BIFOLD Colloquium 11/2024
October
23,
2024 
10:00
- 11:30
Edge-AI for Compression and Inference in Space
Abstract: Traditionally, satellites have been acquiring images that are processed at ground segments to extract information of interest. However, a recent trend is to move computations directly onboard the satellites. This approach provides several advantages in mission management and operation, but it has to deal with the limited computation capabilities available onboard satellites. In my talk I will review the scenario of Edge-AI and present recent developments in the fields of AI-based compression and inference. Specifically, I will describe a new compression algorithm outperforming the most recent CCSDS standards, and a new architecture leveraging self-supervised learning to achieve state-of-the-art inference accuracy while requiring a limited set of labeled training data.
Speaker Bio: Enrico Magli is a Full Professor with Politecnico di Torino, Italy, where he leads the Image Processing and Learning group. He performs research in the fields of deep learning for image and video processing and image compression, with applications to vision and remote sensing. He is a Senior Associate Editor of IEEE Journal on Selected Topics in Signal Processing, and a former Associate Editor of IEEE T-MM and IEEE T-CSVT. He chaired the IEEE Technical Committee on Multimedia Signal processing. He is a Fellow of the IEEE, a Fellow of the ELLIS Society for the advancement of artificial intelligence in Europe, and has been an IEEE Distinguished Lecturer. He was a co-recipient of the IEEE Geoscience and Remote Sensing Society 2011 Transactions Prize Paper Award, the IEEE ICIP 2015 Best Student Paper Award (as senior author), the IEEE ICIP 2019 Best Paper Award, the IEEE Multimedia 2019 Best Paper Award. He has received an ERC consolidator grant in 2011 and an ERC proof-of-concept grant in 2015.