Investigating YOLO Models Towards Outdoor Obstacle Detection For Visually Impaired People

TL;DR

This study compares seven YOLO object detection models to identify the most effective for outdoor obstacle detection to aid visually impaired people, highlighting YOLOv8's superior performance.

Contribution

The paper provides a comprehensive evaluation of various YOLO models on obstacle detection datasets, identifying YOLOv8 as the most effective for this application.

Findings

YOLOv8 achieved 80% precision and 68.2% recall.

YOLO-NAS was less effective despite being the latest model.

Systematic hyperparameter tuning improved model performance.

Abstract

The utilization of deep learning-based object detection is an effective approach to assist visually impaired individuals in avoiding obstacles. In this paper, we implemented seven different YOLO object detection models \textit{viz}., YOLO-NAS (small, medium, large), YOLOv8, YOLOv7, YOLOv6, and YOLOv5 and performed comprehensive evaluation with carefully tuned hyperparameters, to analyze how these models performed on images containing common daily-life objects presented on roads and sidewalks. After a systematic investigation, YOLOv8 was found to be the best model, which reached a precision of $80\%$ and a recall of $68.2\%$ on a well-known Obstacle Dataset which includes images from VOC dataset, COCO dataset, and TT100K dataset along with images collected by the researchers in the field. Despite being the latest model and demonstrating better performance in many other applications, YOLO-NAS was found to be suboptimal for the obstacle detection task.