We propose in this paper the use of Wavelet transform (WT) to detect human falls using a ceiling mounted Doppler range control radar. The radar senses any motions from falls as well as nonfalls due to the Doppler effect. The wavelet transform is very effective in distinguishing the falls from other activities, making it a promising technique for radar fall detection in non-obtrusive in-home elder care applications. The proposed radar fall detector consists of two stages. The prescreen stage uses the coefficients of wavelet decomposition at a given scale to identify the time locations in which fall activities may have occurred. The classification stage extracts the time-frequency content from the wavelet coefficients at many scales to form a feature vector for fall vs nonfall classification. The selection of different wavelet functions is examined to achieve better performance. Experimental results using the data from the laboratory and real in-home environments validate the promising and robust performance of the proposed detector.
Su, B.Y., Ho, K.C., Rantz, M., & Skubic, M. (2015). Doppler radar fall activity detection using the wavelet transform. IEEE Transactions on Biomedical Engineering, 62(3), 865-875.