In this talk, we introduce MPU+, a novel programmable, customizable low-power platform for real-time, localized intelligence at the edge. The platform includes an AI-augmented image signal processor that enables leading image and video quality. In addition, it integrates ultra-low-power object and motion detection capabilities to enable always-on computer vision. A programmable neural processor provides flexibility to efficiently implement new neural networks. And additional specialized engines facilitate image stabilization and audio enhancements.
MPU+: A Transformative Solution for Next-Gen AI at the Edge
Session Speakers
-
Petronel Bigioi
CEO, FotoNation
Petronel is FotoNation’s CEO. Based in Ireland, he is responsible for leading the company’s vision toward edge AI signal processing solutions for the home, automotive and mobile markets. Petronel has more than 250 granted and published patents to date. He is an IEEE Fellow with more than 25 years of experience in the digital still camera and mobile phone industries, working in both signal processing and connectivity. His work has been recognized by the Romanian Academy’s Gheorghe Cartianu Award. A co-founder of several successful companies including FotoNation (acquired in 2008 by Xperi and restarted in 2024), he is a pioneer of digital camera connectivity and a co-author of PTP and PTP-over-IP communication standards. Petronel obtained his PhD in Electronics, master’s degree in ASIC Design and bachelor’s degree in Electronics Engineering from the Transilvania University of Brasov. Petronel also holds a master’s degree in Networks and Communications from the University of Galway.
