Using parallel line information for vision-based landmark location estimation and an application to automatic helicopter landing

摘要: Abstract An approach to landmark location estimation by computer vision techniques is proposed. The objective derive the position and orientation of with respect vehicle a single image. Such information necessary for automatic navigation. This requires lower hardware cost simple computation. vanishing points parallel lines on are used detect orientation. detected relative between camera, which then utilized compute vehicle. size determine position. Sets collinear extracted from their inter-point distances computed. positions point sets evaluated Landing site using identification marking H helicopter landing presented as an application proposed approach. Simulations experiments have been conducted prove feasibility