Depth Map Generation for Aerial Video in Natural Scenery

In this paper, a novel method to generate depth map automatically from aerial video is proposed. Camera intrinsic and extrinsic parameters are estimated by a traditional Structure from Motion (SfM) approach and a post-processing for the camera path optimized for aerial video is used. Depth map is generated directly from the camera path and 3D point without making meshes in 3D space. Proposed method is fast and free from flickering artifacts so it can be used for automatic 2Dto3D conversion or contents classification. This is a description of a demonstration given at the WAVE workshop.