Prof. Monique Thonnat
INRIA Sophia Antipolis, (France)
Behavior recognition by video analysis and applications to cognitive disorders diagnosis
Activity recognition in videos is a crucial element of computer vision with significant implications across various fields. As our dependence on visual data grows, comprehending and interpreting human actions in videos becomes essential for advancing technologies in surveillance, healthcare, autonomous systems, and human-computer interaction. Computer vision has made significant progress with the rise of deep learning methods such as convolutional neural networks (CNNs) pushing the boundaries of computer vision. In this talk after a brief presentation of our computer vision research team STARS at Inria in Sophia Antipolis, France, I will focus on how to recognize human activity from videos and their applications for healthcare monitoring. In particular I will present different deep learning techniques for behavior recognition for elderly monitoring, epilepsy diagnosis and autistic child diagnosis.
Prof. Monique Thonnat received her PhD degree in Optics and Signal Processing from University of Marseille III in 1982. In 1983 she joined INRIA (French National Institute for Research in Computer Science and Control) in Sophia Antipolis on French Riviera as Advanced research scientist. In 1991 she became Senior scientist (Directeur de Recherches) in 1995 she created the Orion project, a multi-disciplinary research team at the frontier of computer vision, knowledge-based systems, and software engineering then in 2008 she created the PULSAR research team. Monique Thonnat is author or co-author of 210 scientific papers and co-author of two international patents (in 2000 on pollen recognition with 3D image and in 2008 on seismic 3D image interpretation by cognitive vision techniques). She worked on pattern recognition and artificial intelligence techniques for complex object recognition (as galaxies, zoopanktons or fishes) and on computer vision for the automatic interpretation of 3D stereo data of indoor scenes or of road scenes (Prometheus). She also developed computer vision and knowledge-based systems for automating the construction of image processing systems. She has proposed to use planning and control of execution techniques (program supervision) for the reuse of programs, in particular image processing and video analysis libraries. In the last years she has focused her activity on realtime video analysis and video understanding (3D analysis, event and scenario recognition) and their applications to video surveillance or health and well being. Monique Thonnat has supervised 29 PhD theses. She teaches computer vision and artificial intelligence in universities and in several High Engineer Schools. She is directly involved in the application of her research in the industrial domain; in particular in the framework of 8 European projects (Eureka Project PROMETHEUS, Esprit Project PASSWORDS, Esprit Project AVS-PV, Esprit Project AVS-RTPW, Climate and Environment Project ASTHMA, IST Project ADVISOR, IST Project AVITRACK) and CARETAKER. In 2005 she created in Sophia Antipolis together with other members of the Orion team, KEENEO, a start-up specialised in video surveillance in charge of the industrialization of the videosurveillance platform VSIP developed by the Orion team. Keeneo belongs since 2011 to Digital Barriers group. In 2008 she was awarded the title of Chevalier de la Legion d'Honneur by the French ministry of research. From 2009 to 2013 she was deputy scientific director of INRIA in charge of the Perception, Cognition and Interaction area. She continued her research activity within the new STARS team with a focus on research on activity recognition and applications on elderly monitoring and assistance. From 2013 to 2017 she was Director of Inria Bordeaux Sud Ouest research center. Since August 2017 she is back as senior scientist in STARS team in INRIA at Sophia Antipolis. She focus her research activity on computer vision and machine learning techniques for human behavior analysis and on new evaluation and stimulation methods for neurocognitive disorders care (e.g. Alzheimer disease with CoBtek team from UCA and Nice hospital). Since June 2024 Monique is Emeritus. She belongs to the new Stars team.