|
Title |
Semantic Segmentation for Multiple Concrete Damage Based on Hierarchical Learning
|
|
Authors |
심승보(Seungbo Shim) ; 민지영(Jiyoung Min) |
|
DOI |
https://doi.org/10.11112/jksmi.2022.26.6.175 |
|
Keywords |
딥러닝; 계층적 학습; 의미론적 분할; 다중 분류; 콘크리트 손상 Deep learning; Hierarchical learning; Semantic segmentation; Multi classification; Concrete damage |
|
Abstract |
The condition of infrastructure deteriorates as the service life increases. Since most infrastructure in South Korea were intensively built duringthe period of economic growth, the proportion of outdated infrastructure is rapidly increasing now. Aging of such infrastructure can lead to safetyaccidents and even human casualties. To prevent these issues in advance, periodic and accurate inspection is essential. For this reason, the need for researchto detect various types of damage using computer vision and deep learning is increasingly required in the field of remotely controlled or autonomousinspection. To this end, this study proposed a neural network structure that can detect concrete damage by classifying it into three types. In particular,the proposed neural network can detect them more accurately through a hierarchical learning technique. This neural network was trained with 2,026damage images and tested with 508 damage images. As a result, we completed an algorithm with average mean intersection over union of 67.04%and F1 score of 52.65%. It is expected that the proposed damage detection algorithm could apply to accurate facility condition diagnosis in the nearfuture
|