Human body action recognition method based on a TP-STG framework

• Main Authors: GONG FAMING, GONG WENJUAN, MA YUHUI
• Format: Patent
• Language: Chinese; English
• Published: 19.03.2019
• Subjects: CALCULATING; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a human body action recognition method based on a TP-STG framework, which comprises the following steps: taking video information as input, adding priori knowledge into an SVMclassifier, and providing a posteriori discrimination criterion to remove a non-personnel target; segmenting a personnel target through a target positioning and detection algorithm, outputting the personnel target in a target frame and coordinate information mode, and providing input data for human body key point detection; utilizing an improved posture recognition algorithm to carry out body partpositioning and correlation degree analysis so as to extract all human body key point information and form a key point sequence; a space-time graph is constructed on a key point sequence through an action recognition algorithm, the space-time graph is applied to multi-layer space-time graph convolution operation, action classification is carried out through a Softmax classifier, and human body action recognition in a comp