AI-ISP: Adding Real-Time AI Functionality to Image Signal Processing with Reduced Memory Footprint and Processing Latency


Date:  Tuesday, May 23

Start Time: 1:30 pm

End Time: 2:00 pm

The AI-ISP IP product from VeriSilicon is a revolutionary solution that adds AI functionality to image signal processing (ISP) while reducing the memory footprint and processing latency. Unlike conventional approaches that require the entire image frame to be stored in memory before processing, the AI-ISP enables real-time AI-based processing of image data with reduced memory usage and processing latency. This approach results in improved image quality and reduced system overhead, making it ideal for a variety of applications, including surveillance, automotive and industrial imaging. In this presentation, we will provide an overview of the AI-ISP product and its key features, and discuss its benefits and potential use cases. We will also share our experience of integrating AI-ISP into our customers’ products and highlight the results obtained from real-world applications.

Track

Session Speakers

  • Mankit Lo is the Chief Architect and Senior Director of NPU IP Development at VeriSilicon, where he leads the development of cutting-edge silicon IP products such as neural processing units. With over 30 years of experience in the industry, Mankit has a track record of delivering innovative solutions for AI and imaging applications, as evidenced by his numerous patents in the field. Prior to joining VeriSilicon, he was responsible for engineering development in the Multimedia, Video and Imaging Group at Xilinx. He also served as Director of Hardware Engineering at Pinnacle Systems. Mankit is a recognized expert in the field of hardware engineering and has made significant contributions to the development of numerous hardware products.


Share

AI-ISP: Adding Real-Time AI Functionality to Image Signal Processing with Reduced Memory Footprint and Processing Latency