Convolutional Neural Networks Make ADAS/AVs See In The Dark

by Mat Dirjish

Addressing ADAS and autonomous-vehicle (AV) designers, Owl Autonomous Imaging’s whitepaper explains how its Owl Thermal Ranger uses convolutional neural networks (CNNs) to reliably locate and classify pedestrians and animals in the dark from their thermal signatures using one infrared camera. Employing a precise, small, and cost-effective Monocular 3D Thermal camera, Owl’s CNN software quickly and accurately classifies and measures the position of vulnerable road users.

When the software identifies a being, the system alerts the driver. If the driver does not react fast enough, the system activates the vehicle’s brakes and steering system.

Additionally, the whitepaper covers the history of CNNs, how the technology works (AI/machine training), why the CNN approach is the best solution to address current pedestrian safety concerns, and how auto manufacturers can implement it. Chuck Gershman, CEO & Co-founder of Owl Autonomous Imaging said, “If you are involved in the development of next generation autonomous vehicle safety and ADAS systems, it is essential for you to understand how CNNs contribute to thermal imaging capabilities. Safety is a critical gating point for the automotive industry’s successful implementation of autonomous and self-driving vehicles. Being able to see at night and recognize pedestrians and animals in the road is an important safety hurdle that needs to conquered.”

For deeper details, visit the Owl Autonomous Imaging website. Also, cut to the chase and request a copy of Owl Autonomous Imaging’s Convolutional Neural Networks whitepaper.

| | 1-516-422-1431 |

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s