Behavior recognition method based on dual-channel depth separable convolution ofskeleton data

A recognition method and dual-channel technology, applied in biometric recognition, character and pattern recognition, instruments, etc., can solve problems such as insufficient performance, and achieve the effects of improving performance, reducing parameters, and improving accuracy
CN112084934APending Publication Date: 2020-12-15ZHEJIANG UNIV OF TECH
0 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
ZHEJIANG UNIV OF TECH
Publication Date
2020-12-15

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a behavior recognition method based on dual-channel depth separable convolution of skeleton data, and belongs to the technical field of human body posture behavior recognition.The method comprises the following steps: 1, acquiring human body behavior posture joint skeleton point data; 2, processing the skeleton point data to extract behavior space features; 3, constructinga D2SE dual-channel depth separable convolution layer, and extracting behavior time features in a time dimension; 4, superposing the space information on the graph convolution and the time information on a D2SE network layer to extract the space-time information of the attitude behavior; and 5, using a ReLu function to obtain bone movement classification. The GCN network layer and the D2SE network layer are used, spatial image convolution is used for human body posture behavior skeleton data to extract spatial information. Based on double channels, extra complexity is not introduced when theperformance of a convolution framework based on deep separation is improved, and parameters of a convolution layer can be obviously reduced.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of human gesture and behavior recognition, and in particular relates to a gesture and behavior recognition method based on two-channel depth separable convolution of bone point data. Background technique

[0002] Human action recognition is a popular research direction in the field of CV in recent years. Skeleton point action recognition is a branch of human action recognition, which aims to identify the skeleton sequence composed of bone point data over time. Another branch of human action recognition is Processes RGB video sequences.

[0003] Based on the RGB video sequence due to its time sequence, it is generally processed by GRU, 3D convolution, LSTM variants, etc.; however, because RGB data will amplify the influence of factors such as illumination, color, and cover, the robustness of the model is not as good as that of bone data. the fitted model.

[0004] The model based on bone data, because its b...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More