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

Vosco Pereira, Satoshi Tamura, Satoru Hayamizu, Hidekazu Fukai

研究成果: Conference contribution

20 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトルProceedings of the 2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018
出版社Institute of Electrical and Electronics Engineers Inc.
ページ279-284
ページ数6
ISBN(電子版)9781538645222
DOI
出版ステータスPublished - 2018 9 28
外部発表はい
イベント2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018 - Singapore, Singapore
継続期間: 2018 7 312018 8 2

出版物シリーズ

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

Conference

Conference2018 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2018
国/地域Singapore
CitySingapore
Period18/7/3118/8/2

ASJC Scopus subject areas

  • 信号処理
  • 情報システムおよび情報管理
  • 経営科学およびオペレーションズ リサーチ
  • 器械工学
  • コンピュータ ネットワークおよび通信
  • コンピュータ サイエンスの応用

フィンガープリント

「A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル