Scientists invent accurate AI-powered heat vision for driving at night

The technology can also be used in fog and smoke, aiding firefighters.
Loukia Papadopoulos
Dark forest road at night
Dark road at night - AI will help light the way


Researchers at Purdue University and Los Alamos National Laboratory have joined forces to engineer something they call “heat-assisted detection and ranging,” or HADAR, which consists of a completely new camera imaging system based on AI interpretations of heat signatures. The technology could soon allow vehicles and robots to see at night time.

This is according to a report by PopSci published on Wednesday. 

A once muddy, unclear tech

We have all seen movies where agents use thermal imaging to see their surroundings in the dark, but in reality, this technology is far from practical because thermal radiation particles diffuse into their nearby environments. This means that trying to image them becomes a complicated, muddy, and unclear process. 

To deal with this issue, the scientists used machine learning algorithms to derive the physical properties of objects and surroundings from information captured by commercial infrared cameras. Powered by artificial intelligence, HADAR is able to sort through optical clutter to effectively detect temperature, material composition, and thermal radiation patterns, even in environments cluttered by visual obstacles such as fog, smoke, and darkness. The end result is incredibly detailed, clear images even in the depth of sheer darkness.

“Active modalities like sonar, radar and LiDAR send out signals and detect the reflection to infer the presence/absence of any object and its distance. This gives extra information of the scene in addition to the camera vision, especially when the ambient illumination is poor,” Zubin Jacob, a professor of electrical and computer engineering at Purdue and article co-author, told PopSci. “HADAR is fundamentally different, it uses invisible infrared radiation to reconstruct a night-time scene with clarity like daytime.”

Seeing in the darkest of places 

Now, the researchers hope that their new technology could be used to power self-driving vehicles, autonomous robots, and even touchless security screenings in the dark and in other difficult-to-see circumstances. One could imagine robots equipped with HADAR entering burning houses to find survivors despite all the smoke and returning victorious.

For the time being, HADAR remains too expensive to be used in everyday applications. However, researchers are working on reducing its price point. This hasn’t stopped them from touting the tech’s many benefits and rejoicing in its efficiency.

“To be honest, I am afraid of the dark. Who isn’t?” added Jacob. “It is great to know that thermal photons carry vibrant information in the night similar to daytime. Someday we will have machine perception using HADAR which is so accurate that it does not distinguish between night and day.”

Add Interesting Engineering to your Google News feed.
Add Interesting Engineering to your Google News feed.
message circleSHOW COMMENT (1)chevron
Job Board