首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Fast robust large-scale mapping from video and internet photo collections
Authors:Jan-Michael Frahm  Marc Pollefeys  Svetlana Lazebnik  David Gallup  Brian Clipp  Rahul Raguram  Changchang Wu  Christopher Zach  Tim Johnson
Institution:1. University of North Carolina at Chapel Hill, NC, USA;2. Eidgenössische Technische Hochschule Zürich, Switzerland;1. Department of Telecommunications and Information Processing (UGent-TELIN-IPI-IBBT), Ghent University, St-Pietersnieuwstraat 41, B-9000 Ghent, Belgium;2. Grontmij Belgium NV, Meersstraat 138A, B-9000 Ghent, Belgium;1. School of Civil Engineering, School of Geosciences and Info-Physics, Central South University, 22 Shaoshan South Road, Changsha 410004, PR China;2. Department of Land Surveying & Geo-Informatics, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong;1. Università degli Studi di Napoli Federico II, Dipartimento di Architettura, Via Monteoliveto 3, 80134 Napoli, Italy;2. Università degli Studi di Napoli Federico II, Centro Interdipartimentale di Ricerca per l’Analisi e la Progettazione Urbana Luigi Pisciotti, Via Toledo 402, 80134 Napoli, Italy;3. Università degli Studi di Salerno, Dipartimento di Informatica, Via Ponte don Melillo, 80084 Fisciano, Italy;1. Cleveland Clinic Florida, 2950 Cleveland Clinic Blvd, Weston, Fl 33331, United States;2. University of Arizona, Office of Academic Placement, Room 102B, Tucson, AZ 85721, United States;1. Orthopaedic Department ULB, Medical School University of Brussels, University Hospital Erasme Brussels, Brussels, Belgium;2. Orthopaedic Surgeon, Athens, Greece;3. Department of Orthopaedic Surgery, Helios ENDO Klinik Hamburg, Hamburg, Germany;4. Clinic of Orthopedics, Azienda Ospedaliero-Universitaria of Udine, Udine, Italy;5. Cappagh National Orthopaedic Hospital, Dublin, Ireland;6. Department of Orthopaedic Surgery, Shoulder and Sports Medicine Service, Hospital for Special Surgery, New York, New York, U.S.A.
Abstract:This paper presents a system approaching fully automatic 3D modeling of large-scale environments. Our system takes as input either a video stream or collection of photographs obtained from Internet photo sharing web-sites such as Flickr. The system achieves high computational performance through algorithmic optimizations for efficient robust estimation, the use of image-based recognition for efficient grouping of similar images, and two-stage stereo estimation for video streams that reduces the computational cost while maintaining competitive modeling results. In addition to algorithmic advances, we achieve a major improvement in computational speed through parallelization and execution on commodity graphics hardware. These improvements lead to real-time video processing and to reconstruction from tens of thousands of images within the span of a day on a single commodity computer. We demonstrate modeling results on a variety of real-world video sequences and photo collections.
Keywords:
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号