SXVPU is an AI-powered imaging platform designed to tackle challenges like object recognition and machine learning integration through its efficient real-time processing of high-resolution video streams up to 4K. It is thus suited for applications like machine control and automation, for example in agricultural engineering, monitoring of construction sites and work environments, as well as collision avoidance systems.

With its specialized AMD-based hardware architecture and support for multiple cameras and sensors, SXVPU is set up to use impeccable image data straight from the sensor for processing by neural networks or conventional algorithms before encoding the data for low-latency transmission to other system components. Thanks to an integrated H.265/H.265 codec, streaming of the compressed video data is supported in resolutions up to 4K – via Ethernet by default, but also via modern wireless networks as an alternative.

SXVPU is designed for secure 24/7 operation, which is possible even in difficult environments with heat, cold, dust, or humidity thanks to its housing with IP67 protection. The customizable device concept provides the necessary flexibility to implement environment- and application-specific interfaces.

The result is a perfect solution for viewing and vision applications in mobile automation.