3D Reconstruction of Periodic Motion from a Single View
2009-09-24
Loading...
View/Download File
Persistent link to this item
Statistics
View StatisticsJournal Title
Journal ISSN
Volume Title
Title
3D Reconstruction of Periodic Motion from a Single View
Alternative title
Authors
Published Date
2009-09-24
Publisher
Type
Report
Abstract
Periodicity has been recognized as an important cue for tasks like activity recognition and gait analysis. However, most existing techniques analyze periodic motions only in image coordinates, making them very dependent on the viewing angle. In this paper we show that it is possible to reconstruct a periodic trajectory in 3{D} given only its appearance in image coordinates from a single camera view. We draw a strong analogy between this problem and that of reconstructing an object from multiple views, which allows us to rely on well-known theoretical results from the multi-view geometry domain and obtain significant guarantees regarding the solvability of the estimation problem. We present two different formulations of the problem, along with techniques for performing the reconstruction in both cases, and an algorithm for estimating the period of motion from its image-coordinate trajectory. Experimental results demonstrate the feasibility of the proposed techniques.
Keywords
Description
Related to
Replaces
License
Series/Report Number
Technical Report; 09-025
Funding information
Isbn identifier
Doi identifier
Previously Published Citation
Other identifiers
Suggested citation
Ribnick, Evan. (2009). 3D Reconstruction of Periodic Motion from a Single View. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/215812.
Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.