作者: Rainer Stiefelhagen , Manuel Martinez
DOI:
关键词:
摘要: We present a vision based method to estimate the respiration rate of subjects from their chest movements. In contrast alternative approaches, our is fully automated, non-invasive, robust occlusions, and only depends on off-the-shelf hardware. project fixed infrared (IR) dot pattern. The dots are detected using camera with matching IR filter. dots' barycenters sub-pixel precision we track them over 30 seconds sliding window. merge all trajectories Principal Component Analysis(PCA) use Autoregressive (AR) Spectral Analysis respiratory rate. system was evaluated 9 range simulated scenarios an artificial chest.