Coarse-to-Fine Crater Matching From Heterogeneous Surfaces of LROC NAC and Chang'e-2 DOM Images

Article Geochemistry & Geophysics

High-Resolution Feature Pyramid Network for Automatic Crater Detection on Mars

Shuojin Yang et al.

Summary: The study introduces a new deep convolutional neural network for crater detection that achieves excellent performance in detecting small craters through new algorithms, feature extraction modules, and loss functions. Additionally, the Mars Day Crater Detection (MDCD) dataset was built to validate the network's performance.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Centimeter-resolution topographic modeling and fine-scale analysis of craters and rocks at the Chang'E-4 landing site

Bo Wu et al.

Summary: This study utilized Pancam images to conduct centimeter-resolution topographic modeling and fine-scale analysis of craters and rocks at the Chang'E-4 landing site. Results revealed a terrain slope of 4 degrees at the landing site, an average depth-to-diameter ratio of 0.061 for small craters, a rock abundance of 0.21%, and a tendency for more rocks to be located inside craters with greater depth-to-diameter ratios.

EARTH AND PLANETARY SCIENCE LETTERS (2021)

添加到收藏夹

Article Geochemistry & Geophysics

A Semiautomatic Registration Method for Chang'E-1 IIM Imagery Based on Globally Geo-Reference LROC-WAC Mosaic Imagery

Ze Yang et al.

Summary: This study proposes a semi-automatic registration method for Chang'E-1 IIM imagery based on global geo-reference LROC-WAC mosaic imagery to address the inaccurate registration issue caused by heterogeneous characteristics in traditional image registration methods. The method utilizes a random sample consensus (RANSAC)-guided affine transformation (AT) model to predict coarse correspondence and a multiwindow image matching approach for fine correspondence. Experimental results show that the proposed method can achieve high image registration accuracy with minimal manual intervention.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2021)

添加到收藏夹

Article Geochemistry & Geophysics

An Improved Global Catalog of Lunar Impact Craters (≥1 km) With 3D Morphometric Information and Updates on Global Crater Analysis

Yiran Wang et al.

Summary: This study introduces a machine-learning approach for automatic crater detection and a method for extracting 3D morphometric information of craters. These approaches were applied to create a global crater dataset containing approximately 1.32 million craters with diameters of 1 km or larger, which were verified against previously published catalogs. This comprehensive crater catalog provides valuable data for various lunar scientific studies.

JOURNAL OF GEOPHYSICAL RESEARCH-PLANETS (2021)

添加到收藏夹

Article Multidisciplinary Sciences