Minimizing the probabilistic magnitude of active vision errors using genetic algorithm

Abstract

Spatial quantization errors are resulted in digitization. The errors are serious when the size of the pixel is significant compared to the allowable tolerance in the object dimension on the image. In placing the active sensor to perform inspection, displacement of the sensors in orientation and location is common. The difference between observed dimensions obtained by the displaced sensor and the actual dimensions is defined as displacement errors. The density functions of quantization errors and displacement errors depend on the camera resolution and camera locations and orientations. We use genetic algorithm to minimize the probabilistic magnitude of the errors subject to the sensor constraints, such as the resolution, field-of-view, focus, and visibility constraints. Since the objective functions and the constraint functions are both complicated and nonlinear, traditional nonlinear programming may not be efficient and trapping at a local minimum may occur. Using crossover operations, mutation operations, and the stochastic selection in genetic algorithm, trapping can be avoided.