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
来源
2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) | 2020年
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 35 条
  • [1] CReSIS airborne radars and platforms for ice and snow sounding
    Arnold, Emily
    Leuschen, Carl
    Rodriguez-Morales, Fernando
    Li, Jilu
    Paden, John
    Hale, Richard
    Keshmiri, Shawn
    [J]. ANNALS OF GLACIOLOGY, 2020, 61 (81) : 58 - 67
  • [2] Automatic Enhancement and Detection of Layering in Radar Sounder Data Based on a Local Scale Hidden Markov Model and the Viterbi Algorithm
    Carrer, Leonardo
    Bruzzone, Lorenzo
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2017, 55 (02): : 962 - 977
  • [3] Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
    Chen, Liang-Chieh
    Zhu, Yukun
    Papandreou, George
    Schroff, Florian
    Adam, Hartwig
    [J]. COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 : 833 - 851
  • [4] CReSIS, 2020, SNOW RAD DAT
  • [5] A comparison of deep networks with ReLU activation function and linear spline-type methods
    Eckle, Konstantin
    Schmidt-Hieber, Johannes
    [J]. NEURAL NETWORKS, 2019, 110 : 232 - 242
  • [6] Automatic Extraction and Analysis of Ice Layering in Radar Sounder Data
    Ferro, Adamo
    Bruzzone, Lorenzo
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2013, 51 (03): : 1622 - 1634
  • [7] Gogineni S., 2013, IEEE MTT-S International Microwave and RF Conference, P1
  • [8] Deep Residual Learning for Image Recognition
    He, Kaiming
    Zhang, Xiangyu
    Ren, Shaoqing
    Sun, Jian
    [J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 770 - 778
  • [9] A System for the Automatic Classification of Ice Sheet Subsurface Targets in Radar Sounder Data
    Ilisei, Ana-Maria
    Bruzzone, Lorenzo
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (06): : 3260 - 3277
  • [10] IPCC, 2014, IPCC AR5 WG1 SUMM PO