Behavior identification method for long-time fast and slow network fusion based on attitude articulation points

Abstract

The invention provides a behavior identification method for long-time fast and slow network fusion based on attitude articulation points. The method comprises the following steps: automatically capturing modes of articulation point structure features and track features in a space and time sequence by utilizing a graph convolutional network; generating an overall space-time feature of each video clip through a feature splicing network model, connecting the overall space-time features in series according to a clip sequence to form the overall space-time features of the video, and fusing the RGBfeatures and the attitude joint point features extracted from the input video at a high level of the convolutional network; and outputting the classification result of the video behavior through a support vector machine classifier in a weighted fusion manner. By extracting the features of the attitude joint points, the data size is greatly reduced, and redundant information is removed. Meanwhile,the space-time features in the long-time-history multi-frame image sequence are extracted to carry out feature compensation, so that the recognition rate and robustness of the video complex behavior are improved.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to a behavior recognition method based on long-term fast and slow network fusion of attitude joint points. Background technique [0002] With the development and application of computer science and artificial intelligence, video analysis technology has risen rapidly and received widespread attention. A core of video analysis is human behavior recognition. The performance of a recognition system largely depends on the ability to extract and utilize relevant information from it. However, extracting such information is difficult due to many complexities such as scale changes, viewpoint changes, and camera motions. Therefore, it becomes crucial to design effective features that can address these challenges while preserving categorical information for behavioral categories. In the form of 2D or 3D coordinates, the dynamic skeletal modality can be naturally repres...

AI Technical Summary

Problems solved by technology

Early research on behavior recognition methods based on deep learning, such as the two-branch convolutional neural network structure laid the foundation for deep learning in the field of behavior recognition, but it is not suitable for the recognition of long videos, and in the extraction of appearance features by behavior recognition methods , the spatial structure characteristics of the behavior are often ignored. The current algorithm is mainly based on the RGB image for feature extraction, which inevitably substitutes redundant information, making the expression of describing the behavior not fine enough.

Images