Kyocera Corporation has developed an night vision system that uses AI to identify collision-risk objects in low-visibility driving conditions, such as at night, or in rain, snow, fog or smoke.
Kyocera’s automotive night vision solution features a headlight that can emit both white (RGB) and near-infrared (NIR) light on the same optical axis. This is expected to enable higher accuracy object recognition than alternative technologies. The system integrates RGB-NIR sensors and an image-fusion AI recognition technology, for object recognition. The integrated headlight also incorporates a bright, miniaturized gallium nitride (GaN) laser.
The system has automatic beam shaping functionality for the RGB and NIR light that prevents glare for oncoming drivers by automatically shifting visible light into a low-beam pattern when necessary, while the NIR light can remain in high-beam mode. Kyocera’s vehicle-mounted RGB-NIR sensor uses fusion recognition AI technology to improve object recognition. Instead of only combining the image data from the two sources, Kyocera’s system uses qualitative AI to compare and assess both RGB and NIR images, differentiating between pedestrians and vehicles with high accuracy even in low visibility conditions.
In addition, Kyocera has developed another AI feature to create training data for more cost-efficient learning and product development. The company’s AI is expected to reduce development costs while improving recognition performance. This is because conventional methods require the collection of vast amounts of NIR training data. Conversely, Kyocera’s AI technology generates training data automatically. As a result, this approach can reduce training costs while maintaining accuracy in recognition performance.
Kyocera will continue R&D for this system and is aiming for commercialization after 2027. The company says that to reduce traffic accidents and promote autonomous driving, auto makers will require more advanced hazard-detection systems. Kyocera’s night vision system is intended to help prevent traffic accidents by notifying drivers of hazards in adverse driving environments.