Human Activity Classification Based on Micro-Doppler Signatures Separation

• Published in: IEEE transactions on geoscience and remote sensing Vol. 60; pp. 1 - 14
• Main Authors: Qiao, Xingshuai, Amin, Moeness G., Shan, Tao, Zeng, Zhengxin, Tao, Ran
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Classification; Computer architecture; Convolutional principal component analysis; Doppler shift; Doppler sonar; Feature extraction; human activity classification; Human performance; Legged locomotion; micro-Doppler (m-D) signatures; Principal component analysis; Principal components analysis; Radar; Rescue operations; Search and rescue; Search and rescue missions; signal separation; Signatures; Spectrogram; Torso; Training
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2021.3105124

Human activity classification based on micro-Doppler (m-D) signatures finds applications in surveillance, search and rescue operations, and healthcare. In this article, we propose a new approach for human activity classification. This approach deals with the situations of reduced limb movements that could be due to the presence of injury or an individual carrying objects. It applies a preprocessing step to separate human m-D signals of the limbs from the Doppler signal corresponding to the torso. The separated m-D signal is input to a two-layer convolutional principal component analysis network (CPCAN) for feature extraction and motion classification. The CPCAN comprises a simple network architecture for efficient training and implementation, and it automatically learns the highly discriminative features. Experiments involving multiple human subjects performing different activities show a high classification accuracy associated with small arm motions.