Inferring the most probable maps of underground utilities using Bayesian mapping model

Muhammad Bilal, Wasiq Khan, Jennifer Muggleton, Emiliano Rustighi, Hugo Jenks, Steve R. Pennock, Phil R. Atkins, Anthony Cohn

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Mapping the Underworld (MTU), a major initiative in the UK, is focused on addressing social, environmental and economic consequences raised from the inability to locate buried underground utilities (such as pipes and cables) by developing a multi-sensor mobile device. The aim of MTU device is to locate different types of buried assets in real time with the use of automated data processing techniques and statutory records. The statutory records, even though typically being inaccurate and incomplete, provide useful prior information on what is buried under the ground and where. However, the integration of information from multiple sensors (raw data) with these qualitative maps and their visualization is challenging and requires the implementation of robust machine learning/data fusion approaches. An approach for automated creation of revised maps was developed as a Bayesian Mapping model in this paper by integrating the knowledge extracted from sensors raw data and available statutory records. The combination of statutory records with the hypotheses from sensors was for initial estimation of what might be found underground and roughly where. The maps were (re)constructed using automated image segmentation techniques for hypotheses extraction and Bayesian classification techniques for segment-manhole connections. The model consisting of image segmentation algorithm and various Bayesian classification techniques (segment recognition and expectation maximization (EM) algorithm) provided robust performance on various simulated as well as real sites in terms of predicting linear/non-linear segments and constructing refined 2D/3D maps.

Original languageEnglish
Pages (from-to)52-66
Number of pages15
JournalJournal of Applied Geophysics
Volume150
Early online date31 Jan 2018
DOIs
Publication statusPublished - 31 Mar 2018

Fingerprint

sensor
sensors
segmentation
machine learning
multisensor fusion
cable
cables
visualization
economics
pipe

Keywords

  • Bayesian data fusion
  • Bayesian regression
  • Image processing
  • Most probable maps
  • MTU sensors

ASJC Scopus subject areas

  • Geophysics

Cite this

Inferring the most probable maps of underground utilities using Bayesian mapping model. / Bilal, Muhammad; Khan, Wasiq; Muggleton, Jennifer; Rustighi, Emiliano; Jenks, Hugo; Pennock, Steve R.; Atkins, Phil R.; Cohn, Anthony.

In: Journal of Applied Geophysics, Vol. 150, 31.03.2018, p. 52-66.

Research output: Contribution to journalArticle

Bilal, Muhammad ; Khan, Wasiq ; Muggleton, Jennifer ; Rustighi, Emiliano ; Jenks, Hugo ; Pennock, Steve R. ; Atkins, Phil R. ; Cohn, Anthony. / Inferring the most probable maps of underground utilities using Bayesian mapping model. In: Journal of Applied Geophysics. 2018 ; Vol. 150. pp. 52-66.
@article{a201d3e67b1d48ec81b50f958451712d,
title = "Inferring the most probable maps of underground utilities using Bayesian mapping model",
abstract = "Mapping the Underworld (MTU), a major initiative in the UK, is focused on addressing social, environmental and economic consequences raised from the inability to locate buried underground utilities (such as pipes and cables) by developing a multi-sensor mobile device. The aim of MTU device is to locate different types of buried assets in real time with the use of automated data processing techniques and statutory records. The statutory records, even though typically being inaccurate and incomplete, provide useful prior information on what is buried under the ground and where. However, the integration of information from multiple sensors (raw data) with these qualitative maps and their visualization is challenging and requires the implementation of robust machine learning/data fusion approaches. An approach for automated creation of revised maps was developed as a Bayesian Mapping model in this paper by integrating the knowledge extracted from sensors raw data and available statutory records. The combination of statutory records with the hypotheses from sensors was for initial estimation of what might be found underground and roughly where. The maps were (re)constructed using automated image segmentation techniques for hypotheses extraction and Bayesian classification techniques for segment-manhole connections. The model consisting of image segmentation algorithm and various Bayesian classification techniques (segment recognition and expectation maximization (EM) algorithm) provided robust performance on various simulated as well as real sites in terms of predicting linear/non-linear segments and constructing refined 2D/3D maps.",
keywords = "Bayesian data fusion, Bayesian regression, Image processing, Most probable maps, MTU sensors",
author = "Muhammad Bilal and Wasiq Khan and Jennifer Muggleton and Emiliano Rustighi and Hugo Jenks and Pennock, {Steve R.} and Atkins, {Phil R.} and Anthony Cohn",
year = "2018",
month = "3",
day = "31",
doi = "10.1016/j.jappgeo.2018.01.006",
language = "English",
volume = "150",
pages = "52--66",
journal = "Journal of Applied Geophysics",
issn = "0926-9851",
publisher = "Elsevier",

