In response to the diverse and complex nature of cracks in ballastless track slabs, the existing crack detection methods suffer from insufficient extraction of crack target features, discontinuity detection and low accuracy. A crack detection enhanced method is proposed based on dynamic snake convolution and deformable attention Transformer. Initially, the approach enhances the ResNet-50 feature extraction backbone by using a dynamic snake convolution on the basis of the Mask2Former segmentation model. The dynamic snake convolution, with its continuous prediction capability, improves the feature extraction network’s ability to fit the geometric features of diverse ballastless track cracks, enhancing the extraction of crack features and overcoming discontinuity detection issues. Subsequently, a deformable attention Transformer decoder module is designed to enable the model to dynamically adapt to changes in local features of ballastless track cracks, in order to enhance the ability to capture global contextual information and improve the accuracy of crack recognition. Furthermore, an improved feedforward network (FFN) is incorporated into the Transformer decoder to learn local information around the cracks, facilitating more accurate capture of local details and improving detection accuracy. Finally, the output of the Transformer decoder is fused with the pixel decoder output to obtain the crack detection results. Experimental results demonstrate that the proposed method accurately detects cracks of various shapes. It achieves a 6.34 percentage points increase in average accuracy, a 4.70 percentage points increase in average recall, and an F1-score of 94.30% compared with the original Mask2Former model. The proposed method exhibits superior performance in the detection of surface cracks on ballastless track slabs, enhancing detection accuracy and outperforming comparative methods in both subjective and objective evaluations.
SONGH L, ZHAOY X, LIUY, et al .Deformation transmission law of tunnel bottom heave of ballasted and ballastless track system[J]. China Railway Science, 2024, 45(2):123-133.(in Chinese)
[3]
YEM X, ZENGZ P, LIP C, et al .Research and prediction of early-age loads in double-block ballastless track structure[J].Transportation Geotechnics, 2024, 49:101426.
[4]
CHENW, LIS Q, WANGW D, et al .Analysis on crack propagation of CRTS Ⅲ slab ballastless track under temperature loads and freeze-thaw deterioration[J]. Theoretical and Applied Fracture Mechanics, 2024, 129:104206.
[5]
RENY P, HUANGJ S, HONGZ Y, et al .Image-based concrete crack detection in tunnels using deep fully convolutional networks[J].Construction and Building Materials, 2020, 234:117367.
[6]
LAUS L H, CHONGE K P, YANGX, et al .Automated pavement crack segmentation using U-net-based convolutional neural network[J].IEEE Access, 2020, 8:114892-114899.
[7]
FUH X, MENGD, LIW H, et al .Bridge crack semantic segmentation based on improved Deeplabv3+[J]. Journal of Marine Science and Engineering, 2021, 9(6): 671-671.
[8]
TANGY Z, ZHANGA A, LUOL, et al .Pixel-level pavement crack segmentation with encoder-decoder network[J]. Measurement, 2021, 184:109914.
[9]
YUANJ W, SONGX L, PUH J, et al .Bridge crack segmentation method based on parallel attention mechanism and multi-scale features fusion[J]. Computers, Materials & Continua, 2023, 74(3): 6485-6503.
[10]
LIH T, YUEZ, LIUJ Y, et al .SCCDNet:a pixel-level crack segmentation network[J]. Applied Sciences, 2021, 11(11):5074.
[11]
SHIP F, SHAOS, FANX N, et al .MCL-CrackNet:a concrete crack segmentation network using multilevel contrastive learning[J].IEEE Transactions on Instrumentation and Measurement, 2023, 72:5030415.
[12]
BEYENED A, HUANGRUI, TOLAK D, et al .DCNAM:automatic detection of pixel level fine crack using a densely connected network with attention mechanism[J]. Structures, 2024, 68:107073.
[13]
XIONGB, HONGR, LIUR, et al .FCT-Net:a dual-encoding-path network fusing atrous spatial pyramid pooling and transformer for pavement crack detection[J].Engineering Applications of Artificial Intelligence, 2024, 137:109190.
[14]
CHENGB W, MISRAI, SCHWINGA G, et al .Masked-attention mask transformer for universal image segmentation[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 18-24, 2022, New Orleans, LA, USA. IEEE, 2022:1280-1289.
[15]
HEK M, ZHANGX Y, RENS Q, et al .Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016:770-778.
TANZ, WANGB X, QINS P, et al .Crack damage detection method based on edge feature reinforcement learning[J]. Journal of Railway Science and Engineering, 2023, 20(8): 3172-3180.(in Chinese)
[18]
QIY L, HEY T, QIX M, et al .Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation[C]//2023 IEEE/CVF International Conference on Computer Vision (ICCV), October 1-6, 2023, Paris, France. IEEE, 2024:6047-6056.
[19]
VASWANIA, SHAZEERN, PARMARN, et al. Attention is all you need[EB/OL]. (2017-06-12)[2024-04-15].
[20]
DOSOVITSKIYA, BEYERL, KIMA, et al. An image is worth 16×16 words: transformers for image recognition at scale[EB/OL]. (2020-10-22)[2024-04-15].
[21]
XIAZ F, PANX R, SONGS J, et al. Vision transformer with deformable attention[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 18-24, 2022, New Orleans, LA, USA. IEEE, 2022:4784-4793.
[22]
LIUQ Y, KAULC, WANGJ, et al .Optimizing vision transformers for medical image segmentation[C]//ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), June 4-10, 2023, Rhodes Island, Greece. IEEE, 2023:1-5.
[23]
FUL H, TIANH Y, ZHAIX P, et al. IncepFormer: efficient inception transformer with pyramid pooling for semantic segmentation[EB/OL]. (2022-12-06)[2024-04-15].
[24]
HEK M, GKIOXARIG, DOLLARP, et al. Mask R-CNN[EB/OL]. (2017-03-20)[2024-04-15].
[25]
LIUZ, LINY T, CAOY, et al. Swin transformer:hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV), October 10-17, 2021, Montreal, QC, Canada. IEEE, 2022: 9992-10002.
[26]
YUZ W, CHENQ Y, SHENY G, et al .Robust pavement crack segmentation network based on transformer and dual-branch decoder[J]. Construction and Building Materials, 2024, 453:139026.