Beyond Crack: Fine-Grained Pavement Defect Segmentation Using Three-Stream Neural Networks | |
Zhang, Yujia1; Wu, Junxian1,2; Li, Qianzhong1,2; Zhao, Xiaoguang1; Tan, Min1 | |
刊名 | IEEE Transactions on Intelligent Transportation Systems |
2021-12-22 | |
卷号 | /期号:/页码:/ |
关键词 | Fine-grained defect segmentation Crack detection Semantic segmentation Pavement inspection |
英文摘要 | Pavement defect segmentation is a fundamental task in the field of transport infrastructure inspection. Existing methods mainly focus on detection/segmentation for long and thin cracks. However, there are many other types of defects with various sizes and shapes that are also essential to segment, which brings more challenges toward detailed road inspection. To address the above problems and provide a more comprehensive understanding of the overall road conditions, we propose a three-stream neural network that combines spatial, contextual and boundary information for fine-grained defect segmentation. Specifically, the spatial stream captures rich low-level spatial features. The contextual stream utilizes an attention mechanism and models high-level contextual relationships over local features. To further refine the segmentation results, the boundary stream encodes detailed boundaries using a global gated convolution and generates additional boundary maps. By combining the above different information, our model can effectively produce pixel-wise predictions for fine-grained road inspection. The network is trained using a dual-task loss in an end-to-end manner, and experiments were performed on three newly collected datasets, i.e., a fine-grained defect dataset and two crack datasets, which shows that the proposed method achieves favorable segmentation results on complex multi-class defects, and is also able to segment single-class cracks. Specifically, on the fine-grained dataset, it achieved state-of-the-art performance over other competing baselines (mPA of 0.54, mIoU of 0.38, Mic$\_$F of 0.78 and Mac$\_$F of 0.65), where each image is resized to 512 $\times$ 512 and the processing speed is 21 FPS on average. |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/47421] |
专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队 |
通讯作者 | Zhang, Yujia |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Zhang, Yujia,Wu, Junxian,Li, Qianzhong,et al. Beyond Crack: Fine-Grained Pavement Defect Segmentation Using Three-Stream Neural Networks[J]. IEEE Transactions on Intelligent Transportation Systems,2021,/(/):/. |
APA | Zhang, Yujia,Wu, Junxian,Li, Qianzhong,Zhao, Xiaoguang,&Tan, Min.(2021).Beyond Crack: Fine-Grained Pavement Defect Segmentation Using Three-Stream Neural Networks.IEEE Transactions on Intelligent Transportation Systems,/(/),/. |
MLA | Zhang, Yujia,et al."Beyond Crack: Fine-Grained Pavement Defect Segmentation Using Three-Stream Neural Networks".IEEE Transactions on Intelligent Transportation Systems /./(2021):/. |
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