Full Automatic Relative Orientation of Unconventional Image Pairs
UAVs are becoming ubiquitous and will be widely deployed in many applications. The result will be a large amount of video data that needs to be organized and searched. A critical image processing application for UAVs will be a Google-like realtime search engine for large image and video databases. We have developed a novel indexing and search method that can be applied to large video databases. This technology enables a user to search for strongly similar images in a large image database created by intelligently subsampling the video sequences. The same image search technology can also be used for the automatic mosaicking of a set of unordered images to create a large panorama. A number of experiments with video taken from UAVs demonstrate the technology.