DIRECT SURFACE PARAMETER-ESTIMATION USING STRUCTURED LIGHT - A PREDICTOR-CORRECTOR BASED APPROACH

The projection of structured light is a technique frequently used in c omputer vision to determine the surface structure of scene objects. In this work, higher level features are extracted from the images and us ed for a direct estimation of second-order object surface model parame ters. In particular, a class of cylinders is emphasized, due to an und erlying application involving the inspection of stored drums containin g mixed waste. The strategy is based upon a predictor-corrector approa ch which utilizes an initial estimate for the surface parameters, foll owed by iterative parameter refinement. A predicted passive image is g enerated using the current surface parameter estimates and significant features are extracted and compared with those in the true passive im age. The estimated surface parameters are corrected based upon feature disparities. In computer simulations and laboratory experiments using real image data, the algorithm was found to converge quickly and to y ield accurate results.