ResearchActivity recognition & augmented reality
Gesture Recognition and Motion Analysis
Recognising gestures and analysing human motion with smartwatches, smartphones and other inertial sensors.
Simple arm gestures recorded by a smartwatch or smartphone can become a natural way to control devices or call for help. We study how to recognise gestures and analyse human motion from inertial sensors.
Accelerometer and gyroscope trajectories are compared across repetitions to build recognisers that users can customise with a few examples. The same techniques support motion analysis in exergames, gait-phase recognition with smart insoles and the classification of movement in assisted living.
- Customisable gesture recognisers
- Inertial motion trajectories
- Exergames and gait analysis
Related publications
Selected work from the lab in this area.
A Lightweight Machine Learning Framework for Post-Stroke Gait Abnormality Classification Using Wearable Gyroscope Features
Sensors, 26(10), p. 3143.
Smart Insoles With Textile Capacitive Sensors for Efficient Gait Phase Recognition
IEEE Sensors Journal, 26(1), pp. 1255–1266.
On the Utilization of Commodity Devices for Efficient Gait Asymmetry Detection
In 2024 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES). IEEE, pp. 396–400.
On unifying deep learning and edge computing for human motion analysis in exergames development
Neural Computing and Applications, 34(2), pp. 951–967.
Introducing an Edge-Native Deep Learning Platform for Exergames
In Artificial Intelligence Applications and Innovations. Springer International Publishing, pp. 88–98.
The HealthSign Project
In Proceedings of the 11th PErvasive Technologies Related to Assistive Environments Conference. ACM, pp. 502–506.
An Easily Customized Gesture Recognizer for Assisted Living Using Commodity Mobile Devices
Journal of Healthcare Engineering, 2018, pp. 1–12.
Gesture recognition using symbolic aggregate approximation and dynamic time warping on motion data
In Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for Healthcare. ACM, pp. 342–347.
Human movement detection using attitude and heading reference system
In Proceedings of the 7th International Conference on PErvasive Technologies Related to Assistive Environments. ACM, pp. 1–7.
Natural interaction expressivity modeling and analysis
In Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments. ACM, pp. 1–6.
Extraction of mid-level semantics from gesture videos using a Bayesian network
International Journal of Intelligent Systems Technologies and Applications, 1(3/4), p. 359.