融合频域增强与线性注意力机制的疲劳裂纹分割与量化网络
收稿日期: 2025-06-03
修回日期: 2025-06-17
录用日期: 2025-07-17
网络出版日期: 2025-07-25
基金资助
国家重点研发计划(2023YFF0720400);强度与结构完整性全国重点实验室开放基金(LSSIKFJJ202402005);陕西省技术创新引导专项(2024ZC-YYDP-28)
A network for fatigue crack segmentation and quantification using frequency-domain enhancement and linear attention mechanism
Received date: 2025-06-03
Revised date: 2025-06-17
Accepted date: 2025-07-17
Online published: 2025-07-25
Supported by
National Key R&D Program of China （MOST）(2023YFF0720400);The Open Fund of National Key Laboratory of Strength and Structural Integrity(LSSIKFJJ202402005);Shaanxi Province Technology Innovation Guidance Program(2024ZC-YYDP-28)
疲劳裂纹是导致工程结构失效的主要诱因之一。针对结构强度试验中疲劳裂纹精准检测的实际需求，提出一种融合频域增强与Mamba线性注意力机制的疲劳裂纹分割与量化网络——CrackDAM-Net。该网络采用局部特征编码器和全局信息编码器双分支并行结构，同时兼顾了疲劳裂纹图像的局部细节特征与全局上下文信息。首先，设计了一种融合频域增强与Mamba线性注意力的全局信息编码器：前2层为混合频域-注意力层，后2层为纯注意力层。该编码器不仅能够有效提取裂纹图像的全局特征，还能显著降低计算复杂度。其次，提出了一种混合空间注意力、通道注意力以及像素注意力机制的多尺度特征融合模块，能够从多个维度充分挖掘和整合局部特征编码器与全局信息编码器之间的互补信息，提升特征表达能力。最后，建立了一种结合正交投影与离散骨架演化的裂纹长度量化方法，以实现结构强度试验中疲劳裂纹长度的精准测量。实验结果表明：CrackDAM-Net在精度与速度间取得良好平衡，其分割精确度、召回率和F1分数分别达到83.11%、77.56%和80.24%，分割速度达到37帧/s，疲劳裂纹长度量化误差在±4%以内，展现出较强的工程应用潜力。
史宝全 , 周嘉明 , 张文东 , 陈先民 , 贺谦 . 融合频域增强与线性注意力机制的疲劳裂纹分割与量化网络[J]. 航空学报, 2025 , 46(21) : 532356 -532356 . DOI: 10.7527/S1000-6893.2025.32356
Fatigue cracks are one of the primary causes of structural failure in engineering structures. To meet the practical need for precise detection of fatigue cracks in structural strength testing， we propose a fatigue crack segmentation and quantification network-CrackDAM-Net-based on frequency domain enhancement and the Mamba linear attention mechanism. This network adopts a dual-branch parallel structure comprising a local feature encoder and a global information encoder， effectively balancing the local detailed features and global contextual information of fatigue crack images. A global information encoder combining frequency domain enhancement and Mamba linear attention is designed： the first two layers are hybrid frequency domain-attention layers， and the last two layers are pure attention layers. This encoder not only effectively extracts global features from crack images but also significantly reduces computational complexity. A multi-scale feature fusion module combining spatial attention， channel attention， and pixel attention mechanisms is proposed， which can fully mine and integrate complementary information between the local feature encoder and the global information encoder from multiple dimensions to enhance feature expression capabilities. A crack length automatic quantification method combining orthogonal projection and discrete skeleton evolution is established to achieve precise measurement of fatigue crack length in structural strength tests. Experimental results demonstrate that CrackDAM-Net achieves a good balance between accuracy and speed， with segmentation accuracy， recall rate， and F1 score reaching 83.11%， 77.56%， and 80.24%， respectively， segmentation speed reaching 37 frame/s， and fatigue crack length quantification error within ±4%， showcasing strong potential for engineering applications.
| [1] | WANG F. Application of deep learning algorithm in crack detection of green building materials［C］∥2022 6th Asian Conference on Artificial Intelligence Technology （ACAIT）. Piscataway： IEEE Press， 2022： 1-6. |
| [2] | WANG Y T， SHEN W W. Mechanical parts detection algorithm based on enhanced faster R-CNN［C］∥2021 China Automation Congress （CAC）. Piscataway： IEEE Press， 2021： 4348-4353. |
| [3] | DING K Y， DING Z H， ZHANG Z B， et al. SCD-YOLO： A novel object detection method for efficient road crack detection［J］. Multimedia Systems， 2024， 30（6）： 351. |
| [4] | LIU Z， ZHOU B. Research and application on the improved SSD chip defect inspection algorithm［C］∥2021 IEEE International Conference on Consumer Electronics and Computer Engineering （ICCECE）. Piscataway： IEEE Press， 2021： 551-555. |
| [5] | TAO H Q， LIU B X， CUI J Q， et al. A convolutional-transformer network for crack segmentation with boundary awareness［C］∥2023 IEEE International Conference on Image Processing （ICIP）. Piscataway： IEEE Press， 2023： 86-90. |
| [6] | ZHENG W W， JIANG X Y， FANG Z J， et al. TV-Net： A structure-level feature fusion network based on tensor voting for road crack segmentation［J］. IEEE Transactions on Intelligent Transportation Systems， 2024， 25（6）： 5743-5754. |
| [7] | ZHANG Q， CHEN S S， WU Y， et al. Improved U-Net network asphalt pavement crack detection method［J］. PLoS One， 2024， 19（5）： e0300679. |
| [8] | ZHOU H P， DENG B， SUN K L， et al. UTE-CrackNet： Transformer-guided and edge feature extraction U-shaped road crack image segmentation［J］. The Visual Computer， 2025， 41（4）： 2271-2283. |
