Research On The Method Of Deth Information Extraction Based On Binocular Vision

With the enhancement of computer signal processing ability and the development of image processing technology,binocular stereoscopic vision has become a hotspot in the field of computer vision as a multidisciplinary field.Binocular stereoscopic vision technology is a way to achiece the three-dimensional information of the target by parallax principle,which simulates the way that how human eyes obtain information.Started with the conception and the method of the binocular stereoscopic vision,binocular stereoscopic vision is widely used in the precise positioning and measurement of spatial geometric dimensions,which leads to a new concept-visual measurement.Based on computer vision theory,visual measurement involves optical,optoelectronics,image processing,pattern recognition,signal and data processing,computer technology and many other disciplines.Its application is gradually penetrating into aerospace,military equipment,biomedical,target recognition,equipment manufacturing,industrial measurement and automation control and many other areas.All of the binocular stereo vision measurement process' s stages include: camera calibration,image acquisition,image preprocessing,feature extraction and matching,3D reconstruction,etc.This paper is based on the binocular stereo vision technology,and conducts theory and experimental research centering around the key techniques such as the camera calibration,image preprocessing,feature point extraction and matching,3D coordinate recovery,etc.Aiming at the commonly used algorithms,a few improved methods are put forward according to the practical application.The main contents of this paper are as follows:1.On the basis of existed algorithms,a set of image preprocessing methods which is suitable for this paper is designed to get rid of the noise and background interference information when acquisiting image that makes the useful information of target object more prominent.2.This paper describes the imaging model of the camera,the transformation relationship between these coordinates,the intrinsic and extrinsic parameters of camera,focus on the Zhang's chessboard calibration method.This paper conducts intensive study on camera calibration principle,and under the condition of the permit of experiment conditions uses zhang calibration method with high precision and simple operation to realize the internal,external parameters calibration of binocular stereo measuring system and achieve a high precision camera calibration.3.In view of the stereo rectification which we can't get the camera intrinsic and extrinsic parameters,this paper focuses on the Hartley's algorithm,this method must estimate the fundamental matrix and restore the Epipolar geometry.Then the key of estimating the fundamental matrix accurately lies on the exact matching of the matching point pairs.Therefore,a new Features based on Harris-SIFT is used.The Features can reduce the computation time and error matching rate of the feature matching,it can also directly represent the structure characteristic information of the image.Finally,We compared the results of Harris-SIFT Features extraction and SIFT Features extraction in terms of computation time and error matching rate.The results show that Harris-SIFT Feature matching can improve the matching accuracy,thus improve the accuracy of estimate of the fundamental matrix,and ultimately improve the efficiency of the Hartley's algorithm.