Detection of TBE elements in images

The aim of this machine learning service is to automatically detect TBE (technical building equipment) elements such as fire safety equipment in images.

The service is able to detect fire extinguishers, smoke detectors, fire alarms, fire blankets in images and locate them visually using a bounding box.

Data

Quality: The documentation images should be of good quality and preferably without blurring. The image can be in horizontal or vertical format. Processing of poor quality images is of course also possible, but tends to produce poorer results.

  • Input data format:
    •  JPG file of a fire protection system from 1-2 meters distance.
  •  Training data available?:
    • Self-made data set
    • External data set: https://www.firenet.xyz/
  • Output data format:
    • ZIP file
      • JSON file
        • List of all detected bounding boxes (per bounding box: coordinates for 2 points in 2D)
      • JPG file
        • Original file for further processing
        •  Visualization of the deketion on the original file

Contact Person:
Angelina Aziz, M. Sc., Lehrstuhl für Informatik im Bauwesen, Ruhr-Universität Bochum