Dangerous behavior identification method based on deep reinforcement learning

The invention discloses a dangerous behavior recognition method based on deep reinforcement learning, and the method comprises the steps: 1, carrying out the data collection through a camera, obtaining a dangerous behavior video, and generating a fishing rod data set; 2, establishing a fishing rod d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HU PINGLU, YANG SHENGSHI, SUN WEI, LI QIYUE, WANG QI, CHANG WENJING, DING LIJIAN, ZHANG XUESONG, LIU XIN, HOU JIANPING, GUAN SHUZHI, LI WEITAO, DING MEISHUANG
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses a dangerous behavior recognition method based on deep reinforcement learning, and the method comprises the steps: 1, carrying out the data collection through a camera, obtaining a dangerous behavior video, and generating a fishing rod data set; 2, establishing a fishing rod detector for detecting a fishing rod, a fishing rod positioner for accurately positioning the fishing rod, and a posture detector for detecting the posture of a human body; 3, a fishing rod detector is trained through the fishing rod data set, and verification is carried out through testing; 4, performing fishing rod target detection through the trained fishing rod detector to obtain a positioning data set; 5, the positioning data set is sent into the fishing rod positioner for training, and verification is carried out through testing; and 6, the dangerous behavior video is sent into a fishing rod detection and human body action recognition model, and the action of the dangerous behavior is obtained through comprehe