Published August 1, 2021 | Version 1.0
Dataset Open

Building Object and Outdoor Scene Segmentation (BOOSS) - Multi-channel (RGB + Thermal) Aerial Imagery Datasets

Creators

  • 1. University of Southern California
  • 2. Karlsruhe Institute of Technology

Description

The dataset of Building Object and Outdoor Scene Segmentation (BOOSS) is based on multi-channel aerial imagery data. It covers 

- Ground Truth

- RGB

- Thermal

The annotations in version 1.0 include roofs, facades, cars, roof equipment, and ground equipment

Please cite as:

Hou, Yu, Meida Chen, Rebekka Volk, and Lucio Soibelman. "An Approach to Semantically Segmenting Building Components and Outdoor Scenes Based on Multichannel Aerial Imagery Datasets." Remote Sensing 13, no. 21 (2021): 4357.

Files

datasets.zip

Files (924.8 MB)

Name Size Download all
md5:4602bb16154d3265b66093c706cbcc5c
924.8 MB Preview Download

Additional details

References

  • Y. Hou, L. Soibelman, R. Volk, and M. Chen, Factors Affecting the Performance of 3D Thermal Mapping for Energy Audits in A District by Using Infrared Thermography (IRT) Mounted on Unmanned Aircraft Systems (UAS), doi: https://doi.org/10.22260/ISARC2019/0036.
  • Y. Hou, R. Volk, M. Chen, and L. Soibelman, (2021). Fusing tie points' RGB and thermal information for mapping large areas based on aerial images: A study of fusion performance under different flight configurations and experimental conditions, Automation in Construction, vol. 124, doi: 10.1016/j.autcon.2021.103554.