The　purpose　of　the　study　is　to　evaluate　the　quality　of　computer　video　image　quality　under　the　Internet　of　things,　so　as　to　improve　the　user＇s　quality　of　experience.　The　research　method　is　studied　with　MATLAB　2017　software　and　NS2+cygwin　and　MyEvalvid　and　visio　2016　software.　The　result　is　that　the　Logistic　function　can　be　used　to　get　the　subjective　and　an　objective　fitting　map,　Logistic　function　is　better　than　other　function　under　the　field　of　video　image　quality　evaluation　under　the　Internet　of　things.　The　conclusion　is　that　the　method　of　video　image　quality　evaluation　model　under　the　Internet　of　things　is　proposed　in　the　paper　is　more　accurate　and　faster　than　the　other　methods.　Because　coefficient　SROCC,　KROCC,　PLCC,　RMSE　is　close　to　1,　so　the　model　has　good　performance.　Access　control　card　recognition,　vehicle　recognition,　license　plate　recognition,　intelligent　transportation　and　IPTV　and　computer　are　all　applications　of　the　Internet　of　things.　©　2019　IEEE.