Location identification using an fisheye lens and landmarks placed on ceiling in a cleaning robot

In this paper, a location identification for a cleaning robot using a camera shooting forward a room ceiling which kas three point landmarks is introduced. These three points are made from a laser source which is placed on an auto charger. A fisheye lens covering almost 150 degrees is utilized and the image is transformed to a camera image grabber. The widly shot image has an inevitable distortion even if wide range is coverd. This distortion is flatten using an image warping scheme. Several vision processing techniques such as an intersection extraction, erosion, and curve fitting are employed. Next, three point marks are identified and their correspondence is investigated. Through this image processing and image distortion adjustment, a robot location in a wide geometrical coverage is identified.