Micro‐Doppler‐based in‐home aided and unaided walking recognition with multiple radar and sonar systems

Abstract

The potential for using micro-Doppler signatures as a basis for distinguishing between aided and unaided gaits is considered in this paper for the purpose of characterizing normal elderly gait and assessment of patient recovery. In particular, five different classes of mobility are considered: normal unaided walking, walking with a limp, walking using a cane or tripod, walking with a walker, and using a wheelchair. This presents a challenging classification problem as the differences in micro-Doppler for these activities can be quite slight. Within this context, the performance of four different radar and sonar systems-a 40 kHz sonar, a 5.8 GHz wireless pulsed Doppler radar mote, a 10 GHz X-band CW radar, and a 24 GHz CW radar-is evaluated using a broad range of features. Performance improvements using feature selection is addressed as well as the impact on performance of sensor placement and potential occlusion due to household objects. Results show that nearly 80% correct classification can be achieved with 10 second observations from the 24 GHz CW radar, while 86% performance can be achieved with 5 second observations of sonar.

Hand Gesture Recognition based on Radar Micro-Doppler Signature Envelopes

“…[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].…”

Toward Unobtrusive In-Home Gait Analysis Based on Radar Micro-Doppler Signatures

“…We analyze two types of limping gait, where one or both legs are not swinging normally. Further, we consider two different synchronization styles between the cane and the legs and their effects on the detection of walking aids; a subject that has gained increased interest in the latest past [25], [26].…”

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

“…The same can be said for the forearm. This is different from hand motions which involve different and flexible motions of the palm and the fingers, and it is certainly distinct from body motions which yield intricate micro-Doppler (MD) signatures [7][8][9][10][11][12][13][14][15].…”