Geo-registered 3D models from crowdsourced image collections
| Autor: | Jan-Michael Frahm, Pierre Fite-Georgel, Enliang Zheng, Jared Heinly, Marc Pollefeys, Enrique Dunn |
|---|---|
| Rok vydání: | 2013 |
| Předmět: |
Computational complexity theory
Computer science business.industry media_common.quotation_subject Geography Planning and Development ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Ambiguity 3D modeling computer.software_genre Image (mathematics) Scalability Structure from motion Computer vision The Internet Data mining Artificial intelligence Computers in Earth Sciences business Scale (map) computer media_common |
| Zdroj: | Geo-spatial Information Science. 16:55-60 |
| ISSN: | 1993-5153 1009-5020 |
| Popis: | In this article we present our system for scalable, robust, and fast city-scale reconstruction from Internet photo collections (IPC) obtaining geo-registered dense 3D models. The major achievements of our system are the efficient use of coarse appearance descriptors combined with strong geometric constraints to reduce the computational complexity of the image overlap search. This unique combination of recognition and geometric constraints allows our method to reduce from quadratic complexity in the number of images to almost linear complexity in the IPC size. Accordingly, our 3D-modeling framework is inherently better scalable than other state of the art methods and in fact is currently the only method to support modeling from millions of images. In addition, we propose a novel mechanism to overcome the inherent scale ambiguity of the reconstructed models by exploiting geo-tags of the Internet photo collection images and readily available StreetView panoramas for fully automatic geo-registration of the 3D... |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|