Automated segmentation of gravel particles from depth images of gravel-soil mixtures

Research output: Contribution to journalArticle

Abstract

We propose an image-based technique to measure the volume, weight and the size distribution of gravel particles in a gravel-soil mixture. The proposed method uses 3D scanning and a surface reconstruction algorithm to generate a high-resolution depth image, which is then used to accurately estimate the volume and weight of each gravel particle. The proposed method is evaluated on several gravel soil samples collected from 25 farming locations. The experimental results show that the proposed technique produces an accurate estimate of gravel volumes and gravel weights. It achieves a relative root mean square error of 4% for large gravel particles and an overall correlation of 0.99 with the ground truth, for the task of gravel volume estimation. For the estimation of gravel weight distribution, the proposed method can reach a low root mean square error of 0.54%. The rapid measurement of the full spectrum of coarse fragments in soil, using this method, is an advantage compared to the manual methods.

Original languageEnglish
Pages (from-to)1-10
Number of pages10
JournalComputers & Geosciences
Volume128
DOIs
Publication statusPublished - Jul 2019

Cite this

@article{8f91d228dd6b48049acfa6b2444fe2b2,
title = "Automated segmentation of gravel particles from depth images of gravel-soil mixtures",
abstract = "We propose an image-based technique to measure the volume, weight and the size distribution of gravel particles in a gravel-soil mixture. The proposed method uses 3D scanning and a surface reconstruction algorithm to generate a high-resolution depth image, which is then used to accurately estimate the volume and weight of each gravel particle. The proposed method is evaluated on several gravel soil samples collected from 25 farming locations. The experimental results show that the proposed technique produces an accurate estimate of gravel volumes and gravel weights. It achieves a relative root mean square error of 4{\%} for large gravel particles and an overall correlation of 0.99 with the ground truth, for the task of gravel volume estimation. For the estimation of gravel weight distribution, the proposed method can reach a low root mean square error of 0.54{\%}. The rapid measurement of the full spectrum of coarse fragments in soil, using this method, is an advantage compared to the manual methods.",
keywords = "Segmentation, Point cloud, Support vector machine, Image classification, Volume estimation, Gravel weight distribution",
author = "Hossein Rahmani and Craig Scanlan and Uzair Nadeem and Mohammed Bennamoun and Richard Bowles",
year = "2019",
month = "7",
doi = "10.1016/j.cageo.2019.03.005",
language = "English",
volume = "128",
pages = "1--10",
journal = "Computers & Geosciences",
issn = "0098-3004",
publisher = "Elsevier",

}

TY - JOUR

T1 - Automated segmentation of gravel particles from depth images of gravel-soil mixtures

AU - Rahmani, Hossein

AU - Scanlan, Craig

AU - Nadeem, Uzair

AU - Bennamoun, Mohammed

AU - Bowles, Richard

PY - 2019/7

Y1 - 2019/7

N2 - We propose an image-based technique to measure the volume, weight and the size distribution of gravel particles in a gravel-soil mixture. The proposed method uses 3D scanning and a surface reconstruction algorithm to generate a high-resolution depth image, which is then used to accurately estimate the volume and weight of each gravel particle. The proposed method is evaluated on several gravel soil samples collected from 25 farming locations. The experimental results show that the proposed technique produces an accurate estimate of gravel volumes and gravel weights. It achieves a relative root mean square error of 4% for large gravel particles and an overall correlation of 0.99 with the ground truth, for the task of gravel volume estimation. For the estimation of gravel weight distribution, the proposed method can reach a low root mean square error of 0.54%. The rapid measurement of the full spectrum of coarse fragments in soil, using this method, is an advantage compared to the manual methods.

AB - We propose an image-based technique to measure the volume, weight and the size distribution of gravel particles in a gravel-soil mixture. The proposed method uses 3D scanning and a surface reconstruction algorithm to generate a high-resolution depth image, which is then used to accurately estimate the volume and weight of each gravel particle. The proposed method is evaluated on several gravel soil samples collected from 25 farming locations. The experimental results show that the proposed technique produces an accurate estimate of gravel volumes and gravel weights. It achieves a relative root mean square error of 4% for large gravel particles and an overall correlation of 0.99 with the ground truth, for the task of gravel volume estimation. For the estimation of gravel weight distribution, the proposed method can reach a low root mean square error of 0.54%. The rapid measurement of the full spectrum of coarse fragments in soil, using this method, is an advantage compared to the manual methods.

KW - Segmentation

KW - Point cloud

KW - Support vector machine

KW - Image classification

KW - Volume estimation

KW - Gravel weight distribution

U2 - 10.1016/j.cageo.2019.03.005

DO - 10.1016/j.cageo.2019.03.005

M3 - Article

VL - 128

SP - 1

EP - 10

JO - Computers & Geosciences

JF - Computers & Geosciences

SN - 0098-3004

ER -