A Fast Bilinear Structure from Motion Algorithm Using a Video Sequence and Inertial Sensors

TitleA Fast Bilinear Structure from Motion Algorithm Using a Video Sequence and Inertial Sensors
Publication TypeJournal Articles
Year of Publication2011
AuthorsRamachandran M, Veeraraghavan A, Chellappa R
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Pagination186 - 193
Date Published2011/01//
ISBN Number0162-8828
Keywords3D urban modeling, algorithms, Artificial intelligence, CAMERAS, computer vision., Convergence, fast bilinear structure, Google StreetView research data set, Image Interpretation, Computer-Assisted, Image reconstruction, Image sensors, Image sequences, Imaging, Three-Dimensional, inertial sensors, Information Storage and Retrieval, Linear systems, minimization, MOTION, motion algorithm, Motion estimation, multiple view geometry, Pattern Recognition, Automated, Sensors, SfM equations, sparse bundle adjustment algorithm, structure from motion, Three dimensional displays, vertical direction, Video Recording, video sequence, video signal processing

In this paper, we study the benefits of the availability of a specific form of additional information-the vertical direction (gravity) and the height of the camera, both of which can be conveniently measured using inertial sensors and a monocular video sequence for 3D urban modeling. We show that in the presence of this information, the SfM equations can be rewritten in a bilinear form. This allows us to derive a fast, robust, and scalable SfM algorithm for large scale applications. The SfM algorithm developed in this paper is experimentally demonstrated to have favorable properties compared to the sparse bundle adjustment algorithm. We provide experimental evidence indicating that the proposed algorithm converges in many cases to solutions with lower error than state-of-art implementations of bundle adjustment. We also demonstrate that for the case of large reconstruction problems, the proposed algorithm takes lesser time to reach its solution compared to bundle adjustment. We also present SfM results using our algorithm on the Google StreetView research data set.