Gesture identification system and method based on Chebyshev feed forward neural network

Abstract

The present invention discloses a gesture identification system based on a Chebyshev feed forward neural network. The system comprises a signal emission module, a signal receiving module and a signal pre-processing module which are connected in order, and an attribute characteristic vector extraction module connected with the signal pre-processing module. The attribute characteristic vector extraction module is connected with a Chebyshev feed forward neural network classifier; the signal emission module is configured to emit ultrasonic signals; the signal receiving module is configured to receive the reflected ultrasonic echo signals; the signal pre-processing module is configured to perform pre-processing of the received ultrasonic echo signals; and the attribute characteristic vector extraction module is configured to extract the attribute characteristic vectors of the gesture motions; and the Chebyshev feed forward neural network classifier is configured to identify the attribute characteristic vectors and output identification results. The gesture identification system and method based on a Chebyshev feed forward neural network are able to perform accurate identification of different users' gestures at different environments.

Description

technical field [0001] The invention relates to the technical field of gesture recognition, in particular to a gesture recognition system and method based on a Chebyshev forward neural network. Background technique [0002] Gesture recognition technology has gained more and more attention in the current era, and more successful products include Microsoft Kinect camera, LeapMotion gesture capture device, etc. Both the Kinect camera and the LeapMotion gesture capture device use computer vision recognition technology to model human body movements or track fingertips to obtain continuous multi-frame images, and then analyze the continuous multi-frame images to obtain gesture recognition results. Using this method to recognize gestures requires a large amount of computing and storage resources in terms of technical implementation, which not only has high cost, high power consumption, and is greatly affected by ambient lighting conditions, but also has hidden dangers of user priva...

AI Technical Summary

Problems solved by technology

However, the application only proposes to calculate the Doppler frequency shift generated during the period from when the ultrasonic signal is emitted by the ultrasonic transmitter to when it is received by the ultrasonic receiver, and convert the Doppler frequency shift into a corresponding Gesture feature signals are recognized by matching with gesture feature signals in the gesture library, but there is no description of how to convert the Doppler frequency shift into corresponding gesture feature signals, and what the so-called corresponding gesture feature signals are. Difficult for technicians to achieve

In addition, due to individual differences in gesture actions, different people may obtain different attribute values ​​when making the same action, while traditional gesture recognition libraries set different thresholds for the attributes of feature vectors, and perform gesture recognition based on the threshold or combination of attributes. Actions are classified. This simple classification recognition method has low recognition accuracy and cannot meet the application requirements.

Images