Modeling and estimating persistent motion with geometric flows
Name
Grimson_Modeling and estimating.pdf
Size
1.7 MB
Format
Adobe PDF
Checksum (MD5)
d4e15c58a219da31d6b2581ddd3f1c55
Author(s)
Lin, Dahua
Grimson, Eric
Fisher, John W., III
Date Issued
August 2010
Journal
2010 IEEE Conference on Computer Vision and Pattern Recognition
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Lin, Dahua, Eric Grimson, and John Fisher. “Modeling and Estimating Persistent Motion with Geometric Flows.” IEEE, 2010. 1–8. © Copyright 2010 IEEE
Version
Final published version
Abstract
We propose a principled framework to model persistent motion in dynamic scenes. In contrast to previous efforts on object tracking and optical flow estimation that focus on local motion, we primarily aim at inferring a global model of persistent and collective dynamics. With this in mind, we first introduce the concept of geometric flow that describes motion simultaneously over space and time, and derive a vector space representation based on Lie algebra. We then extend it to model complex motion by combining multiple flows in a geometrically consistent manner. Taking advantage of the linear nature of this representation, we formulate a stochastic flow model, and incorporate a Gaussian process to capture the spatial coherence more effectively. This model leads to an efficient and robust algorithm that can integrate both point pairs and frame differences in motion estimation. We conducted experiments on different types of videos. The results clearly demonstrate that the proposed approach is effective in modeling persistent motion.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPR.2010.5539848
