TriCrackNet: Trilateral Segmentation Network for Real-Time Crack Segmentation

Haixin Jia , Han Wang , Xiaoqiang Shi , Guoying Zhang , Hanqi Jiang , Jianbo Peng

CAAI Transactions on Intelligence Technology ›› 2026, Vol. 11 ›› Issue (4) : 1144 -1160.

PDF (3360KB)
CAAI Transactions on Intelligence Technology ›› 2026, Vol. 11 ›› Issue (4) :1144 -1160. DOI: 10.1049/cit2.70129
ORIGINAL RESEARCH
research-article
TriCrackNet: Trilateral Segmentation Network for Real-Time Crack Segmentation
Author information +
History +
PDF (3360KB)

Abstract

To achieve high-precision real-time crack segmentation, we propose TriCrackNet, an efficient network based on a tri-branch collaborative architecture incorporating boundary constraints, semantic parsing, and spatial refinement. In the semantic branch, efficient atrous spatial pyramid pooling (EASPP) is integrated. The EASPP performs feature grouping and efficiently utilises each group's features through hierarchical residual connections. Simultaneously, it employs progressive dilated convolutions with incrementally expanding receptive fields to comprehensively capture multi-scale crack features. Meanwhile, an efficient feature enhancement module (EFEM) was inserted between the semantic branch and the other two branches. This module selectively utilises global features from the semantic branch to provide semantic guidance for the other branches, while enabling self-adaptive enhancement of local features in the target branches based on their own feature characteristics. Finally, the features of the last three branches are efficiently fused through an efficient feature fusion module that performs adaptive spatial weight weighting. Compared with other state-of-the-art methods, TriCrackNet achieves the best trade-off between inference speed and accuracy on CrackForest, Crack500, and DeepCrack datasets.

Keywords

attention mechanism / feature fusion / multi-scale features / real-time segmentation

Cite this article

Download citation ▾
Haixin Jia, Han Wang, Xiaoqiang Shi, Guoying Zhang, Hanqi Jiang, Jianbo Peng. TriCrackNet: Trilateral Segmentation Network for Real-Time Crack Segmentation. CAAI Transactions on Intelligence Technology, 2026, 11 (4) : 1144-1160 DOI:10.1049/cit2.70129

登录浏览全文

4963

注册一个新账户 忘记密码

References

[1]

Z. Chen, Z. Lai, J. Chen, and J. Li, “ Mind Marginal Non-Crack Regions: Clustering-Inspired Representation Learning for Crack Segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2024), 12698-12708.

[2]

C. Han, H. Yang, and Y. Yang, “ Enhancing Pixel-Level Crack Segmentation With Visual Mamba and Convolutional Networks,” Automation in Construction 168 (2024): 105770, https://doi.org/10.1016/j.autcon.2024.105770.

[3]

C. Zhu, L. Li, Y. Wu, and Z. Sun, “ Saswot: Real-Time Semantic Segmentation Architecture Search Without Training,” Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 7 (2024): 7722-7730, https://doi.org/10.1609/aaai.v38i7.28606.

[4]

Y. Wu, S. Li, J. Zhang, Y. Li, Y. Li, and Y. Zhang, “ Dual Attention Transformer Network for Pixel-Level Concrete Crack Segmentation Considering Camera Placement,” Automation in Construction 157 (2024): 105166, https://doi.org/10.1016/j.autcon.2023.105166.

[5]

M. Ren, Y. Li, T. Hussain, Y. Wu, and J. Li, “ Pixel-Level Concrete Crack Quantification Through Super Resolution Reconstruction and Multi-Modality Fusion,” Advanced Engineering Informatics 69 (2026): 103807, https://doi.org/10.1016/j.aei.2025.103807.

[6]

Y. Wang, S. Li, Y. Zhang, and Y. Li, “ Lightweight Concrete Crack Segmentation Network for Drone Image With Complex Backgrounds Using Multi-Scale Feature Fusion and Optimized Architecture,” Construction and Building Materials 495 (2025): 143667, https://doi.org/10.1016/j.conbuildmat.2025.143667.

[7]

X. Ma, Y. Li, Z. Yang, S. Li, and Y. Li, “ Lightweight Network for Millimeter-Level Concrete Crack Detection With Dense Feature Connection and Dual Attention,” Journal of Building Engineering 94 (2024): 109821, https://doi.org/10.1016/j.jobe.2024.109821.

