Embedded solution to detect and classify head level objects using stereo vision for visually impaired people with audio feedback

Abstract This work presents an embedded solution for detecting and classifying head-level objects using stereo vision to assist blind individuals. A custom dataset was created, featuring five classes of head-level objects, selected based on a survey of visually impaired users. Object detection and c...

Full description

Saved in:
Bibliographic Details
Main Authors: Kevin Muñoz, Mario Chavarria, Luisa Ortiz, Silvan Suter, Klaus Schönenberger, Bladimir Bacca-Cortes
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01529-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387871072419840
author Kevin Muñoz
Mario Chavarria
Luisa Ortiz
Silvan Suter
Klaus Schönenberger
Bladimir Bacca-Cortes
author_facet Kevin Muñoz
Mario Chavarria
Luisa Ortiz
Silvan Suter
Klaus Schönenberger
Bladimir Bacca-Cortes
author_sort Kevin Muñoz
collection DOAJ
description Abstract This work presents an embedded solution for detecting and classifying head-level objects using stereo vision to assist blind individuals. A custom dataset was created, featuring five classes of head-level objects, selected based on a survey of visually impaired users. Object detection and classification were achieved using deep-neural networks such as YoloV5. The system computes the relative range and orientation of detected head-level objects and provides audio feedback to alert the user about nearby objects. Four types of tests were conducted: a dataset-based test, achieving a mAP@0.95 of 0.89 for head-level objects classification; a quantitative assessment of range and orientation, with an average error of 0.028 m ± 0.004 and 2.05°±0.09, respectively; a field test conducted over a week at different times and lighting conditions, yielding a precision/recall of 98.21%/93.75% for head-level object classification; and user tests with Head-level identification accuracy of 91% and obstacle-avoidance/local-navigation where users reported an average of 88.75% for low or middle risk.
format Article
id doaj-art-be4bab81d22244d7a0938c8e7e0835fa
institution Kabale University
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-be4bab81d22244d7a0938c8e7e0835fa2025-08-20T03:42:28ZengNature PortfolioScientific Reports2045-23222025-05-0115111910.1038/s41598-025-01529-7Embedded solution to detect and classify head level objects using stereo vision for visually impaired people with audio feedbackKevin Muñoz0Mario Chavarria1Luisa Ortiz2Silvan Suter3Klaus Schönenberger4Bladimir Bacca-Cortes5School of Electrical and Electronic Engineering, Universidad del ValleSwiss Federal Institute of Technology Lausanne, EssentialTechFaculty of Engineering and Basic Sciences, Universidad Autónoma de OccidentSwiss Federal Institute of Technology Lausanne, EssentialTechSwiss Federal Institute of Technology Lausanne, EssentialTechSchool of Electrical and Electronic Engineering, Universidad del ValleAbstract This work presents an embedded solution for detecting and classifying head-level objects using stereo vision to assist blind individuals. A custom dataset was created, featuring five classes of head-level objects, selected based on a survey of visually impaired users. Object detection and classification were achieved using deep-neural networks such as YoloV5. The system computes the relative range and orientation of detected head-level objects and provides audio feedback to alert the user about nearby objects. Four types of tests were conducted: a dataset-based test, achieving a mAP@0.95 of 0.89 for head-level objects classification; a quantitative assessment of range and orientation, with an average error of 0.028 m ± 0.004 and 2.05°±0.09, respectively; a field test conducted over a week at different times and lighting conditions, yielding a precision/recall of 98.21%/93.75% for head-level object classification; and user tests with Head-level identification accuracy of 91% and obstacle-avoidance/local-navigation where users reported an average of 88.75% for low or middle risk.https://doi.org/10.1038/s41598-025-01529-7Audio feedbackConvolutional neural networksEmbedded systemsHead-level object detectionVisually impaired people
spellingShingle Kevin Muñoz
Mario Chavarria
Luisa Ortiz
Silvan Suter
Klaus Schönenberger
Bladimir Bacca-Cortes
Embedded solution to detect and classify head level objects using stereo vision for visually impaired people with audio feedback
Scientific Reports
Audio feedback
Convolutional neural networks
Embedded systems
Head-level object detection
Visually impaired people
title Embedded solution to detect and classify head level objects using stereo vision for visually impaired people with audio feedback
title_full Embedded solution to detect and classify head level objects using stereo vision for visually impaired people with audio feedback
title_fullStr Embedded solution to detect and classify head level objects using stereo vision for visually impaired people with audio feedback
title_full_unstemmed Embedded solution to detect and classify head level objects using stereo vision for visually impaired people with audio feedback
title_short Embedded solution to detect and classify head level objects using stereo vision for visually impaired people with audio feedback
title_sort embedded solution to detect and classify head level objects using stereo vision for visually impaired people with audio feedback
topic Audio feedback
Convolutional neural networks
Embedded systems
Head-level object detection
Visually impaired people
url https://doi.org/10.1038/s41598-025-01529-7
work_keys_str_mv AT kevinmunoz embeddedsolutiontodetectandclassifyheadlevelobjectsusingstereovisionforvisuallyimpairedpeoplewithaudiofeedback
AT mariochavarria embeddedsolutiontodetectandclassifyheadlevelobjectsusingstereovisionforvisuallyimpairedpeoplewithaudiofeedback
AT luisaortiz embeddedsolutiontodetectandclassifyheadlevelobjectsusingstereovisionforvisuallyimpairedpeoplewithaudiofeedback
AT silvansuter embeddedsolutiontodetectandclassifyheadlevelobjectsusingstereovisionforvisuallyimpairedpeoplewithaudiofeedback
AT klausschonenberger embeddedsolutiontodetectandclassifyheadlevelobjectsusingstereovisionforvisuallyimpairedpeoplewithaudiofeedback
AT bladimirbaccacortes embeddedsolutiontodetectandclassifyheadlevelobjectsusingstereovisionforvisuallyimpairedpeoplewithaudiofeedback