Human motion recognition based on feature fusion and residual networks
Abstract Addressing the issue of low recognition accuracy in human motion detection when relying on a single feature, a novel approach integrating Frequency Modulated Continuous Wave (FMCW) radar technology with a Residual Network (ResNet) architecture has been proposed. This method commences by cap...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-80783-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850129176847187968 |
|---|---|
| author | Xiaoyu Luo Qiusheng Li |
| author_facet | Xiaoyu Luo Qiusheng Li |
| author_sort | Xiaoyu Luo |
| collection | DOAJ |
| description | Abstract Addressing the issue of low recognition accuracy in human motion detection when relying on a single feature, a novel approach integrating Frequency Modulated Continuous Wave (FMCW) radar technology with a Residual Network (ResNet) architecture has been proposed. This method commences by capturing the echo signals of six distinct human motions using an FMCW radar. These signals undergo preprocessing, followed by the application of a two-dimensional Fourier transform to derive the Range-time Map (RTM) and Doppler-time Map (DTM) representations of the human motions. To enhance the extraction and precise identification of human motion features, the conventional single-channel input structure of convolutional neural networks has been refined. Specifically, the ResNet18 residuals have been upgraded by incorporating Inception V1 modules. Furthermore, the Convolutional Block Attention Module (CBAM) has been integrated to engineer a dual-channel fusion residual network capable of recognizing and classifying human motions effectively. Empirical results demonstrate that the recognition accuracy of human motion detection has been enhanced by 1–4% when employing this dual-feature fusion structure, as compared to single-feature domain recognition. This improvement attests to the robust recognition capabilities of the proposed model. |
| format | Article |
| id | doaj-art-eaa88ba9f91e418797c469828a9b0798 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-eaa88ba9f91e418797c469828a9b07982025-08-20T02:33:05ZengNature PortfolioScientific Reports2045-23222024-11-0114111310.1038/s41598-024-80783-7Human motion recognition based on feature fusion and residual networksXiaoyu Luo0Qiusheng Li1Research Center of Intelligent Control Engineering Technology, Gannan Normal UniversityResearch Center of Intelligent Control Engineering Technology, Gannan Normal UniversityAbstract Addressing the issue of low recognition accuracy in human motion detection when relying on a single feature, a novel approach integrating Frequency Modulated Continuous Wave (FMCW) radar technology with a Residual Network (ResNet) architecture has been proposed. This method commences by capturing the echo signals of six distinct human motions using an FMCW radar. These signals undergo preprocessing, followed by the application of a two-dimensional Fourier transform to derive the Range-time Map (RTM) and Doppler-time Map (DTM) representations of the human motions. To enhance the extraction and precise identification of human motion features, the conventional single-channel input structure of convolutional neural networks has been refined. Specifically, the ResNet18 residuals have been upgraded by incorporating Inception V1 modules. Furthermore, the Convolutional Block Attention Module (CBAM) has been integrated to engineer a dual-channel fusion residual network capable of recognizing and classifying human motions effectively. Empirical results demonstrate that the recognition accuracy of human motion detection has been enhanced by 1–4% when employing this dual-feature fusion structure, as compared to single-feature domain recognition. This improvement attests to the robust recognition capabilities of the proposed model.https://doi.org/10.1038/s41598-024-80783-7Human motion recognitionFrequency modulated continuous wave (FMCW) radarFeature fusionResidual networksCBAM |
| spellingShingle | Xiaoyu Luo Qiusheng Li Human motion recognition based on feature fusion and residual networks Scientific Reports Human motion recognition Frequency modulated continuous wave (FMCW) radar Feature fusion Residual networks CBAM |
| title | Human motion recognition based on feature fusion and residual networks |
| title_full | Human motion recognition based on feature fusion and residual networks |
| title_fullStr | Human motion recognition based on feature fusion and residual networks |
| title_full_unstemmed | Human motion recognition based on feature fusion and residual networks |
| title_short | Human motion recognition based on feature fusion and residual networks |
| title_sort | human motion recognition based on feature fusion and residual networks |
| topic | Human motion recognition Frequency modulated continuous wave (FMCW) radar Feature fusion Residual networks CBAM |
| url | https://doi.org/10.1038/s41598-024-80783-7 |
| work_keys_str_mv | AT xiaoyuluo humanmotionrecognitionbasedonfeaturefusionandresidualnetworks AT qiushengli humanmotionrecognitionbasedonfeaturefusionandresidualnetworks |