FireNet
Jan Boehm
Fabio Panella
Victor Melatti
10.5522/04/9137798.v1
https://rdr.ucl.ac.uk/articles/dataset/FireNet/9137798
<p>FireNet <br></p>
<p> </p>
<p>FireNet is an open ML training dataset for visual recognition of fire
safety equipment. Our dataset directly links the objects to their
respective Uniclass, the construction sector’s classification scheme to name
objects. </p>
<p> </p>
<p>FireNet has been designed as a ML training dataset for experimentation
and therefore fulfills multiple machine learning scenarios (classification,
object detection, semantic segmentation). It is intended as a domain specific
dataset to refine pre-trained standard architectures. </p><p><br></p><p></p><p>Uniclass & Description </p>
<p>Pr_40_50_28_64 Portable
fire extinguishers</p>
<p>Pr_75_75_30_50 Manual
call points </p>
<p>Pr_40_50_28_29 Fire
protective blankets </p>
<p>Pr_40_10_77_32 Fire
escape route signs </p>
<p>Pr_40_10_77_31 Fire
equipment signs </p>
<p>Pr_75_75_30_97 Visual
alarm signal devices Pr_75_75_30_30 Fire
alarm sounders </p><p></p>
<p>Pr_75_75_30_65 Point
smoke detectors </p><br><p></p>
2019-07-31 14:59:21
Fire Safety Equipment
Training Images
Machine Learning
Geomatic Engineering not elsewhere classified