Action recognition method based on skeleton and image data fusion

• Main Authors: SHEN YIXIN, SUN YAN
• Format: Patent
• Language: Chinese; English
• Published: 24.03.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses an action recognition method based on skeleton and image data fusion. A behavior recognition network model based on skeleton data comprises a sampling module guided by coordinate motion information, a multi-scale motion information fusion module and a multi-stream space-time relative Transform model; the behavior recognition network model based on the image data comprises an image cutting module based on joint points and a feature extraction model based on key image blocks; and fusing the prediction probability of each action category obtained by the behavior recognition network model of the skeleton data and the behavior recognition network model based on the image data to obtain the final classification prediction probability of the whole model so as to complete the action recognition process for public safety. According to the invention, the recognition network model fully excavates skeleton motion information, builds dependence for long-distance articulation points, and enhances th