A Distance Measuring Method Using Visual Image Processing

This paper presents a visual approach for distance measuring. Firstly, images are taken in different positions. Then the scaling parameter between these images could be calculated with the Fourier-Mellin transform. The Fourier-Mellin transform is successfully utilized for figuring out the scaling and rotation parameters between images, meanwhile the transform itself is translation independent. So when the images are rotated or translated, we can also get a correspondingly accurate scaling parameter. Finally, the distance from the optical center of the camera to the object can be figured out with the pinhole model by two parameters: one is the image scaling parameter; the other is the changing amount of position which is treated as a known parameter during the processing. Experimental results show that the proposed method is practical for providing satisfactory measuring results.