Real-Time Pupil Localization Algorithm for Blurred Images Based on Double Constraints

Accurate pupil localization is crucial for the eye-tracking technology used in monitoring driver fatigue. However, factors such as poor road conditions may result in blurred eye images being captured by eye-tracking devices, affecting the accuracy of pupil localization. To address the above problems...

Full description

Saved in:
Bibliographic Details
Main Authors: Shufang Qiu, Yi Wang, Zeyuan Liu, Huaiyu Cai, Xiaodong Chen
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/6/1749
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850087956937703424
author Shufang Qiu
Yi Wang
Zeyuan Liu
Huaiyu Cai
Xiaodong Chen
author_facet Shufang Qiu
Yi Wang
Zeyuan Liu
Huaiyu Cai
Xiaodong Chen
author_sort Shufang Qiu
collection DOAJ
description Accurate pupil localization is crucial for the eye-tracking technology used in monitoring driver fatigue. However, factors such as poor road conditions may result in blurred eye images being captured by eye-tracking devices, affecting the accuracy of pupil localization. To address the above problems, we propose a real-time pupil localization algorithm for blurred images based on double constraints. The algorithm is divided into three stages: extracting the rough pupil area based on grayscale constraints, refining the pupil region based on geometric constraints, and determining the pupil center according to geometric moments. First, the rough pupil area is adaptively extracted from the input image based on grayscale constraints. Then, the designed pupil shape index is used to refine the pupil area based on geometric constraints. Finally, the geometric moments are calculated to quickly locate the pupil center. The experimental results demonstrate that the algorithm exhibits superior localization performance in both blurred and clear images, with a localization error within 6 pixels, an accuracy exceeding 97%, and real-time performance of up to 85 fps. The proposed algorithm provides an efficient and precise solution for pupil localization, demonstrating practical applicability in the monitoring of real-world driver fatigue.
format Article
id doaj-art-fbcaebd4b32e4b78976371e16d5233d3
institution DOAJ
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-fbcaebd4b32e4b78976371e16d5233d32025-08-20T02:43:07ZengMDPI AGSensors1424-82202025-03-01256174910.3390/s25061749Real-Time Pupil Localization Algorithm for Blurred Images Based on Double ConstraintsShufang Qiu0Yi Wang1Zeyuan Liu2Huaiyu Cai3Xiaodong Chen4Key Laboratory of Opto-Electronics Information Technology of Ministry of Education, School of Precision Instruments and Optoelectronic Engineering, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Opto-Electronics Information Technology of Ministry of Education, School of Precision Instruments and Optoelectronic Engineering, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Opto-Electronics Information Technology of Ministry of Education, School of Precision Instruments and Optoelectronic Engineering, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Opto-Electronics Information Technology of Ministry of Education, School of Precision Instruments and Optoelectronic Engineering, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Opto-Electronics Information Technology of Ministry of Education, School of Precision Instruments and Optoelectronic Engineering, Tianjin University, Tianjin 300072, ChinaAccurate pupil localization is crucial for the eye-tracking technology used in monitoring driver fatigue. However, factors such as poor road conditions may result in blurred eye images being captured by eye-tracking devices, affecting the accuracy of pupil localization. To address the above problems, we propose a real-time pupil localization algorithm for blurred images based on double constraints. The algorithm is divided into three stages: extracting the rough pupil area based on grayscale constraints, refining the pupil region based on geometric constraints, and determining the pupil center according to geometric moments. First, the rough pupil area is adaptively extracted from the input image based on grayscale constraints. Then, the designed pupil shape index is used to refine the pupil area based on geometric constraints. Finally, the geometric moments are calculated to quickly locate the pupil center. The experimental results demonstrate that the algorithm exhibits superior localization performance in both blurred and clear images, with a localization error within 6 pixels, an accuracy exceeding 97%, and real-time performance of up to 85 fps. The proposed algorithm provides an efficient and precise solution for pupil localization, demonstrating practical applicability in the monitoring of real-world driver fatigue.https://www.mdpi.com/1424-8220/25/6/1749eye trackerblurred imagespupil center localizationgrayscale constraintsgeometric constraintspupil shape index
spellingShingle Shufang Qiu
Yi Wang
Zeyuan Liu
Huaiyu Cai
Xiaodong Chen
Real-Time Pupil Localization Algorithm for Blurred Images Based on Double Constraints
Sensors
eye tracker
blurred images
pupil center localization
grayscale constraints
geometric constraints
pupil shape index
title Real-Time Pupil Localization Algorithm for Blurred Images Based on Double Constraints
title_full Real-Time Pupil Localization Algorithm for Blurred Images Based on Double Constraints
title_fullStr Real-Time Pupil Localization Algorithm for Blurred Images Based on Double Constraints
title_full_unstemmed Real-Time Pupil Localization Algorithm for Blurred Images Based on Double Constraints
title_short Real-Time Pupil Localization Algorithm for Blurred Images Based on Double Constraints
title_sort real time pupil localization algorithm for blurred images based on double constraints
topic eye tracker
blurred images
pupil center localization
grayscale constraints
geometric constraints
pupil shape index
url https://www.mdpi.com/1424-8220/25/6/1749
work_keys_str_mv AT shufangqiu realtimepupillocalizationalgorithmforblurredimagesbasedondoubleconstraints
AT yiwang realtimepupillocalizationalgorithmforblurredimagesbasedondoubleconstraints
AT zeyuanliu realtimepupillocalizationalgorithmforblurredimagesbasedondoubleconstraints
AT huaiyucai realtimepupillocalizationalgorithmforblurredimagesbasedondoubleconstraints
AT xiaodongchen realtimepupillocalizationalgorithmforblurredimagesbasedondoubleconstraints