[8]

G. Su, Y. Qin, H. Xu, and J. Liang, “ Automatic Real-Time Crack Detection Using Lightweight Deep Learning Models,” Engineering Applications of Artificial Intelligence 138 (2024): 109340, https://doi.org/10.1016/j.engappai.2024.109340.

[9]

H. Zhao, X. Qi, X. Shen, J. Shi, and J. Jia, “ Icnet for Real-Time Semantic Segmentation on High-Resolution Images,” in Proceedings of the European Conference on Computer Vision (ECCV), (2018), 405-420.

[10]

Y. Li, R. Ma, H. Liu, and G. Cheng, “ Real-Time High-Resolution Neural Network With Semantic Guidance for Crack Segmentation,” Automation in Construction 156 (2023): 105112, https://doi.org/10.1016/j.autcon.2023.105112.

[11]

A. G. Howard, M. Zhu, B. Chen, et al., “ Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” arXiv preprint arXiv:1704.04861 (2017).

[12]

T. H. Tsai and Y. W. Tseng, “ BiSeNet V3: Bilateral Segmentation Network With Coordinate Attention for Real-Time Semantic Segmentation,” Neurocomputing 532 (2023): 33-42, https://doi.org/10.1016/j.neucom.2023.02.025.

[13]

C. Yu, J. Wang, C. Peng, C. Gao, G. Yu, and N. Sang, “ Bisenet: Bilateral Segmentation Network for Real-Time Semantic Segmentation,” in Proceedings of the European Conference on Computer Vision (ECCV), (2018), 325-341.

[14]

C. Yu, C. Gao, J. Wang, G. Yu, C. Shen, and N. Sang, “ Bisenet v2: Bilateral Network With Guided Aggregation for Real-Time Semantic Segmentation,” International Journal of Computer Vision 129, no. 11 (2021): 3051-3068, https://doi.org/10.1007/s11263-021-01515-2.

[15]

Q. Zou, Z. Zhang, Q. Li, X. Qi, Q. Wang, and S. Wang, “ Deepcrack: Learning Hierarchical Convolutional Features for Crack Detection,” IEEE Transactions on Image Processing 28, no. 3 (2018): 1498-1512, https://doi.org/10.1109/tip.2018.2878966.

[16]

J. Xu, Z. Xiong, and S. P. Bhattacharyya, “ PIDNet: A Real-Time Semantic Segmentation Network Inspired by PID Controllers,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2023), 19529-19539.

[17]

X. Shi, Z. Yin, G. Han, et al., “ BSSNet: A Real-Time Semantic Segmentation Network for Road Scenes Inspired From AutoEncoder,” IEEE Transactions on Circuits and Systems for Video Technology (2023), https://doi.org/10.1109/TCSVT.2023.3325360.

[18]

R. Xian, X. Xiong, H. Peng, J. Wang, A. R. de Arellano Marrero, and Q. Yang, “ Feature Fusion Method Based on Spiking Neural Convolutional Network for Edge Detection,” Pattern Recognition 147 (2024): 110112, https://doi.org/10.1016/j.patcog.2023.110112.

[19]

J. Shen, Y. Chen, Y. Liu, X. Zuo, H. Fan, and W. Yang, “ ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection,” Pattern Recognition 145 (2024): 109913, https://doi.org/10.1016/j.patcog.2023.109913.

[20]

W. Liu, Y. Gong, G. Zhang, J. Lu, Y. Zhou, and J. Liao, “ GLMDriveNet: Global-Local Multimodal Fusion Driving Behavior Classification Network,” Engineering Applications of Artificial Intelligence 129, no. 107575 (2024): 20232024, https://doi.org/10.1016/j.engappai.2023.107575.

[21]

X. Liu, Z. Wu, A. Li, et al., “ NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2024), 6571-6594.

[22]

Z. Chen, Z. He, and Z. M. Lu, “ DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention,” IEEE Transactions on Image Processing 33 (2024): 1002-1015, https://doi.org/10.1109/tip.2024.3354108.

[23]

Y. Dai, F. Gieseke, S. Oehmcke, Y. Wu, and K. Barnard, “ Attentional Feature Fusion,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, (2021), 3560-3569.

[24]

W. Liu, J. Lu, J. Liao, et al., “ Feature-Attention-Embedding-Based Multimodal-Fusion Driving-Behavior-Classification Network,” IEEE Transactions on Computational Social Systems (2024), https://doi.org/10.1109/TCSS.2024.3411486.

