ResearchActivity recognition & augmented reality

Activity Recognition

Recognising human activity and posture from a single ceiling-mounted fisheye camera.

Activity Recognition

Understanding what a person is doing at home — walking, sitting or lying down — is the basis of many assistive services. We recognise human activity and posture from a single ceiling-mounted fisheye camera that covers a whole room.

The pipeline separates the person from the background, refines the silhouette and estimates their trajectory, then fits a parametric 3D human model using a calibrated fisheye camera model. We have also used Zernike descriptors and convolutional neural networks for pose recognition directly on omni-directional images.

  • Silhouette segmentation in omni-directional video
  • Fisheye camera calibration
  • 3D pose estimation and recognition

Related publications

Selected work from the lab in this area.

2026

Spatio-Temporal Analysis of Handball Players

Katsioulas, K. and Maglogiannis, I. (2026)

Actions from Broadcast Videos Using Deep Learning’, Big Data and Cognitive Computing, 10(4), p. 118.

DOI

2023

Setting a Baseline for Long-Shot Real-Time Player and Ball Detection in Soccer Videos

Moutselos, K. and Maglogiannis, I. (2023)

In 2023 14th International Conference on Information, Intelligence, Systems & Applications (IISA). IEEE, pp. 1–7.

DOI

2022

Automated Posture Analysis for the Assessment of Sports Exercises

Pardos, A., Tziomaka, M., Menychtas, A. and Maglogiannis, I. (2022)

In Proceedings of the 12th Hellenic Conference on Artificial Intelligence. ACM, pp. 1–9.

DOI

2022

Amateur football analytics using computer vision

Mavrogiannis, P. and Maglogiannis, I. (2022)

Neural Computing and Applications, 34(22), pp. 19639–19654.

DOI

2018

Feature Extraction and Pattern Recognition from Fisheye Images in the Spatial Domain

Delibasis, K.K. and Maglogiannis, I. (2018)

In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. SCITEPRESS – Science and Technology Publications, pp. 460–465.

DOI

2018

Pose recognition using convolutional neural networks on omni-directional images

Georgakopoulos, S.V., Kottari, K., Delibasis, K., Plagianakos, V.P. and Maglogiannis, I. (2018)

Neurocomputing, 280, pp. 23–31.

DOI

2016

Silhouette labeling and tracking in calibrated omnidirectional video sequences

Delibasis, K.K., Maglogiannis, I. and Plagianakos, V. (2016)

In Proceedings of the 9th ACM International Conference on PErvasive Technologies Related to Assistive Environments. ACM, pp. 1–7.

DOI

2016

Convolutional Neural Networks for Pose Recognition in Binary Omni-directional Images

Georgakopoulos, S.V., Kottari, K., Delibasis, K., Plagianakos, V.P. and Maglogiannis, I. (2016)

In Artificial Intelligence Applications and Innovations. Springer International Publishing, pp. 106–116.

DOI

2016

Video Analytics for Activity Recognition in Indoor Environments Using Fisheye Cameras

Maglogiannis, I. and Delibasis, K. (2016)

In XIV Mediterranean Conference on Medical and Biological Engineering and Computing 2016. Springer International Publishing, pp. 1105–1110.

DOI

2016

Geodesically-corrected Zernike descriptors for pose recognition in omni-directional images

Delibasis, K.K., Georgakopoulos, S.V., Kottari, K., Plagianakos, V.P. and Maglogiannis, I. (2016)

Integrated Computer-Aided Engineering, 23(2), pp. 185–199.

DOI

2016

A novel robust approach for handling illumination changes in video segmentation

Delibasis, K.K., Goudas, T. and Maglogiannis, I. (2016)

Engineering Applications of Artificial Intelligence, 49, pp. 43–60.

DOI

2015

Joint segmentation and classification of actions using a conditional random field

Kosmopoulos, D. and Maglogiannis, I. (2015)

In Proceedings of the 8th ACM International Conference on PErvasive Technologies Related to Assistive Environments. ACM, pp. 1–4.

DOI

2015

A novel hybrid approach for human silhouette segmentation

Delibasis, K.K., Goudas, T. and Maglogiannis, I. (2015)

In Proceedings of the 8th ACM International Conference on PErvasive Technologies Related to Assistive Environments. ACM, pp. 1–4.

DOI

2014

Multicamera fusion for online analysis of structured processes

Kosmopoulos, D. and Maglogiannis, I. (2014)

In Proceedings of the 7th International Conference on PErvasive Technologies Related to Assistive Environments. ACM, pp. 1–7.

