Lunar crater identification via deep learning

@article{Silburt2019LunarCI,
  title={Lunar crater identification via deep learning},
  author={Ari Silburt and Mohamad Ali-Dib and Chenchong Zhu and Alan P. Jackson and Diana Valencia and Yevgeni Kissin and Daniel Tamayo and Kristen Menou},
  journal={Icarus},
  year={2019}
}

Figures and Tables from this paper

Lunar Crater Detection based on Grid Partition using Deep Learning

  • Shintaro HashimotoKenji Mori
  • Geology
    2019 IEEE 13th International Symposium on Applied Computational Intelligence and Informatics (SACI)
  • 2019
This research showed that a small crater found in images of the lunar south pole region, taken by the Narrow Angle Camera of the Lunar Reconnaissance Orbiter, had higher resolution than DEM.

Autonomous crater detection on asteroids using a fully-convolutional neural network

This paper shows the application of autonomous Crater Detection using the U-Net, a Fully-Convolutional Neural Network, on Ceres. The U-Net is trained on optical images of the Moon Global Morphology

Semi-Supervised Deep Learning for Lunar Crater Detection Using CE-2 DOM

A new crater detection model (Crater R-CNN) is proposed, which can effectively extract the spatial and semantic information of craters from DOM data and has strong robustness and better generalization ability for crater detection within 1 km in different terrains, making it possible to detect small craters with high accuracy when using DOM data.

The Identification of Impact Craters from GRAIL-Acquired Gravity Data by U-Net Architecture

The identification of impact craters on the Moon and other planetary bodies is of great significance to studying and constraining the dynamical process and evolution of the Solar System.

Automated Detection of Lunar Craters Using Deep Learning

Based on the Image segmentation convolutional network U-Net model, an automatic crater extraction method based on the improved U- net model is proposed, which can quickly and accurately detected craters on the lunar surface.

Segmentation Convolutional Neural Networks for Automatic Crater Detection on Mars

A segmentation network using convolutional neural networks is successfully implemented to find 65%–76% of craters in common with a human annotated dataset.

Lunar Crater Detection on Digital Elevation Model: A Complete Workflow Using Deep Learning and Its Application

This paper attempts to reduce the gap between the existing DEM-based CDAs and the advanced CNN methods for object detection, and proposes a complete workflow including an end-to-end deep learning pipeline for lunar crater detection, in particular for craters smaller than 50 km in diameter.
...

References

SHOWING 1-10 OF 58 REFERENCES

Crater Detection via Convolutional Neural Networks

A method for automatic crater detection using advanced machine learning to deal with the large amount of satellite imagery collected and looks to Convolutional Neural Networks (CNNs) which have shown their dominance in computer vision.

Automatic Crater Detection Using Convex Grouping and Convolutional Neural Networks

A new crater detection algorithm (CDA) is proposed which employs a multi-scale candidate region detection step based on convexity cues and candidate region verification based on machine learning.

Learning to Detect Small Impact Craters

The SVM approach with normalized image patches provides detection and localization performance closest to that of human labelers and is shown to be substantially superior to boundary-based approaches such as the Hough transform.

Detecting Impact Craters in Planetary Images Using Machine Learning

Prompted by crater counts as the only available tool for measuring remotely the relative ages of geologic formations on planets, advances in remote sensing have produced a very large database of high

AUTOMATIC CRATER RECOGNITION USING MACHINE LEARNING WITH DIFFERENT FEATURES AND THEIR COMBINATION

A classification system which enables the automatic recognition of lunar craters based on different modalities is presented, which consists of two subsequent stages, a detection stage provides possible candidates and is followed by the classification stage which reduces false positive recognitions.

Identifying Exoplanets with Deep Learning: A Five-planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90

A method for classifying potential planet signals using deep learning, a class of machine learning algorithms that have recently become state-of-the-art in a wide variety of tasks, is presented and two new planets are identified with high confidence by this model.
...