极地研究

极地研究 ›› 2023, Vol. 35 ›› Issue (2): 277-287.DOI: 10.13679/j.jdyj.20220202

• 研究论文 • 上一篇    下一篇

基于深度学习算法的冰雷达图像冰面与基岩界面提取

邢治瑞1,2  窦银科1  李霖2  杨望笑1  张锋1  崔祥斌2   

  1. 1太原理工大学电气与动力工程学院, 山西 太原 030024; 
    2中国极地研究中心, 上海 200136
  • 出版日期:2023-06-30 发布日期:2023-06-20
  • 通讯作者: 崔祥斌
  • 作者简介:邢治瑞, 男, 1998年生。硕士研究生, 主要从事冰雷达数据处理方法研究。E-mail: xingzhirui2022@163.com
  • 基金资助:
    国家自然科学基金(41730102,41776186,42176231)、上海市科技计划项目(21ZR1469700)资助

Ice sheet surface and bedrock interface extraction from ice radar image based on deep learning algorithm

Xing Zhirui1,2, Dou Yinke1, Li Lin2, Yang Wangxiao1, Zhang Feng1, Cui Xiangbin2   

  1. 1 College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, China;
    2 Polar Research Institute of China, Shanghai 200136, China
  • Online:2023-06-30 Published:2023-06-20

PDF (PC)

1001

摘要： 极地冰盖底部的冰-基岩界面记录了冰盖的历史演变, 反映了冰层的几何特征和冰底环境属性, 是推断冰盖动力学和解释冰下地貌的重要指标。机载冰雷达是一种有效的极地冰盖探测方法, 但雷达数据受探测环境和仪器自身局限性的影响, 会包含各类噪声。为了高效准确地提取冰雷达图像中基岩界面和冰面、降低噪声干扰, 利用2015—2016年度中国第32次南极科学考察在伊丽莎白公主地的航空冰雷达观测数据, 基于深度学习的pix2pix算法建立了一种自动化提取雷达图像冰面和基岩界面的模型。实验结果表明, 该模型提取冰面/基岩界面的精确率为0.863/0.948, 峰值信噪比为24.814 dB, 均高于以往的K-SVD和CycleGAN同类算法, 能更有效地去除噪声、提高图像质量, 更高精度地还原现在通用的人工提取效果。

关键词: pix2pix, 冰雷达, 基岩提取, 冰下地形, 南极冰盖

Abstract: The ice-rock interface at the bottom of the polar ice sheet records the historical evolution of the ice sheet, reflecting the geometric characteristics of the ice layer and the environmental properties of the ice bottom. Moreover, it is an important indicator both for inferring the dynamics of the ice sheet and for explaining the subglacial topography. Airborne ice radar is an effective method for detection of polar ice cover; however, the radar data contain many types of noise due to the detection environment and to the limitations of the instrument itself. For efficient and accurate extraction of the bedrock interface and the ice surface in an ice radar image, and for reduction in noise interference, we established an automatic method for extraction of the ice surface and bedrock interface in a radar image based on the deep learning pix2pix algorithm and observational airborne ice radar data of Princess Elizabeth Land acquired during the 32nd Chinese National Antarctic Research Expedition in 2015–2016. Experimental results showed that the accuracy of the model proposed for extracting the ice surface/bedrock interface was 0.863/0.948, and that the peak signal-to-noise ratio was 24.814 dB; i.e., higher than that realized previously using the K-SVD and CycleGAN algorithms. Thus, the proposed method was demonstrated to be more effective in removing noise, improving image quality, and restoring the common manual extraction effect with high accuracy.

Key words: pix2pix, ice-penetrating radar, bedrock extraction, subglacial topography, Antarctic ice sheet