pachi / PointER

A LiDAR-Derived Point Cloud Dataset of One Million English Buildings Linked to Energy Characteristics

Home Page:https://arxiv.org/ftp/arxiv/papers/2306/2306.16020.pdf

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Points for Energy Renovation (PointER):

A LiDAR-Derived Point Cloud Dataset of One Million English Buildings Linked to Energy Characteristics

Getting Started

  • Please see our setup documentation for a step by step description.
  • Please check our related paper for information about the method and the resulting dataset. The pre-print version is available here.
  • A dataset comprising one million building point clouds with half of the buildings linked to energy features is available here.

Prerequisites

Running the Code

  • To run an example point cloud generation, please use the jupyter notebook.
  • To run the point cloud generation for an entire area of interest, please see the point cloud generation documentation.
  • The main program can be found here. Please note, that the point cloud generation process involves some upfront data preparation.

The process involves 6 steps:

img

Due to the size of the point cloud files, it is recommended to set up the container on a machine with a large working memory. We ran the code without problems on a machine with 48 GB, but a machine with 16 GB or more should work.

Dataset

The dataset contains one million building point clouds for 16 Local Authority Districts in England. These Local Authority Districts are representative for the English building stock and selected across the country (see image).

img

This is an example of a resulting point cloud: img

Data Sources

Versioning

V0.1 Initial version

Authors

Author: Sebastian Krapf, Kevin Mayer

License

This project is licensed under the MIT License.

About

A LiDAR-Derived Point Cloud Dataset of One Million English Buildings Linked to Energy Characteristics

https://arxiv.org/ftp/arxiv/papers/2306/2306.16020.pdf

License:MIT License


Languages

Language:Python 87.4%Language:Jupyter Notebook 12.6%