in the correspondence between scene and model features, and 2) eliminating many erroneous model objects and irrelevant scene features. A novel method is presented for e ciently constructing a CSP corresponding to a combination of 2-D and 3-D scene features. Performance of the proposed framework is demonstrated using simulated and real experiments involving visual (2-D) and tactile (3-D) data. 2