Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Generalization of Fitness Exercise Recognition from Doppler Measurements by Domain-Adaption and Few-Shot Learning

: Fu, Biying; Damer, Naser; Kirchbuchner, Florian; Kuijper, Arjan


Bimbo, A. del ; IEEE Computer Society:
Pattern Recognition. ICPR International Workshops and Challenges. Proceedings. Pt.IV : Virtual Event, January 10-15, 2021
Cham: Springer Nature, 2021 (Lecture Notes in Computer Science 12664)
ISBN: 978-3-030-68798-4 (Print)
ISBN: 978-3-030-68799-1 (Online)
International Conference on Pattern Recognition (ICPR) <25, 2021, Online>
Conference Paper
Fraunhofer IGD ()
human activity recognition; Lead Topic: Individual Health; Research Line: Computer vision (CV); Research Line: Human computer interaction (HCI); mobile sensors; human activity recognition; physical activity monitoring; domain adaptation

In previous works, a mobile application was developed using an unmodified commercial smartphone to recognize whole-body exercises. The working principle was based on the ultrasound Doppler sensing with the device built-in hardware. Applying such a lab environment trained model on realistic application variations causes a significant drop in performance, and thus decimate its applicability. The reason of the reduced performance can be manifold. It could be induced by the user, environment, and device variations in realistic scenarios. Such scenarios are often more complex and diverse, which can be challenging to anticipate in the initial training data. To study and overcome this issue, this paper presents a database with controlled and uncontrolled subsets of fitness exercises. We propose two concepts to utilize small adaption data to successfully improve model generalization in an uncontrolled environment, increasing the recognition accuracy by two to six folds compared to the baseline for different users.