Sleep　is　a　very　important　physiological　activity　in　life.　The　quality　of　sleep　directly　affects　people　＇s　health.　At　present,　common　sleep　monitoring　products　from　smart　mattresses　to　smart　bracelets,　although　they　can　monitor　sleep,　must　either　be　laid　on　the　bed　or　must　be　worn　throughout　the　night,　which　does　not　provide　a　good　user　experience.　At　the　same　time,　such　products　mainly　rely　on　the　single　factor　of　physical　activity　to　judge　sleep,　and　many　details　of　the　sleep　process　cannot　be　discussed　in　depth,　such　as　breathing　and　snoring.　In　order　to　solve　the　above　problems,　this　paper　proposes　a　non-contact　human　sleep　monitoring　method,　which　judges　sleep　staging　by　two　aspects　of　body　motion　and　respiration　and　compares　it　with　traditional　wristband　products　to　verify　the　effectiveness　of　the　method.　©　2020　IEEE.