English

Activity-dependent resolution adjustment for radar-based human activity recognition

Signal Processing 2025-12-23 v3

Abstract

The rising demand for detecting hazardous situations has led to increased interest in radar-based human activity recognition (HAR). Conventional radar-based HAR methods predominantly rely on micro-Doppler spectrograms for recognition tasks. However, conventional spectrograms employ a fixed resolution regardless of the varying characteristics of human activities, leading to limited representation of micro-Doppler signatures. To address this limitation, we propose a time-frequency domain representation method that adaptively adjusts the resolution based on activity characteristics. This approach adaptively adjusts the spectrogram resolution in a nonlinear manner, emphasizing frequency ranges that vary with activity intensity and are critical to capturing micro-Doppler signatures. We validate the proposed method by training deep learning-based HAR models on datasets generated using our adaptive representation. Experimental results demonstrate that models trained with our method achieve superior recognition accuracy compared to those trained with conventional methods.

Keywords

Cite

@article{arxiv.2411.15057,
  title  = {Activity-dependent resolution adjustment for radar-based human activity recognition},
  author = {Do-Hyun Park and Min-Wook Jeon and Hyoung-Nam Kim},
  journal= {arXiv preprint arXiv:2411.15057},
  year   = {2025}
}

Comments

14 pages, 5 figures

R2 v1 2026-06-28T20:09:12.163Z