3D mapping and estimation from moving direction of indoor mobile robot using vanishing points

There are many boundaries of artificial objects which are appeared as edges in the image. These line segments as edge impose information for understanding indoor environment. We obtain 3-dimension positional information as we use a stereo camera. There are three dominant vanishing points(VPs) in 3D world. We can separate lines and estimate forward direction by using VP. Groups of such coinciding lines which extend to the same VP are determined by angles between them. Also the crossing points transform to ICIS (inverted coordinates image space). The ICIS is proposed method to detect VPs in an infinite or finite image space. If the crossing points exist in the image, there is not transformation. However, crossing points are out of image, then, crossing points transform to ICIS. VPs are determined by distribution in ICIS. They impose maximally 3 groups. Disparity of depth direction VP calculates for its 3D position. Among them, we need to determine a dominant VP which comes from vertical lines for corresponding. To correspond the line segments, the smallest SAD (sum of absolute difference) value used beside area of them. We also compare the order and direction of lines. Disparities from corresponding lines between stereo images are calculated for this so that 3D position is calculated by triangulation. Evading from the perspective effect which occur 3D scene projects into 2D image thus size or angle changes, geometric ratios are used for rectifying such changes. We already know 3D position of depth direction VP and vertical lines before rectifying. So, rectification is to add before rectifying values to obtained values which are geometric ratio between VP and vertical lines. 3D map is obtained from rectifying 3D position. Also, moving direction estimates from angle between VP and principal point. We experiment several slant, tilt or pan images. VP and principal point detected, when the robot also looked at floor or wall.