Video　transmission　services　on　wireless　networks　are　extremely　severely　affected　by　wireless　network　packet　loss.　It　cannot　meet　the　high-quality　requirements　of　real-time　video　services.　Traditional　remedial　measures　adopt　error　recovery　strategies　such　as　Negative-ACKnowledge　character　(NACK),　Forward　Error　Correction　(FEC),　and　Hybrid　Automatic　Re-peat　reQuest　(HARQ),　these　cannot　well　meet　the　increasingly　stringent　needs　of　users　in　time-varying　networks.　This　article　first　analyzes　three　commonly　used　anti-packet　loss　strategies　in　real-time　video　transmission,　and　takes　into　account　the　performance　effects　of　different　strategies　in　the　aspects　of　delay,　quality,　and　transmission　efficiency.　Moreover,　we　propose　an　adaptive　anti-packet　strategy　selection　algorithm　based　on　the　three　schemes.　We　establish　a　unified　system　delay　model　and　adopts　channel　response　measures　in　different　link　delay　performance　environments.　Experimental　results　show　that　the　proposed　algorithm　can　dynamically　select　the　optimal　anti-packet　loss　solution　more　sensitively,　and　optimize　the　data　transmission　efficiency　on　the　premise　of　ensuring　the　video　quality.　©　2021　IEEE.