分割
计算机科学
人工智能
模棱两可
交叉口(航空)
选择(遗传算法)
领域(数学)
计算机视觉
模式识别(心理学)
块(置换群论)
感受野
集合(抽象数据类型)
工程类
数学
航空航天工程
程序设计语言
纯数学
几何学
作者
Yonghao Han,Xingjie Li,Kun Song,Erfeng Shang,Huiyu Liu,Yunhui Yan
标识
DOI:10.1016/j.ndteint.2020.102345
摘要
In order to ensure the safety of important castings, the ADR (Automatic-Defect-Recognition) system should recognize, locate, and count the area of internal defects that are undetectable to the naked eye. However, small differences between inter-classes, large defect scale change, and uncertainly annotation limit the achievement for ADR system. To solve these challenges, this paper presents an adaptive depth and receptive field selection network for defect semantic segmentation on castings X-rays. Firstly, the Resnet18 with ADSM (adaptive depth selection mechanism) is elaborately designed to extract and adaptively aggregate the different depth features, which is beneficial to distinguish the similar defect. Then the ARFB (adaptive receptive field block) is proposed to select the optimum receptive field in a data-driven manner to adapt to the scale change of defects. To overcome the problem of inaccurate labeling caused by the ambiguity of defect edges and the subjectivity of manual annotation, we propose a data augmentation method called “lazy-label”. Finally, we set up a castings defect segmentation dataset, called SRIF-CDS, to train and evaluate our method. Experiments on this dataset indicate that our method achieves 0.86 mIoU (mean intersection-over-union) and 0.92 mAcc (mean accuracy), which has better performance than the state-of-the-art semantic segmentation baseline.
科研通智能强力驱动
Strongly Powered by AbleSci AI