EFFICIENT AND ACCURATE STRUCTURED LIGHT ALGORITHM FOR DIRECT MEASUREMENT OF CYLINDRICAL SURFACE PARAMETERS

The recognition of surface shapes using structured light is an importa nt component of many industrial vision systems. The iterative correcti on algorithm (ICA) for the recognition of cylindrical objects is based upon a predictor-corrector approach Which utilizes an initial estimat e for the surface parameters, followed by iterative parameter refineme nt. A predicted passive image is generated using the current surface p arameter estimates and significant features are extracted and compared with those in the true passive image. The estimated surface parameter s are corrected based upon feature disparities. In this paper, the ICA is enhanced with a new method for computing passive-image point coord inates and tested. Future research directions are indicated. (C) 1997 Society oi Photo-Optical Instrumentation Engineers.