The Computer Electronics Show saw demonstrations of the collaboration between QNX Systems and Luxoft on computer vision based augmented reality systems.
Luxoft’s CVNAR computer vision and augmented reality software framework was successfully used in a demonstration of ADAS and automated driving capabilities presented by QNX Software Systems at the International Consumer Electronics Show (CES) 2016 show which took place recently in Las Vegas.
Installed in QNX’s modified Jeep Wrangler reference vehicle, the CVNAR framework ran algorithms to highlight turn-by-turn navigation arrows, street names, pedestrian crossings, destinations, points-of-interest and forward collision alerts.
In working on the demonstration, Luxoft applied road model-based computer vision algorithms for the tracking of objects, such as vehicles, pedestrians, building facades and road signs, to build a road scene reconstruction engine that runs on the QNX Neutrino operating system. The road scene reconstruction engine uses Luxoft’s proprietary software for augmented reality such as advanced augmented guidance, navigation, points of interest (POIs) and destination highlighting. The Luxoft augmented navigation engine provides precise road positioning to empower semi-autonomous driving capabilities.
Commenting on the application of Luxoft’s approach to autonomous driving, the company’s Head of ADAS, Andrey Golubinskiy said, “The key differentiator of our ADAS software is that, from the very beginning, we used scientific algorithms to resolve the fundamental problems of computer vision in an in-vehicle environment. By applying these algorithms to the vehicle embedded systems and field-testing them, we were able to create a robust and reliable answer.”
Speaking about the role QNX Software Systems in such developments, the company’s Strategic Alliance Manager, Romain Saha continued, “Next-generation ADAS and automated driving applications need a realtime Operating System with proven safety credentials; they also need sophisticated computer-vision algorithms to make sense of the world around them.”
Luxoft’s CVNAR brings together a unique set of features and capabilities and can be used in several ways. It can be adapted to a particular OEM’s requirements and present a ready-to-use product on already supported systems-on-chip (SoCs), or it can be made available as a hardware-independent embedded product. The framework can be easily integrated with head-up and LCD displays, and supports smart glasses. Using eye-tracking algorithms and vehicle’s sensor data, augmented navigation provides navigational hints, highlights road obstacles and destinations and more.