User-assisted reflection detection and feature point tracking

Mohamed Elgharib, François Pitite, Anil Kokaram, Venkatesh Saligrama

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

Abstract

Reflections in image sequences violate the single layer model used by most current image processing techniques. As a result reflections cause many techniques to fail e.g. detection, tracking, motion estimation, etc. Recent work was proposed by Ahmed et al. [5] to detect reflections. Their technique is robust to pathological motion and motion blur. This paper has three main contributions. The first simplifies and fully automates the technique of Ahmed et al. User feedback is common in post-production video manipulation tools. Hence in the second contribution we propose an effective way of integrating few user-assisted masks to improve detection rates. The third contribution of this paper is an application for reflection detection. Here we explore better feature point tracking for the regions detected as reflection. Tracks usually die quickly in such regions due to temporal color inconsistencies. In this paper we show that the lifespan of such tracks can be extended through layer separation. Results show reduction in missed detections and in computational load over Ahmed et al. Results also show the generation of more reliable tracks despite strong layer mixing.

Original languageEnglish
Title of host publicationACM International Conference Proceeding Series
DOIs
Publication statusPublished - 1 Dec 2013
Externally publishedYes
Event10th European Conference on Visual Media Production, CVMP 2013 - London, United Kingdom
Duration: 6 Nov 20137 Nov 2013

Other

Other10th European Conference on Visual Media Production, CVMP 2013
CountryUnited Kingdom
CityLondon
Period6/11/137/11/13

Fingerprint

Motion estimation
Masks
Image processing
Color
Feedback

Keywords

  • feature point tracks
  • layer separation
  • reflection detection
  • user-assisted masks

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Elgharib, M., Pitite, F., Kokaram, A., & Saligrama, V. (2013). User-assisted reflection detection and feature point tracking. In ACM International Conference Proceeding Series https://doi.org/10.1145/2534008.2534011

User-assisted reflection detection and feature point tracking. / Elgharib, Mohamed; Pitite, François; Kokaram, Anil; Saligrama, Venkatesh.

ACM International Conference Proceeding Series. 2013.

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

Elgharib, M, Pitite, F, Kokaram, A & Saligrama, V 2013, User-assisted reflection detection and feature point tracking. in ACM International Conference Proceeding Series. 10th European Conference on Visual Media Production, CVMP 2013, London, United Kingdom, 6/11/13. https://doi.org/10.1145/2534008.2534011
Elgharib M, Pitite F, Kokaram A, Saligrama V. User-assisted reflection detection and feature point tracking. In ACM International Conference Proceeding Series. 2013 https://doi.org/10.1145/2534008.2534011
Elgharib, Mohamed ; Pitite, François ; Kokaram, Anil ; Saligrama, Venkatesh. / User-assisted reflection detection and feature point tracking. ACM International Conference Proceeding Series. 2013.
@inproceedings{a9aaa0950fe147b08c7d30b3d8550e26,
title = "User-assisted reflection detection and feature point tracking",
abstract = "Reflections in image sequences violate the single layer model used by most current image processing techniques. As a result reflections cause many techniques to fail e.g. detection, tracking, motion estimation, etc. Recent work was proposed by Ahmed et al. [5] to detect reflections. Their technique is robust to pathological motion and motion blur. This paper has three main contributions. The first simplifies and fully automates the technique of Ahmed et al. User feedback is common in post-production video manipulation tools. Hence in the second contribution we propose an effective way of integrating few user-assisted masks to improve detection rates. The third contribution of this paper is an application for reflection detection. Here we explore better feature point tracking for the regions detected as reflection. Tracks usually die quickly in such regions due to temporal color inconsistencies. In this paper we show that the lifespan of such tracks can be extended through layer separation. Results show reduction in missed detections and in computational load over Ahmed et al. Results also show the generation of more reliable tracks despite strong layer mixing.",
keywords = "feature point tracks, layer separation, reflection detection, user-assisted masks",
author = "Mohamed Elgharib and Fran{\cc}ois Pitite and Anil Kokaram and Venkatesh Saligrama",
year = "2013",
month = "12",
day = "1",
doi = "10.1145/2534008.2534011",
language = "English",
isbn = "9781450325899",
booktitle = "ACM International Conference Proceeding Series",

}

TY - GEN

T1 - User-assisted reflection detection and feature point tracking

AU - Elgharib, Mohamed

AU - Pitite, François

AU - Kokaram, Anil

AU - Saligrama, Venkatesh

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Reflections in image sequences violate the single layer model used by most current image processing techniques. As a result reflections cause many techniques to fail e.g. detection, tracking, motion estimation, etc. Recent work was proposed by Ahmed et al. [5] to detect reflections. Their technique is robust to pathological motion and motion blur. This paper has three main contributions. The first simplifies and fully automates the technique of Ahmed et al. User feedback is common in post-production video manipulation tools. Hence in the second contribution we propose an effective way of integrating few user-assisted masks to improve detection rates. The third contribution of this paper is an application for reflection detection. Here we explore better feature point tracking for the regions detected as reflection. Tracks usually die quickly in such regions due to temporal color inconsistencies. In this paper we show that the lifespan of such tracks can be extended through layer separation. Results show reduction in missed detections and in computational load over Ahmed et al. Results also show the generation of more reliable tracks despite strong layer mixing.

AB - Reflections in image sequences violate the single layer model used by most current image processing techniques. As a result reflections cause many techniques to fail e.g. detection, tracking, motion estimation, etc. Recent work was proposed by Ahmed et al. [5] to detect reflections. Their technique is robust to pathological motion and motion blur. This paper has three main contributions. The first simplifies and fully automates the technique of Ahmed et al. User feedback is common in post-production video manipulation tools. Hence in the second contribution we propose an effective way of integrating few user-assisted masks to improve detection rates. The third contribution of this paper is an application for reflection detection. Here we explore better feature point tracking for the regions detected as reflection. Tracks usually die quickly in such regions due to temporal color inconsistencies. In this paper we show that the lifespan of such tracks can be extended through layer separation. Results show reduction in missed detections and in computational load over Ahmed et al. Results also show the generation of more reliable tracks despite strong layer mixing.

KW - feature point tracks

KW - layer separation

KW - reflection detection

KW - user-assisted masks

UR - http://www.scopus.com/inward/record.url?scp=84897601762&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897601762&partnerID=8YFLogxK

U2 - 10.1145/2534008.2534011

DO - 10.1145/2534008.2534011

M3 - Conference contribution

SN - 9781450325899

BT - ACM International Conference Proceeding Series

ER -