Visual precis generation using coresets
Author(s)
Paul, Rohan; Feldman, Dan; Newman, Paul; Rus, Daniela L.
DownloadRus_Visual precis.pdf (2.204Mb)
OPEN_ACCESS_POLICY
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
Given an image stream, our on-line algorithm will select the semantically-important images that summarize the visual experience of a mobile robot. Our approach consists of data pre-clustering using coresets followed by a graph based incremental clustering procedure using a topic based image representation. A coreset for an image stream is a set of representative images that semantically compresses the data corpus, in the sense that every frame has a similar representative image in the coreset. We prove that our algorithm efficiently computes the smallest possible coreset under natural well-defined similarity metric and up to provably small approximation factor. The output visual summary is computed via a hierarchical tree of coresets for different parts of the image stream. This allows multi-resolution summarization (or a video summary of specified duration) in the batch setting and a memory-efficient incremental summary for the streaming case.
Date issued
2014-05Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryJournal
Proceedings of the 2014 IEEE International Conference on Robotics and Automation (ICRA)
Citation
Paul, Rohan, Dan Feldman, Daniela Rus, and Paul Newman. “Visual Precis Generation Using Coresets.” 2014 IEEE International Conference on Robotics and Automation (ICRA) (May 2014).
Version: Author's final manuscript
ISBN
978-1-4799-3685-4