-
Automatic Building Extraction in Aerial Scenes
Aerial images and building footprints from GIS resources -
Base de données d'apprentissage profond photo-voltaïque (BDAPPV)
A crowdsourced dataset of aerial images with annotated solar photovoltaic arrays and installation metadata. -
LARD – Landing Approach Runway Detection – Dataset for Vision Based Landing
A dataset of high-quality aerial images for the task of runway detection during approach and landing phases. -
MapAI: Precision in building segmentation
The dataset used in this paper for building extraction from LiDAR data and aerial images. -
Vaihingen dataset
The Vaihingen dataset consists of 1440 scenes with a size of 250×250 pixels. Each scene is a colour-infrared (CIR) true orthophoto and a height grid (digital surface model; DSM)... -
VisDrone2019
The VisDrone2019 dataset contains 10,209 high-resolution images with ten categories: pedestrian, people, bicycle, car, van, truck, tricycle, awning-tricycle, bus, and motor. -
You Only Look Clusters (YOLC)
Detecting objects from aerial images poses significant challenges due to the following factors: 1) Aerial images typically have very large sizes, generally with millions or even... -
DOTA: A Large-scale Dataset for Object Detection in Aerial Images
Remote sensing images have different shooting angles and methods compared to ordinary ones, which makes remote sensing images play an irreplaceable role in some areas. -
Sampling Equivariant Self-attention Networks for Object Detection in Aerial I...
Object detection in aerial images has greater rotational and scale variations because of the overhead image capture, which requires the detection model to more flexibly handle... -
Map-to-Image Translation Dataset
A dataset of paired map and aerial images, used to train a Pix2Pix model for image-to-image translation. -
DOTA dataset
DOTA dataset is a large-scale dataset for object detection in aerial images including 2806 aerial images with each image ranging from 800 × 800 to 4000 × 4000 pixels collected... -
Deep Learning-based Aerial Image Segmentation with Open Data for Disaster Imp...
Satellite images are an extremely valuable resource in the aftermath of natural disasters such as hurricanes and tsunamis where they can be used for risk assessment and disaster... -
BridgeDetV1
A dataset for bridge detection in aerial images, containing 5,000 images with 668 × 668 to 1,000 × 1,000 pixels. -
Dataset for Object Detection in Aerial Images (DOTA)
The DOTA dataset contains annotated aerial images with object detection tasks. -
NWPU-RESISC45
NWPU-RESISC45 dataset was collected from more than 100 countries and regions in the world, consists of 31,500 remote sensing images.
