Abstract
Stereo Vision is used to locate spatial point,which is an important research field of Computer Vision.Binocular Stereo Vision is the famous one in Stereo Vision,due to its characteristic of simulating the manner of man’s eyes processing information,which has great applicability.
In this paper, we take the method of Digital Camera Positioning. Digital Camera Positioning can determine the location of some feature points by the digital camera photo . A point of the object which is caught by two fixed cameras in different position create two image in each camera's Phase plane.As soon as we precisely get the relative position of the two cameras, we can get the location of the feature points by geometric method .Thus , determining the relative position of two cameras accurately is the key to the process of Determination of binocular vision,which is named System calibration. The approach of System calibration is: Print a number of points in a flat-panel,then use two cameras get the pictures respectively at the same time ,.As we get these points in the images, we can get the relative positions of two cameras by using the geometric relationship between these points .
The main contents of this paper are list as follows: Make a detailed description of binocular vision; Make a detailed description of the basic model and then given the framework of the system; Get the feature point by the establishment of mathematical model ; Use Tsai algorithm to determine precise relative position of two cameras. At lase complete the theory of the determination of binocular vision.
Keywords：Binocular vision;Digital Camera Positioning;Feature Point Extraction;Tsai algorithm;System calibration
