PROBLEM
Machine vision helps robots and autonomous vehicles react to their environments without human intervention. Thermal imaging is the best sensing method to create that vision; it passively collects invisible heat radiation originating from all objects in a setting. It can sense through darkness, inclement weather and solar glare. But because heat is constantly emitted and scattered, images show no textures or features. This loss of information, texture and features is a roadblock for machine perception using heat radiation.
SOLUTION
Researchers at Purdue University have developed HADAR TeX, or heat-assisted detection and ranging. It uses machine learning to vividly recover the texture from a cluttered heat signal and accurately disentangles temperature, emissivity and texture, or TeX, of all objects in a scene. It sees texture and depth through the darkness as if it were day and also perceives physical attributes beyond RGB visible imaging or conventional thermal sensing.
PRIMARY INVESTIGATOR
Zubin Jacob, the Elmore Associate Professor of Electrical and Computer Engineering
IN THE MEDIA
Read More
LICENSING CONTACTS
Email: otcip@prf.org
MEDIA CONTACT
Email: Steve Martin // sgmartin@prf.org
QUOTE
“HADAR has the potential to greatly improve the reliability and safety of autonomous vehicles such as cars, trucks, and drones.” Aaron Taggart, Licensing Associate – Physical Sciences