A YOLOv8-Based Tactile Paving Intrusion Judgment and Walking Safety Support Platform for Visually Impaired Pedestrians

doi:10.22716/sckt.2026.14.3.006

All Issue

2026 Vol.14, Issue 3 Preview Page Next Page

Research Article

A YOLOv8-Based Tactile Paving Intrusion Judgment and Walking Safety Support Platform for Visually Impaired Pedestrians YOLOv8 기반 점자블록 침범 판정 및 시각장애인 보행 안전 지원 플랫폼: Seunghyun-Lee¹, Juphil-Cho², and Jeonggon-Kim³
이승현¹, 조주필², 김정곤³; ¹M.S., Department of IT Semiconductor Convergence Engineering, Tech University of Korea
²Professor, Department of IT Convergence and Communication Engineering, Kunsan National University
³Professor, Department of Electronic Engineering, Tech University of Korea

¹한국공학대학교 IT 반도체 융합공학과 석사과정, ²국립군산대학교 IT융합통신공학과 교수, ³한국공학대학교 전자공학과 교수

30 September 2026. pp. 79-95

PDF

Abstract

점자블록 상에 무단 점유된 킥보드, 자전거, 적치물 등은 시각장애인 안전사고를 야기하는 위험 요인이다. 본 연구에서는 YOLOv8(You Only Look Once version 8) 기반 점자블록 침범 판정과 보행 안전 지원 플랫폼을 제안한다. 제안 방법은 점자블록 영역을 YOLOv8 segmentation으로 추출하고 킥보드를 YOLOv8 detection으로 검출한 뒤, 두 영역의 공간적 중첩 관계를 overlap ratio로 분석하여 침범 여부를 판정한다. 판정 결과와 검출 이미지는 Firebase 기반 저장 구조 및 Android 애플리케이션과 연동하여 모바일 환경에서 확인할 수 있도록 구현하였다. 침범 100장과 비침범 100장으로 구성된 200장 균형 평가셋의 정량 평가 결과, 제안한 polygon-overlap 방식은 detection-only baseline의 F1-score 76.86%보다 높은 F1-score 88.26%를 보였으며, 영역 유효성 검토를 포함한 최종 판정 규칙 적용 시 Accuracy 91.00%, F1-score 91.26%의 성능을 확인하였다.

Unauthorized obstacles on tactile paving, such as kickboards, bicycles, and stacked objects, are major safety hazards for visually impaired pedestrians. This study proposes a YOLOv8(You Only Look Once version 8)-based platform to detect tactile paving intrusions and support pedestrian safety. The proposed method extracts tactile paving regions using YOLOv8 segmentation and detects electric scooters using YOLOv8 detection, then determines intrusions by analyzing the spatial overlap between the two regions through an overlap ratio. The judgment results and detected images are integrated with a Firebase-based storage architecture and an Android application for mobile verification. A quantitative evaluation using a balanced dataset of 100 intrusion and 100 non-intrusion images showed that the polygon-overlap-based method achieved an F1-score of 88.26%, outperforming the detection-only baseline F1-score of 76.86%. With the final decision rule including region-validity verification, the proposed method achieved 91.00% accuracy and a 91.26% F1-score.

Keywords

YOLOv8

Tactile paving

Polygon overlap

Intrusion judgment

Edge AI

Mobile accessibility

References

국토교통부, “교통약자의 이동편의 증진법 시행규칙,” 국가법령정보센터, https://www.law.go.kr/LSW/lsInfoP.do?lsiSeq=273215, accessed Jul. 3, 2026.
Department for Transport, “Guidance on the Use of Tactile Paving Surfaces,” United Kingdom Government, 2022, https://www.gov.uk/government/publications/inclusive-mobility-using-tactile-paving-surfaces, accessed Jul. 3, 2026.
윤희일, “점자블록 위에 전동킥보드 던져놓고 가는 당신···시각장애인은 어떡하라고?,” 경향신문, 2021, https://www.khan.co.kr/article/202109121145001, accessed Jul. 3, 2026.
Ultralytics, “Object Detection - Ultralytics YOLO Docs,” Ultralytics Documentation, https://docs.ultralytics.com/tasks/detect/, accessed Jul. 3, 2026.
Ultralytics, “Instance Segmentation - Ultralytics YOLO Docs,” Ultralytics Documentation, https://docs.ultralytics.com/tasks/ segment/, accessed Jul. 3, 2026.
Google LLC, “Firebase Realtime Database,” Firebase Documentation, https://firebase.google.com/docs/database, accessed Jul. 3, 2026.
R. Tachiquin, R. Velázquez, C. Del-Valle-Soto, C.A. Gutiérrez, M. Carrasco, R. De Fazio, A. Trujillo-León, P. Visconti, and F. Vidal-Verdú, “Wearable Urban Mobility Assistive Device for Visually Impaired Pedestrians Using a Smartphone and a Tactile-Foot Interface,” Sensors, Vol. 21, No. 16, 5274, 2021. https://doi.org/10.3390/s21165274
10.3390/s21165274 34450714 PMC8398265
A.B.M. Kassim, T. Yasuno, H. Suzuki, M.S.M. Aras, A.Z. Shukor, H.I. Jaafar, and F.A. Jafar, “Vision-Based Tactile Paving Detection Method in Navigation Systems for Visually Impaired Persons,” Advances in Human and Machine Navigation Systems, IntechOpen, 2018. https://doi.org/10.5772/intechopen.79886
10.5772/intechopen.79886
W. Wang, B. Jing, X. Yu, Y. Sun, L. Yang, and C. Wang, “YOLO-OD: Obstacle Detection for Visually Impaired Navigation Assistance,” Sensors, Vol. 24, No. 23, 7621, 2024. https://doi.org/10.3390/s24237621
10.3390/s24237621 39686158 PMC11645096
K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, pp. 2980-2988, 2017. https://doi.org/10.1109/ICCV.2017.322
10.1109/ICCV.2017.322
Raspberry Pi Ltd., “Camera software,” Raspberry Pi Documentation, https://www.raspberrypi.com/documentation/computers/ camera_software.html, accessed Jul. 3, 2026.
Shapely Development Team, “shapely.Polygon,” Shapely Documentation, https://shapely.readthedocs.io/en/stable/lierence/ shapely.Polygon.html, accessed Jul. 3, 2026.
Shapely Development Team, “shapely.intersection,” Shapely Documentation, https://shapely.readthedocs.io/en/stable/lierence/ shapely.intersection.html, accessed Jul. 3, 2026.
Google LLC, “Cloud Storage for Firebase,” Firebase Documentation, https://firebase.google.com/docs/storage, accessed Jul. 3, 2026.
Google LLC, “Firebase Cloud Messaging,” Firebase Documentation, https://firebase.google.com/docs/cloud-messaging, accessed Jul. 3, 2026.

