Abstract
Most millimeter-wave radar-based multi-person activity recognition (MPAR) systems are the point cloud-based, which require multiple-input-multiple-output (MIMO) sensors and cause high cost and power consumption of the systems. To realize an MPAR system using only the single-input-single-output (SISO) radar, a novel recognition algorithm is proposed in this paper, which realizes MPAR through a newly designed SVM classification model based on range and Doppler feature maps. A new feature map synthesis method is proposed for efficient generation of training data and a real-time recognition system is built to evaluate the performance of the algorithms. The experimental results for three scenarios show that the proposed recognition algorithm outperforms the conventional point cloud-based algorithms in terms of average recognition accuracy.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
