Event　recognition　is　the　process　of　determining　the　event　type　and　state　of　crowd　on　video　under　analysis　by　a　machine　learning　process.　In　order　to　improve　the　accuracy,　this　paper　proposes　a　method　that　using　optical　flow　of　corner　points　and　convolutional　neural　network　to　recognize　crowd　events　on　video.　First,　extract　and　filter　the　FAST　(Features　from　Accelerated　Segment　Test)　corner　points.　Then,　track　those　points　using　Lucas-Kanade　optical　flow　and　get　coordinate　vectors.　Finally,　train　an　improved　convolutional　neural　network　based　on　LeNet　model.　Experiment　on　the　PETS　2009　dataset　using　surveillance　systems　shows　that,　Average　error　rate　for　classifying　the　6　crowd　events　is　0.11.　So　the　method　can　recognize　a　variety　of　defined　crowd　events　and　improve　the　accuracy　of　recognition.