Countless applications will benefit from the capabilities offered by robots that can autonomously sense, compute, communicate and collaboratively decide. The algorithms running in these autonomous robots need to adapt in response to unknown or dynamic environments and to changes in the assigned task. In this talk I will present recent methods for robots to move and to interact locally to reach coordinated decisions under resource and physical constraints. I will discuss how smart cameras can self-evaluate their performance and improve the quality of the task they are executing through collaboration, adaptively. I will cover several examples of smart cameras for visual and auditory sensing, distributed perception, multi-robot active sensing and distributed decision making.
Andrea Cavallaro is Professor and the Director of the Centre for Intelligent Sensing at Queen Mary University of London, UK. He is also a Turing Fellow at the Alan Turing Institute, the UK National Institute for Data Science and Artificial Intelligence. He received his Ph.D. in Electrical Engineering from the Swiss Federal Institute of Technology (EPFL), Lausanne, in 2002. He was a Research Fellow with British Telecommunications (BT) in 2004/2005 and was awarded the Royal Academy of Engineering teaching Prize in 2007; three student paper awards on target tracking and perceptually sensitive coding at IEEE ICASSP in 2005, 2007 and 2009; and the best paper award at IEEE AVSS 2009. Prof. Cavallaro is Senior Area Editor for the IEEE Transactions on Image Processing; and Associate Editor for the IEEE Transactions on Circuits and Systems for Video Technology and IEEE Multimedia. He is a past Area Editor for the IEEE Signal Processing Magazine (2012-2014) and past Associate Editor for the IEEE Transactions on Image Processing (2011-2015), IEEE Transactions on Signal Processing (2009-2011), IEEE Transactions on Multimedia (2009-2010) and IEEE Signal Processing Magazine (2008-2011). He is vice chair of the IEEE Signal Processing Society, Image, Video, and Multidimensional Signal Processing Technical Committee and an elected member of the IEEE Video Signal Processing and Communication Technical Committee. He is a past elected member of the IEEE Multimedia Signal Processing Technical Committee and of the IEEE Signal Processing Society, Image, Video, and Multidimensional Signal Processing Technical Committee, and chair of its Awards committee. Prof. Cavallaro has published over 250 journal and conference papers, one monograph on Video tracking (2011, Wiley) and three edited books: Multi-camera networks (2009, Elsevier); Analysis, retrieval and delivery of multimedia content (2012, Springer); and Intelligent multimedia surveillance (2013, Springer).
Title: Feature extraction at sensor level in CMOS vision chips
Abstract: Real-time automatic interpretation of the scene requires high-speed detection and classification of objects and events. In applications like autonomous driving, unsupervised surveillance, privacy-aware monitoring, augmented reality in mobile platforms, or robot vision, this needs to be achieved under a restricted power budget. Conventional camera architectures separate sensing from processing. All the pixel values are converted to digital and stored in memory before operating upon them. In embedded systems this energy waste cannot be afforded. CMOS vision chips provide processing at sensor level in order to anticipate extraction and learning of the relevant features of the image. This concurrency of sensing and processing reduces the amount of data to be handled at early stages, increasing power efficiency.
Bio: Ricardo Carmona-Galán is Senior Member of the IEEE. He graduated in Electronic Physics and got a Ph.D. in 2002 in Microelectronics from the University of Seville, Spain. He worked as a Research Assistant at the EECS Department of the University of California, Berkeley and he was Assistant Professor at the School of Engineering of the University of Seville. Since 2005, he is a Tenured Scientist at the Institute of Microelectronics of Seville (CSIC-University of Seville). His main research focus has been on VLSI implementation of concurrent sensor/processor arrays for real time image processing and vision. He has designed several vision chips implementing different focal plane operators for early vision processing. He also held a Postdoc at the University of Notre Dame, Indiana, where he worked in interfaces for CMOS compatible nanostructures for multispectral light sensing. His current research interests lie in the design of low-power smart image sensors, single-photon detection and ToF estimation, and 3-D integrated circuits for autonomous vision systems.
He has coauthored more than 150 journal and conference papers and a book on low-power vision sensors for vision-enabled sensor networks. He is co-inventor of several patents. He has collaborated with start-up companies in Seville (Anafocus) and Berkeley (Eutecus). Ricardo Carmona-Galán is member of the IEEE Circuits and Systems and Solid-State Circuits Societies, the IEEE Sensor Council and the ACM. He has been Associate Editor for IEEE TCAS-I and now is for Springer’s Journal on Real-Time Image Processing. He got a Certificate of Teaching Excellence from the University of Seville. He is Secretary-Elect of the IEEE CASS Technical Committee on Sensory Systems since May 2017. He is the coordinator of a EU H2020 MSCA-funded innovative training network on advanced hardware/software components for integrated/embedded vision systems (ACHIEVE).