Publikation
A Comparison of Few-Shot Classification of Human Movement Trajectories
Lisa Gutzeit
In: Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM. International Conference on Pattern Recognition Applications and Methods (ICPRAM-2021), February 4-6, Pages 243-250, ISBN 978-989-758-486-2, SciTePress, 2/2021.
Zusammenfassung
In the active research area of human action recognition, a lot of different approaches to classify behavior
have been proposed and evaluated. However, evaluations on movement recognition with a limited number of
training examples, also known as Few-shot classification, are rare. In many applications, the generation of
labeled training data is expensive. Manual efforts can be reduced if algorithms are used which give reliable
results on small datasets. In this paper, three recognition methods are compared on gesture and stick-throwing
movements of different complexity performed individually without detailed instructions in experiments in
which the number of the examples used for training is limited. Movements were recorded with markerbased
motion capture systems. Three classification algorithms, the Hidden Markov Model, Long Short-Term
Memory network and k-Nearest Neighbor, are compared on their performance in recognition of these arm
movements. The methods are evaluated regarding accuracy with limited training data, computation time and
generalization to different subjects. The best results regarding training with a small number of examples and
generalization are achieved with LSTM classification. The shortest calculation times are observed with k-NN
classification, which shows also very good classification accuracies on data of low complexity.
Projekte
- TransFit - Flexible Interaktion für Infrastrukturaufbau mittels Teleoperation und direkte Kollaboration und Transfer in Industrie 4.0
- HaLeR - HaLeR - Erkennung von Handlungsabweichungen durch Lernen mit eingeschränkten Rechenressourcen, Teilvorhaben: Evaluation von Lernmethoden zur Erkennung von Handlungsabweichungen mit eingeschränkten Rechenressourcen