A start-up approaching firefighters. XXII, a software publisher that uses artificial intelligence techniques and more specifically computer vision, approached Meuse’s departmental fire and rescue service (SDIS). The start-up founded in 2015 in Paris has developed a real-time video analysis solution and wants to offer a new fire detection feature from September. Ultimately, the idea is to connect the software to a city’s cameras so it can diagnose, identify and alert quickly in the event of a fire outbreak.
Study in real conditions
XXII is still in the study and validation stage and wants to make sure its systems recognize lights, such as vehicle lights. The start-up has already conducted fire starting experiments but in other contexts such as with recycling companies. “But the fire is different, it is necessary to have other situations”said Damien Mulhem, Chief Data Officer and co-founder of XXII.
So far, because it is so rare to find burning vehicles, the start-up has worked with little study. But it is better to learn and understand the removal of fires in vehicles directly on the ground. “Our algorithms must be fed with knowledge”simple explanation by Damien Mulhem.
It is therefore natural that XXII approached the firefighters to join the exercises conducted by the SDIS de la Meuse on the night of June 27 to 28 and on the day of June 28. This rapprochement became easy because the teams of XXII were there was a volunteer firefighter to make the link between the two. The SDIS, through the voice of Lieutenant-Colonel David Hantzo of the SDIS de la Meuse, yields a “partnership” and make sure there is “no interest in the economy” at “This approach is in the collective interest.”
Explanations of different parameters
During these exercises, “Fires in depolluted vehicles are lit in various configurations so that new firefighters can train”, summarizes David Hantzo. For XXII, this experiment should enable its algorithms, make sure they can detect fire start in real conditions, and educate its neural networks about other fire start events. “The goal is to film fire at multiple distances and different heights so that our systems are agnostic to distance and viewpoint angles”explained Damien Mulhem.
XXII wants to better understand fire outbreaks in vehicles and above all to teach its neural networks the different types of fire and how to evaluate them. Here, expert firefighters can explain live to XXII teams the parameters to be considered (fire colors, height, smoke, etc.) and their influence on the evolution of fire, both to more understand the evolution of fire and send the right information. Then, the software will be able to automatically detect these fires, analyze them and warn firefighters by telling them what stage the fire has reached and assessing its severity.
The many uses of AI
The software developed by XXII can be used by anyone, whether it is a community or a private company and eventually individuals. Damien Mulhem evokes a “agnostic platform that can be used in different ways”. Beyond fire detection, XXII also wants to develop a drowning detection solution. But data on this topic is scarce, so it should be replicated.
Another topic of interest to startups is the discovery of special vehicles (fire, ambulance, police, SAMU, vehicle -carrying organs, etc.). Once these vehicles are detected, and XXII software is already associated with smart cities, it is possible to control the traffic lights to facilitate the circulation of these vehicles.
For firefighters, artificial intelligence can have many uses, but the cost of this technology currently limits its use. David Hantzo develops the use of artificial intelligence that accompanies sensors in nozzle holders to very quickly alert firefighters when a fire is about to break out when certain elements (temperature, light, smoke, heat) are combined. There is also personal protective equipment with probes that recreate the operational situation (heat, smoke, etc.) using artificial intelligence. Uses that may multiply in the coming years.