A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste

Vosco Pereira; Satoshi Tamura; Satoru Hayamizu; Hidekazu Fukai

doi:10.1109/SOLI.2018.8476795

A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste

Vosco Pereira, Satoshi Tamura, Satoru Hayamizu, Hidekazu Fukai

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

43 Citations (Scopus)

Abstract

This research proposes a low-cost solution for detecting road potholes image by using convolutional neural network (CNN). Our model is trained entirely on the image which collected from several different places and has variation such as in wet, dry and shady conditions. The experiment using the 500 testing images showed that our model can achieve (99.80 %) of Accuracy, Precision (100%), Recall (99.60%), and F-Measure (99.60%) simultaneously.

Original language	English
Title of host publication	Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	279-284
Number of pages	6
ISBN (Electronic)	9781538645222
DOIs	https://doi.org/10.1109/SOLI.2018.8476795
Publication status	Published - 2018 Sept 28
Externally published	Yes
Event	2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018 - Singapore, Singapore Duration: 2018 Jul 31 → 2018 Aug 2

Publication series

Name	Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018

Conference

Conference	2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018
Country/Territory	Singapore
City	Singapore
Period	18/7/31 → 18/8/2

Keywords

Convolutional Neural Network
Deep Learning
Image Classification
Potholes

ASJC Scopus subject areas

Signal Processing
Information Systems and Management
Management Science and Operations Research
Instrumentation
Computer Networks and Communications
Computer Science Applications

Access to Document

10.1109/SOLI.2018.8476795

Cite this

Pereira, V., Tamura, S., Hayamizu, S., & Fukai, H. (2018). A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste. In Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018 (pp. 279-284). [8476795] (Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SOLI.2018.8476795

A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste. / Pereira, Vosco; Tamura, Satoshi; Hayamizu, Satoru et al.

Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 279-284 8476795 (Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Pereira, V, Tamura, S, Hayamizu, S & Fukai, H 2018, A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste. in Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018., 8476795, Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018, Institute of Electrical and Electronics Engineers Inc., pp. 279-284, 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018, Singapore, Singapore, 18/7/31. https://doi.org/10.1109/SOLI.2018.8476795

Pereira V, Tamura S, Hayamizu S, Fukai H. A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste. In Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 279-284. 8476795. (Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018). doi: 10.1109/SOLI.2018.8476795

Pereira, Vosco ; Tamura, Satoshi ; Hayamizu, Satoru et al. / A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste. Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 279-284 (Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018).

@inproceedings{c065cd25ab32454c882805053fd7fa33,

title = "A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste",

abstract = "This research proposes a low-cost solution for detecting road potholes image by using convolutional neural network (CNN). Our model is trained entirely on the image which collected from several different places and has variation such as in wet, dry and shady conditions. The experiment using the 500 testing images showed that our model can achieve (99.80 %) of Accuracy, Precision (100%), Recall (99.60%), and F-Measure (99.60%) simultaneously.",

keywords = "Convolutional Neural Network, Deep Learning, Image Classification, Potholes",

author = "Vosco Pereira and Satoshi Tamura and Satoru Hayamizu and Hidekazu Fukai",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018 ; Conference date: 31-07-2018 Through 02-08-2018",

year = "2018",

month = sep,

day = "28",

doi = "10.1109/SOLI.2018.8476795",

language = "English",

series = "Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "279--284",

booktitle = "Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018",

}

TY - GEN

T1 - A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste

AU - Pereira, Vosco

AU - Tamura, Satoshi

AU - Hayamizu, Satoru

AU - Fukai, Hidekazu

PY - 2018/9/28

Y1 - 2018/9/28

N2 - This research proposes a low-cost solution for detecting road potholes image by using convolutional neural network (CNN). Our model is trained entirely on the image which collected from several different places and has variation such as in wet, dry and shady conditions. The experiment using the 500 testing images showed that our model can achieve (99.80 %) of Accuracy, Precision (100%), Recall (99.60%), and F-Measure (99.60%) simultaneously.

AB - This research proposes a low-cost solution for detecting road potholes image by using convolutional neural network (CNN). Our model is trained entirely on the image which collected from several different places and has variation such as in wet, dry and shady conditions. The experiment using the 500 testing images showed that our model can achieve (99.80 %) of Accuracy, Precision (100%), Recall (99.60%), and F-Measure (99.60%) simultaneously.

KW - Convolutional Neural Network

KW - Deep Learning

KW - Image Classification

KW - Potholes

UR - http://www.scopus.com/inward/record.url?scp=85055654637&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055654637&partnerID=8YFLogxK

U2 - 10.1109/SOLI.2018.8476795

DO - 10.1109/SOLI.2018.8476795

M3 - Conference contribution

AN - SCOPUS:85055654637

T3 - Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018

SP - 279

EP - 284

BT - Proceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018

Y2 - 31 July 2018 through 2 August 2018

ER -

A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this