Automated Generation of Room Usage Semantics from Point Cloud Data

被引:0
|
作者
Cai, Guoray [1 ]
Pan, Yimu [1 ]
机构
[1] Penn State Univ, Coll Informat Sci & Technol, University Pk, PA 16802 USA
关键词
3D Models; indoor environment; room semantics; point clouds processing; deep learning;
D O I
10.3390/ijgi12100427
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Room usage semantics in models of large indoor environments such as public buildings and business complex are critical in many practical applications, such as health and safety regulations, compliance, and emergency response. Existing models such as IndoorGML have very limited semantic information at room level, and it remains difficult to capture semantic knowledge of rooms in an efficient way. In this paper, we formulate the task of generating rooms usage semantics as a special case of room classification problems. Although methods for room classification tasks have been developed in the field of social robotics studies and indoor maps, they do not deal with room usage and occupancy aspects of semantics, and they ignore the value of furniture objects in understanding room usage. We propose a method for generating room usage semantics based on the spatial configuration of room objects (e.g., furniture, walls, windows, doors). This method uses deep learning architecture to support a room usage classifier that can learn spatial configuration features directly from semantically labelled point cloud (SLPC) data that represent room scenes with furniture objects in place. We experimentally assessed the capacity of our method in classifying rooms in office buildings using the Stanford 3D (S3DIS) dataset. The results showed that our method was able to achieve an overall accuracy of 91% on top-level room categories (e.g., offices, conference rooms, lounges, storage) and above 97% accuracy in recognizing offices and conference rooms. We further show that our classifier can distinguish fine-grained categories of of offices and conference rooms such as shared offices, single-occupancy offices, large conference rooms, and small conference rooms, with comparable intelligence to human coders. In general, our method performs better on rooms with a richer variety of objects than on rooms with few or no furniture objects.
引用
收藏
页数:18
相关论文
共 50 条
  • [41] Automated Rock Detection and Shape Analysis from Mars Rover Imagery and 3D Point Cloud Data
    Di, Kaichang
    Yue, Zongyu
    Liu, Zhaoqin
    Wang, Shuliang
    JOURNAL OF EARTH SCIENCE, 2013, 24 (01) : 125 - 135
  • [42] An automated algorithm for mapping building impervious areas from airborne LiDAR point-cloud data for flood hydrology
    Hung, Chen-Ling J.
    James, L. Allan
    Hodgson, Michael E.
    GISCIENCE & REMOTE SENSING, 2018, 55 (06) : 793 - 816
  • [43] Point Cloud Generation with Continuous Conditioning
    Triess, Larissa T.
    Buehler, Andre
    Peter, David
    Flohr, Fabian B.
    Zoellner, J. Marius
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
  • [44] Generation of a template for usage point determination in facebook
    Teh, Phoey Lee
    Batch, Yamen
    Ji, Ma Ling
    WORLD CONFERENCE ON INFORMATION TECHNOLOGY (WCIT-2010), 2011, 3
  • [45] Automated rock detection and shape analysis from mars rover imagery and 3D point cloud data
    Kaichang Di
    Zongyu Yue
    Zhaoqin Liu
    Shuliang Wang
    Journal of Earth Science, 2013, 24 : 125 - 135
  • [46] Automated Rock Detection and Shape Analysis from Mars Rover Imagery and 3D Point Cloud Data
    邸凯昌
    岳宗玉
    刘召芹
    王树良
    Journal of Earth Science, 2013, 24 (01) : 125 - 135
  • [47] Conditional GAN for Point Cloud Generation
    Yang, Zhulun
    Chen, Yijun
    Zheng, Xianwei
    Chang, Yadong
    Li, Xutao
    COMPUTER VISION - ACCV 2022, PT VII, 2023, 13847 : 117 - 133
  • [48] Automated Capturing and Systematic Usage of DevOps Knowledge for Cloud Applications
    Wettinger, Johannes
    Andrikopoulos, Vasilios
    Leymann, Frank
    2015 IEEE INTERNATIONAL CONFERENCE ON CLOUD ENGINEERING (IC2E 2015), 2015, : 60 - 65
  • [49] Scan-to-graph: Automatic generation and representation of highway geometric digital twins from point cloud data
    Pan, Yuandong
    Wang, Mudan
    Lu, Linjun
    Wei, Ran
    Cavazzi, Stefano
    Peck, Matt
    Brilakis, Ioannis
    AUTOMATION IN CONSTRUCTION, 2024, 166
  • [50] Generation of Triangulated Patches Smoothed from Original Point Cloud Data with Noise and Its Application to Robotic Machining
    Nagata, Fusaomi
    Takeshita, Kazuhiro
    Watanabe, Keigo
    Habib, Maki K.
    2016 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION, 2016, : 535 - 540