YOLO-Crater Model for Small Crater Detection
-
Published:2023-10-20
Issue:20
Volume:15
Page:5040
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Mu Lingli12, Xian Lina123, Li Lihong123, Liu Gang4, Chen Mi5, Zhang Wei12ORCID
Affiliation:
1. Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, China 2. Key Laboratory of Space Utilization, Chinese Academy of Sciences, Beijing 100094, China 3. School of Aeronautics and Astronautics, University of Chinese Academy of Sciences, Beijing 100049, China 4. School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan 430070, China 5. School of Sociology and Population Studies, Renmin University of China, Beijing 100872, China
Abstract
Craters are the most prominent geomorphological features on the surface of celestial bodies, which plays a crucial role in studying the formation and evolution of celestial bodies as well as in landing and planning for surface exploration. Currently, the main automatic crater detection models and datasets focus on the detection of large and medium craters. In this paper, we created 23 small lunar crater datasets for model training based on the Chang’E-2 (CE-2) DOM, DEM, Slope, and integrated data with 7 kinds of visualization stretching methods. Then, we proposed the YOLO-Crater model for Lunar and Martian small crater detection by replacing EioU and VariFocal loss to solve the crater sample imbalance problem and introducing a CBAM attention mechanism to mitigate interference from the complex extraterrestrial environment. The results show that the accuracy (P = 87.86%, R = 66.04%, and F1 = 75.41%) of the Lunar YOLO-Crater model based on the DOM-MMS (Maximum-Minimum Stretching) dataset is the highest and better than that of the YOLOX model. The Martian YOLO-Crater, trained by the Martian dataset from the 2022 GeoAI Martian Challenge, achieves good performance with P = 88.37%, R = 69.25%, and F1 = 77.65%. It indicates that the YOLO-Crater model has strong transferability and generalization capability, which can be applied to detect small craters on the Moon and other celestial bodies.
Funder
National High Technology Research and Development Program of China National Natural Science Foundation of China
Subject
General Earth and Planetary Sciences
Reference54 articles.
1. Salih, A.L., Schulte, P., Grumpe, A., Wöhler, C., and Hiesinger, H. (September, January 28). Automatic crater detection and age estimation for mare regions on the lunar surface. Proceedings of the 25th European Signal Processing Conference (EUSIPCO), Kos, Greece. 2. Hartmann, W.K. (2022). Impact Crater Densities as a Tool for Dating Planetary Surfaces, Oxford University Press. 3. Changela, H.G., Chatzitheodoridis, E., Antunes, A., Beaty, D., Bouw, K., Bridges, J.C., Capova, K.A., Cockell, C.S., Conley, C.A., and Dadachov, E. (2022). Mars: New insights and unresolved questions—Corrigendum. Int. J. Astrobiol., 21. 4. Morphometric Characterization and Reconstruction Effect Among Lunar Impact Craters;Cheng;Earth Moon Planets,2014 5. Potential martian mineral resources: Mechanisms and terrestrial analogues;West;Planet. Space Sci.,2010
|
|