Compensating for camera translation in video eye-movement recordings by tracking a representative landmark selected automatically by a genetic algorithm

Faisal Karmali, Mark J Shelhamer

Research output: Contribution to journalArticle

Abstract

It is common in oculomotor and vestibular research to use video or still cameras to acquire data on eye movements. Unfortunately, such data are often contaminated by unwanted motion of the face relative to the camera, especially during experiments in dynamic motion environments. We develop a method for estimating the motion of a camera relative to a highly deformable surface, specifically the movement of a camera relative to the face and eyes. A small rectangular region of interest (ROI) on the face is automatically selected and tracked throughout a set of video frames as a measure of vertical camera translation. The specific goal is to present a process based on a genetic algorithm that selects a suitable ROI for tracking: one whose translation within the camera image accurately matches the actual relative motion of the camera. We find that co-correlation, a statistic describing the time series of a large group of ROIs, predicts the accuracy of the ROIs, and can be used to select the best ROI from a group. After the genetic algorithm finds the best ROIs from a group, it uses recombination to form a new generation of ROIs that inherit properties of the ROIs from the previous generation. We show that the algorithm can select an ROI that will estimate camera translation and determine the direction that the eye is looking with an average accuracy of 0.75°, even with camera translations of 2.5 mm at a viewing distance of 120 mm, which would cause an error of 11° without correction.

Original languageEnglish (US)
Pages (from-to)157-165
Number of pages9
JournalJournal of Neuroscience Methods
Volume176
Issue number2
DOIs
StatePublished - Jan 30 2009

Fingerprint

Eye Movements
Public Opinion
Genetic Recombination
Research

Keywords

  • Cross-correlation
  • Eye
  • Genetic algorithm
  • Video
  • Video-oculography
  • VOG

ASJC Scopus subject areas

  • Neuroscience(all)

Cite this

@article{c69be9e7c7e34d47b06ba811fc4eb34a,
title = "Compensating for camera translation in video eye-movement recordings by tracking a representative landmark selected automatically by a genetic algorithm",
abstract = "It is common in oculomotor and vestibular research to use video or still cameras to acquire data on eye movements. Unfortunately, such data are often contaminated by unwanted motion of the face relative to the camera, especially during experiments in dynamic motion environments. We develop a method for estimating the motion of a camera relative to a highly deformable surface, specifically the movement of a camera relative to the face and eyes. A small rectangular region of interest (ROI) on the face is automatically selected and tracked throughout a set of video frames as a measure of vertical camera translation. The specific goal is to present a process based on a genetic algorithm that selects a suitable ROI for tracking: one whose translation within the camera image accurately matches the actual relative motion of the camera. We find that co-correlation, a statistic describing the time series of a large group of ROIs, predicts the accuracy of the ROIs, and can be used to select the best ROI from a group. After the genetic algorithm finds the best ROIs from a group, it uses recombination to form a new generation of ROIs that inherit properties of the ROIs from the previous generation. We show that the algorithm can select an ROI that will estimate camera translation and determine the direction that the eye is looking with an average accuracy of 0.75°, even with camera translations of 2.5 mm at a viewing distance of 120 mm, which would cause an error of 11° without correction.",
keywords = "Cross-correlation, Eye, Genetic algorithm, Video, Video-oculography, VOG",
author = "Faisal Karmali and Shelhamer, {Mark J}",
year = "2009",
month = "1",
day = "30",
doi = "10.1016/j.jneumeth.2008.09.010",
language = "English (US)",
volume = "176",
pages = "157--165",
journal = "Journal of Neuroscience Methods",
issn = "0165-0270",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Compensating for camera translation in video eye-movement recordings by tracking a representative landmark selected automatically by a genetic algorithm

AU - Karmali, Faisal

AU - Shelhamer, Mark J

PY - 2009/1/30

Y1 - 2009/1/30

N2 - It is common in oculomotor and vestibular research to use video or still cameras to acquire data on eye movements. Unfortunately, such data are often contaminated by unwanted motion of the face relative to the camera, especially during experiments in dynamic motion environments. We develop a method for estimating the motion of a camera relative to a highly deformable surface, specifically the movement of a camera relative to the face and eyes. A small rectangular region of interest (ROI) on the face is automatically selected and tracked throughout a set of video frames as a measure of vertical camera translation. The specific goal is to present a process based on a genetic algorithm that selects a suitable ROI for tracking: one whose translation within the camera image accurately matches the actual relative motion of the camera. We find that co-correlation, a statistic describing the time series of a large group of ROIs, predicts the accuracy of the ROIs, and can be used to select the best ROI from a group. After the genetic algorithm finds the best ROIs from a group, it uses recombination to form a new generation of ROIs that inherit properties of the ROIs from the previous generation. We show that the algorithm can select an ROI that will estimate camera translation and determine the direction that the eye is looking with an average accuracy of 0.75°, even with camera translations of 2.5 mm at a viewing distance of 120 mm, which would cause an error of 11° without correction.

AB - It is common in oculomotor and vestibular research to use video or still cameras to acquire data on eye movements. Unfortunately, such data are often contaminated by unwanted motion of the face relative to the camera, especially during experiments in dynamic motion environments. We develop a method for estimating the motion of a camera relative to a highly deformable surface, specifically the movement of a camera relative to the face and eyes. A small rectangular region of interest (ROI) on the face is automatically selected and tracked throughout a set of video frames as a measure of vertical camera translation. The specific goal is to present a process based on a genetic algorithm that selects a suitable ROI for tracking: one whose translation within the camera image accurately matches the actual relative motion of the camera. We find that co-correlation, a statistic describing the time series of a large group of ROIs, predicts the accuracy of the ROIs, and can be used to select the best ROI from a group. After the genetic algorithm finds the best ROIs from a group, it uses recombination to form a new generation of ROIs that inherit properties of the ROIs from the previous generation. We show that the algorithm can select an ROI that will estimate camera translation and determine the direction that the eye is looking with an average accuracy of 0.75°, even with camera translations of 2.5 mm at a viewing distance of 120 mm, which would cause an error of 11° without correction.

KW - Cross-correlation

KW - Eye

KW - Genetic algorithm

KW - Video

KW - Video-oculography

KW - VOG

UR - http://www.scopus.com/inward/record.url?scp=57649171510&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57649171510&partnerID=8YFLogxK

U2 - 10.1016/j.jneumeth.2008.09.010

DO - 10.1016/j.jneumeth.2008.09.010

M3 - Article

C2 - 18835407

AN - SCOPUS:57649171510

VL - 176

SP - 157

EP - 165

JO - Journal of Neuroscience Methods

JF - Journal of Neuroscience Methods

SN - 0165-0270

IS - 2

ER -