Phase-Based Classification for Arm Gesture and Gross-Motor Activities Using Histogram of Oriented Gradients

Micro-Doppler spectrograms are a conventional data representation domain for movement recognition such as Human Activity Recognition (HAR) or gesture detection. However, they present the problem of time-frequency resolution trade-offs of Short-Time Fourier Transform (STFT), which may have limitations due to unambiguous Doppler frequency, and the STFT computation may be onerous in constrained embedded environments. We propose in this paper an alternative classification approach based on the radar phase information directly extracted from high-resolution Range Map (RM). This novel approach does not use the aforementioned micro-Doppler processing, and yet achieves equivalent or even superior classification results. This shows a potential advantage for low-latency, real-time applications, or computationally constrained scenarios. The proposed method exploits the Histogram of Oriented Gradients (HOG) algorithm as an effective feature extraction algorithm, specifically its capability to capture the unique shape and patterns present in the wrapped phase domains, such as their contour intensity and distributions. Validation results consistently above 92 demonstrate the effectiveness of this method on two independent datasets of arm gestures and gross-motor activities. These were classified with three algorithms, namely the Nearest Neighbor (NN), the linear Support Vector Machine (SVM), and the Gaussian SVM classifiers using the proposed phase information. Feature fusion of different data domains, e.g. the modulus of the RM fused with the RM phase information, is also investigated and shows classification improvement specifically for the robustness of activity performances, such as the aspect angle and the speed of performance.

Automated summary

The paper introduces an alternative classification approach based on radar phase information extracted from high-resolution Range Maps, showing equivalent or superior classification results compared to traditional micro-Doppler processing. Additionally, feature fusion of different data domains, such as modulus of the RM with RM phase information, improves classification performance, especially for robust activity performances.