Foresight Shows its Stereo Automotive Camera System with Object Detection at CES

author: Eric Walz   

LAS VEGAS — Foresight demonstrated its Quadsight forward facing camera solution at CES this week. The QuadSight system sets a new bar for autonomous vehicle vision – it features near 100% obstacle detection with near zero false alerts, under all weather and lighting conditions, including complete darkness, rain, haze, fog and direct sunlight.

The QuadSight system, a first of its kind quad-camera multispectral vision solution, is driven by advanced and proven image processing algorithms. The system is a seamless fusion of four cameras – two sets of stereoscopic infrared and visible-light cameras, enabling highly accurate and reliable obstacle detection. Stereo technology is an image processing concept which uses two synchronized cameras to mimic the human depth perception and obtain 3D view.

Israeli based Foresight is a wholly-owned subsidiary Foresight Automotive Ltd. (NASDAQ: FRSX), that specializes in the design, development and commercialization of stereo/quad-camera vision systems for the automotive industry. The company's patented technology incorporates 3D video analysis, advanced algorithms for image processing and sensor fusion.

Dror Elbaz, Foresight's VP of R&D, demonstrated the system for me, which was installed in a Porsche Panamera parked in front of a large video screen in order to show off the features and capabilities. Although Foresight said that CES attendees were not allowed to film inside of the demo car, Elbaz demonstrated all of the features of the system once inside.

The four camera systems uses sensor fusion, fusing visible-light and infrared cameras for seamless vision, and 100% obstacle detection, regardless of its shape, form or material. Foresight says its cameras can detect and classify pedestrians from 150 meters away, and highlights them on a widescreen dashboard video display, so drivers are aware of their presence, or any other hazards ahead.

The cameras capture 45 frames per second, allowing detection when the vehicle is traveling at high speeds, with a 45 degree field of view, which covers the entire roadway ahead. Each side of the stereo camera setup contains one infrared camera and one visible light camera.

Foresight applies Advanced algorithms for accurate depth analysis and obstacle detection. This provides near 100% obstacle detection with zero false alerts. The camera system can operate in all weather and lighting conditions. It is robust enough to detect a 35 x 25 cm object from 100 meters away.

The system is still in development. Foresight says the cameras will be small enough to be concealed and integrate into a vehicle without altering design aesthetics. The cameras can be used in addition to other safety systems, providing redundancy for object detection in front of a vehicle.

Eric Walz

Originally from New Jersey, Eric is a automotive & technology reporter covering the high-tech industry in Silicon Valley. Eric has over 15 years of automotive experience and a bachelors degree in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the auto industry and beyond. He has worked at Uber on self-driving cars and as a technical writer, helping people to understand and work with technology. Outside of work, Eric likes to travel to new places, play guitar, and explore the outdoors.