期刊
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
卷 21, 期 5, 页码 2190-2205出版社
SAGE PUBLICATIONS LTD
DOI: 10.1177/14759217211053776
关键词
Image segmentation; image analysis; concrete crack segmentation; image synthesis; pixel-level classification; real-time processing; computer vision; damage detection; deep learning; semantic segmentation
资金
- NSERC [RGPIN-2016-05923]
- CFI JELF grant [3739,4]
In this paper, a novel semantic transformer representation network (STRNet) is developed for crack segmentation with fast processing speed and high performance. The network is trained and tested in complex scenes, achieving high precision, recall, F1 score, and mIoU. Comparing with other advanced networks, STRNet shows the best performance in evaluation metrics with the fastest processing speed.
Recently, crack segmentation studies have been investigated using deep convolutional neural networks. However, significant deficiencies remain in the preparation of ground truth data, consideration of complex scenes, development of an object-specific network for crack segmentation, and use of an evaluation method, among other issues. In this paper, a novel semantic transformer representation network (STRNet) is developed for crack segmentation at the pixel level in complex scenes in a real-time manner. STRNet is composed of a squeeze and excitation attention-based encoder, a multi head attention-based decoder, coarse upsampling, a focal-Tversky loss function, and a learnable swish activation function to design the network concisely by keeping its fast-processing speed. A method for evaluating the level of complexity of image scenes was also proposed. The proposed network is trained with 1203 images with further extensive synthesis-based augmentation, and it is investigated with 545 testing images (1280 x 720, 1024 x 512); it achieves 91.7%, 92.7%, 92.2%, and 92.6% in terms of precision, recall, F1 score, and mIoU (mean intersection over union), respectively. Its performance is compared with those of recently developed advanced networks (Attention U-net, CrackSegNet, Deeplab V3+, FPHBN, and Unet++), with STRNet showing the best performance in the evaluation metrics-it achieves the fastest processing at 49.2 frames per second.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据