datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Road_Damage_Detection_USA
Road Damage Detection — YOLOv11 (US Roads)
Model Description
This model is a YOLOv11 object detection model that is meant to detect and identify road damage in images captured by cameras mounted to vehicles. Given an image, the model will output a bounding box and a label that shows the location and the type of damage there is.
Training approach: This model was fine tuned with pretrained weights on a subset of the Road Damage Detector dataset, using only images… See the full description on the dataset page: https://huggingface.co/datasets/cvtechniques/Road_Damage_Detection_USA.road-damage
Road Damage Dataset - Global Road Condition Observations - EmbedEarth
This dataset contains geolocated observations selected for the semantic query “Road Damage.” The records were retrieved because their source text, visual context, or metadata matched the query; this is a discovery-oriented collection rather than a complete administrative inventory. It is useful for exploratory mapping, visual search evaluation, geospatial research, and building retrieval or monitoring… See the full description on the dataset page: https://huggingface.co/datasets/EmbedEarth/road-damage.RoadDamageDetection-Egyptdamage-roadRoadDamageDetectionThis dataset is a derived and reorganized version of the Road Damage Detection 2022 (RDD2022) dataset, released under the Creative Commons Attribution-ShareAlike 4.0 (CC BY-SA 4.0) license.
The original dataset was created as part of the Crowd Sensing-based Road Damage Detection Challenge (CRDDC 2022).
This version has been randomly split and reorganized for competition use. This is NOT the official RDD2022.
license: cc-by-sa-4.0
road_damageUAV Dataset for Automated Road Surface Degradation
road-damage-zero-shotrescuenet-damaged-road-clipsRoad_DamageRoad-Damage-Detectionroad-damage-classification