Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public Transportation

Advancements in automation and artificial intelligence have significantly impacted accessibility for individuals with visual impairments, particularly in the realm of bus public transportation. Effective bus detection and bus point-of-view (POV) classification are crucial for enhancing the independe...

Full description

Saved in:
Bibliographic Details
Main Authors: Rio Arifando, Shinji Eto, Tibyani Tibyani, Chikamune Wada
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Informatics
Subjects:
Online Access:https://www.mdpi.com/2227-9709/12/1/7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850090736930783232
author Rio Arifando
Shinji Eto
Tibyani Tibyani
Chikamune Wada
author_facet Rio Arifando
Shinji Eto
Tibyani Tibyani
Chikamune Wada
author_sort Rio Arifando
collection DOAJ
description Advancements in automation and artificial intelligence have significantly impacted accessibility for individuals with visual impairments, particularly in the realm of bus public transportation. Effective bus detection and bus point-of-view (POV) classification are crucial for enhancing the independence of visually impaired individuals. This study introduces the Improved-YOLOv10, a novel model designed to tackle challenges in bus identification and pov classification by integrating Coordinate Attention (CA) and Adaptive Kernel Convolution (AKConv) into the YOLOv10 framework. The Improved YOLOv10 advances the YOLOv10 architecture through the incorporation of CA, which enhances long-range dependency modeling and spatial awareness, and AKConv, which dynamically adjusts convolutional kernels for superior feature extraction. These enhancements aim to improve both detection accuracy and efficiency, essential for real-time applications in assistive technologies. Evaluation results demonstrate that the Improved-YOLOv10 offers significant improvements in detection performance, including better Accuracy, Precision and Recall compared to YOLOv10. The model also exhibits reduced computational complexity and storage requirements, highlighting its efficiency. While the classification results show some trade-offs, with slightly decreased overall F1 score, the complexity of Giga Floating Point Operations (GFLOPs), Parameters, and Weight/MB in the Improved-YOLOv10 remains advantageous for classification tasks. The model’s architectural improvements contribute to its robustness and efficiency, making it a suitable choice for real-time applications and assistive technologies.
format Article
id doaj-art-2b4a4cf969ef493fb9d05cd086a17eb9
institution DOAJ
issn 2227-9709
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Informatics
spelling doaj-art-2b4a4cf969ef493fb9d05cd086a17eb92025-08-20T02:42:31ZengMDPI AGInformatics2227-97092025-01-01121710.3390/informatics12010007Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public TransportationRio Arifando0Shinji Eto1Tibyani Tibyani2Chikamune Wada3Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, 2–4 Hibikino, Wakamatsu-ku, Kitakyushu 808-0196, JapanGraduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, 2–4 Hibikino, Wakamatsu-ku, Kitakyushu 808-0196, JapanDepartment of Information Systems, Faculty of Computer Science, Brawijaya University, Malang 65145, IndonesiaGraduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, 2–4 Hibikino, Wakamatsu-ku, Kitakyushu 808-0196, JapanAdvancements in automation and artificial intelligence have significantly impacted accessibility for individuals with visual impairments, particularly in the realm of bus public transportation. Effective bus detection and bus point-of-view (POV) classification are crucial for enhancing the independence of visually impaired individuals. This study introduces the Improved-YOLOv10, a novel model designed to tackle challenges in bus identification and pov classification by integrating Coordinate Attention (CA) and Adaptive Kernel Convolution (AKConv) into the YOLOv10 framework. The Improved YOLOv10 advances the YOLOv10 architecture through the incorporation of CA, which enhances long-range dependency modeling and spatial awareness, and AKConv, which dynamically adjusts convolutional kernels for superior feature extraction. These enhancements aim to improve both detection accuracy and efficiency, essential for real-time applications in assistive technologies. Evaluation results demonstrate that the Improved-YOLOv10 offers significant improvements in detection performance, including better Accuracy, Precision and Recall compared to YOLOv10. The model also exhibits reduced computational complexity and storage requirements, highlighting its efficiency. While the classification results show some trade-offs, with slightly decreased overall F1 score, the complexity of Giga Floating Point Operations (GFLOPs), Parameters, and Weight/MB in the Improved-YOLOv10 remains advantageous for classification tasks. The model’s architectural improvements contribute to its robustness and efficiency, making it a suitable choice for real-time applications and assistive technologies.https://www.mdpi.com/2227-9709/12/1/7YOLOv10coordinate attentionadaptive Kernel convolutionbus detectionPOV classificationassistive technology
spellingShingle Rio Arifando
Shinji Eto
Tibyani Tibyani
Chikamune Wada
Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public Transportation
Informatics
YOLOv10
coordinate attention
adaptive Kernel convolution
bus detection
POV classification
assistive technology
title Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public Transportation
title_full Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public Transportation
title_fullStr Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public Transportation
title_full_unstemmed Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public Transportation
title_short Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public Transportation
title_sort improved yolov10 for visually impaired balancing model accuracy and efficiency in the case of public transportation
topic YOLOv10
coordinate attention
adaptive Kernel convolution
bus detection
POV classification
assistive technology
url https://www.mdpi.com/2227-9709/12/1/7
work_keys_str_mv AT rioarifando improvedyolov10forvisuallyimpairedbalancingmodelaccuracyandefficiencyinthecaseofpublictransportation
AT shinjieto improvedyolov10forvisuallyimpairedbalancingmodelaccuracyandefficiencyinthecaseofpublictransportation
AT tibyanitibyani improvedyolov10forvisuallyimpairedbalancingmodelaccuracyandefficiencyinthecaseofpublictransportation
AT chikamunewada improvedyolov10forvisuallyimpairedbalancingmodelaccuracyandefficiencyinthecaseofpublictransportation