As the key to the successful deployment of machine vision and artificial intelligence, edge visual intelligence requires accurate optical signal processing in a real-time manner, which is insoluble with conventional imaging systems. Though compressive imaging has empowered a new wave of revolutionary solutions, it usually needs complicated algorithms to retrieve the desired signal, leading to the corresponding high-energy consumption. 

To address these issues, this project sets forth to realize advanced compressive imaging for edge visual intelligence, through low-cost and low-power optical signal compression, and efficient and effective computational algorithms. Indeed, the success of this project can contribute unprecedentedly to the AI software and application ecosystems, and promote the long-term strategic development in the high-tech domain.