2022
DOI: 10.1007/s11760-021-02034-w
|View full text |Cite
|
Sign up to set email alerts
|

DcsNet: a real-time deep network for crack segmentation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
7
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 29 publications
(7 citation statements)
references
References 27 publications
0
7
0
Order By: Relevance
“…To prove the advancement of CCSNet, this section compares CCSNet with seven SOTA professional crack segmentation networks, including the tunnel crack segmentation network CrackSegNet (Ren et al., 2020), lightweight crack segmentation network CrackFormer (Miao et al., 2021), bridge crack segmentation network BC‐DUnet (Liu et al., 2022), building crack segmentation network DCSNet (Pang et al., 2022), concrete crack segmentation network CrackW‐Net (C. Han et al., 2022), road crack segmentation network HC‐UNet++ (Cao et al., 2023), and ARD‐Unet (Yu et al., 2023). As can be seen from the results in Table 7, to make each network achieve the best training parameters, the Adam optimizer and SGD optimizer are used to do two groups of training.…”
Section: Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…To prove the advancement of CCSNet, this section compares CCSNet with seven SOTA professional crack segmentation networks, including the tunnel crack segmentation network CrackSegNet (Ren et al., 2020), lightweight crack segmentation network CrackFormer (Miao et al., 2021), bridge crack segmentation network BC‐DUnet (Liu et al., 2022), building crack segmentation network DCSNet (Pang et al., 2022), concrete crack segmentation network CrackW‐Net (C. Han et al., 2022), road crack segmentation network HC‐UNet++ (Cao et al., 2023), and ARD‐Unet (Yu et al., 2023). As can be seen from the results in Table 7, to make each network achieve the best training parameters, the Adam optimizer and SGD optimizer are used to do two groups of training.…”
Section: Methodsmentioning
confidence: 99%
“…Liu et al (2022) proposed a bridge crack segmentation network named BC-DUnet, which effectively improves the feature saliency of tiny cracks by weakening background features. Pang et al (2022) proposed a deep crack segmentation network named DCSNet, which achieves a good balance between accuracy and segmentation speed. DCSNet utilized small steps and shallow detail branches to supplement the detailed information of the crack.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Tao et al [27] designed a Boundary Awareness Module in their proposed approach, but their label-based learning is prone to misjudge background noise. Pang et al [28] introduced a two-branch lightweight network into crack detection, but the lightweight design limited the network's ability to extract global information, so the network was easy to miss small cracks. Holistic nested edge detection (HED) [29] and side-output residual network (SRN) [30] are two edge detection networks that build on the idea of deep supervision.…”
Section: Introductionmentioning
confidence: 99%
“…A novel deep crack segmentation network was proposed [ 69 ] to succeed in two mutually exclusive tasks: increasing speed and accuracy. The feature extraction consists of two directions—morphological and shallow detail.…”
Section: Introductionmentioning
confidence: 99%