Binocular Stereoscopic Vision (Binocular Stereo vision) is an important form of machine vision, it is based on the parallax principle and uses the imaging equipment to obtain the measured object from different location two images, by calculating the position deviation between the corresponding points of the image, to obtain three-dimensional geometric information method. By fusing the images obtained from two eyes and observing the differences between them, we can gain a clear sense of depth, establish correspondence between features, and map the same spatial physical points to the images in different images, which we call parallax (disparity) images. [1] Binocular Stereo Vision Measurement method has the advantages of high efficiency, suitable accuracy, simple system structure and low cost, and is very suitable for on-line, non-contact product inspection and quality control in manufacturing field. In the measurement of moving objects (including animals and human bodies), the stereo vision method is a more effective method because the image acquisition is done instantaneously. Binocular Stereoscopic Vision System is one of the key technologies of computer vision, and it is the most basic content in the research of computer vision to get the distance information of space three-dimensional scene. [1] The groundbreaking work of Binocular stereoscopic vision began in the middle of the 60 's in the last century. Roberts of the United States MIT by extracting the three-dimensional structure of simple rule multipatch, such as cubes, wedges and prism from digital images, and describing the shape and spatial relation of the object, the simple two-dimensional image analysis of the past is extended to the complex three-dimensional scene, which marks the birth of stereoscopic vision technology. With the research in depth, the research scope from the edge, corner and other features of the extraction, line, plane, surface and other geometric elements analysis, until the image shading, texture, motion and imaging geometry, and set up a variety of data structures and inference rules. Especially in the early 80, Marr the research results of image processing, psychological physics, neurophysiology and clinical psychiatry from the angle of information processing, and created the framework of visual computing theory. This basic theory has brought great impetus to the development of stereoscopic vision technology, which has formed a complete system from image acquisition to final visual surface reconstruction of three-dimensional scene, making stereoscopic vision become a very important branch in computer vision. [1] After decades of development, stereoscopic vision in the field of robot vision, aerial mapping, reverse engineering, military applications, medical imaging and industrial detection and other fields of more and more widely used. [
Binocular Stereoscopic Vision
