Estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network

Ground-penetrating radar (GPR) has been used as a non-destructive tool for tree root inspection. Estimating root-related parameters from GPR radargrams greatly facilitates root health monitoring and imaging. However, the task of estimating root-related parameters is challenging as the root reflec...

Full description

Saved in:
Bibliographic Details
Main Authors: Sun, Hai-Han, Lee, Yee Hui, Dai, Qiqi, Li, Chongyi, Ow, Genevieve, Mohamed Lokman Mohd Yusof, Yucel, Abdulkadir C.
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/162648
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-162648
record_format dspace
spelling sg-ntu-dr.10356-1626482022-11-02T01:55:09Z Estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network Sun, Hai-Han Lee, Yee Hui Dai, Qiqi Li, Chongyi Ow, Genevieve Mohamed Lokman Mohd Yusof Yucel, Abdulkadir C. School of Computer Science and Engineering School of Electrical and Electronic Engineering Engineering::Computer science and engineering Engineering::Electrical and electronic engineering Deep Learning Ground-Penetrating Radar Ground-penetrating radar (GPR) has been used as a non-destructive tool for tree root inspection. Estimating root-related parameters from GPR radargrams greatly facilitates root health monitoring and imaging. However, the task of estimating root-related parameters is challenging as the root reflection is a complex function of multiple root parameters and root orientations. Existing methods can only estimate a single root parameter at a time without considering the influence of other parameters and root orientations, resulting in limited estimation accuracy under different root conditions. In addition, soil heterogeneity introduces clutter in GPR radargrams, making the data processing and interpretation even harder. To address these issues, a novel neural network architecture, called mask-guided multi-polarimetric integration neural network (MMI-Net), is proposed to automatically and simultaneously estimate multiple root-related parameters in heterogeneous soil environments. The MMI-Net includes two sub-networks: a MaskNet that predicts a mask to highlight the root reflection area to eliminate interfering environmental clutter, and a ParaNet that uses the predicted mask as guidance to integrate, extract, and emphasize informative features in multi-polarimetric radargrams for accurate estimation of five key root-related parameters. The parameters include the root depth, diameter, relative permittivity, horizontal and vertical orientation angles. Experimental results demonstrate that the proposed MMI-Net achieves high estimation accuracy in these root-related parameters. This is the first work that takes the combined contributions of root parameters and spatial orientations into account and simultaneously estimates multiple root-related parameters. The data and code implemented in the paper can be found at https://haihan-sun.github.io/GPR.html. Ministry of National Development (MND) National Parks Board This work was supported by the Ministry of National Development Research Fund, National Parks Board, Singapore. 2022-11-02T01:55:09Z 2022-11-02T01:55:09Z 2021 Journal Article Sun, H., Lee, Y. H., Dai, Q., Li, C., Ow, G., Mohamed Lokman Mohd Yusof & Yucel, A. C. (2021). Estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network. IEEE Transactions On Geoscience and Remote Sensing, 60, 1-16. https://dx.doi.org/10.1109/TGRS.2021.3138974 0196-2892 https://hdl.handle.net/10356/162648 10.1109/TGRS.2021.3138974 2-s2.0-85122332082 60 1 16 en IEEE Transactions on Geoscience and Remote Sensing © 2021 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Engineering::Electrical and electronic engineering
Deep Learning
Ground-Penetrating Radar
spellingShingle Engineering::Computer science and engineering
Engineering::Electrical and electronic engineering
Deep Learning
Ground-Penetrating Radar
Sun, Hai-Han
Lee, Yee Hui
Dai, Qiqi
Li, Chongyi
Ow, Genevieve
Mohamed Lokman Mohd Yusof
Yucel, Abdulkadir C.
Estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network
description Ground-penetrating radar (GPR) has been used as a non-destructive tool for tree root inspection. Estimating root-related parameters from GPR radargrams greatly facilitates root health monitoring and imaging. However, the task of estimating root-related parameters is challenging as the root reflection is a complex function of multiple root parameters and root orientations. Existing methods can only estimate a single root parameter at a time without considering the influence of other parameters and root orientations, resulting in limited estimation accuracy under different root conditions. In addition, soil heterogeneity introduces clutter in GPR radargrams, making the data processing and interpretation even harder. To address these issues, a novel neural network architecture, called mask-guided multi-polarimetric integration neural network (MMI-Net), is proposed to automatically and simultaneously estimate multiple root-related parameters in heterogeneous soil environments. The MMI-Net includes two sub-networks: a MaskNet that predicts a mask to highlight the root reflection area to eliminate interfering environmental clutter, and a ParaNet that uses the predicted mask as guidance to integrate, extract, and emphasize informative features in multi-polarimetric radargrams for accurate estimation of five key root-related parameters. The parameters include the root depth, diameter, relative permittivity, horizontal and vertical orientation angles. Experimental results demonstrate that the proposed MMI-Net achieves high estimation accuracy in these root-related parameters. This is the first work that takes the combined contributions of root parameters and spatial orientations into account and simultaneously estimates multiple root-related parameters. The data and code implemented in the paper can be found at https://haihan-sun.github.io/GPR.html.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Sun, Hai-Han
Lee, Yee Hui
Dai, Qiqi
Li, Chongyi
Ow, Genevieve
Mohamed Lokman Mohd Yusof
Yucel, Abdulkadir C.
format Article
author Sun, Hai-Han
Lee, Yee Hui
Dai, Qiqi
Li, Chongyi
Ow, Genevieve
Mohamed Lokman Mohd Yusof
Yucel, Abdulkadir C.
author_sort Sun, Hai-Han
title Estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network
title_short Estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network
title_full Estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network
title_fullStr Estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network
title_full_unstemmed Estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network
title_sort estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network
publishDate 2022
url https://hdl.handle.net/10356/162648
_version_ 1749179140631691264