Machine Learning
| Hi-index | 0.00 |
Detection of human activity behind barriers such as walls and debris is a topic of relevance for earthquake survivor detection. The preferred sensors are radars since they have the ability to penetrate deep through dielectric barriers. Doppler radars are used to recognize signs of life by recognizing micro-Doppler signatures of human activity, such as arm swinging, breathing, and torso bending. Such movements induce different types of Doppler spectra depending on the manner in which limbs and other body parts move, which can be analyzed by several well-known time-frequency approaches, including the recently-developed empirical mode decomposition (EMD) analysis. We have developed simple models to characterize the above activities, and analyzed the Doppler signals induced using EMD. A comparison of these simulated results with actual measured data using a millimeter-wave CW radar system shows good agreement.