| [9] | LIU H J， YANG J， MIAO X Y， et al. CrackFormer network for pavement crack segmentation［J］. IEEE Transactions on Intelligent Transportation Systems， 2023， 24（9）： 9240-9252. |
| [10] | SHAN J H， HUANG Y， JIANG W. DCUFormer： Enhancing pavement crack segmentation in complex environments with dual-cross/upsampling attention［J］. Expert Systems with Applications， 2025， 264： 125891. |
| [11] | LIU Z， LIN Y T， CAO Y， et al. Swin Transformer： Hierarchical vision transformer using shifted windows［C］∥2021 IEEE/CVF International Conference on Computer Vision （ICCV）. Piscataway： IEEE Press， 2021： 9992-10002. |
| [12] | HE K M， ZHANG X Y， REN S Q， et al. Deep residual learning for image recognition［C］∥2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2016： 770-778. |
| [13] | PATRO B N， NAMBOODIRI V P， AGNEESWARAN V S. SpectFormer： Frequency and attention is what you need in a vision transformer［C］∥2025 IEEE/CVF Winter Conference on Applications of Computer Vision （WACV） . Piscataway： IEEE Press， 2017： 1800-1807. |
| [14] | SHI W Z， CABALLERO J， HUSZáR F， et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network［C］∥2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2016： 1874-1883. |
| [15] | CHOLLET F. Xception： Deep learning with depthwise separable convolutions［C］∥2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2017： 1800-1807. |
| [16] | GU A， DAO T. Mamba： Linear-time sequence modeling with selective state spaces［DB/OL］. arXiv preprint：2312. 00752， 2024. |
| [17] | HAN D C， WANG Z Y， XIA Z F， et al. Demystify Mamba in vision： A linear attention perspective［C］∥38th Conference on Neural Information Processing Systems （NeurIPS 2024）. Vancouver： OpenReview， 2024. |
| [18] | BLUM H. Biological shape and visual science （part I）［J］. Journal of Theoretical Biology， 1973， 38（2）： 205-287. |
| [19] | BAI X， LATECKI L J. Discrete skeleton evolution［M］∥Energy Minimization Methods in Computer Vision and Pattern Recognition. Berlin， Heidelberg： Springer， 2007： 362-374. |
| [20] | MONTANARI U. A method for obtaining skeletons using a Quasi-Euclidean distance［J］. Journal of the ACM， 1968， 15（4）： 600-624. |
| [21] | SHI Y， CUI L M， QI Z Q， et al. Automatic road crack detection using random structured forests［J］. IEEE Transactions on Intelligent Transportation Systems， 2016， 17（12）： 3434-3445. |
| [22] | YANG F， ZHANG L， YU S J， et al. Feature pyramid and hierarchical boosting network for pavement crack detection［J］. IEEE Transactions on Intelligent Transportation Systems， 2020， 21（4）： 1525-1535. |
| [23] | SHI Y， CUI L M， QI Z Q， et al. Automatic road crack detection using random structured forests［J］. IEEE Transactions on Intelligent Transportation Systems， 2016， 17（12）： 3434-3445. |
| [24] | ZOU Q， CAO Y， LI Q Q， et al. CrackTree： Automatic crack detection from pavement images［J］. Pattern Recognition Letters， 2012， 33（3）： 227-238. |
| [25] | ZOU Q， ZHANG Z， LI Q Q， et al. DeepCrack：Learning hierarchical convolutional features for crack detection［J］. IEEE Transactions on Image Processing， 2018， 28（3）： 1498-1512. |
| [26] | CHEN L C， ZHU Y K， PAPANDREOU G， et al. Encoder-decoder with atrous separable convolution for semantic image segmentation［C］∥Computer Vision-ECCV 2018. Cham： Springer， 2018： 833-851. |
| [27] | LIU Y H， YAO J， LU X H， et al. DeepCrack： A deep hierarchical feature learning architecture for crack segmentation［J］. Neurocomputing， 2019， 338： 139-153. |
| [28] | LAU S L H， CHONG E K P， YANG X， et al. Automated pavement crack segmentation using U-net-based convolutional neural network［J］. IEEE Access， 2020， 8： 114892-114899. |
| [29] | CHEN J， LU Y， YU Q， et al. TransUNet： Transformers make strong encoders for medical image segmentation［DB/OL］. arXiv preprint： 2102. 04306， 2021. |
| [30] | PANG J， ZHANG H， ZHAO H， et al. DcsNet： A real-time deep network for crack segmentation［J］. Signal， Image and Video Processing， 2022， 16（4）： 911-919. |
| [31] | WU H S， CHEN S H， CHEN G L， et al. FAT-Net： Feature adaptive transformers for automated skin lesion segmentation［J］. Medical Image Analysis， 2022， 76： 102327. |
| [32] | XIANG C， GUO J J， CAO R， et al. A crack-segmentation algorithm fusing transformers and convolutional neural networks for complex detection scenarios［J］. Automation in Construction， 2023， 152： 104894. |
| [33] | TAO H Q， LIU B X， CUI J Q， et al. A convolutional-transformer network for crack segmentation with boundary awareness［C］∥2023 IEEE International Conference on Image Processing （ICIP）. Piscataway： IEEE Press， 2023： 86-90. |
| [34] | ZHANG J M， ZENG Z G， SHARMA P K， et al. A dual encoder crack segmentation network with Haar wavelet-based high–low frequency attention［J］. Expert Systems with Applications， 2024， 256： 124950. |
/
| 〈 |
|
〉 |
CJA