Augmentation for Accuracy Improvement of YOLOv8 in Blind Navigation System

This study addresses the critical need for enhanced accuracy in YOLOv8 models designed for visually impaired navigation systems. Existing models often struggle with consistency in object detection and distance estimation under varying environmental conditions, leading to potential safety risks. To o...

Full description

Saved in:
Bibliographic Details
Main Authors: Erwin Syahrudin, Ema Utami, Anggit Dwi Hartanto
Format: Article
Language:English
Published: Ikatan Ahli Informatika Indonesia 2024-08-01
Series:Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Subjects:
Online Access:https://jurnal.iaii.or.id/index.php/RESTI/article/view/5931
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850119220485947392
author Erwin Syahrudin
Ema Utami
Anggit Dwi Hartanto
author_facet Erwin Syahrudin
Ema Utami
Anggit Dwi Hartanto
author_sort Erwin Syahrudin
collection DOAJ
description This study addresses the critical need for enhanced accuracy in YOLOv8 models designed for visually impaired navigation systems. Existing models often struggle with consistency in object detection and distance estimation under varying environmental conditions, leading to potential safety risks. To overcome these challenges, this research implements a rigorous approach combining data augmentation and meticulous model optimization techniques. The process begins with the meticulous collection of a diverse dataset, essential for training a robust model. Subsequent preprocessing of images in the HSV color space ensures standardized input features, crucial for consistency in model training. Augmentation techniques are then applied to enrich the dataset, enhancing model generalization and robustness. The YOLOv8 model is trained using this augmented dataset, leading to significant enhancements in key performance metrics. Specifically, mean average precision (mAP) improved by 13.3%, from 0.75 to 0.85, precision increased by 10%, from 0.80 to 0.88, and recall rose by 10.3%, from 0.78 to 0.86. Further optimization efforts, including parameter tuning and the strategic integration of a Kalman Filter, notably improved object tracking and distance estimation capabilities. Final validation in real-world scenarios confirms the efficacy of the optimized model, demonstrating its readiness for practical deployment. This comprehensive approach showcases tangible advances in navigational assistance technology, significantly improving safety and reliability for visually impaired users.
format Article
id doaj-art-589930e3be47489ea94aa00492ef685f
institution OA Journals
issn 2580-0760
language English
publishDate 2024-08-01
publisher Ikatan Ahli Informatika Indonesia
record_format Article
series Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
spelling doaj-art-589930e3be47489ea94aa00492ef685f2025-08-20T02:35:40ZengIkatan Ahli Informatika IndonesiaJurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)2580-07602024-08-018457958810.29207/resti.v8i4.59315931Augmentation for Accuracy Improvement of YOLOv8 in Blind Navigation SystemErwin Syahrudin0Ema Utami1Anggit Dwi Hartanto2Universitas Amikom YogyakartaUniversitas Amikom YogyakartaUniversitas Amikom YogyakartaThis study addresses the critical need for enhanced accuracy in YOLOv8 models designed for visually impaired navigation systems. Existing models often struggle with consistency in object detection and distance estimation under varying environmental conditions, leading to potential safety risks. To overcome these challenges, this research implements a rigorous approach combining data augmentation and meticulous model optimization techniques. The process begins with the meticulous collection of a diverse dataset, essential for training a robust model. Subsequent preprocessing of images in the HSV color space ensures standardized input features, crucial for consistency in model training. Augmentation techniques are then applied to enrich the dataset, enhancing model generalization and robustness. The YOLOv8 model is trained using this augmented dataset, leading to significant enhancements in key performance metrics. Specifically, mean average precision (mAP) improved by 13.3%, from 0.75 to 0.85, precision increased by 10%, from 0.80 to 0.88, and recall rose by 10.3%, from 0.78 to 0.86. Further optimization efforts, including parameter tuning and the strategic integration of a Kalman Filter, notably improved object tracking and distance estimation capabilities. Final validation in real-world scenarios confirms the efficacy of the optimized model, demonstrating its readiness for practical deployment. This comprehensive approach showcases tangible advances in navigational assistance technology, significantly improving safety and reliability for visually impaired users.https://jurnal.iaii.or.id/index.php/RESTI/article/view/5931yolov8object detectiondata augmentationmodel optimizationvisual impairment
spellingShingle Erwin Syahrudin
Ema Utami
Anggit Dwi Hartanto
Augmentation for Accuracy Improvement of YOLOv8 in Blind Navigation System
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
yolov8
object detection
data augmentation
model optimization
visual impairment
title Augmentation for Accuracy Improvement of YOLOv8 in Blind Navigation System
title_full Augmentation for Accuracy Improvement of YOLOv8 in Blind Navigation System
title_fullStr Augmentation for Accuracy Improvement of YOLOv8 in Blind Navigation System
title_full_unstemmed Augmentation for Accuracy Improvement of YOLOv8 in Blind Navigation System
title_short Augmentation for Accuracy Improvement of YOLOv8 in Blind Navigation System
title_sort augmentation for accuracy improvement of yolov8 in blind navigation system
topic yolov8
object detection
data augmentation
model optimization
visual impairment
url https://jurnal.iaii.or.id/index.php/RESTI/article/view/5931
work_keys_str_mv AT erwinsyahrudin augmentationforaccuracyimprovementofyolov8inblindnavigationsystem
AT emautami augmentationforaccuracyimprovementofyolov8inblindnavigationsystem
AT anggitdwihartanto augmentationforaccuracyimprovementofyolov8inblindnavigationsystem