文献类型： 外文期刊

作者： Xu, Jihe ¹ ; Zhang, Chengtao ¹ ; Zeng, Wei ¹ ;

作者机构： 1.Guangxi Univ Sci & Technol, Sch Mech & Automot Engn, Liuzhou 545006, Peoples R China

2.Minist Educ, Engn Res Ctr Adv Design & Mfg Heavy Vehicle Compon, Liuzhou 545006, Peoples R China

3.Beijing Acad Agr & Forestry Sci, Res Ctr Intelligent Equipment, Beijing 100097, Peoples R China

关键词： Semantic segmentation; Diffusion models; Noise; Feature extraction; Decoding; Adaptation models; Transformers; Semantics; Training; Noise reduction; Conditional diffusion model; crack detection; semantic segmentation; transformer; aggregated pixel attention

期刊名称：IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS （ 影响因子：8.4； 五年影响因子：9.5 ）

ISSN： 1524-9050

年卷期： 2025 年

页码：

收录情况： SCI

摘要： Pavement cracks pose a direct threat to the safety of transportation systems. ConditionCrack Segmentation (CCS), a pavement crack segmentation model based on conditional diffusion, is proposed in this study. The model progressively removes noise from a random Gaussian distribution, and it is guided by image conditions to generate crack predictions. The model comprises two components: the image encoder and the map decoder. As the image encoder, the combination of MiT and FPN, aggregates multi-scale features and uses the encoded feature map as a conditional input to supplement and constrain noised labels. The map decoder uses stacked transformer layers, reducing the number of parameters in the denoising network and enhancing the ability of the decoder to model both the local details of fractures and global sequences. The model introduces Classifier-Free Guidance (CFG) and a Sampling Drift Calibration Module (SDCM) to adaptively calibrate the decoder, ensuring the effectiveness of the conditional inputs. The proposed CCS approach achieves the highest mIoU on all three evaluated public datasets (mIoU = 84.46 on CRACK500, mIoU = 89.17 on DeepCrack, and mIoU = 79.47 on CFD), outperforming both mainstream semantic segmentation models and pavement crack segmentation models using diffusion models. Moreover, the proposed CCS model achieves 32 FPS, providing a practical real-time detection system framework after performing structural optimization.