An Innovative Monocular Mobile Object Self-localization Approach Based on Ceiling Vision

This study deals with the estimation of the position of a mobile object using ceiling landmarks images acquired by a low resolution camera placed on a mobile object. The mobile object is moving in an indoor environment where light is given by electric lamps with circular holders. The images of the circular holders are projected on the image plane of the camera and are processed by means of computer vision algorithms. The pixels of the images of the light holders on the ceiling are mapped to the pixels of the images of the light holders on the image plane of the camera by means of a two dimensional dynamic programming algorithm (2D-DPA). The projection distortions are thus compensated and this reduces the estimation errors. The algorithm described in this paper estimates the distance from the camera lens to the center of the landmarks using only ceiling vision. Localization can be easily obtain from such distance estimations. The projections are geometrically described and the distance estimation is based on the pixels mapping information obtained by 2D-DPA.