A multi-channel physiological signal somatosensory gesture recognition method based on pso-pca-svm

Abstract

The invention discloses a multi-channel physiological signal somatosensory gesture recognition method based on PSO-PCA-SVM, Step1: collect the original sample of human physiological signal; Step2: extract the feature of the physiological signal; Step3: extract key features by principal component analysis; Step4: establish Multi-channel physiological signal somatosensory gesture SVM recognition model; Step5: PSO optimization training multi-channel physiological signal somatosensory gesture PCA and SVM recognition model. The invention provides a multi-channel physiological signal somatosensory gesture recognition method based on PSO-PCA-SVM. After using the method, the recognition accuracy is high, the real-time performance is good, and the recognition robustness is good.

Description

technical field [0001] The invention belongs to the field of gesture recognition, in particular to a multi-channel physiological signal somatosensory gesture recognition method based on PSO-PCA-SVM. Background technique [0002] With the development of the economy and the improvement of the level of science and technology, Tangible Interaction (Tangible Interaction), as a new type of interactive mode rich in behavioral capabilities, is changing people's understanding of traditional product design and exploring new behaviors. Somatosensory interaction is an interactive method that directly uses body movements, voices, eye movements, etc. to interact with surrounding devices or environments, which greatly improves people's quality of life. Only when the interactive system recognizes people's somatosensory gestures can it perform the functions people want to achieve. Therefore, somatosensory gesture recognition technology is an important part of somatosensory interaction, but i...

AI Technical Summary

Problems solved by technology

[0003] The traditional method uses computer vision-based somatosensory recognition technology. However, this method cannot fully meet the needs of somatosensory gesture recognition due to strong privacy intrusion, limited observation range, and easy to be affected by various factors such as lighting conditions and occlusions.

With the development of sensor technology, sensor-based somatosensory gesture recognition is becoming more and more common. For example, kinect is used to obtain depth images and bone information to recognize somatosensory gestures. It has made great progress in gesture recognition, but kinect is still affected by the occlusion environment. influences

Images