Batch Reconstruction from UAV Images with Prior Information

With the latest deregulation and opening-up policy of the Chinese government on low altitude airspace to private sectors, the applications of unmanned aerial vehicles (UAV) will be a huge potential market. Currently the automatic processing technology of UAV images is far behind the market demand, and has become the bottleneck of various applications. This work is meant to apply hugely successful scene reconstruction techniques in computer vision field to large scene reconstruction from UAV images. To this end, at first, specific problems of direct application of the Bundler, a popular increment reconstruction technique in computer vision, are investigated. Then a batch reconstruction method from UAV images is proposed by fully taking into account various pieces of prior information which are usually available in UAV images, such as those from GPS, IMU, DSM etc. Our method is tested with several sets of UAV images, and the experiments show that our method performs satisfactorily in terms of robustness, accuracy and scalability for UAV images.