[25]

J. Chen, S. H. Kao, H. He, et al., “ Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2023), 12021-12031.

[26]

H. Pan, Y. Hong, W. Sun, and Y. Jia, “ Deep Dual-Resolution Networks for Real-Time and Accurate Semantic Segmentation of Traffic Scenes,” IEEE Transactions on Intelligent Transportation Systems 24, no. 3 (2022): 3448-3460, https://doi.org/10.1109/tits.2022.3228042.

[27]

Y. Zhang, T. Yao, Z. Qiu, and T. Mei, “ Lightweight and Progressively-Scalable Networks for Semantic Segmentation,” International Journal of Computer Vision 131, no. 8 (2023): 2153-2171, https://doi.org/10.1007/s11263-023-01801-1.

[28]

T. Zhang, D. Wang, and Y. Lu, “ ECSNet: An Accelerated Real-Time Image Segmentation CNN Architecture for Pavement Crack Detection,” IEEE Transactions on Intelligent Transportation Systems 24, no. 12 (2023): 15105-15112, https://doi.org/10.1109/tits.2023.3300312.

[29]

Z. Guo, L. Bian, H. Wei, J. Li, H. Ni, and X. Huang, “ Dsnet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation,” IEEE Transactions on Circuits and Systems for Video Technology (2024), https://doi.org/10.1109/TCSVT.2024.3509504.

[30]

G. Li, I. Yun, J. Kim, and J. Kim, “ Dabnet: Depth-Wise Asymmetric Bottleneck for Real-Time Semantic Segmentation,” arXiv preprint arXiv:1907.11357 (2019).

[31]

K. Li, J. Yang, S. Ma, et al., “ Rethinking Lightweight Convolutional Neural Networks for Efficient and High-Quality Pavement Crack Detection,” IEEE Transactions on Intelligent Transportation Systems 25, no. 1 (2024): 237-250, https://doi.org/10.1109/tits.2023.3307286.

[32]

Y. Shi, L. Cui, Z. Qi, F. Meng, and Z. Chen, “ Automatic Road Crack Detection Using Random Structured Forests,” IEEE Transactions on Intelligent Transportation Systems 17, no. 12 (2016): 3434-3445, https://doi.org/10.1109/tits.2016.2552248.

[33]

F. Yang, L. Zhang, S. Yu, D. Prokhorov, X. Mei, and H. Ling, “ Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection,” IEEE Transactions on Intelligent Transportation Systems 21, no. 4 (2019): 1525-1535, https://doi.org/10.1109/tits.2019.2910595.

[34]

Y. Liu, J. Yao, X. Lu, R. Xie, and L. Li, “ DeepCrack: A Deep Hierarchical Feature Learning Architecture for Crack Segmentation,” Neurocomputing 338 (2019): 139-153, https://doi.org/10.1016/j.neucom.2019.01.036.

[35]

H. Wang, X. Jiang, H. Ren, Y. Hu, and S. Bai, “ Swiftnet: Real-Time Video Object Segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2021), 1296-1305.

[36]

K. He, X. Zhang, S. Ren, and J. Sun, “ Deep Residual Learning for Image Recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2016), 770-778.

[37]

H. Li, P. Xiong, H. Fan, and J. Sun, “ Dfanet: Deep Feature Aggregation for Real-Time Semantic Segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2019), 9522-9531.

[38]

F. Chollet, “ Xception: Deep Learning With Depthwise Separable Convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2017), 1251-1258.

[39]

M. Gamal, M. Siam, and M. Abdel-Razek, “ Shuffleseg: Real-Time Semantic Segmentation Network,” arXiv preprint arXiv:1803.03816 (2018).

[40]

X. Zhang, X. Zhou, M. Lin, and J. Sun, “ Shufflenet: An Extremely Efficient Convolutional Neural Network for Mobile Devices,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2018), 6848-6856.

[41]

G. Zhu, J. Liu, Z. Fan, et al., “ A Lightweight Encoder-Decoder Network for Automatic Pavement Crack Detection,” Computer-Aided Civil and Infrastructure Engineering 39, no. 12 (2024): 1743-1765, https://doi.org/10.1111/mice.13103.

[42]

Z. Xu, D. Wu, C. Yu, X. Chu, N. Sang, and C. Gao, “ Sctnet: Single-Branch Cnn With Transformer Semantic Information for Real-Time Segmentation,” Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 6 (2024): 6378-6386, https://doi.org/10.1609/aaai.v38i6.28457.

[43]

L. Chen, H. Dai, and Y. Zheng, “ RAFNet: Reparameterizable Across-Resolution Fusion Network for Real-Time Image Semantic Segmentation,” IEEE Transactions on Circuits and Systems for Video Technology 34, no. 2 (2023): 1212-1227, https://doi.org/10.1109/tcsvt.2023.3293166.

