A　corner　event　detection　method　based　on　HMM　(Hidden　Markov　Model)　in　soccer　videos.　Through　analysis　of　the　semantic　structure　of　corner　events,　define　and　extract　six　multi-　modal　semantic　clues　to　describe　shot　sequences,　which　constitute　observation　sequences　as　the　HMM　model　input.　By　the　iterative　training　of　the　HMM　model　and　the　continuous　optimization　of　model　parameters,　construct　the　HMM　model　of　corner　events.　From　two　aspects　of　audio　and　video,　dig　the　inherent　pattern　of　corner　events　and　realize　corner　events　automatic　detection　based　on　HMM　accurately.　The　experimental　results　show　that　the　present　method　achieves　89.6%　recall　and　96.3%　precision,　which　has　the　better　performance.　©　2015　SERSC.