Abstract

Impact craters are the most prominent features on the surface of the Moon, Mars, and Mercury. They play an essential role in constructing lunar bases, the dating of Mars and Mercury, and the surface exploration of other celestial bodies. The traditional crater detection algorithms (CDA) are mainly based on manual interpretation which is combined with classical image processing techniques. The traditional CDAs are, however, inefficient for detecting smaller or overlapped impact craters. In this paper, we propose a Split-Attention Networks with Self-Calibrated Convolution (SCNeSt) architecture, in which the channel-wise attention with multi-path representation and self-calibrated convolutions can generate more prosperous and more discriminative feature representations. The algorithm first extracts the crater feature model under the well-known target detection R-FCN network framework. The trained models are then applied to detecting the impact craters on Mercury and Mars using the transfer learning method. In the lunar impact crater detection experiment, we managed to extract a total of 157,389 impact craters with diameters between 0.6 and 860 km. Our proposed model outperforms the ResNet, ResNeXt, ScNet, and ResNeSt models in terms of recall rate and accuracy is more efficient than that other residual network models. Without training for Mars and Mercury remote sensing data, our model can also identify craters of different scales and demonstrates outstanding robustness and transferability.

Highlights

  • Impact craters are considered to be one of the most important features of the Moon, Mars, and Mercury [1]

  • Due to the variety of deep space objects, the recognition model based on single star surface impact craters offers a poor generalization ability, especially in recognizing overlapping and small impact craters

  • We propose a SCNeSt architecture in which the channel-wise attention with multipath representation and self-calibrated convolutions provide a higher detection and estimation accuracy for small impact craters

Read more

Summary

Introduction

Impact craters are considered to be one of the most important features of the Moon, Mars, and Mercury [1]. U-Net model of image semantic segmentation in deep learning They transferred their model to the Mercury surface impact crater recognition and achieved reasonable results. Due to the variety of deep space objects, the recognition model based on single star surface impact craters offers a poor generalization ability, especially in recognizing overlapping and small impact craters. To address this issue, in this paper, we consider the deep space star surface impact crater and combine the existing Moon image and DEM data of the. The lunar crater model is trained, and transfer learning is used to detect the impact craters on Mercury and Mars This is shown to increase the model’s generalization ability.

Methods
SCNeSt Backbone Network
FMulti-Scale
Multi-Scale Feature Extractor
Position-Sensitive
Dataset
Evaluation Metrics
Objective function
Results
Comparison
Comparison of Crater Detection Performance of Different Networks
92.7 Soft-NMS
Performance Comparison of Multi-Scale Impact Crater Networks
Transfer
14. Crater Detection Analysis
14. Transfer
Conclusions

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.