Welcome to my portfolio site. Feel free the take a look around.

Real-Time People Detection using Thermal Vision

Desktop Applications April 2014

This research aims at creating a system which is able to detect people within thermal imagery no matter what their background. It also detects them in real time meaning the processing and analysis of the images take milliseconds to complete. In the end, the average time for 1 image (from this dataset, which contains relatively small images at around 320 x 240) to be successfully processed and the person located was 0.003812 seconds. This kind of speed clearly meets the real-time objective of this research.

There are many possible uses for this kind of application. For example, it could support a security team by selecting video feeds from camera that detect the presence of people rather than showing the feeds which contain nothing. This would help the security personnel as they would not be bombard with unnecessary video feeds.

This was part of my Computer Vision and Robotics module for year 4 for my Masters of Computing (MCOMP) degree with The University of Lincoln. If you would like a copy any documentation (including the corresponding report), then please contact me using the facilities on this website.

Browse portfolio

Client

  • The University of Lincoln