DOI

2014

Fish-Eye Camera Video Processing and Trajectory Estimation Using 3D Human Models

Kottari, K., Delibasis, K., Plagianakos, V. and Maglogiannis, I. (2014)

In Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Springer International Publishing, pp. 385–394.

DOI

2014

Calculation of Complex Zernike Moments with Geodesic Correction for Pose Recognition in Omni-directional Images

Delibasis, K.K., Georgakopoulos, S., Plagianakos, V. and Maglogiannis, I. (2014)

In Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Springer International Publishing, pp. 375–384.

DOI

2014

Activity Recognition in Assistive Environments: The STHENOS Approach

Maglogiannis, I., Delibasis, K., Kosmopoulos, D., Goudas, T. and Doukas, C. (2014)

In Universal Access in Human-Computer Interaction. Aging and Assistive Environments. Springer International Publishing, pp. 525–536.

DOI

2014

Pose Recognition in Indoor Environments using a Fisheye Camera and a Parametric Human Model

Delibasis, K., Plagianakos, V. and Maglogiannis, I. (2014)

In Proceedings of the 9th International Conference on Computer Vision Theory and Applications. SCITEPRESS – Science and Technology Publications, pp. 470–477.

DOI

2014

Refinement of human silhouette segmentation in omni-directional indoor videos

Delibasis, K.K., Plagianakos, V.P. and Maglogiannis, I. (2014)

Computer Vision and Image Understanding, 128, pp. 65–83.

DOI

2013

Human segmentation and pose recognition in fish-eye video for assistive environments

Delibasis, K.K., Plagianakos, V.P., Goudas, T. and Maglogiannis, I. (2013)

In 13th IEEE International Conference on BioInformatics and BioEngineering. IEEE, pp. 1–5.

DOI

2013

Real Time Indoor Robot Localization Using a Stationary Fisheye Camera

Delibasis, K.K., Plagianakos, V.P. and Maglogiannis, I. (2013)

In Artificial Intelligence Applications and Innovations. Springer Berlin Heidelberg, pp. 245–254.

DOI

2013

Fusion of Color and Depth Video for Human Behavior Recognition in an Assistive Environment

Kosmopoulos, D.I., Doliotis, P., Athitsos, V. and Maglogiannis, I. (2013)

In Distributed, Ambient, and Pervasive Interactions. Springer Berlin Heidelberg, pp. 42–51.

DOI

2013

Video Segmentation of Moving Humans for Assistive Environments

Maglogiannis, I., Delibasis, K.K., Goudas, T., Prentza, A., Malamateniou, F. and Vassilacopoulos, G. (2013)

In Informatics, Management and Technology in Healthcare. IOS Press.

DOI

2013

Fisheye camera modeling for human segmentation refinement in indoor videos

Delibasis, K.K., Goudas, T., Plagianakos, V.P. and Maglogiannis, I. (2013)

In Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments. ACM, pp. 1–8.

DOI

2012

Near real-time human silhouette and movement detection in indoor environments using fixed cameras

Christodoulidis, A., Delibasis, K.K. and Maglogiannis, I. (2012)

In Proceedings of the 5th International Conference on PErvasive Technologies Related to Assistive Environments. ACM, pp. 1–7.

DOI

2010

Video-surveillance and context aware system for activity recognition

Kolovou, X. and Maglogiannis, I. (2010)

In Proceedings of the 3rd International Conference on PErvasive Technologies Related to Assistive Environments. ACM, pp. 1–2.

DOI

2025

Intelligent Sampling Consensus for Homography Estimation in Football Videos Using Featureless Unpaired Points

Nousias, G., Delibasis, K.K. and Maglogiannis, I.G. (2025)

IEEE Access, 13, pp. 187843–187857.

DOI

2024

Using synthetic camera poses for camera calibration in soccer videos

Mavrogiannis, P. and Maglogiannis, I. (2024)

Multimedia Tools and Applications, 84(18), pp. 18967–18991.

DOI

2026

CNN-Based Visible Light Positioning via Passive Wall-Distributed Optical Sensors

Delibasis, K.K., Baltadourou, M., Nousias, G., Vaiopoulos, N., Vavoulas, A., Maglogiannis, I. and Sandalidis, H.G. (2026)

In Artificial Intelligence Applications and Innovations. Springer Nature Switzerland, pp. 378–391.

DOI
Browse all publications
Computational Biomedicine Lab
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.