Bo(V)W models for object recognition from video

Warren Rieutort-Louis, Ognjen Arandelovic

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

5 Citations (Scopus)

Abstract

In this paper we introduce two novel methods for object recognition from video. Our major contributions are (i) the use of dense, overlapping local descriptors as means of accurately capturing the appearance of generic, even untextured objects, (ii) a framework for employing such sets for recognition using video, (iii) a detailed empirical examination of different aspects of the proposed model and (iv) a comparative performance evaluation on a large object database. We describe and compare two bag-of-visual-words (BoVW)-based representations of an object's appearance in a video sequence, one using a per-sequence bag-of-words and one using a set of per-frame bag-of-words. Empirical results demonstrate the effectiveness of both representations with a somewhat favourable performance of the former.

Original languageEnglish
Title of host publication2015 22nd International Conference on Systems, Signals and Image Processing - Proceedings of IWSSIP 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages89-92
Number of pages4
ISBN (Print)9781467383530
DOIs
Publication statusPublished - 30 Oct 2015
Event22nd International Conference on Systems, Signals and Image Processing, IWSSIP 2015 - London, United Kingdom
Duration: 10 Sept 201512 Sept 2015

Conference

Conference22nd International Conference on Systems, Signals and Image Processing, IWSSIP 2015
Country/TerritoryUnited Kingdom
CityLondon
Period10/09/1512/09/15

Keywords

  • Dense
  • Features
  • Histogram
  • Matching
  • Overlap

Fingerprint

Dive into the research topics of 'Bo(V)W models for object recognition from video'. Together they form a unique fingerprint.

Cite this