}

TY - JOUR

T1 - Inferring the most probable maps of underground utilities using Bayesian mapping model

AU - Bilal, Muhammad

AU - Khan, Wasiq

AU - Muggleton, Jennifer

AU - Rustighi, Emiliano

AU - Jenks, Hugo

AU - Pennock, Steve R.

AU - Atkins, Phil R.

AU - Cohn, Anthony

PY - 2018/3/31

Y1 - 2018/3/31

N2 - Mapping the Underworld (MTU), a major initiative in the UK, is focused on addressing social, environmental and economic consequences raised from the inability to locate buried underground utilities (such as pipes and cables) by developing a multi-sensor mobile device. The aim of MTU device is to locate different types of buried assets in real time with the use of automated data processing techniques and statutory records. The statutory records, even though typically being inaccurate and incomplete, provide useful prior information on what is buried under the ground and where. However, the integration of information from multiple sensors (raw data) with these qualitative maps and their visualization is challenging and requires the implementation of robust machine learning/data fusion approaches. An approach for automated creation of revised maps was developed as a Bayesian Mapping model in this paper by integrating the knowledge extracted from sensors raw data and available statutory records. The combination of statutory records with the hypotheses from sensors was for initial estimation of what might be found underground and roughly where. The maps were (re)constructed using automated image segmentation techniques for hypotheses extraction and Bayesian classification techniques for segment-manhole connections. The model consisting of image segmentation algorithm and various Bayesian classification techniques (segment recognition and expectation maximization (EM) algorithm) provided robust performance on various simulated as well as real sites in terms of predicting linear/non-linear segments and constructing refined 2D/3D maps.

AB - Mapping the Underworld (MTU), a major initiative in the UK, is focused on addressing social, environmental and economic consequences raised from the inability to locate buried underground utilities (such as pipes and cables) by developing a multi-sensor mobile device. The aim of MTU device is to locate different types of buried assets in real time with the use of automated data processing techniques and statutory records. The statutory records, even though typically being inaccurate and incomplete, provide useful prior information on what is buried under the ground and where. However, the integration of information from multiple sensors (raw data) with these qualitative maps and their visualization is challenging and requires the implementation of robust machine learning/data fusion approaches. An approach for automated creation of revised maps was developed as a Bayesian Mapping model in this paper by integrating the knowledge extracted from sensors raw data and available statutory records. The combination of statutory records with the hypotheses from sensors was for initial estimation of what might be found underground and roughly where. The maps were (re)constructed using automated image segmentation techniques for hypotheses extraction and Bayesian classification techniques for segment-manhole connections. The model consisting of image segmentation algorithm and various Bayesian classification techniques (segment recognition and expectation maximization (EM) algorithm) provided robust performance on various simulated as well as real sites in terms of predicting linear/non-linear segments and constructing refined 2D/3D maps.

KW - Bayesian data fusion

KW - Bayesian regression

KW - Image processing

KW - Most probable maps

KW - MTU sensors

UR - http://www.scopus.com/inward/record.url?scp=85044639536&partnerID=8YFLogxK

U2 - 10.1016/j.jappgeo.2018.01.006

DO - 10.1016/j.jappgeo.2018.01.006

M3 - Article

VL - 150

SP - 52

EP - 66

JO - Journal of Applied Geophysics

JF - Journal of Applied Geophysics

SN - 0926-9851

ER -