基于多层次分割的月表撞击坑自动检测

doi:10.13474/j.cnki.11-2246.2023.0321

摘要/Abstract

摘要： 对月表不同尺寸撞击坑的提取具有重要研究价值。目前针对直径1 km以下的撞击坑检测取得了理想的效果,但对于相对较大的撞击坑检测率有待进一步提升。本文提出了一种具有良好稳健性的撞击坑自动检测模型,基于LOLA发布的全月DEM数据生成了月表地形参数,采用面向对象的多层次分割方法并结合机器学习技术提取撞击坑,选取3个典型样区进行了试验分析。结果表明,对于直径范围在1～120 km内的撞击坑,召回率和精确率分别为86.5%和81.2%,具有良好的检测率。

关键词: 撞击坑, 自动检测, 面向对象, 多层次分割

Abstract: The extraction of craters of different sizes on the lunar surface is of great value. Currently, crater detection algorithmsare effective for craters less than one kilometer, but the detection rate of largercraters needs to be improved. We propose an automatic crater detection model with good robustness.Firstly, we generate the terrain parameters based on the who lelunar DEM published by LOLA, then detect craters by object-oriented multilevel sesgmentation combined with machine learning.Three typical regions are selected for experiment and analysis, the recall and accuracy rates for craters between 1~120 km in diameter are 86.5% and 81.2% respectively, with a good detection rate.

Key words: impact crater, automatic detection, object-orientation, multilevel segmentation

中图分类号:

P237

李海鹏, 董有福, 张昊. 基于多层次分割的月表撞击坑自动检测[J]. 测绘通报, 2023, 0(11): 18-22.

LI Haipeng, DONG Youfu, ZHANG Hao. Lunar impact crater detection based on multilevel segmentation[J]. Bulletin of Surveying and Mapping, 2023, 0(11): 18-22.

参考文献

[1] YANG Chen,ZHAO Haishi,BRUZZONE L,et al. Lunar impact crater identification and age estimation with Chang' E data by deep and transfer learning[J]. Nature Communications,2020,11: 6358.
[2] WU Bo,LI Yuan,LIU W C,et al. Centimeter-resolution topographic modeling and fine-scale analysis of craters and rocks at the Chang' E-4 landing site[J]. Earth and Planetary Science Letters,2021,553: 116666.
[3] RUBANENKO L,VENKATRAMAN J,PAIGE D A. Thick ice deposits in shallow simple craters on the Moon and Mercury[J]. Nature Geoscience,2019,12(8): 597-601.
[4] SILVESTRINI S,PICCININ M,ZANOTTI G,et al. Optical navigation for Lunar landing based on convolutional neural network crater detector[J]. Aerospace Science and Technology,2022,123: 107503.
[5] KANG Zhizhong,LUO Zhongfei,HU Teng,et al. Automatic extraction and identification of lunar impact craters based on optical data and DEMs acquired by the Chang'E satellites[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(10): 4751-4761.
[6] SAWABE Y,MATSUNAGA T,ROKUGAWA S. Automated detection and classification of lunar craters using multiple approaches[J]. Advances in Space Research,2006,37(1): 21-27.
[7] 鲁宇航,苗放,都骏. 基于特征匹配的月球撞击坑自动提取研究[J]. 测绘科学,2013,38(5): 108-111.
[8] 罗中飞,康志忠,刘心怡. 融合嫦娥一号CCD影像与DEM数据的月球撞击坑自动提取和识别[J]. 测绘学报,2014,43(9): 924-930.
[9] KANG Zhizhong,WANG Xingkun,HU Teng,et al. Coarse-to-fine extraction of small-scale lunar impact craters from the CCD images of the Chang’E lunar orbiters[J]. IEEE Transactions on Geoscience and Remote Sensing,2019,57(1): 181-193.
[10] WANG Yiran,WU Bo. Active machine learning approach for crater detection from planetary imagery and digital elevation models[J]. IEEE Transactions on Geoscience and Remote Sensing,2019,57(8): 5777-5789.
[11] WANG Yaqiong,XIE Huan,HUANG Qian,et al. A novel approach for multiscale lunar crater detection by the use of path-profile and isolation forest based on high-resolution planetary images[J]. IEEE Transactions on Geoscience and Remote Sensing,2022,60: 1-24.
[12] LIN Xuxin,ZHU Zhenwei,YU Xiaoyuan,et al. Lunar crater detection on digital elevation model: a complete workflow using deep learning and its application[J]. Remote Sensing,2022,14(3): 621.
[13] ZHOU Yi,ZHAO Hao,CHEN Min,et al. Automatic detection of lunar craters based on DEM data with the terrain analysis method[J]. Planetary and Space Science,2018,160: 1-11.
[14] ZUO Wei,ZHANG Zhoubin,LI Chunlai,et al. Contour-based automatic crater recognition using digital elevation models from Chang' E missions[J]. Computers & Geosciences,2016,97: 79-88.
[15] CHEN Min,LIU Danyang,QIAN Kejian,et al.Lunar crater detection based on terrain analysis and mathematical morphology methods using digital elevation models[J]. IEEE Transactions on Geoscience and Remote Sensing,2018,56(7): 3681-3692.
[16] 岳宗玉,刘建忠,吴淦国. 应用面向对象分类方法对月球撞击坑进行自动识别[J]. 科学通报,2008,53(22): 2809-2813.
[17] VAMSHI G T,MARTHA T R,VINOD KUMAR K. An object-based classification method for automatic detection of lunar impact craters from topographic data[J]. Advances in Space Research,2016,57(9): 1978-1988.
[18] 何江,刘勇. 基于多层次分割及形状因子优化的高分辨率遥感影像城市建筑物和道路提取研究[J]. 测绘技术装备,2019,21(1): 26-31.
[19] DRǍGUŢ L,TIEDE D,LEVICK S R. ESP: a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data[J]. International Journal of Geographical Information Science,2010,24(6): 859-871.