Human body posture feature extracting method based on 3D joint point coordinates

Abstract

The invention discloses a human body posture feature extracting method based on 3D joint point coordinates. Two features are extracted in total, one is the global feature based on the body part location (BPL), the other is the local feature based on the local joint structure (LJS), and the final feature is the feature formed after the two features are fused. The experiment proves that the extracted features can effectively describe human body postures, and the human body postures can be well recognized when the features are applied to a support vector machine classification model.

Description

technical field [0001] The present invention relates to the technical field of human-computer interaction, in particular to a human body posture feature extraction method based on 3D joint point coordinates Background technique [0002] In the field of human-computer interaction, the accurate recognition of human motion is the premise of somatosensory interaction, so it is necessary to construct an effective motion representation method, specifically, to propose an effective human body posture feature extraction method. Traditional human action recognition is based on RGB images, extracting low-level image features to construct high-level semantic feature descriptions, and extracting a feature description for an action. This method requires a large amount of training data when dealing with different perspectives. In addition, the calculation cost of features is usually high, and it is difficult to achieve the application level for real-time interactive systems. [0003] In ...

AI Technical Summary

Problems solved by technology

However, some global features based on joint points cannot distinguish actions well in some cases. Therefore, a more effective human body posture feature extraction method based on joint point coordinates must be sought.

Images