Prediction of a bed-exit motion: Multi-modal sensing approach and incorporation of biomechanical knowledge

This paper aims to answer the following questions: 1) How to detect and predict a bed-exit movement, and 2) How early a bed-exit movement can be predicted before it actually occurs. To achieve the above goals we consider the following sensing modalities for observing the human motion during a bed-exit: RGB images, depth images and radio frequency (RF) sensing. Using the measurements from the aforementioned sensing modalities, we investigate different approaches to infer information on the human motion. Specifically, motion history images are extracted from the RGB-Depth images for motion classification. Depth images complement the analysis with the lost range information of the two dimensional RGB images, which enables three dimensional human motion analysis. The combination of RGB and depth images significantly enhances the performance of motion recognition. A RF sensor, a ultrawideband radar in this research work, is used for performance improvement and for detecting human motion in the cases where image sensors lose the vision.