The　Internet　of　Things　(IoT)　has　become　the　hottest　in　both　the　research　community　and　industry.　Among　them,　Radio　Frequency　Identification　(RFID)　plays　a　key　role　in　IoT.　On　the　RFID　tags　estimation　problem,　most　existing　researches　are　trying　to　identifying　tags＇　ID　rather　than　counting　the　number　of　tags.　But　the　number　of　tags　is　useful　information　in　many　applications　such　as　stock　management　and　traffic　flow　management.　Massive　tags　cause　taking　a　lot　of　cost　and　time　in　the　estimate.　So　an　essential　problem　is　how　to　quickly　and　accurately　estimate　the　number　of　massive　tags.　In　order　to　solve　this　problem,　this　paper　proposes　an　accuracy　and　efficiency　hybrid　scheme　by　decreasing　time　and　space　complexity.　The　results　of　simulation　conducted　to　test　the　effectiveness　of　the　proposed　approach,　which　matches　well　with　the　theoretical　analytical　model.　©　2019　IEEE.