Unsupervised domain adaptation for micro-doppler human motion classification via feature fusion

Lang, Yue, Wang, Qing, Yang, Yang, Hou, Chunping, Huang, Danyang, and Xiang, Wei (2019) Unsupervised domain adaptation for micro-doppler human motion classification via feature fusion. IEEE Geoscience and Remote Sensing Letters, 16 (3). pp. 392-396.

[img] PDF (Published version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1109/LGRS.2018.287377...
3


Abstract

Micro-Doppler-based human motion classification has become a topical area of research recently. However, the current research is limited by the lack of labeled training data. Domain adaptation, namely, the ability to take advantage of knowledge from an available source data set and apply it to an unlabeled target data set, is useful in this situation. A typical strategy for this transfer learning technique is to extract domain-invariant feature representations. In this letter, an unsupervised domain adaptation method for micro-Doppler classification is proposed. Given no available measurement training samples, we creatively utilize the motion capture database as an auxiliary and adapt its interior knowledge to the measurement data set. To achieve domain-invariant features, three types of features are extracted and fused including low-level deep features from the convolutional neural network, empirical features, and statistical features. After feature fusion, a k-nearest neighbor classifier is applied to the measurement data to classify seven human activities. Experimental results show that our approach outperforms several state-of-the-art unsupervised domain adaptation methods. The impact of the output from different convolution layers is further investigated, and ablation studies of the efficacy of each feature are also carried out in this letter.

Item ID: 57545
Item Type: Article (Research - C1)
ISSN: 1545-598X
Keywords: domain adaptation; human motion classification; micro-Doppler
Copyright Information: © 2018 IEEE
Funders: National Science Foundation of China (NSFC)
Projects and Grants: NSFC Grant 61520106002, Grant 61731003, and Grant 61871282
Date Deposited: 20 Mar 2019 07:40
FoR Codes: 09 ENGINEERING > 0906 Electrical and Electronic Engineering > 090609 Signal Processing @ 100%
SEO Codes: 89 INFORMATION AND COMMUNICATION SERVICES > 8999 Other Information and Communication Services > 899999 Information and Communication Services not elsewhere classified @ 100%
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page