Title: Towards Bringing Spatial AI to Smart Firefighting
Abstract: Despite its indispensability, firefighting remains as one of the most strenuous and dangerous jobs in the world. 897 firefighters died on duty in the USA over a 10 year period from 2010 - 2019. Lack of real-time spatial awareness of a fireground is widely regarded as the culprit of firefighter fatality and casualty. A fire incident is often accompanied by a variety of airborne obscurants (e.g., dust, fog and smoke) and poor-illumination (e.g., dimness, darkness and flame glare). Consequently, firefighters often experience severe visual degradation and are difficult to localise, perceive or navigate in such environments.
In this talk, I will discuss our recent work on the design and development of SLAM systems against the visual degradation in firefighting by using emerging sensors and machine learning techniques. I will also scope out how these works lay the foundation for the vision of bringing spatial AI upfront to firefighting and emergency response at large.