The Stars research team focuses on the design of cognitive vision systems for Activity Recognition. More precisely, we are interested in the real-time semantic interpretation of dynamic scenes observed by video cameras and other sensors. We study long-term spatio-temporal activities performed by agents such as human beings, animals or vehicles in the physical world. The major issue in semantic interpretation of dynamic scenes is to bridge the gap between the subjective interpretation of data and the objective measures provided by sensors. To address this problem Stars develops new techniques in the field of cognitive vision, deep learning and cognitive systems for physical object detection, activity understanding, activity learning, vision system design and evaluation. We focus on two principal application domains: visual surveillance and healthcare monitoring.
We have two main research themes: * Scene understanding for activity recognition: scene understanding aims at solving the complete interpretation problem ranging from low level signal analysis to semantic description of what is happening in the scene viewed by video cameras and possibly other sensors. We work more particularly on perception, understanding and learning. * Software architecture for activity recognition: this research direction consists in studying generic systems for activity recognition and in elaborating a methodology for their design. We wish to ensure genericity, modularity, re-usability, extensibility, dependability and maintainability. We work more particularly on models, platform architecture, and system safeness.
International and industrial relations
Stars collaborates with academics: Univ. Reading (UK), Kingston (UK) , Hamburg,(D), Tainan (Taiwan), USC (Los Angeles, USA), CSTB, CHU Nice, CEA, UCA… as well as industrials FantasticSourcing, ESI, Kontron, Digital Barriers (Keeneo), Ekinnox, Nively… Stars has a strong partnership with CoBTeK and Nice hospital.