C2B-DeformYOLO:基于YOLOv10的实时无人机路面病害检测方法
DOI:
CSTR:
作者:
作者单位:

重庆电子科技职业大学

作者简介:

通讯作者:

中图分类号:

基金项目:

重庆市教育科学规划课题(K24YC3090019)


C2B-DeformYOLO: Real-time UAV Road Damage Detection Built on YOLOv10
Author:
Affiliation:

Fund Project:

Chongqing Municipal Education Science Planning Project (K24YC3090019)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对无人机高空视角下路面裂缝细长断连与坑洼边界形变复杂导致的漏检与定位偏差问题,提出一种基于YOLOv10的端到端路面病害检测网络C2B-DeformYOLO。方法在基准网络上引入C2GD Neck,通过全局信息收集与连续条件门控实现跨尺度特征的自适应融合,增强裂缝目标的连贯表征。同时设计BOS Conv,在有限计算预算下对高响应区域进行稀疏偏移采样与重建,提高对非凸边界与几何失配的建模能力并兼顾推理效率。实验在无人机路面数据与公开RDD2022数据集上验证了方法的有效性,在保持实时性的同时提升检测精度与跨域泛化表现。

    Abstract:

    We propose C2B-DeformYOLO, an end-to-end real-time UAV road damage detector built on YOLOv10, with targeted architectural improvements for two core issues: cross-scale discontinuous representations of elongated cracks and accurate localization of nonconvex pothole boundaries. First, we introduce a Continuous Conditioned Gather Distribute neck, termed C2GD Neck, which performs global information gathering over multi-level features and generates continuous conditioning weights to adaptively allocate and fuse features in a bidirectional manner. This design strengthens coherent responses for thin crack patterns and enhances long-range dependency modeling across scales. Second, we present Budgeted Offset Sparse Convolution, called BOS Conv, which conducts sparse offset sampling and reconstruction on high-response regions under a constrained computation budget, improving geometric alignment and boundary deformation modeling while preserving efficient inference. Experiments on a UAV road damage dataset and the public RDD2022 benchmark demonstrate consistent gains in detection accuracy and cross-domain generalization over the baseline, without sacrificing real-time performance.

    参考文献
    相似文献
    引证文献
引用本文
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2026-03-08
  • 最后修改日期:2026-03-27
  • 录用日期:2026-04-15
  • 在线发布日期:
  • 出版日期:
文章二维码