Automatic surface defect segmentation for hot-rolled steel strip using depth-wise separable U-shape network | |
Huang Z(黄钲)1,2,3; Wu JJ(吴嘉俊)1,2,3; Xie, Feng2,3 | |
刊名 | Materials Letters |
2021 | |
卷号 | 301页码:1-4 |
关键词 | Surface defect segmentation Depth-wise separable U-shape network Hot-rolled steel strip |
ISSN号 | 0167-577X |
产权排序 | 1 |
英文摘要 | Accurate and efficient image segmentation can contribute to improving the recognition rate of surface defects for hot-rolled steel strips. However, due to its variances in shape, position, defect type and fuzzy boundary, surface defect segmentation is a challenging task. To address this issue, a depth-wise separable U-shape network (DSUNet) is proposed. In order to reduce the computation complexity and accelerate the segmentation performance, depth-wise separable convolution is employed to replace the traditional convolutional layer. In addition, a multi-scale module is proposed to extract multi-scale context and improve the segmentation accuracy. The experimental results indicate that the accuracy and dice of DSUNet reach 95.42% and 80.8%, respectively, and the DSUNet can segment 38.5 images per second, which suggests that the DSUNet can precisely segment surface defects for hot-rolled steel strip with high efficiency. |
资助项目 | National Key R&D Program of China[2017YFB1302802] ; National Natural Science Foundation of China[61703394] |
WOS研究方向 | Materials Science ; Physics |
语种 | 英语 |
WOS记录号 | WOS:000675889300013 |
资助机构 | National Key R&D Program of China [grant number 2017YFB1302802] ; National Natural Science Foundation of China [grant number 61703394] |
内容类型 | 期刊论文 |
源URL | [http://ir.sia.cn/handle/173321/29317] |
专题 | 沈阳自动化研究所_机器人学研究室 |
通讯作者 | Wu JJ(吴嘉俊) |
作者单位 | 1.University of Chinese Academy of Sciences, Beijing 100049, China 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China |
推荐引用方式 GB/T 7714 | Huang Z,Wu JJ,Xie, Feng. Automatic surface defect segmentation for hot-rolled steel strip using depth-wise separable U-shape network[J]. Materials Letters,2021,301:1-4. |
APA | Huang Z,Wu JJ,&Xie, Feng.(2021).Automatic surface defect segmentation for hot-rolled steel strip using depth-wise separable U-shape network.Materials Letters,301,1-4. |
MLA | Huang Z,et al."Automatic surface defect segmentation for hot-rolled steel strip using depth-wise separable U-shape network".Materials Letters 301(2021):1-4. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论