セグメンテーションに画像処理を併用したひび割れ検出サポートシステムの基礎研究

橋本 岳; 橋本 智洋; 武井 祐馬; 山本 耀平; 山本 茂広; 中嶋 規人; 井澤 大介; 高野 隼行; 阿部 雅人; 杉崎 光一; 全 邦釘

doi:10.11532/jsceiii.2.J2_589

BASIC RESEARCH ON CRACK DETECTION SUPPORT SYSTEM BY COMBINING IMAGE PROCESSING TO SEGMENTATION

Takeshi HASHIMOTO, Tomohiro HASHMOTO, Yuma TAKEI, Yohei YAMAMOTO, Shigehiro YAMAMOTO, Norito NAKAJIMA, Daisuke IZAWA, Yoshiyuki TAKANO, Masato ABE, Koichi SUGISAKI, Pang-jo CHUN

Author information

Takeshi HASHIMOTO
[in Japanese]
Tomohiro HASHMOTO
[in Japanese]
Yuma TAKEI
[in Japanese]
Yohei YAMAMOTO
[in Japanese]
Shigehiro YAMAMOTO
[in Japanese]
Norito NAKAJIMA
[in Japanese]
Daisuke IZAWA
[in Japanese]
Yoshiyuki TAKANO
[in Japanese]
Masato ABE
[in Japanese]
Koichi SUGISAKI
[in Japanese]
Pang-jo CHUN
[in Japanese]

JOURNAL OPEN ACCESS

2021 Volume 2 Issue J2 Pages 589-597

DOI https://doi.org/10.11532/jsceiii.2.J2_589

Details

Abstract

We have been studying a support system for human extraction of cracks in concrete structures from the viewpoint of image processing. The purpose of this support system is to prevent cracks from being overlooked. Therefore, we attempted to improve the detection rate of cracks by combining image processing with DeepLab v3+, a powerful method of semantic segmentation. Concretely, we examined the image of a box culvert slab taken by a UAV-mounted camera. As a result, we showed that annotation expansion and bright-ness adjustment were effective in the image processing.

Corresponding author

Register with J-STAGE for free!