Non-contact emotional recognition method based on dual-mode sensor

Abstract

The invention discloses a non-contact emotional recognition method based on a dual-mode sensor, wherein the non-contact emotional recognition method comprises the following steps: obtaining vital signsignals from echo signals collected by radar sensors, and extracting breathing signals and heartbeat signals from the signals; selecting a human face region from video images collected by video sensors, and obtaining the heartbeat signals and optical flow vector signals according to the human face region; for the heartbeat signals, carrying out heartbeat optimization treatment based on a light intensity method; based on the optical flow vector signals, carrying out body motion optimization treatment on the breathing signals obtained by the radar sensors; for the optimized heartbeat and breathing signals, carrying out characteristic extraction; carrying out characteristic selection on heartbeat characteristics and breathing characteristics, and establishing an emotion recognition model according to the screened characteristics; and according to the emotion recognition model, recognizing the emotion to be recognized. The non-contact measurement not only cannot introduce discomfort, butalso can reduce measurement error, and has the advantages of high recognition accuracy, good robustness and wider applicability.

Description

technical field [0001] The invention belongs to the field of emotion recognition, in particular to a non-contact emotion recognition method based on a dual-mode sensor. Background technique [0002] Emotion is a kind of psychological state that people face in the face of objective things. Different emotional states will have different effects on people's memory, learning and other behaviors. With the improvement of people's quality of life, the health awareness of the whole people has generally increased, and emotional health has become an issue of increasing concern to the public. Bad emotional states will affect the quality of personal life. Especially for some special groups, such as drivers, pilots, soldiers, doctors, etc., the emotional health of such groups may even affect public safety and social stability. Emotions play a very important role in people's daily life, and it is particularly important to identify and study emotions. [0003] Common emotion recognition ...

AI Technical Summary

Problems solved by technology

[0004] Existing studies on emotion recognition use physiological signals in a contact way, which will have a certain impact on the induction of emotions, and the discomfort brought to the subjects will also increase the measurement error

Images