![]() Denmark: 293 crop/vegetation catgeories, 600k parcels. LPIS agricultural field boundaries Denmark - Netherlands - FranceĪnnual datasets. Open AI Challenge: Tanzania (WeRobotics & Wordlbank, Nov 2018)īuilding footprints & 3 building conditions, RGB UAV imagery - Link to data 2019Īirbus Ship Detection Challenge (Airbus, Nov 2018)ġ31k ships, 104k train / 88k test image chips, satellite imagery (1.5m res.), raster mask labels in in run-length encoding format, Kaggle kernels. Bi-cubicly resampled to same number of pixels in each image to counter courser native resolution with higher off-nadir angles, Paper: Weir et al. SpaceNet 4: Off-Nadir Buildings (CosmiQ Works, DigitalGlobe, Radiant Solutions, AWS, Dec 2018)ġ26k building footprints (Atlanta), 27 WorldView 2 images (0.3m res.) from 7-54 degrees off-nadir angle. Microsoft BuildingFootprints Canada & USA & Uganda/Tanzania & Australia (Microsoft, Mar 2019)ġ2.6mil (Canada) & 125.2mil (USA) & 17.9mil (Uganda/Tanzania) & 11.3mil (Australia) building footprints, GeoJSON format, delineation based on Bing imagery using ResNet34 architecture. ĥ50k building footprints & 4 damage scale categories, 20 global locations and 7 disaster types (wildfire, landslides, dam collapses, volcanic eruptions, earthquakes/tsunamis, wind, flooding), Worldview-3 imagery (0.3m res.), pre-trained baseline model. XView 2 Building Damage Asessment Challenge (DIUx, Nov 2019). ISAID: Large-scale Dataset for Object Detection in Aerial Images (IIAI & Wuhan University, Dec 2019)ġ5 categories from plane to bridge, 188k instances, object instances and segmentation masks (MS COCO format), Google Earth & JL-1 image chips, Faster-RCNN baseline model (MXNet), devkit, Academic use only, replaces DOTA dataset, Paper: Zamir et al. SpaceNet: Multi-Sensor All-Weather Mapping (CosmiQ Works, Capella Space, Maxar, AWS, Intel, Feb 2020)Ĥ8k building footprints (enhanced 3DBAG dataset, building height attributes), Capella Space SAR data (0.5m res., four polarizations) & Worldview-3 imagery (0.3m res.), Rotterdam, Netherlands.Īgriculture-Vision Database & CVPR 2020 challenge (UIUC,Īgricultural Pattern Analysis, 21k aerial farmland images (RGB-NIR, USA, 2019 season, 512x512px chips), label masks for 6 field anomaly patterns (Cloud shadow, Double plant, Planter skip, Standing Water, Waterway and Weed cluster). Synthetic (630k planes, 50k images) and real (14.7k planes, 253 Worldview-3 images (0.3m res.), 122 locations, 22 countries) plane annotations & properties and satellite images. RarePlanes: Synthetic Data Takes Flight (CosmiQ Works, A.I.Reverie, June 2020) res) timeseries for 2 years, 100 locations around the globe, for building footprint evolution & address propagation. Monthly building footprints and Planet imagery (4m. SpaceNet 7: Multi-Temporal Urban Development Challenge (CosmiQ Works, Planet, Aug 2020) PASTIS: Panoptic Agricultural Satellite TIme Series (IGN, July 2021) ![]() Maritime object bounding boxes for 1k Sentinel-1 scenes (VH & VV polarizations), ancillary data (land/ice mask, bathymetry, wind speed, direction, quality). XView3 Dark Vessel Detection 2021 (xView3 Team, Aug 2021) PASTIS : Panoptic Agricultural Satellite TIme Series (IGN, July 2021)ġ24,422 Agricultural parcels, 2,433 Sentinel-2 image chip timeseries, France, panoptic labels (instance index + semantic label for each pixel). Recent additions and ongoing competitionsįloodNet (University of Maryland, Jun 2021)Ģ343 image chips (drone imagery), 10 landcover categories (background, water, building flooded, building non-flooded, Newest datasets at the top of each category (Instance segmentation, object detection, semantic segmentation, scene classification, other). List of aerial and satellite imagery datasets with annotations for computer vision and deep learning. Please see these fantastic ressources for more recent datasets:Īwesome_Satellite_Benchmark_Datasets Awesome Satellite Imagery Datasets ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |