当前位置: X-MOL 学术Autom. Constr. › 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.)
Impact of color and mixing proportion of synthetic point clouds on semantic segmentation
Automation in Construction ( IF 9.6 ) Pub Date : 2025-01-18 , DOI: 10.1016/j.autcon.2025.105963
Shaojie Zhou, Jia-Rui Lin, Peng Pan, Yuandong Pan, Ioannis Brilakis

Deep learning (DL)-based point cloud segmentation is essential for understanding built environment. Despite synthetic point clouds (SPC) having the potential to compensate for data shortage, how synthetic color and mixing proportion impact DL-based segmentation remains a long-standing question. Therefore, this paper addresses this question with extensive experiments by introducing: 1) method to generate SPC with real colors and uniform colors from BIM, and 2) enhanced benchmarks for better performance evaluation. Experiments on DL models including PointNet, PointNet++, and DGCNN show that model performance on SPC with real colors outperforms that on SPC with uniform colors by 8.2 % + on both OA and mIoU. Furthermore, a higher than 70 % mixing proportion of SPC usually leads to better performance. And SPC can replace real ones to train a DL model for detecting large and flat building elements. Overall, this paper unveils the performance-improving mechanism of SPC and brings new insights to boost SPC's value.

中文翻译:


合成点云的颜色和混合比例对语义分割的影响



基于深度学习 (DL) 的点云分割对于了解建筑环境至关重要。尽管合成点云 (SPC) 有可能弥补数据短缺,但合成颜色和混合比例如何影响基于 DL 的分割仍然是一个长期存在的问题。因此,本文通过广泛的实验来解决这个问题,方法是引入:1) 从 BIM 生成具有真实颜色和均匀颜色的 SPC 的方法,以及 2) 增强的基准以更好地评估性能。在包括 PointNet、PointNet++ 和 DGCNN 在内的 DL 模型上的实验表明,在 OA 和 mIoU 上,具有真实颜色的 SPC 上的模型性能比具有统一颜色的 SPC 上的模型性能高出 8.2 % +。此外,高于 70% 的 SPC 混合比例通常会带来更好的性能。SPC 可以替换真实模型来训练 DL 模型,以检测大型和扁平的建筑元素。总体而言,本文揭示了 SPC 的性能改进机制,并为提升 SPC 的价值提供了新的见解。
更新日期:2025-01-18
down
wechat
bug