[44]

J. Wang, C. Gou, Q. Wu, et al., “ Rtformer: Efficient Design for Real-Time Semantic Segmentation With Transformer,” Advances in Neural Information Processing Systems 35 (2022): 7423-7436.

[45]

M. H. Guo, Z. N. Liu, T. J. Mu, and S. M. Hu, “ Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks,” IEEE Transactions on Pattern Analysis and Machine Intelligence 45, no. 5 (2022): 5436-5447, https://doi.org/10.1109/TPAMI.2022.3211006.

[46]

B. Liu, J. Kang, H. Guan, et al., “ Boundary-Guided Real-Time Semantic Segmentation and Pixel-Level Quantification of Pavement Cracks,” IEEE Transactions on Intelligent Transportation Systems (2025), https://doi.org/10.1109/TITS.2025.3642011.

[47]

Z. Yin, L. Qin, G. Han, et al., “ DDSNet: Deep Dual-Branch Networks for Surface Defect Segmentation,” IEEE Transactions on Instrumentation and Measurement (2024), https://doi.org/10.1109/TIM.2024.3427806.

[48]

L. C. Chen, G. Papandreou, F. Schroff, and H. Adam, “ Rethinking Atrous Convolution for Semantic Image Segmentation,” arXiv preprint arXiv:1706.05587 (2017).

[49]

F. Wang, J. Mei, and A. Yuille, “ Sclip: Rethinking Self-Attention for Dense Vision-Language Inference,” in European Conference on Computer Vision, (2024), 315-332.

[50]

L. Cui, X. Tian, Q. Wei, and Y. Liu, “ A Self-Attention Based Contrastive Learning Method for Bearing Fault Diagnosis,” Expert Systems With Applications 238 (2024): 121645, https://doi.org/10.1016/j.eswa.2023.121645.

[51]

O. Oktay, J. Schlemper, L. L. Folgoc, et al., “ Attention U-Net: Learning Where to Look for the Pancreas,” arXiv preprint arXiv:1804.03999 (2018).

[52]

B. Liu, C. Wang, T. Cao, K. Jia, and J. Huang, “ Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2024), 7817-7826.

[53]

X. Li, A. You, Z. Zhu, et al., “ Semantic Flow for Fast and Accurate Scene Parsing,” in Computer Vision-ECCV 2020: 16Th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part I 16 (Springer International Publishing, 2020), 775-793.

[54]

Z. Huang, Y. Wei, X. Wang, W. Liu, T. S. Huang, and H. Shi, “ Alignseg: Feature-Aligned Segmentation Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence 44, no. 1 (2021): 550-557, https://doi.org/10.1109/TPAMI.2021.3062772.

[55]

S. Zhou, D. Chen, J. Pan, J. Shi, and J. Yang, “ Adapt or Perish: Adaptive Sparse Transformer With Attentive Feature Refinement for Image Restoration,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2024), 2952-2963.

[56]

J. Fan, F. Wang, H. Chu, X. Hu, Y. Cheng, and B. Gao, “ Mlfnet: Multi-Level Fusion Network for Real-Time Semantic Segmentation of Autonomous Driving,” IEEE Transactions on Intelligent Vehicles 8, no. 1 (2022): 756-767, https://doi.org/10.1109/tiv.2022.3176860.

[57]

J. Hu, L. Shen, and G. Sun, “ Squeeze-and-Excitation Networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (2018), 7132-7141.

[58]

M. Noman, M. Fiaz, H. Cholakkal, S. Khan, and F. S. Khan, “ ELGC-Net: Efficient Local-Global Context Aggregation for Remote Sensing Change Detection,” IEEE Transactions on Geoscience and Remote Sensing 62 (2024): 1-11, https://doi.org/10.1109/tgrs.2024.3362914.

[59]

S. W. Zamir, A. Arora, S. Khan, et al., “ Learning Enriched Features for Real Image Restoration and Enhancement,” in Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXV, Vol. 16, (2020), 492-511.

[60]

Y. Xu, D. Wang, L. Zhang, and L. Zhang, “ Dual Selective Fusion Transformer Network for Hyperspectral Image Classification,” Neural Networks 187 (2025): 107311, https://doi.org/10.1016/j.neunet.2025.107311.

PDF (3360KB)

0

Accesses

0

Citation

Detail

Sections
Recommended

/

〈 〉