Information

Publisher :The Society of Convergence Knowledge
Publisher(Ko) :융복합지식학회
Journal Title :The Society of Convergence Knowledge Transactions
Journal Title(Ko) :융복합지식학회논문지
Volume : 14
No :3
Pages :79-95
DOI :https://doi.org/10.22716/sckt.2026.14.3.006

[1] 국토교통부, “교통약자의 이동편의 증진법 시행규칙,” 국가법령정보센터, https://www.law.go.kr/LSW/lsInfoP.do?lsiSeq=273215, accessed Jul. 3, 2026.

[2] Department for Transport, “Guidance on the Use of Tactile Paving Surfaces,” United Kingdom Government, 2022, https://www.gov.uk/government/publications/inclusive-mobility-using-tactile-paving-surfaces, accessed Jul. 3, 2026.

[3] 윤희일, “점자블록 위에 전동킥보드 던져놓고 가는 당신···시각장애인은 어떡하라고?,” 경향신문, 2021, https://www.khan.co.kr/article/202109121145001, accessed Jul. 3, 2026.

[4] Ultralytics, “Object Detection - Ultralytics YOLO Docs,” Ultralytics Documentation, https://docs.ultralytics.com/tasks/detect/, accessed Jul. 3, 2026.

[5] Ultralytics, “Instance Segmentation - Ultralytics YOLO Docs,” Ultralytics Documentation, https://docs.ultralytics.com/tasks/ segment/, accessed Jul. 3, 2026.

[6] Google LLC, “Firebase Realtime Database,” Firebase Documentation, https://firebase.google.com/docs/database, accessed Jul. 3, 2026.

[7] R. Tachiquin, R. Velázquez, C. Del-Valle-Soto, C.A. Gutiérrez, M. Carrasco, R. De Fazio, A. Trujillo-León, P. Visconti, and F. Vidal-Verdú, “Wearable Urban Mobility Assistive Device for Visually Impaired Pedestrians Using a Smartphone and a Tactile-Foot Interface,” Sensors, Vol. 21, No. 16, 5274, 2021. https://doi.org/10.3390/s21165274
10.3390/s21165274 34450714 PMC8398265

[8] A.B.M. Kassim, T. Yasuno, H. Suzuki, M.S.M. Aras, A.Z. Shukor, H.I. Jaafar, and F.A. Jafar, “Vision-Based Tactile Paving Detection Method in Navigation Systems for Visually Impaired Persons,” Advances in Human and Machine Navigation Systems, IntechOpen, 2018. https://doi.org/10.5772/intechopen.79886
10.5772/intechopen.79886

[9] W. Wang, B. Jing, X. Yu, Y. Sun, L. Yang, and C. Wang, “YOLO-OD: Obstacle Detection for Visually Impaired Navigation Assistance,” Sensors, Vol. 24, No. 23, 7621, 2024. https://doi.org/10.3390/s24237621
10.3390/s24237621 39686158 PMC11645096

[10] K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, pp. 2980-2988, 2017. https://doi.org/10.1109/ICCV.2017.322
10.1109/ICCV.2017.322

[11] Raspberry Pi Ltd., “Camera software,” Raspberry Pi Documentation, https://www.raspberrypi.com/documentation/computers/ camera_software.html, accessed Jul. 3, 2026.

[12] Shapely Development Team, “shapely.Polygon,” Shapely Documentation, https://shapely.readthedocs.io/en/stable/lierence/ shapely.Polygon.html, accessed Jul. 3, 2026.

[13] Shapely Development Team, “shapely.intersection,” Shapely Documentation, https://shapely.readthedocs.io/en/stable/lierence/ shapely.intersection.html, accessed Jul. 3, 2026.

[14] Google LLC, “Cloud Storage for Firebase,” Firebase Documentation, https://firebase.google.com/docs/storage, accessed Jul. 3, 2026.

[15] Google LLC, “Firebase Cloud Messaging,” Firebase Documentation, https://firebase.google.com/docs/cloud-messaging, accessed Jul. 3, 2026.

The Society of Convergence Knowledge Transactions ISSN:2287-8920(Print) 융복합지식학회논문지

All Issue