9 files

Multi-Type Bridge Damage Detection Method Based on YOLO

Download all (3 MB)
posted on 24.11.2021, 04:17 by Ji DANG, Pang-jo ChunPang-jo Chun, Taiga MIZUMOTO, Jiaming LIU, Tonan FUJISHIMA

In this study, we try to solve the problem by using UAV and YOLO, which is one of the deep learning methods, for bridge inspection work, which is concerned about labor shortage and cost. By using deep learning, it is possible to shorten the work time by programming the work and suppress oversights and mistakes by add-ing an objective element to the diagnosis of damage. In the verification using CNN conducted by Tabata et al. As a previous study, the damaged part could be roughly recognized by the damage recognition of the image tak-en by the UAV, but the background part that had not been trained was mistakenly recognized as the damage. In addition, the UAV video diagnosis took a long time to detect, making it unsuitable for practical use. For these problems, we will verify using the YOLO v3 model, which is resistant to false detection of the background and can perform detection at high speed.


Manuscript title

Multi-Type Bridge Damage Detection Method Based on YOLO

Article DOI


Corresponding author email address


Translated title


Translated description

本研究では, 人手不足やコストが懸念されている橋梁点検業務に, UAV画像から物体検出のための深層学習の手法の一つであるYOLOを用いて, 同一画像から複数の損傷を同時に検出方法を検討する.深層学習を用いる事で, 作業のプログラム化による作業時間の短縮と損傷の診断に客観的要素を加えることによる見落とし, ミスの抑制を行う事ができる.既往の研究として田畑らが行ったCNNを用いた検証では, UAVで撮影した画像の損傷認識では, 損傷部分を大まかに認識できていたものの, 学習させていなかった背景部分を損傷と誤認識してしまっていたことによるものであった.またUAV動画の診断では検出時間が大きくかかってしまい, 実用には向かないものとなってしまった.これらの問題に対し背景の誤検出に強く, 検出を高速で行う事ができるYOLOモデルを用いて検証を行う.

Translated manuscript title


Translated authors

党 紀, 水元 大雅,刘 佳明, 藤嶋 斗南