USING PARALLEL LINE INFORMATION FOR VISION-BASED LANDMARK LOCATION ESTIMATION AND AN APPLICATION TO AUTOMATIC HELICOPTER LANDING

An approach to landmark location estimation by computer vision techniq ues is proposed. The objective is to derive the position and the orien tation of the landmark with respect to the vehicle by a single image. Such information is necessary for automatic vehicle navigation. This a pproach requires lower hardware cost and simple computation. The vanis hing points of the parallel lines on the landmark are used to detect t he landmark orientation. The detected vanishing points are used to der ive the relative orientation between the landmark and the camera, whic h is then utilized to compute the landmark orientation with respect to the vehicle. The size of the landmark is used to determine the landma rk position. Sets of collinear points are extracted from the landmark and their inter-point distances are computed. The positions of the col linear point sets are evaluated and used to determine the landmark pos ition. Landing site location estimation by using the identification ma rking H on the helicopter landing site for automatic helicopter landin g is presented as an application of the proposed approach. Simulations and experiments have been conducted to prove the feasibility of the p roposed approach. (C) 1998 Elsevier Science Ltd. All rights reserved.