Subspace Classification of Human Gait Using Radar Micro-Doppler Signatures

Hand Gesture Recognition based on Radar Micro-Doppler Signature Envelopes

“…Over the past decade, much work has been done in human motion classifications which include daily activities of walking, kneeling, sitting, standing, bending, falling, etc. [6][7][8][9][10][11][12][13][14][15][16][17][18]. Distinguishing among the different motions is viewed as an inter-class classification [6][7][8][9][10][11][12], whereas the intra-class classification amounts to identifying the different members of the same class, e.g., classifying normal and abnormal gaits [13][14][15][16][17][18].…”

“…[6][7][8][9][10][11][12][13][14][15][16][17][18]. Distinguishing among the different motions is viewed as an inter-class classification [6][7][8][9][10][11][12], whereas the intra-class classification amounts to identifying the different members of the same class, e.g., classifying normal and abnormal gaits [13][14][15][16][17][18]. There are two main approaches of human motion classifications, namely those relying on handcrafted features that relate to human motion kinematics [7,8,[13][14][15], and others which are data driven and include low-dimension representations [6,16], frequency-warped cepstral analysis [12], and neural networks [9-11, 17, 18].…”

“…We compare the proposed approach with that based on subspace decomposition methods, namely PCA [6,16] and with the one using compressive sensing methods, namely sparse reconstruction employing Gaussian-windowed Fourier dictionary [19]. In the latter, the classifier was applied to hand gesture data showing signatures comprising rather detached power concentrated time-frequency regions.…”

RF Sensing Technologies for Assisted Daily Living in Healthcare: A Comprehensive Review

“…Activity recognition and estimation of gait parameter are medically essential components of remote health monitoring systems that can improve quality of life, enable personalized treatments, acquire continual medical data to better inform doctors of the patient well-being, reduce health costs, and ensure rapid response to medical emergencies [30].The radar sensing technologies can be used to detect different kinds of gaits by extracting the range, Doppler, amplitude, and phase information [31]. These capabilities enable to detect daily routine activities and classification of human gait [32] such as walking, sitting and standing, squatting, bending down to grab objects, walking while carrying a box and critical events such as fall [33] [34]. These relatively simple actions can potentially be combined to detect macro-activities such as food preparation, getting dressed, or house cleaning, which can be used to monitor the wellbeing of people.…”

Arm Motion Classification Using Time-Series Analysis of the Spectrogram Frequency Envelopes

“…The main novelty of our work is that, to the best of our knowledge, this is the first time where time-series recognition methods are employed to classify arm motions by the maximum instantaneous Doppler frequency features. Commonly applied methods for classification are more suitable for image-like data, such as handcrafted feature-based methods and low-dimension representation techniques based on PCA and CNN [2,4,5,40]. The principal motivation of using time-series recognition methods is to exploit the time relations between the different envelope values for improved classification.…”