Superior Image Quality Combined with Cloud AI Ideal for Real-Time Video Analysis System
Yokohama, May 17, 2018 --- Socionext Inc. today introduced its new ‘M820L‘, the latest device from the company's Hybrid Codec M820 Series. Optimized for flexibility and performance, the M820L is designed to maximize the value of video data in broadening its usage.
In addition to decoding and encoding of multi-channel, high-resolution, high-quality image and video data, the M820 series combines the industry’s highest performance processing power using dedicated codec hardware and flexible software processing via high-efficiency CPU. Its advanced video data processing capabilities include extracting information from a video and integrating it into the output data and thereby improving the value of video data for a wide range of applications.
The ‘M820L‘ is the latest addition to the series, with functions assembled into a PCIe low profile card. It can be inserted into a PCIe slot of a PC or a server and functions as an accelerator to reduce the load of a CPU's encoding processing. The M820L can enhance existing systems’ encoding performance or extend system capabilities for new function and performance requirements.
Socionext has collaborated with Fujitsu Limited to develop a video analysis system that demonstrates the full function and performance of the M820L, in combination with the ‘FUJITSU Human-Centric AI Zinrai‘. The way it works is that the M820L receives signals from cameras and converts them to highly compressed, high-quality image data. In parallel, it extracts information for video processing and analysis, and inputs such data to the Zinrai Server Inference, which efficiently performs real-time analysis of high-resolution, high-quality video images, a process that cannot be achieved with conventional cloud video processing systems. Applications that can benefit from the video analysis system include advanced surveillance camera, digital marketing, sports video analysis, and content management in video distribution services.
Socionext plans for the delivery of the system in December 2018. The company will demonstrate the video analysis system at the ‘Fujitsu Forum 2018‘ at the Tokyo International Forum, May 17 and 18.
