The invention discloses a student sleeping safety
intelligent management method based on video
behavior recognition. The invention relates to the field of
informatization, video analysis and image recognition, in particular to an object behavior standard detection method based on a student sleeping scene environment. According to the behavior specification intelligent judgment and detection method, only aiming at the scenes of student going to
bed, abnormity early warning and checking
processing, in the scenes, students need to leave the dormitory at
fixed time and return to the dormitory at
fixed time, whether going out late, going to early and going to late belong to abnormal conditions, and school managers need to pay attention and process the abnormal conditions. Meanwhile, due to theparticularity and privacy of the dormitory, dormitory managers and school logistics managers needs pay attention to people entering the dormitory, especially strangers to
handle the situation in unconventional
access time. The method comprises the steps that when students in a school fall asleep scene, people in a scene are arranged according to school
sleeping time regulations, a face recognitiontechnology and a video behavior analysis technology are combined, intelligent training is carried out on the basis of correct and wrong behavior specifications in the scene, the sleeping state of students and the state that strangers enter a dormitory are intelligently judged, and abnormal behaviors are combined with violation pictures to be output.