Seaman abnormal behavior detection and identity recognition method based on deep learning

• Main Authors: GAO DING, DU LIBIN, MA YUNGE, LI ZHENGBAO, GAO JIE
• Format: Patent
• Language: Chinese; English
• Published: 05.05.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses a crew abnormal behavior detection and identity recognition method based on deep learning, and belongs to the technical field of computer vision and shipping safety, and the method comprises the steps: obtaining and processing video data, and obtaining a crew abnormal behavior data set and a crew face recognition data set; on the basis of the improved Center Net network model CA-Center Net, a crew abnormal behavior detection model is designed; designing a crew face recognition model based on a face posture evaluation algorithm; and writing the crew abnormal behavior category, the crew position information image, the crew face image and the crew identity information detected by the model into a corresponding database, and notifying the management personnel on the ship to process. The system can accurately detect the abnormal behaviors of the sailors in real time and identify the identity information of the sailors, reduces the potential production safety hazards caused by the abnormal b