Deep Ice Layer Tracking and Thickness Estimation using Fully Convolutional Networks

被引:13
|
作者
Varshney, Debvrat [1 ]
Rahnemoonfar, Maryam [1 ]
Yari, Masoud [1 ]
Paden, John [2 ]
机构
[1] Univ Maryland Baltimore Cty, Comp Vis & Remote Sensing Lab, Baltimore, MD 21228 USA
[2] Univ Kansas, Ctr Remote Sensing Ice Sheets CReSIS, Lawrence, KS 66045 USA
关键词
Ice Layer Thickness; Semantic Segmentation; Fully Convolutional Networks; Radargrams; RADAR; IMAGERY; SURFACE;
D O I
10.1109/BigData50022.2020.9378070
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Global warming is rapidly reducing glaciers and ice sheets across the world. Real time assessment of this reduction is required so as to monitor its global climatic impact. In this paper, we introduce a novel way of estimating the thickness of each internal ice layer using Snow Radar images and Fully Convolutional Networks. The estimated thickness can be used to understand snow accumulation each year. To understand the depth and structure of each internal ice layer, we perform multi-class semantic segmentation on radar images, which hasn't been performed before. As the radar images lack good training labels, we carry out a pre-processing technique to get a clean set of labels. After detecting each ice layer uniquely, we calculate its thickness and compare it with the processed ground truth. This is the first time that each ice layer is detected separately and its thickness calculated through automated techniques. Through this procedure we were able to estimate the ice-layer thicknesses within a Mean Absolute Error of approximately 3.6 pixels. Such a Deep Learning based method can be used with ever-increasing datasets to make accurate assessments for cryospheric studies.
引用
收藏
页码:3943 / 3952
页数:10
相关论文
共 50 条
  • [41] Fully Automatic Karyotyping via Deep Convolutional Neural Networks
    Wang, Chengyu
    Yu, Limin
    Su, Jionglong
    Shen, Juming
    Selis, Valerio
    Yang, Chunxiao
    Ma, Fei
    IEEE ACCESS, 2024, 12 : 46081 - 46092
  • [42] Paragraph Image Captioning with Deep Fully Convolutional Neural Networks
    Li R.-F.
    Liang H.-Y.
    Feng F.-X.
    Zhang G.-W.
    Wang X.-J.
    Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications, 2019, 42 (06): : 155 - 161
  • [43] Fully automatic wound segmentation with deep convolutional neural networks
    Chuanbo Wang
    D. M. Anisuzzaman
    Victor Williamson
    Mrinal Kanti Dhar
    Behrouz Rostami
    Jeffrey Niezgoda
    Sandeep Gopalakrishnan
    Zeyun Yu
    Scientific Reports, 10
  • [44] Fully automatic wound segmentation with deep convolutional neural networks
    Wang, Chuanbo
    Anisuzzaman, D. M.
    Williamson, Victor
    Dhar, Mrinal Kanti
    Rostami, Behrouz
    Niezgoda, Jeffrey
    Gopalakrishnan, Sandeep
    Yu, Zeyun
    SCIENTIFIC REPORTS, 2020, 10 (01)
  • [45] Feature Enhanced Fully Convolutional Networks for Monocular Depth Estimation
    Shi, Chunxiu
    Chen, Jie
    Chen, Juan
    Zhang, Zheng
    2019 IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA 2019), 2019, : 270 - 276
  • [46] Water Level Estimation in Sewer Pipes Using Deep Convolutional Neural Networks
    Haurum, Joakim Bruslund
    Bahnsen, Chris H.
    Pedersen, Malte
    Moeslund, Thomas B.
    WATER, 2020, 12 (12) : 1 - 14
  • [47] Polarimetric Radar Quantitative Precipitation Estimation Using Deep Convolutional Neural Networks
    Li, Wenyuan
    Chen, Haonan
    Han, Lei
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [48] Historical Manuscript Production Date Estimation using Deep Convolutional Neural Networks
    Wahlberg, Fredrik
    Wilkinson, Tomas
    Brun, Anders
    PROCEEDINGS OF 2016 15TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2016, : 205 - 210
  • [49] Joint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks
    Cui, Ying
    Guo, Dongyan
    Shao, Yanyan
    Wang, Zhenhua
    Shen, Chunhua
    Zhang, Liyan
    Chen, Shengyong
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 130 (02) : 550 - 566
  • [50] Joint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks
    Ying Cui
    Dongyan Guo
    Yanyan Shao
    Zhenhua Wang
    Chunhua Shen
    Liyan Zhang
    Shengyong Chen
    International Journal of Computer Vision, 2022, 130 : 550 - 566