Mosaic-based 3D scene representation and rendering of circular aerial video

摘要

Circular aerial video provides a persistent view over a scene and generates a large amount of imagery, much of which is redundant. The interesting features of the scene are the 3D structural data, moving objects, and scenery changes. Mosaic-based scene representations work well in detecting and modeling these features while greatly reducing the amount of storage required to store a scene. In the past, mosaic-based methods have worked well for video sequences with straight camera paths in a dominant motion direction11. Here we expand on this method to handle circular camera motion. By using a polar transformation about the center of the scene, we are able to transform circular motion into an approximate linear motion. This allows us to employ proven 3D reconstruction and moving object detection methods that we have previously developed. Once features are found, they only need to be transformed back to the Cartesian space from the polar coordinate system.