A Survey on Image-Based Automation of CCTV and SSET Sewer Inspections

Joakim Bruslund Haurum; Thomas B. Moeslund

doi:10.1016/j.autcon.2019.103061

A Survey on Image-Based Automation of CCTV and SSET Sewer Inspections

Joakim Bruslund Haurum^*, Thomas B. Moeslund

^*Corresponding author for this work

Research output: Contribution to journal › Review article › peer-review

63 Citations (Scopus)

Abstract

This survey presents an in-depth overview of the last 25 years of research within the field of image-based automation of Closed-Circuit Television (CCTV) and Sewer Scanner and Evaluation Technology (SSET) sewer inspection. The survey investigates both the algorithmic pipeline, and the datasets and corresponding evaluation protocols.As a result of the indepth survey, several trends within the research field are revealed, discussed, and future research directions are proposed. Based on the conducted survey, we put forth a set of three recommendations, which we believe will further improve and open the research field, aswell as make the future research more reproducible: 1) The introduction of free and public benchmark datasets, 2) Standardized evaluation metrics, and 3) Open-sourcing the associated code.

Original language	English
Article number	103061
Journal	Automation in Construction
Volume	111
Number of pages	19
ISSN	0926-5805
DOIs	https://doi.org/10.1016/j.autcon.2019.103061
Publication status	Published - Mar 2020

Keywords

Automated inspection
Closed-Circuit Television
Computer ision
Machine learning
Sewer inspection
Sewer pipes
Sewerage infrastructure
Survey

Access to Document

10.1016/j.autcon.2019.103061

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@article{c94e4044b7c743d1b193813ce82ad452,

title = "A Survey on Image-Based Automation of CCTV and SSET Sewer Inspections",

abstract = "This survey presents an in-depth overview of the last 25 years of research within the field of image-based automation of Closed-Circuit Television (CCTV) and Sewer Scanner and Evaluation Technology (SSET) sewer inspection. The survey investigates both the algorithmic pipeline, and the datasets and corresponding evaluation protocols.As a result of the indepth survey, several trends within the research field are revealed, discussed, and future research directions are proposed. Based on the conducted survey, we put forth a set of three recommendations, which we believe will further improve and open the research field, aswell as make the future research more reproducible: 1) The introduction of free and public benchmark datasets, 2) Standardized evaluation metrics, and 3) Open-sourcing the associated code. ",

keywords = "Automated inspection, Closed-Circuit Television, Computer ision, Machine learning, Sewer inspection, Sewer pipes, Sewerage infrastructure, Survey",

author = "Haurum, {Joakim Bruslund} and Moeslund, {Thomas B.}",

year = "2020",

month = mar,

doi = "10.1016/j.autcon.2019.103061",

language = "English",

volume = "111",

journal = "Automation in Construction",

issn = "0926-5805",

publisher = "Elsevier",

}

TY - JOUR

T1 - A Survey on Image-Based Automation of CCTV and SSET Sewer Inspections

AU - Haurum, Joakim Bruslund

AU - Moeslund, Thomas B.

PY - 2020/3

Y1 - 2020/3

N2 - This survey presents an in-depth overview of the last 25 years of research within the field of image-based automation of Closed-Circuit Television (CCTV) and Sewer Scanner and Evaluation Technology (SSET) sewer inspection. The survey investigates both the algorithmic pipeline, and the datasets and corresponding evaluation protocols.As a result of the indepth survey, several trends within the research field are revealed, discussed, and future research directions are proposed. Based on the conducted survey, we put forth a set of three recommendations, which we believe will further improve and open the research field, aswell as make the future research more reproducible: 1) The introduction of free and public benchmark datasets, 2) Standardized evaluation metrics, and 3) Open-sourcing the associated code.

AB - This survey presents an in-depth overview of the last 25 years of research within the field of image-based automation of Closed-Circuit Television (CCTV) and Sewer Scanner and Evaluation Technology (SSET) sewer inspection. The survey investigates both the algorithmic pipeline, and the datasets and corresponding evaluation protocols.As a result of the indepth survey, several trends within the research field are revealed, discussed, and future research directions are proposed. Based on the conducted survey, we put forth a set of three recommendations, which we believe will further improve and open the research field, aswell as make the future research more reproducible: 1) The introduction of free and public benchmark datasets, 2) Standardized evaluation metrics, and 3) Open-sourcing the associated code.

KW - Automated inspection

KW - Closed-Circuit Television

KW - Computer ision

KW - Machine learning

KW - Sewer inspection

KW - Sewer pipes

KW - Sewerage infrastructure

KW - Survey

UR - http://www.scopus.com/inward/record.url?scp=85077927607&partnerID=8YFLogxK

U2 - 10.1016/j.autcon.2019.103061

DO - 10.1016/j.autcon.2019.103061

M3 - Review article

SN - 0926-5805

VL - 111

JO - Automation in Construction

JF - Automation in Construction

M1 - 103061

ER -

A Survey on Image-Based Automation of CCTV and SSET Sewer Inspections

Abstract

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

ASIR: ASIR: Autonomous Sewer Inspection Robot

Robots find defects in sewers

FORSKER I SPILDEVAND: Kontinuerlig inspektion af kloakrør kan spare forsyninger for et trecifret millionbeløb – om året

Tv-inspektioner af kloakker kan automatiseres

Data og algoritmer skal hjælpe med at vedligeholde vores kloakker

Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification

Cite this

A Survey on Image-Based Automation of CCTV and SSET Sewer Inspections

Abstract

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Projects

ASIR: ASIR: Autonomous Sewer Inspection Robot

Impacts

Robots find defects in sewers

Press/Media

FORSKER I SPILDEVAND: Kontinuerlig inspektion af kloakrør kan spare forsyninger for et trecifret millionbeløb – om året

Tv-inspektioner af kloakker kan automatiseres

Data og algoritmer skal hjælpe med at vedligeholde vores kloakker

Research output

Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification

Cite this