Next-Generation Under Vehicle Inspection System

Israeli startup UVeye developed an AI-based recognition system that scans the underside of moving vehicles to identify potential hidden threats.

“UVeye is changing the way people approach security when traveling by vehicle with a fast, accurate and automatic machine learning inspection system that can detect threatening objects or unlawful substances, for example, bombs, unexposed weapons and drugs,” Amir Hever, CEO and co-founder of UVeye.

Using GTX 1080 Ti GPUs and the cuDNN-accelerated TensorFlow deep learning framework, the technology is able to identify any modifications made to the structure of a vehicle’s underside in real-time.

Five HD cameras are used to scan the undercarriage of the vehicle and produces a 3D color map which allows the system to automatically identify any suspicious objects, changes, or additions made that are different than the manufacturer’s specifications.

“In the era of Mobility-as-a-Service, companies such as car rental companies, fleets, car dealerships, vehicle repair shops, and OEMs all rely on seamless vehicle operation. UVeye’s machine learning system can detect vehicle leaks, wear and tear, and any damages that would previously go unnoticed. Detecting any of these damages can save companies the time and costs involved in conventional inspection methods,” explains Hever about finding a second market for their technology.

Read more >

About Brad Nemire

Brad Nemire
Brad Nemire is on the Developer Marketing team and loves reading about all of the fascinating research being done by developers using NVIDIA GPUs. Reach out to Brad on Twitter @BradNemire and let him know how you’re using GPUs to accelerate your research. Brad graduated from San Diego State University and currently resides in San Jose, CA. Follow @BradNemire on Twitter