The First In-vehicle Scene Understanding™ AI
We created the world’s most advanced and comprehensive portfolio of vision-based Deep Neural Networks for In-vehicle Scene Understanding (ISU). Eyeris ISU uses multiple automotive-grade 2D RGB-IR image sensors to provide real-time visuospatial data analytics on the edge. Specifically designed for vision-optimized AI chip hardware, Eyeris ISU augments safety, comfort and convenience to the automotive and new mobility ecosystems in this new type of consumer space.
Object Localization (OL)
Surface Classification (SC)
Interior Semantic Segmentation (ISS)
Human Behavior Understanding
Eyeris HBU portfolio of DNNs includes body tracking analytics, face analytics and emotion recognition along with action and activity recognition for all occupants inside the vehicle.
Eyeris Object Localization DNN enables detection and classification of all objects inside the cabin, and provides data analytics about their size, contour, region and position.
Eyeris Surface Classification provides identification and position of all in-cabin surfaces such as footwells, door panels, center console, etc., relative to occupants and objects position.
Interior Image Segmentation
We believe that every inch of the interior space must be understood with the highest level of confidence in order to maximize safety and comfort. Our patent-pending method for Interior Image Segmentation provides a pixel map where every pixel in the vehicle interior scene is associated with a class label such as human, object or surface, along with their corresponding regions and contours. Eyeris Interior Image Segmentation enables us to perceive the in-vehicle environment with a much more robust knowledge than through traditional detection and classification networks for greater interior scene understanding accuracy.
Automotive Grade AI Chip Enablement
Eyeris’ unique vision AI software portfolio architecture integrates into computer vision-specific AI chip hardware solutions, enabling fast and efficient inference of the EyerisNet neural networks from multiple 2D camera sensors. The EyerisNet proprietary architecture optimizes real-time edge computing performance by maximizing AI chip throughput while maintaining low power consumption.
In 2017, The TU Automotive Awards Named Eyeris
Best Connected Service or Product for Commercial Market
“Because they are at the cutting edge of where the commercial vehicle industry is going, Eyeris occupant monitoring AI really stands out in the wide range of in-cabin monitoring tools out there.”
Defining the In-Cabin Experience for The Future of Mobility
While the focus on autonomous vehicles has revolved around exterior vision, in-cabin vision technologies will be just as groundbreaking in defining the future of mobility. So much of the future of autonomous vehicles is naturally focused on the car as a mode of transportation, but as augmented intelligence advances, vehicles will become a new type of consumer space, or a third-living space. Eyeris ISU enables new ways in how interiors will be designed, and how the interaction among passengers and outside environments will evolve.