Image ranking in video sequences using pairwise image comparisons and temporal smoothing

Michael Burke

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The ability to predict the importance of an image is highly desirable in computer vision. This work introduces an image ranking scheme suitable for use in video or image sequences. Pairwise image comparisons are used to determine image `interest' values within a standard Bayesian ranking framework, and a Rauch-Tung-Striebel smoother is used to improve these interest scores. Results show that the training data requirements typically associated with pairwise ranking systems are dramatically reduced by incorporating temporal smoothness constraints. Experiments on a coastal image dataset show that smoothed pairwise ranking can provide ranking results equivalent to standard pairwise ranking with less than half the training data.
Original languageEnglish
Title of host publication2016 Pattern Recognition Association of South Africa and Robotics and Mechatronics
Place of PublicationStellenbosch, South Africa
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages6
ISBN (Electronic)978-1-5090-3335-5
ISBN (Print)978-1-5090-3336-2
DOIs
Publication statusPublished - 16 Jan 2017
EventSymposium of the Pattern Recognition Association of South Africa (PRASA) and Conference of Robotics and Mechatronics (RobMech) 2016 - Stellenbosch, South Africa
Duration: 30 Nov 20162 Dec 2016
http://blogs.sun.ac.za/prasarobmech2016/

Conference

ConferenceSymposium of the Pattern Recognition Association of South Africa (PRASA) and Conference of Robotics and Mechatronics (RobMech) 2016
Abbreviated titlePRASA-RobMech 2016
CountrySouth Africa
CityStellenbosch
Period30/11/162/12/16
Internet address

Fingerprint Dive into the research topics of 'Image ranking in video sequences using pairwise image comparisons and temporal smoothing'. Together they form a unique fingerprint.

Cite this