"PothRGBD: RGB and Depth Images of Potholes"

"\ud83d\udcc4 Dataset Description PothRGBD: RGB and Depth Images of Potholes is a publicly available dataset containing 1,000 paired RGB and depth images of real-world potholes, collected using the Intel RealSense D415 depth camera. Each image is annotated for YOLOv8-style segmentation, enabling accurate detection and measurement of pothole features such as perimeter and depth.The dataset was designed to facilitate research in:Deep learning-based pothole detectionDepth-aware segmentation and measurement tasksReal-time embedded systems in intelligent transportationModel benchmarking for RGB-D image processingKey Features:1,000 RGB-D image pairs (640\u00d7480 resolution)YOLO-compatible segmentation masksLabeled using RoboflowCollected under real-road conditionsSuitable for training, validation, and benchmarking of detection models\ud83d\udcda Citation Request If you use this dataset in your research or application, please cite the following paper:Yurdakul, M., & Ta\u015fdemir, \u015e. An Enhanced YOLOv8 Model for Real-Time and Accurate Pothole Detection and Measurement, 2025. arXiv: https:\/\/arxiv.org\/abs\/2505.04207"