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

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

1 Citation (Scopus)

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 International Conference (PRASA-RobMech 2016)
EditorsMichael Burke, Deon Sabatta
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9781509033355
ISBN (Print)9781509033362
DOIs
Publication statusPublished - 2017
Externally publishedYes
EventPattern Recognition Association of South Africa and Robotics and Mechatronics International Conference 2016 - Stellenbosch, South Africa
Duration: 30 Nov 20162 Dec 2016
https://ieeexplore.ieee.org/xpl/conhome/7794375/proceeding (Proceedings)
http://blogs.sun.ac.za/prasarobmech2016/ (Website)

Conference

ConferencePattern Recognition Association of South Africa and Robotics and Mechatronics International Conference 2016
Abbreviated titlePRASA-RobMech 2016
CountrySouth Africa
CityStellenbosch
Period30/11/162/12/16
Internet address

Cite this