Visual precis generation using coresets

Rohan Paul; Dan Feldman; Daniela Rus; Paul Newman

doi:10.1109/ICRA.2014.6907021

Visual precis generation using coresets

Rohan Paul
, Dan Feldman
, Daniela Rus
, Paul Newman

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

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 language	English
Title of host publication	Proceedings - IEEE International Conference on Robotics and Automation
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1304-1311
Number of pages	8
ISBN (Electronic)	9781479936854, 9781479936854
DOIs	https://doi.org/10.1109/ICRA.2014.6907021
State	Published - 22 Sep 2014
Externally published	Yes
Event	2014 IEEE International Conference on Robotics and Automation, ICRA 2014 - Hong Kong, China Duration: 31 May 2014 → 7 Jun 2014

Publication series

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

Conference

Conference	2014 IEEE International Conference on Robotics and Automation, ICRA 2014
Country/Territory	China
City	Hong Kong
Period	31/05/14 → 7/06/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

ASJC Scopus subject areas

Software
Control and Systems Engineering
Electrical and Electronic Engineering
Artificial Intelligence

Access to Document

10.1109/ICRA.2014.6907021

Cite this

Paul, R., Feldman, D., Rus, D., & Newman, P. (2014). Visual precis generation using coresets. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 1304-1311). Article 6907021 (Proceedings - IEEE International Conference on Robotics and Automation). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRA.2014.6907021

@inproceedings{8813f7dba939419c99b39d28bb4ddc46,

title = "Visual precis generation using coresets",

abstract = "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.",

author = "Rohan Paul and Dan Feldman and Daniela Rus and Paul Newman",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE International Conference on Robotics and Automation, ICRA 2014 ; Conference date: 31-05-2014 Through 07-06-2014",

year = "2014",

month = sep,

day = "22",

doi = "10.1109/ICRA.2014.6907021",

language = "English",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1304--1311",

booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

address = "United States",

}

Paul, R, Feldman, D, Rus, D & Newman, P 2014, Visual precis generation using coresets. in Proceedings - IEEE International Conference on Robotics and Automation., 6907021, Proceedings - IEEE International Conference on Robotics and Automation, Institute of Electrical and Electronics Engineers Inc., pp. 1304-1311, 2014 IEEE International Conference on Robotics and Automation, ICRA 2014, Hong Kong, China, 31/05/14. https://doi.org/10.1109/ICRA.2014.6907021

Visual precis generation using coresets. / Paul, Rohan; Feldman, Dan; Rus, Daniela et al.
Proceedings - IEEE International Conference on Robotics and Automation. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1304-1311 6907021 (Proceedings - IEEE International Conference on Robotics and Automation).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Visual precis generation using coresets

AU - Paul, Rohan

AU - Feldman, Dan

AU - Rus, Daniela

AU - Newman, Paul

PY - 2014/9/22

Y1 - 2014/9/22

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/84929224383

U2 - 10.1109/ICRA.2014.6907021

DO - 10.1109/ICRA.2014.6907021

M3 - Conference contribution

AN - SCOPUS:84929224383

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 1304

EP - 1311

BT - Proceedings - IEEE International Conference on Robotics and Automation

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 IEEE International Conference on Robotics and Automation, ICRA 2014

Y2 - 31 May 2014 through 7 June 2014

ER -

Visual precis generation using coresets

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this