AeroRunway: Diverse Weather and Time of Day Aerial Dataset for Autonomous Landing Training

Abstract

Acquiring a sufficient amount of diverse and accurate real-world data poses a significant challenge in advancing autonomous systems, which are becoming increasingly popular. Despite the aerospace industry's keen practical and economic interest in autonomous landing systems, readily available open-source datasets containing aerial photographs are scarce. To address this issue, we present a dataset named AeroRunway, comprising high-quality aerial photos designed to aid in runway recognition during the approach and landing stages. The dataset is composed of images using X-Plane, a flight simulator software developed by Laminar Research. It is a highly realistic and detailed flight simulation program that allows users to experience the sensation of piloting various aircraft in a virtual environment. These synthetic images were collected mostly in variable weather conditions above 5000 feet to supplement existing satellite imagery that can be used for extreme situations. This dataset was created from 28 different airports in different weather conditions, such as foggy and rainy, at various times of the day, such as day and night, and consists of 3880 images and is approximately 13.3 GB in size.

Keywords

• Aerodrome detection
• spatial awareness
• artificial intelligence
• deep learning
• machine learning

References

1. Z.-Q. Zhao, P. Zheng, S.-t. Xu, X. Wu, Object detection with deep learning: A review, IEEE Transactions on Neural Networks and Learning Systems 30 (11) (2019) 3212–3232.
2. G. Cheng, J. Han, X. Lu, Remote sensing image scene classification: Benchmark and state of the art, Proceedings of the IEEE 105 (10) (2017) 1865–1883.
3. G. Cheng, J. Han, P. Zhou, L. Guo, Multi-class geospatial object detection and geographic image classification based on collection of part detectors, ISPRS Journal of Photogrammetry and Remote Sensing (98) (2014) 119–132.
4. G. Cheng, J. Han, A survey on object detection in optical remote sensing images, ISPRS Journal of Photogrammetry and Remote Sensing (117) (2016) 11–28.
5. G. Cheng, P. Zhou, J. Han, Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images, IEEE Transactions on Geoscience and Remote Sensing 54 (12) (2016) 7405–7415.
6. 2D semantic labeling - Vaihingen dataset, https://paperswithcode.com/dataset/isprs-vaihingen, Accessed on 21 June 2023.
7. T. Bakirman, E. Sertel, HRPlanes: High resolution airplane dataset for deep learning, International Journal of Engineering and Geosciences 8 (3) (2022) 212-223.
8. G. Cheng, J. Wang, K. Li, X. Xie, C. Lang, Y. Yao, J. Han, Anchor-free oriented proposal generator for object detection, IEEE Transactions on Geoscience and Remote Sensing (60) (2022) 1–11.

9. W. Yu, G. Cheng, J. Wang, Y. Yao, X. Xie, X. Yao, J. Han, MAR20: A benchmark for military aircraft recognition in remote sensing images, National Remote Sensing Bulletin 27 (12) (2024) 2688–2696.
10. J. Ding, N. Xue, G.-S. Xia, X. Bai, W. Yang, M. Y. Yang, S. Belongie, J. Luo, M. Datcu, M. Pelillo, L. Zhang, Object detection in aerial images: A large-scale benchmark and challenges, IEEE Transactions on Pattern Analysis and Machine Intelligence 44 (11) (2022) 7778–7796.
11. B. Zhou, A. Lapedriza, A. Khosla, A. Oliva, A. Torralba, Places: A 10 million image database for scene recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence 40 (6) (2017) 1452–1464.
12. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, L. Fei-Fei, ImageNet large scale visual recognition challenge, International Journal of Computer Vision (115) (2015) 211–252.
13. T.-Y. Lin, M. Maire, S. Belongie, L. Bourdev, R. Girshick, J. Hays, P. Perona, D. Ramanan, C. L. Zitnick, P. Dollár, Microsoft COCO: Common objects in context, in: D. Fleet, T. Pajdla, B. Schiele, T. Tuytelaars (Eds.), Computer Vision–ECCV 2014: 13th European Conference, Zurich, 2014, pp. 740-755.
14. G. A. Miller, WordNet: A lexical database for English, Communications of the ACM 38 (11) (1995) 39–41.
15. X. Sun, P. Wang, Z. Yan, F. Xu, R. Wang, W. Diao, J. Chen, J. Li, Y. Feng, T. Xu, M. Weinmann, S. Hinz, C. Wang, K. Fu, FAIR1M: A benchmark dataset for fine-grained object recognition in high-resolution remote sensing imagery, ISPRS Journal of Photogrammetry and Remote Sensing (184) (2022) 116-130.
16. L. Yu and P. Gong, Google Earth as a virtual globe tool for Earth science applications at the global scale: progress and perspectives, International Journal of Remote Sensing 33 (12) 2012 3966–3986.
17. Google. Google Earth studio, https://www.google.com/intl/eng/earth/studio/, Accessed on 21 June 2023.
18. Google. Google Earth studio, https://www.google.com/earth/about/versions/, Accessed on 21 June 2023.
19. M. Ducoffe, M. Carrere, L. Féliers, A. Gauffriau, V. Mussot, C. Pagetti, T. Sammour, LARD – Landing approach runway detection – dataset for vision based landing, arXiv preprint arXiv:2304.09938 (2023).
20. A. T. Lee, Flight simulation: Virtual environments in aviation, Routledge, New York, 2017.
21. T. Longbridge, J. Burki-Cohen, T. Go, Flight simulator fidelity considerations for total airline pilot training and evaluation, AIAA Modeling and Simulation Technologies Conference and Exhibit, Montreal, Quebec, 2001, pp. 4425
22. G. Balduzzi, M. F. Bravo, A. Chernova, C. Cruceru, L. van Dijk, P. de Lange, J. Jerez, N. Koehler, M. Koerner, C. Perret-Gentil, Z. Pillio, R. Polak, H. Silva, R. Valentin, I. Whittington, G. Yakushev, Neural network based runway landing guidance for general aviation autoland, U.S. Department of Transportation Federal Aviation Administration, New Jersey, 2021.
23. N. Bor, (2024). AeroRunway, Zenodo. https://zenodo.org/records/11577457, Accessed on 22 September 2024.