road-damage-detection

Detect road anomalies such as cracks, potholes, and bumps using our trained YOLOv8 models with visual demo. Real-time detection via Streamlit and Flask app

Road Damage Detection Based on Unsupervised Disparity Map Segmentation (T-ITS)

Integrated real-time data analytics for optimized public transport, innovative road monitoring using demand prediction, and conditioning tech for sustainability, real time pothole detection either by image or video, smart parking count system for efficiency using AI/ML.

Detect damages like cracks and potholes of roads

基于YOLO模型的路面缺陷检测（Road Damage Detection）

An application for automatic road damage assessment using semantic segmentation on high-resolution images. The project helps municipal authorities and maintenance teams detect and prioritize road repairs, improving safety and reducing costs.

YOLOv7-based road damage detection system trained on RDD2022 multi-national dataset. Achieves 63.85% mAP for detecting cracks and potholes. Includes Gradio UI.

PyTorch implementation of EfficientDet (D0, D2, D3) for Road Damage Detection on RDD2022 dataset. Includes K-Medoids anchors, DDP training, and COCO evaluation.

YOLO-based road anomaly detection project with a Streamlit app, packaged model weights, archived evaluation artifacts, and ready-to-run local setup.

Real-time pothole detection Android application using computer vision, OpenCV, and native C++ processing. Developed during a designathon that led to an Ericsson internship.

Baseline implementation of Road Damage Object Detection using YOLOv8, YOLOv10, and YOLO11 with Hyperparameter Tuning and Streamlit deployment.

AI-powered ADAS pothole detection system using YOLO, Random Forest, Flask and OpenCV.

This project is an AI-powered pothole monitoring platform that detects road defects using YOLO, allows citizens to report issues, and provides administrators with a dashboard to track and resolve them. It combines computer vision, backend automation, and user interfaces to make road maintenance faster and smarter.

Real-time road damage detection on Raspberry Pi 5 using YOLOv8 Nano with NCNN and Hailo-8 backends. Engineering thesis — AGH UST 2026.

Deep Learning-based road damage detection and classification. Features a CNN pipeline for image analysis, a web-based monitoring dashboard, and an integrated messaging service for real-time safety alerts.

AI-powered road damage detection and road health assessment using YOLO, Streamlit, and GPS visualization.

Transfer learning benchmark: ResNet-50, EfficientNet-B3, ViT-B/16, MobileNet-V3 on RDD2022 Japan pavement distress dataset — accuracy, calibration, latency, and parameter count evaluated.

AIQYN — қала жол инфрақұрылымының ақауын AI арқылы автоматты анықтап, ресми құжатын дайындайтын жүйе (SmartCity Hackathon 2026, Шымкент)

🛣️ 📌 An end-to-end Computer Vision and Deep Learning pipeline designed to detect, classify, and localize road surface damage. This project goes beyond standard model training by conducting a comparative benchmark across three generations of YOLO architectures (v8,v9, and v11) to find the optimal balance between inference speed (FPS), computatio

YOLOv8 road damage detection pipeline with MLflow tracking and production-style MLOps workflow.