Our website use cookies to improve and personalize your experience and to display advertisements(if any). Our website may also include cookies from third parties like Google Adsense, Google Analytics, Youtube. By using the website, you consent to the use of cookies. We have updated our Privacy Policy. Please click on the button to check our Privacy Policy.

BBC Click to Detect Wildfire

“BBC Click is the BBC’s flagship tech show. We broadcast internationally and have an audience reach of 380 million. We focus on the amazing things that technology can do to help people.”

BBC Click research team contacted us last May. We worked together in early September to demonstrate how AI can detect early-stage wildfire outbreaks. Our collaboration was shown in the BBC Click episode broadcast on 29/10/2022.  

Fig 1: The BBC Click 29/10/2022 episode talks about crash test dummy based on a female body, drone-based sea saving tech, and early wildfire detection system. Source: BBC

It was an interesting project with the BBC Click team. Their research team found RoboticsCats from the EIE program. EIE is a major startup program in Scotland, organized by the Bayes Centre of the University of Edinburgh. There were 36 high-growth startups in the EIE 2022 program and RoboticsCats was of them.

BBC Click team contacted us and wanted to know more about our technologies. I was a bit surprised that BBC was interested in wildfires since wildfire was not a big problem in the United Kingdom until 2022. There were wildfires last September which were very unusual.


Fig 2: Laura Goodwin of BBC Click and Andre Cheung on the rooftop of the Bayes Centre. A beautiful afternoon in Edinburgh.

After several online meetings and many email communications, we agreed to film a demonstration of our AI wildfire detection technology when I was visiting Edinburgh in early September.

It was challenging to arrange a fire test to demonstrate our technologies. Typically we will work with a firefighting organization to find a suitable place to do control burns during the off-season. We install cameras to detect the fire ignition and evaluate how accurately and how fast it finds the fire. It takes time to get approval. It was not likely we were allowed to do it when firefighters were busy with the unexpectedly high number of wildfires in Scotland between April and August.

The BBC team then suggested a think-out-of-the-box idea: to show wildfire videos on a monitor, use a smartphone with our new LookOut Cam Android app installed to capture images, and send them to our AI wildfire detection and test its performance in real-time. It was a creative idea! With support from EIE, we arranged the demonstration and videography at the Bayes Centre.


Fig 3: The demonstration setup: a phone working as a surveillance camera, a notebook showing wildfire videos, another phone receiving detection alert. Source: BBC

Thank the BBC Click team and the Bayes Centre for their preparation. They were very professional and friendly. The weather was good and the filming was smooth. We had some time to chat and I learned from the BBC Click team about their recent relocation from London to Glasgow. It was part of BBC’s plan to spread out its operations in the United Kingdom, get closer to its audiences across the country, and tell the stories that need to be heard from all corners of the UK.

From all corners of the world indeed.

Fig 4: The BBC Click team: Martin Sharkey, Laura Goodwin, and Danielle Fleming (from left to right)


We built the new LookOut Cam app for two reasons:

  1. to provide handy tools for our summer interns in California to evaluate the performance of our “quick to deploy, easy to use” LookOut wildfire detection software-as-a-service. The LookOut Cam app will use the smartphone’s rear camera to take images periodically and send them to LookOut for forest fire detection.
  2. to provide low-cost wildfire detection “cameras” by reusing unused smartphones. Performance-wise it is not as good as a surveillance camera. However, it is a good option for users near WUI (wildland-urban interface) to implement proof-of-concept, urgent or interim applications.

And unexpectedly, I use the new LookOut Cam app very often to do demonstrations. From image input (LookOut Cam app) to alert output (ReportFires app), it is an end-to-end mobile solution that is always with me. Anytime, anywhere.


Fig 5: End-to-end mobile wildfire detection solution: image input from LookOut Cam app and alert output via ReportFires app.

Please contact us at info@roboticscats.com if you have any question or suggestion.

By Andre Cheung

I am lucky working in the ICT industry in the past 20 years to collaborate with colleagues, partners and customers to use technologies to change the way we work, live, play and learn! I have strong interests in cloud computing, AI and information security. “It is the technologies marry with liberal arts, marry with the humanities, that yields us the result that makes our hearts sing!”

Related Posts