Detecting socially occupied spaces with depth cameras: evaluating location and body orientation as relevant social features
Studying people’s movement and social interaction in indoor spaces requires detecting where and when interactions happen. So far, sensor-based systems for detecting interactions focused on identifying physically occupied spaces, i.e., spaces determined by the presence of physically measurable objects. In contrast, our goal is to detect socially occupied spaces, i.e., spaces occupied not by people but by social interactions that they support. We focus on detecting F-Formations, a representation of the space structure between two or more potentially interacting building occupants. We propose a system that uses infrared depth cameras to anonymously derivate body orientation from skeleton joints. The orientation of the shoulders and spine, together with the face orientation and the temporal information on occupants' walking trajectories, is used to calculate the body orientation from which socially occupied space is identified. In a user study evaluating the system, we collected data in 32 patterns within two distinct cases: individuals and dyads and evaluated the system’s accuracy. The evaluation included the intended orientation and the socially accepted orientation. Experimental results show accuracy well above 90% for assessing the socially-relevant body orientation. Our algorithm to detect body orientation contributes to the automated detection of socially occupied spaces. The system shows potential to detect more complex social structures. This would have an impact on research areas that study group interactions within complex indoor settings.
📆 A month ago, I had the honor to start the presentations at the IPIN2021 Conference in the group for pedestrian and monitoring research, presenting our work on modeling Human Social Behavior with depth cameras. It was a great experience in which we had the opportunity to exchange ideas, projects, and smiles with people from all over the world.
I presented our paper “Detecting Socially Occupied Spaces with Depth Cameras: evaluating body orientation and navigation as relevant social features” at the IPIN 2021 Conference on Indoor Positioning and Navigation! This paper is part of my research in analyzing social human behavior in trajectories during my phd in Geoinformatics at the University of Münster!
📢 The conference had four tutorials, four keynote speakers, including Peiying Zhu , Michael Gould, Malcom Bain and Christos Laoudias. Additionally, several Full and Work-In-Progress Papers related to indoor positioning techniques and tools ranging from magnetic field base odometry, depthcameras, smarthphone location, wifi printing, LoRa, TDoA, with several algorithms' implementation, and much more was available!
👏🏻 Big applause for the local organizers Joaquín Torres-Sospedra, Antoni Pérez-Navarro, Raul Montoliu Colas, and Universitat Oberta de Catalunya (UOC), Universitat Jaume I, iNIT (Institute of new imaging technologies), Ubik Geospatial Solutions, and to all the committee for their VERY detailed organization to enjoy this academic event in one of the safest environment I have been so far with their implementation of health measurements.
✨ Thank you to the sponsors for their support in this mega event! Huawei, MDPI Nexus Geographics , IEEE ,IEEE Instrumentation & Measurement Society & Sensors MDPI. As a previous conference organizer, I know YOUR contributions make a BIG impact.