Human Behavioral Analysis, Monitoring and Simulation
Key Research Topics: Occupancy Detection, Tracking and Extraction, Image segmentation, Foreground extraction, Dynamic Background Extraction, Human Presence, Movement and Behavior Recognition and Analysis, Building Monitoring, Facility Management, Early Defect Detection and Maintenance, Building Occupancy Simulation
Human behavioral monitoring and analysis is a topic of utmost importance in an extensive set of applications, such as energy management, building’s spaces refinement, new building design, facility monitoring, facility management, building and land surveillance, etc.). To this end, our research group is developing new algorithms and novel technologies that combine computer vision, 2D/3D image and video processing and pattern recognition for robust Occupancy Extraction (human presence and movements). Novel algorithms have been developed that cope with multiple-space occupancy extraction in indoor/outdoor environments using privacy-preserving sensors (depth and thermal cameras), whereas the extracted occupancy models can be used for Building Energy Performance Analysis and Simulation and/or for land surveillance.
As occupancy is the main catalyst in Energy Consumption in Buildings, as well as to land surveillance, the research is focused on the human detection algorithms exploiting image segmentation, foreground and background extraction (adaptive dual-band background algorithm, virtual top-view camera, etc.), on the human tracking utilizing a variety of feature extraction techniques (e.g. spatio-temporal height histograms), fuzzy logic (e.g. fuzzy confidence voting) and variations of classical tracking algorithms, such Kalman filtering. Spatio-temporal analysis of all collected data (occupant trajectories, etc.), classification and movement analysis (real-time or offline) techniques lead to the facility management and surveillance applications.
Furthermore, the occupancy data (human trajectories) correlated with information from other sources (RFIDs, energy meters, environmental meters etc.) provide semantic information about the business activities and processes (BPs) occurring in the monitoring environments. As occupancy of an environment is mainly driven by the BPs occurring in it, BPs-based simulation approaches are developed by the research group utilizing methodologies such as Multiple-Module (MuMo), agent-based simulation, etc. These simulations have a variety of applications, since they can be used to the design of new buildings or to the refurbishment of existing buildings. Finally, as the group has expertise in intelligent information visualization, novel Visual Analytics algorithms have been developed for tackling with the analysis of the large amount of Building Performance Simulation.
- D.Ioannidis, D.Tzovaras, C.Malavazos, "Occupancy and Business Modelling", in 9th European conference on product and process modelling (ECPPM 2012), 3rd Workshop on eeBDM, eeBIM, Reykjavik, Iceland, July 2012.
- J. Hreno, M. Skokan, D. Ioannidis, D. Tzovaras, "1st VoCamp Energy Efficiency Modeling", in eeBEMS ICT for sustainable Places Conference, Nice, France, September 2013.
- D.Ioannidis, S.Krinidis, G.Stavropoulos, D.Tzovaras and S.Likothanassis, “Full-Automated Acquisition System for Occupancy and Energy Measurement Data Extraction”, Symposium on Simulation for Architecture and Urban Design (SimAUD) at at the 2014 Spring Simulation Conference (SpringSim'14) in Tampa, FL, USA from April 13-16, 2014 (accepted for publication)
- S.Krinidis, G.Stavropoulos, D.Ioannidis and D.Tzovaras, “A Robust and Real-Time Multi-Space Occupancy Extraction System Exploiting Privacy-Preserving Sensors”, International Symposium on Communications, Control, and Signal Processing (ISCCSP'14), May 21-23, 2014 (accepted for publication)
- Moschonas, Panagiotis; Krinidis, Stelios; Ioannidis, Dimosthenis; Tzovaras, Dimitrios, “Building Performance Simulation using Business Process Modelling”, in 10th European Conference on Product and Process Modelling (ECPPM 2014), 17-19 September 2014, Vienna, Austria (accepted for publication)