当前位置: X-MOL 学术Tunn. Undergr. Space Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
SAM4Tun: No-training model for tunnel lining point cloud component segmentation
Tunnelling and Underground Space Technology ( IF 6.7 ) Pub Date : 2025-01-24 , DOI: 10.1016/j.tust.2025.106401
Zehao Ye, Wei Lin, Asaad Faramarzi, Xiongyao Xie, Jelena Ninić

Asset management ensures the safety and longevity of structures through regular maintenance. Reality capture technologies are increasingly being used for asset inspections to obtain information by generating point cloud data, which is becoming more prevalent in tunnel asset management for precise documentation of tunnel geometry and condition. Integrating semantic information from point clouds is crucial for creating accurate as-built Building Information Models (BIM), essential for project delivery, maintenance, and operations. In this paper, we propose SAM4Tun, a zero-shot automated instance segmentation method for tunnel lining segments. It is based on a Large Vision Model (LVM), prompt-based Segment Anything Model (SAM), and various point cloud and image processing techniques, enabling accurate instance segmentation without requiring any training. The process starts by unfolding tunnel point clouds to generate 2D panoramic images, enabling SAM to be extend its capabilities to point cloud segmentation. To enhance performance, we propose: (i) a local point cloud density-variation method to filter out non-segment parts, and (ii) a geometry feature-guided multi-step point cloud up-sampling method to address uneven point cloud density during projection. Then, we focus on prompt engineering, using traditional image processing techniques to automatically generate template prompt, enabling SAM’s zero-shot ability to achieve precise instance-level segmentation of tunnel linings. The results demonstrate that our no-training model achieved highly accurate instance segmentation, even surpassing supervised learning algorithms. The proposed method addresses the issue of data dependency and serves as the foundation for component-level damage localization and displacement monitoring in tunnel. Our code is available at https://github.com/zxy239/SAM4Tun.

中文翻译:


SAM4Tun:用于隧道衬砌点云组件分割的免训练模型



资产管理通过定期维护确保结构的安全性和使用寿命。现实捕捉技术越来越多地用于资产检查,通过生成点云数据来获取信息,这在隧道资产管理中越来越普遍,用于精确记录隧道的几何形状和状况。集成来自点云的语义信息对于创建准确的竣工建筑信息模型 (BIM) 至关重要,这对于项目交付、维护和运营至关重要。在本文中,我们提出了 SAM4Tun,一种用于隧道衬砌管片的零镜头自动实例分割方法。它基于大型视觉模型 (LVM)、基于提示的 Segment Anything Model (SAM) 以及各种点云和图像处理技术,无需任何培训即可实现准确的实例分割。该过程首先展开隧道点云以生成 2D 全景图像,使 SAM 能够将其功能扩展到点云分割。为了提高性能,我们提出了:(i) 一种局部点云密度变化方法来过滤掉非段部分,以及 (ii) 一种几何特征引导的多步点云上采样方法,以解决投影过程中点云密度不均匀的问题。然后,我们专注于提示工程,使用传统的图像处理技术自动生成模板提示,使 SAM 的零镜头能力能够实现隧道衬砌的精确实例级分割。结果表明,我们的无训练模型实现了高度准确的实例分割,甚至超过了监督学习算法。 所提出的方法解决了数据依赖性问题,为隧道中组件级损伤定位和位移监测奠定了基础。我们的代码可在 https://github.com/zxy239/SAM4Tun 上找到。
更新日期:2025-01-24
down
wechat
bug