作者: Manuel Martinez , Boris Schauerte , Rainer Stiefelhagen
DOI: 10.1007/978-3-642-40261-6_56
关键词:
摘要: We investigate computer vision methods to monitor Intensive Care Units ICU and assist in sedation delivery accident prevention. propose the use of a Bed Aligned Map BAM analyze patient's body. depth camera localize bed, estimate its surface divide it into 10 cm × cells. Here, represents average cell height over mattress. This depth-based is independent illumination bed positioning, improving consistency between patients. representation allow us develop metrics occupancy, body localization, agitation sleeping position. Experiments with 23 subjects show an accuracy 4-level tests 88% 73% supine fetal positions respectively, while position was recognized 100% 4-class test.