Automatic Arm Motion Recognition Based on Radar Micro-Doppler Signature Envelopes

TL;DR

This paper presents a simple, energy-based method for recognizing arm motions using radar micro-Doppler signatures, achieving over 97% accuracy and outperforming some traditional techniques.

Contribution

The study introduces an energy thresholding approach to extract micro-Doppler envelopes and uses a nearest neighbor classifier, offering a simple yet effective alternative to complex models.

Findings

Achieves over 97% classification accuracy for six arm motions.

Outperforms handcrafted feature-based methods and PCA-based techniques.

Comparable to CNN-based methods in recognition performance.

Abstract

In considering human-machine interface (HMI) for smart environment, a simple but effective method is proposed for automatic arm motion recognition with a Doppler radar sensor. Arms, in lieu of hands, have stronger radar cross-section and can be recognized from relatively longer distances. An energy-based thresholding algorithm is applied to the spectrograms to extract the micro-Doppler (MD) signature envelopes. The positive and negative frequency envelopes are concatenated to form a feature vector. The nearest neighbor (NN) classifier with Manhattan distance (L1) is then used to recognize the arm motions. It is shown that this simple method yields classification accuracy above 97 percent for six classes of arm motions. Despite its simplicity, the proposed method is superior to those of handcrafted featurebased classifications and low-dimension representation techniques based on principal component analysis (PCA), and is comparable to convolutional neural network (CNN).