Florian Grützmacher

Florian Grützmacher

Tel.: +49 381 498 7289
Raum: W1337


  • Energy-efficient online activity recognition
  • Recognition algorithms on heterogeneous multi-core architectures
  • Model-based algorithm distribution


Florian Grützmacher, Johann-Peter Wolff, Albert Hein, Polichronis Lepidis, Rainer Dorsch, Thomas Kirste, Christian Haubelt:
Towards Energy Efficient Sensor Nodes for Online Activity Recognition
In Proceedings of the 43th Annual Conference of the IEEE Industrial Electronics Society (IECON 2017), pp. 8291-8296, Peking, China, November 2017

Albert Hein, Florian Grützmacher, Christian Haubelt, Thomas Kirste:
Fast care – real-time sensor data analysis framework for intelligent assistance systems
In International Journal Current Directions in Biomedical Engineering, Vol. 3, Nr. 2, pp. 743–747, ISSN: 2364-5504, DOI: 10.1515/cdbme-2017-0157, Verlag De Gruyter, Berlin, Deutschland, September 2017

Florian Grützmacher, Benjamin Beichler, Bart Theelen, Christian Haubelt:
Dataflow-based Modeling and Performance Analysis for Online Gesture Recognition
In Proceedings of the Second International Workshop on modeling, analysis and control of complex Cyber-Physical Systems (CPSData'16), pp. 1-8, ISBN: 978-1-5090-1154-4, DOI:10.1109/CPSData.2016.7496423, Wien, Österreich, April 2016

Florian Grützmacher, Johann-Peter Wolff, Christian Haubelt:
Sensor-Based Online Hand Gesture Recognition on Multi-Core DSPs
In Proceedings of the IEEE Symposium on Signal Processing on Graphics Processing Units and Multicores (GlobalSIP), pp. 898-902, ISBN: 978-1-4799-7591-4, DOI:10.1109/GlobalSIP.2015.7418327, Orlando, Florida, USA, Dezember 2015

Florian Grützmacher, Johann-Peter Wolff, Christian Haubelt:
Exploiting Thread-Level Parallelism in Template-Based Gesture Recognition with Dynamic Time Warping
In Proceedings of the International Workshop on Sensor-based Activity Recognition and Interaction (WoAR'15), pp. 6:1 – 6:6, ISBN: 978-1-4503-3454-9, DOI:10.1145/2790044.2790050, Rostock, Deutschland, Juni 2015


  • fast care - Teilvorhaben: Verteilte Inferenz-Algorithmen auf Multi-Sensor-Plattformen