差分画像とGrad-CAMを利用した大規模天井の損傷領域の特定方法に関する研究

幸田雄太, 川口健一, 水本旭洋, 松田裕貴: “差分画像とGrad-CAMを利用した大規模天井の損傷領域の特定方法に関する研究,” 日本建築学会技術報告集, Vol.29, No.71, pp.132-137, 2023.

Abstract

The authors suggest a novel detection method for ceiling damage using image differencing and Grad-CAM. The proposed method requires the latest image and the past image of the facility to compare. It adjusts the difference due to camera position, sunlight condition, etc. The authors show validity of this method showing four pairs of input images. The proposed method can appropriately detect damaged areas with better accuracy for facility inspection by narrowing the areas of inspection using image differencing and Grad-CAM procedures.

Links

DOI: https://doi.org/10.3130/aijt.29.132

PDF: https://yukimat.jp/data/pdf/paper/tenjo-check_j_202302_koda_AIJT.pdf

BibTeX

code:references.bib

@article{bib:koda_tenjocheck_aijt2023,

author={幸田雄太 and 川口健一 and 水本旭洋 and 松田裕貴},

title={差分画像とGrad-CAMを利用した大規模天井の損傷領域の特定方法に関する研究},

journal={日本建築学会技術報告集},

volume={29},

number={71},

pages={132--137},

year={2023},

url={https://doi.org/10.3130/aijt.29.132},

doi={10.3130/aijt.29.132}

}

https://scrapbox.io/files/688184c920655976b2430617.png