The Image Processing Technology of Monocular Vision Aided Target Measurement

The process and practical results of the image processing technology of monocular vision aided target measurement are given. Firstly, the image was enhanced by mathematical morphology and segmented wih geometry-based feature extraction; Then according to least square ellipse fitting algorithm,the center coordinates of mark point was accurately striked; Finally, improved algorithm based on the elliptical error evaluation was presented, which had high accuracy and good stability. The experiments show that the shape error is about one pixel, and it is reduced significantly after the algorithm improvement.This method can be widely used in monocular vision measurement.