Scan2BIM-NET: Deep Learning Method for Segmentation of Point Clouds for Scan-to-BIM

点云 分割 深度学习 计算机科学 人工智能 过程(计算) 建筑信息建模 人工神经网络 天花板(云) 云计算 计算机视觉 卷积神经网络 模式识别(心理学) 数据挖掘 点(几何) 工程类 结构工程 几何学 操作系统 化学工程 数学 相容性(地球化学)
作者
Yeritza Perez-Perez,Mani Golparvar‐Fard,Khaled El‐Rayes
出处
期刊:Journal of the Construction Division and Management [American Society of Civil Engineers]
卷期号:147 (9) 被引量:68
标识
DOI:10.1061/(asce)co.1943-7862.0002132
摘要

The architecture, engineering, and construction (AEC) industry perform thousands of scans each year. The majority of these point clouds are used for generating three-dimensional (3D) models—a process formally known as scan to building information modeling (Scan-to-BIM)—that represent the current conditions of a construction scene. Although point cloud data provide the scene’s geometric information, its use presents several challenges that make the process of generating a 3D model from point cloud data time-consuming, labor-intensive, and error-prone. In order to address the mentioned challenges, this paper presents a new end-to-end deep learning method, named Scan2BIM-NET, for semantically segmenting the structural, architectural, and mechanical components present in point cloud data. It classifies beam, ceiling, column, floor, pipe, and wall elements using three main networks: two convolutional neural network (CNN) and one recurrent neural network (RNN). The method was trained and tested using 83 rooms from point cloud data representing real-world industrial and commercial buildings. The process returned an average accuracy of 86.13%, and the beam, ceiling, column, floor, pipe, and wall categories obtained an accuracy of 82.47%, 92.60%, 59.31%, 98.71%, 82.79%, and 84.46%, respectively. The experimental results showed that deep learning improves the accuracy of semantic segmentation of architectural, structural, and mechanical components. This new method has the potential of being a tool during the Scan-to-BIM process, especially for semantically segmenting underceiling areas where mechanical components are close to structural elements.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
是龙龙呀完成签到,获得积分10
1秒前
小马甲应助微微采纳,获得10
1秒前
1秒前
2秒前
2秒前
华仔应助Yimi采纳,获得10
2秒前
淡然的凝荷关注了科研通微信公众号
2秒前
zb完成签到,获得积分10
3秒前
下雨天完成签到,获得积分10
3秒前
ai六月份完成签到,获得积分10
3秒前
吴邪发布了新的文献求助10
3秒前
科研通AI2S应助冷静的奇迹采纳,获得10
3秒前
Song发布了新的文献求助10
4秒前
123完成签到,获得积分10
4秒前
5秒前
jinxixi完成签到,获得积分10
5秒前
terrell完成签到,获得积分10
5秒前
Orange应助自信以冬采纳,获得10
5秒前
1234567完成签到,获得积分10
6秒前
杨仔完成签到,获得积分10
6秒前
邢遇完成签到,获得积分10
6秒前
zb发布了新的文献求助10
7秒前
7秒前
123完成签到,获得积分10
8秒前
搬运工完成签到,获得积分10
8秒前
ALONE完成签到,获得积分10
8秒前
9秒前
西部牛仔完成签到,获得积分20
9秒前
10秒前
porcelain完成签到,获得积分10
11秒前
11秒前
11秒前
FashionBoy应助freedom采纳,获得10
11秒前
许愿完成签到 ,获得积分10
12秒前
怡然的向南完成签到,获得积分10
12秒前
温柔以冬发布了新的文献求助10
12秒前
分分钟妙不可言完成签到,获得积分10
12秒前
12秒前
lzh发布了新的文献求助10
13秒前
13秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968844
求助须知:如何正确求助?哪些是违规求助? 3513769
关于积分的说明 11169920
捐赠科研通 3249095
什么是DOI,文献DOI怎么找? 1794630
邀请新用户注册赠送积分活动 875278
科研通“疑难数据库(出版商)”最低求助积分说明 804755