An Enhanced YOLOv8 Model for Real-Time and Accurate Pothole Detection and Measurement

2025-05-07

AI Summary

Existing 2D RGB-based pothole detection methods lack physical dimension estimation, hindering effective road safety warning. To address this, we propose the first depth-aware lightweight pothole detection and measurement framework. Methodologically, we introduce PothRGBD—the first publicly available RGB-D pothole dataset comprising 1,000 frames with precise instance segmentation and dense depth annotations. We further design an enhanced YOLOv8n-seg model incorporating dynamic snake convolution (DSConv), SimAM attention, and GELU activation, enabling joint pothole detection, irregular boundary segmentation, and accurate depth- and perimeter-based metric estimation within a single-stage architecture. Experiments demonstrate a mAP@50 of 93.8% (+2.07%), recall of 90.4%, measurement error below 3%, and only 2.8M parameters—enabling real-time inference on edge devices.

Technology Category

• Computer Vision: Segmentation
• Intelligent Robots: State Estimation
• Machine Learning: Hardware-aware ML

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Potholes cause vehicle damage and traffic accidents, creating serious safety and economic problems. Therefore, early and accurate detection of potholes is crucial. Existing detection methods are usually only based on 2D RGB images and cannot accurately analyze the physical characteristics of potholes. In this paper, a publicly available dataset of RGB-D images (PothRGBD) is created and an improved YOLOv8-based model is proposed for both pothole detection and pothole physical features analysis. The Intel RealSense D415 depth camera was used to collect RGB and depth data from the road surfaces, resulting in a PothRGBD dataset of 1000 images. The data was labeled in YOLO format suitable for segmentation. A novel YOLO model is proposed based on the YOLOv8n-seg architecture, which is structurally improved with Dynamic Snake Convolution (DSConv), Simple Attention Module (SimAM) and Gaussian Error Linear Unit (GELU). The proposed model segmented potholes with irregular edge structure more accurately, and performed perimeter and depth measurements on depth maps with high accuracy. The standard YOLOv8n-seg model achieved 91.9% precision, 85.2% recall and 91.9% mAP@50. With the proposed model, the values increased to 93.7%, 90.4% and 93.8% respectively. Thus, an improvement of 1.96% in precision, 6.13% in recall and 2.07% in mAP was achieved. The proposed model performs pothole detection as well as perimeter and depth measurement with high accuracy and is suitable for real-time applications due to its low model complexity. In this way, a lightweight and effective model that can be used in deep learning-based intelligent transportation solutions has been acquired.

Problem

• Detects potholes in real-time using enhanced YOLOv8 model
• Measures pothole perimeter and depth accurately with RGB-D data
• Improves detection precision and recall over standard YOLOv8

Innovation

• Enhanced YOLOv8 model with DSConv and SimAM
• RGB-D dataset creation for pothole analysis
• Accurate perimeter and depth measurements