Reflection detection in image sequences

Mohamed Elgharib, Francois Pitie, Anil Kokaram

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

10 Citations (Scopus)

Abstract

Reflections in image sequences consist of several layers superimposed over each other. This phenomenon causes many image processing techniques to fail as they assume the presence of only one layer at each examined site e.g. motion estimation and object recognition. This work presents an automated technique for detecting reflections in image sequences by analyzing motion trajectories of feature points. It models reflection as regions containing two different layers moving over each other. We present a strong detector based on combining a set of weak detectors. We use novel priors, generate sparse and dense detection maps and our results show high detection rate with rejection to pathological motion and occlusion.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages705-712
Number of pages8
DOIs
Publication statusPublished - 22 Sep 2011
Externally publishedYes
Event2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011 - Colorado Springs, CO, United States
Duration: 20 Jun 201125 Jun 2011

Other

Other2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
CountryUnited States
CityColorado Springs, CO
Period20/6/1125/6/11

Fingerprint

Detectors
Object recognition
Motion estimation
Image processing
Trajectories

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Elgharib, M., Pitie, F., & Kokaram, A. (2011). Reflection detection in image sequences. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 705-712). [5995670] https://doi.org/10.1109/CVPR.2011.5995670

Reflection detection in image sequences. / Elgharib, Mohamed; Pitie, Francois; Kokaram, Anil.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2011. p. 705-712 5995670.

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

Elgharib, M, Pitie, F & Kokaram, A 2011, Reflection detection in image sequences. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 5995670, pp. 705-712, 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, United States, 20/6/11. https://doi.org/10.1109/CVPR.2011.5995670
Elgharib M, Pitie F, Kokaram A. Reflection detection in image sequences. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2011. p. 705-712. 5995670 https://doi.org/10.1109/CVPR.2011.5995670
Elgharib, Mohamed ; Pitie, Francois ; Kokaram, Anil. / Reflection detection in image sequences. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2011. pp. 705-712
@inproceedings{a00549b053b24627ad02c267d971dec1,
title = "Reflection detection in image sequences",
abstract = "Reflections in image sequences consist of several layers superimposed over each other. This phenomenon causes many image processing techniques to fail as they assume the presence of only one layer at each examined site e.g. motion estimation and object recognition. This work presents an automated technique for detecting reflections in image sequences by analyzing motion trajectories of feature points. It models reflection as regions containing two different layers moving over each other. We present a strong detector based on combining a set of weak detectors. We use novel priors, generate sparse and dense detection maps and our results show high detection rate with rejection to pathological motion and occlusion.",
author = "Mohamed Elgharib and Francois Pitie and Anil Kokaram",
year = "2011",
month = "9",
day = "22",
doi = "10.1109/CVPR.2011.5995670",
language = "English",
isbn = "9781457703942",
pages = "705--712",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Reflection detection in image sequences

AU - Elgharib, Mohamed

AU - Pitie, Francois

AU - Kokaram, Anil

PY - 2011/9/22

Y1 - 2011/9/22

N2 - Reflections in image sequences consist of several layers superimposed over each other. This phenomenon causes many image processing techniques to fail as they assume the presence of only one layer at each examined site e.g. motion estimation and object recognition. This work presents an automated technique for detecting reflections in image sequences by analyzing motion trajectories of feature points. It models reflection as regions containing two different layers moving over each other. We present a strong detector based on combining a set of weak detectors. We use novel priors, generate sparse and dense detection maps and our results show high detection rate with rejection to pathological motion and occlusion.

AB - Reflections in image sequences consist of several layers superimposed over each other. This phenomenon causes many image processing techniques to fail as they assume the presence of only one layer at each examined site e.g. motion estimation and object recognition. This work presents an automated technique for detecting reflections in image sequences by analyzing motion trajectories of feature points. It models reflection as regions containing two different layers moving over each other. We present a strong detector based on combining a set of weak detectors. We use novel priors, generate sparse and dense detection maps and our results show high detection rate with rejection to pathological motion and occlusion.

UR - http://www.scopus.com/inward/record.url?scp=80052904035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052904035&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2011.5995670

DO - 10.1109/CVPR.2011.5995670

M3 - Conference contribution

AN - SCOPUS:80052904035

SN - 9781457703942

SP - 705

EP - 712

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -