Enhanced Pedestrian Safety with 3D Thermal Ranging using AI for ADAS/AV Applications

Not only have pedestrian injuries and deaths been rising for years but the systems now installed on automobiles intended to protect pedestrians, fail to work at night when more than 76% of the fatalities occur. Recognizing the shortcomings of the current testing protocols, the European Traffic Safety Council (ETSC) has highlighted the need for “New tests show AEB systems need to work better in wet, fog, and low-light situations” and Euro NCAP, in its Vision 2030 report, committed to extending its AEB test requirements as soon as viable solutions are identified. Owl AI believes a viable solution for pedestrian safety is near using Thermal Ranger technology which allows sensing of pedestrians in all conditions. The current de-facto Automotive Driver Assist System (ADAS) sensor suite typically comprises mutually dependent visible-light cameras and radar, but when one of these sensors becomes ineffective, so too does the entire sensor suite. This scenario happens often especially when it comes to pedestrians, cyclists, and animals at night or in inclement weather. We will discuss a novel modality known as monocular 3D Thermal Ranging that dramatically improves pedestrian safety to reduce accidents and save lives. The solution is based on custom HD thermal imaging and innovative AI/Machine-Learning based computer vision algorithms. Operating in the thermal spectrum, these algorithms exploit angular, temporal and intensity data to produce ultra-dense 3D point clouds (up to 150x that of LIDAR) along with highly refined classification for object identification. We will discuss how to derive ultra-high-density range maps from a monocular thermal camera running a purpose-built AI/ML CNN and bespoke embedded optics. The resulting new sensor modality provides all the benefits of a thermal camera, including all weather and day/night operation and instant classification of animals and vehicles, while simultaneously delivering a geospatially registered 3D range map of such density that perception stacks may enjoy unprecedented awareness. Finally, we will show real world night-time results using the Thermal Ranger tested against the latest NHTSA NCAP night-time PAEB test procedures. Pedestrian (animal, cyclist, …) safety concerns are now top of mind for ADAS/AV systems. This talk addresses sensor and sensor fusion gaps in addressing these safety concerns. The adoption of a new sensor modality known as Monocular 3D Thermal Ranging, powered by AI, which supplements existing sensor suites has now been shown to markedly improve pedestrian safety at night and in foul weather conditions directly addressing the safety parameters put forward by NHTSA.