VISION-BASED OBSTACLE DETECTION AND GROUPING FOR HELICOPTER GUIDANCE

Electro-optical sensors can be used to compute range to objects in the night path of a helicopter, The computation is based on the optical f low/motion at different points in the Image. The motion algorithms pro vide a sparse set of ranges to discrete features in the image sequence as a function of azimuth and elevation. For obstacle avoidance guidan ce and display purposes, these discrete sets of ranges, varying from a few hundred to several thousand, need to be grouped into sets that co rrespond to objects in the real world. This paper presents a new metho d for object segmentation based on clustering the sparse range informa tion provided by motion algorithms together with the spatial relation provided by the static image. Object grouping allows interpolation wit hin a group and enables the creation of dense range maps. The paper pr esents object segmentation results for a sequence of flight images.