An interactive image segmentation method for lithological boundary detection: A rapid mapping tool for geologists

Research output: Contribution to journalArticle

11 Citations (Scopus)
94 Downloads (Pure)

Abstract

Large volumes of images are collected by geoscientists using remote sensing platforms. Manual analysis of these images is a time consuming task and there is a need for fast and robust image interpretation tools. In particular the reliable mapping of lithological boundaries is a critical step for geological interpretation. In this contribution we developed an interactive image segmentation algorithm that harnesses the geologist's input and exploits automated image analysis to provide a practical tool for lithology boundary detection, using photographic images of rock surfaces. In the proposed method, the user is expected to draw rough markings to indicate the locations of different geological units in the image. Image segmentation is performed by segmenting regions based on their homogeneity in colour. This results in a high density of segmented regions which are then iteratively merged based on the colour of different geological units and the user input. Finally, a post-processing step allows the user to edit the boundaries. An experiment was conducted using photographic rock surface images collected by a UAV and a handheld digital camera. The proposed technique was applied to detect lithology boundaries. It was found that the proposed method reduced the interpretation time by a factor of four relative to manual segmentation, while achieving more than 96% similarity in boundary detection. As a result the proposed method has the potential to provide practical support for interpreting large volume of complex geological images.

Original languageEnglish
Pages (from-to)27-40
Number of pages14
JournalComputers and Geosciences
Volume100
DOIs
Publication statusPublished - 1 Mar 2017

Fingerprint

Lithology
Image segmentation
segmentation
Rocks
Color
Digital cameras
Unmanned aerial vehicles (UAV)
Image analysis
Remote sensing
Processing
Experiments
lithology
method
detection
image analysis
rock
homogeneity
remote sensing

Cite this

@article{bde3584bd27f44d192ede6c837343fae,
title = "An interactive image segmentation method for lithological boundary detection: A rapid mapping tool for geologists",
abstract = "Large volumes of images are collected by geoscientists using remote sensing platforms. Manual analysis of these images is a time consuming task and there is a need for fast and robust image interpretation tools. In particular the reliable mapping of lithological boundaries is a critical step for geological interpretation. In this contribution we developed an interactive image segmentation algorithm that harnesses the geologist's input and exploits automated image analysis to provide a practical tool for lithology boundary detection, using photographic images of rock surfaces. In the proposed method, the user is expected to draw rough markings to indicate the locations of different geological units in the image. Image segmentation is performed by segmenting regions based on their homogeneity in colour. This results in a high density of segmented regions which are then iteratively merged based on the colour of different geological units and the user input. Finally, a post-processing step allows the user to edit the boundaries. An experiment was conducted using photographic rock surface images collected by a UAV and a handheld digital camera. The proposed technique was applied to detect lithology boundaries. It was found that the proposed method reduced the interpretation time by a factor of four relative to manual segmentation, while achieving more than 96{\%} similarity in boundary detection. As a result the proposed method has the potential to provide practical support for interpreting large volume of complex geological images.",
keywords = "Interactive image segmentation, Lithological boundary detection, Multi label segmentation, Real time boundary editing, Region merging",
author = "Yathunanthan Vasuki and Holden, {Eun Jung} and Peter Kovesi and Steven Micklethwaite",
year = "2017",
month = "3",
day = "1",
doi = "10.1016/j.cageo.2016.12.001",
language = "English",
volume = "100",
pages = "27--40",
journal = "Computers & Geosciences",
issn = "0098-3004",
publisher = "Elsevier",

}

TY - JOUR

T1 - An interactive image segmentation method for lithological boundary detection

T2 - A rapid mapping tool for geologists

AU - Vasuki, Yathunanthan

AU - Holden, Eun Jung

AU - Kovesi, Peter

AU - Micklethwaite, Steven

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Large volumes of images are collected by geoscientists using remote sensing platforms. Manual analysis of these images is a time consuming task and there is a need for fast and robust image interpretation tools. In particular the reliable mapping of lithological boundaries is a critical step for geological interpretation. In this contribution we developed an interactive image segmentation algorithm that harnesses the geologist's input and exploits automated image analysis to provide a practical tool for lithology boundary detection, using photographic images of rock surfaces. In the proposed method, the user is expected to draw rough markings to indicate the locations of different geological units in the image. Image segmentation is performed by segmenting regions based on their homogeneity in colour. This results in a high density of segmented regions which are then iteratively merged based on the colour of different geological units and the user input. Finally, a post-processing step allows the user to edit the boundaries. An experiment was conducted using photographic rock surface images collected by a UAV and a handheld digital camera. The proposed technique was applied to detect lithology boundaries. It was found that the proposed method reduced the interpretation time by a factor of four relative to manual segmentation, while achieving more than 96% similarity in boundary detection. As a result the proposed method has the potential to provide practical support for interpreting large volume of complex geological images.

AB - Large volumes of images are collected by geoscientists using remote sensing platforms. Manual analysis of these images is a time consuming task and there is a need for fast and robust image interpretation tools. In particular the reliable mapping of lithological boundaries is a critical step for geological interpretation. In this contribution we developed an interactive image segmentation algorithm that harnesses the geologist's input and exploits automated image analysis to provide a practical tool for lithology boundary detection, using photographic images of rock surfaces. In the proposed method, the user is expected to draw rough markings to indicate the locations of different geological units in the image. Image segmentation is performed by segmenting regions based on their homogeneity in colour. This results in a high density of segmented regions which are then iteratively merged based on the colour of different geological units and the user input. Finally, a post-processing step allows the user to edit the boundaries. An experiment was conducted using photographic rock surface images collected by a UAV and a handheld digital camera. The proposed technique was applied to detect lithology boundaries. It was found that the proposed method reduced the interpretation time by a factor of four relative to manual segmentation, while achieving more than 96% similarity in boundary detection. As a result the proposed method has the potential to provide practical support for interpreting large volume of complex geological images.

KW - Interactive image segmentation

KW - Lithological boundary detection

KW - Multi label segmentation

KW - Real time boundary editing

KW - Region merging

UR - http://www.scopus.com/inward/record.url?scp=85002487050&partnerID=8YFLogxK

U2 - 10.1016/j.cageo.2016.12.001

DO - 10.1016/j.cageo.2016.12.001

M3 - Article

VL - 100

SP - 27

EP - 40

JO - Computers & Geosciences

JF - Computers & Geosciences

SN - 0098-3004

ER -