Visual precis generation using coresets

Rohan Paul, Dan Feldman, Daniela Rus, Paul Newman

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


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.

Original languageEnglish
Title of host publicationIEEE International Conference on Robotics and Automation (ICRA) 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages8
ISBN (Electronic)9781479936854, 9781479936854
StatePublished - 22 Sep 2014
Externally publishedYes
Event2014 IEEE International Conference on Robotics and Automation, ICRA 2014 - Hong Kong, China
Duration: 31 May 20147 Jun 2014

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729


Conference2014 IEEE International Conference on Robotics and Automation, ICRA 2014
CityHong Kong

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering


Dive into the research topics of 'Visual precis generation using coresets'. Together they form a unique fingerprint.

Cite this