Model-Based GA Evolutionary 3-D Position Measurement Method

Abstract

This paper presents a vision-related technique for 3-D position measurement. The proposed method utilizes the genetic algorithm (GA) and unprocessed grayscale image input from vision, in order to perform recognition of a target being imaged with known target object shape. The problem to recognize the target shape and simultaneous detection of the position, is converted to an optimistic problem of a model-based evaluation function, named as surface-strips model-based fitness function that consists in the computation of the brightness difference between an internal surface and a contour-strips. In order to evaluate the proposed 3-D recognition method, experiments by an unprocessed grayscale image have been input to recognize a ball in the image. The results show the effectiveness of this method for 3-D position detection.