The authors of the iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images dataset have introduced the first benchmark dataset for instance segmentation in aerial imagery, which merges instance-level object detection and pixel-level segmentation tasks. It contains 655,451 object instances spanning 15 different categories across 2,806 high-resolution images. Precise per-pixel annotations have been provided for each instance, ensuring accurate localization for detailed scene analysis. Compared to existing small-scale aerial image-based instance segmentation datasets, iSAID boasts 15 times the number of object categories and 5 times the number of instances.

Context

Existing Earth Vision datasets are either suitable for semantic segmentation or object detection. iSAID is the first benchmark dataset for instance segmentation in aerial images. This large-scale and densely annotated dataset contains 655,451 object instances for 15 categories across 2,806 high-resolution images. The distinctive characteristics of iSAID are the following: (a) large number of images with high spatial resolution, (b) fifteen important and commonly occurring categories, (c) large number of instances per category, (d) large count of labelled instances per image, which might help in learning contextual information, (e) huge object scale variation, containing small, medium and large objects, often within the same image, (f) Imbalanced and uneven distribution of objects with varying orientation within images, depicting real-life aerial conditions, (g) several small size objects, with ambiguous appearance, can only be resolved with contextual reasoning, (h) precise instance-level annotations carried out by professional annotators, cross-checked and validated by expert annotators complying with well-defined guidelines.

Content

The images of iSAID is the same as the DOTA-v1.0 dataset, which are manily collected from the Google Earth, some are taken by satellite JL-1, the others are taken by satellite GF-2 of the China Centre for Resources Satellite Data and Application.

Use of the images from Google Earth must respect the corresponding terms of use: "Google Earth" terms of use.

All images and their associated annotations in iSAID can be used for academic purposes only, but any commercial use is prohibited.

Object Category The object categories in iSAID include: plane, ship, storage tank, baseball diamond, tennis court, basketball court, ground track field, harbor, bridge, large vehicle, small vehicle, helicopter, roundabout, soccer ball field and swimming pool.

Annotation format The iSAID uses pixel-level annotations. Each pixel represents a particular class. The annotation follows the format of MS COCO.

Acknowledgements

@inproceedings{waqas2019isaid, title={iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images}, author={Waqas Zamir, Syed and Arora, Aditya and Gupta, Akshita and Khan, Salman and Sun, Guolei and Shahbaz Khan, Fahad and Zhu, Fan and Shao, Ling and Xia, Gui-Song and Bai, Xiang}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops}, pages={28--37}, year={2019} }

@InProceedings{Xia_2018_CVPR, author = {Xia, Gui-Song and Bai, Xiang and Ding, Jian and Zhu, Zhen and Belongie, Serge and Luo, Jiebo and Datcu, Mihai and Pelillo, Marcello and Zhang, Liangpei}, title = {DOTA: A Large-Scale Dataset for Object Detection in Aerial Images}, booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2018} }

512).

This is Version 6.0, 20200130 of the catalog of publicly available USAID datasets

The best results in the experiments are indicated by the values in bold in each column.

USAID - India