Title
Point Transformer-Based Human Activity Recognition Using High-Dimensional Radar Point Clouds
Author
Guo, Zhongyuan (Student TU Delft)
Guendel, Ronny (TU Delft Microwave Sensing, Signals & Systems) 
Yarovoy, Alexander (TU Delft Microwave Sensing, Signals & Systems)
Fioranelli, F. (TU Delft Microwave Sensing, Signals & Systems)
Date
2023
Abstract
Radar-based Human Activity Recognition(HAR) is considered by using snapshots of point clouds. Such point cloudsinterpret 2D images generated by an mm-wave FMCW MIMO radar enriched byincluding Doppler and temporal information. We use the similarity between suchradar data representation and the core of the self-attention concept inartificial intelligence. Three self-attention models (Point Transformer) areinvestigated to classify Activities of Daily Living (ADL). An experimentaldataset collected at TU Delft is used to explore the best combination ofdifferent input features, the effect of a proposed Adaptive ClutterCancellation (ACC) method, and the robustness in a leave-one-subject-outscenario. Results with a macro F1 score in the order of 90% are demonstratedwith the proposed method, including activities that are static postures withlittle associated Doppler.
Subject
Human Activity Recognition
Imaging Radar
Deep Learning
Point Transformer
Activities of Daily Living
To reference this document use:
http://resolver.tudelft.nl/uuid:8b3f2a07-0af3-4089-a6cb-82a4201c848c
DOI
https://doi.org/10.1109/RadarConf2351548.2023.10149679
Publisher
IEEE, Piscataway
Embargo date
2023-12-21
ISBN
978-1-6654-3670-0
Source
Proceedings of the 2023 IEEE Radar Conference (RadarConf23)
Event
2023 IEEE Radar Conference (RadarConf23), 2023-05-01 → 2023-05-05, San Antonio, United States
Bibliographical note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Part of collection
Institutional Repository
Document type
conference paper
Rights
© 2023 Zhongyuan Guo, Ronny Guendel, Alexander Yarovoy, F. Fioranelli