Parallel Binocular Vision
摘要
Camera imaging is a process that maps the three-dimensional world onto a two-dimensional image. If we want to recover the information of the three-dimensional world from the image, we need to solve a crucial problem: recovering the depth information lost during the camera imaging process. Given a single image, we cannot determine the coordinates of the point in the three-dimensional space corresponding to each pixel. This is because all points in the three-dimensional space along the ray from the camera’s optical center to the imaging plane can be projected onto the same pixel. Only when we know the depth corresponding to a pixel can we accurately determine its spatial position in the three-dimensional space. In this chapter, we will introduce the structure and imaging principle of parallel binocular cameras, as well as how to use parallel binocular cameras to obtain depth information of the scene.