Gesture recognition method based on deep learning

Abstract

The invention provides a gesture recognition method based on deep learning, and the method comprises an image collection step: collecting a video image, carrying out the video decoding of the video image, and obtaining input video data; a neural network training step: training a neural network model to perform hand position detection, gesture key point position extraction and gesture classification based on gesture key points; a gesture recognition step: carrying out hand position detection and gesture key point position extraction on the input video data by utilizing a neural network model, and carrying out gesture classification on gesture key points; an indication response step: obtaining a gesture operation instruction, and making a real-time response by the system according to the gesture operation instruction; in the neural network training step, at least three neural network models are adopted, and a data set in an online open database and / or a self-sampled and calibrated data set are / is used as input samples to train the neural network models.

Description

technical field [0001] The invention relates to the field of deep learning image recognition, in particular to the realization of human-computer interaction through gesture recognition by using target detection and target tracking methods. Background technique [0002] With the increasing intelligence of cars and roads, the way of processing information is constantly changing, and automotive electronic equipment is booming, and a large number of electronic devices continue to enter the vehicle driving space. Complicated on-board operating equipment not only improves the driving safety and comfort of the vehicle, but also increases the amount and complexity of the driver's operations. [0003] At present, human-computer interaction technology is gradually changing from a computer-centered to a human-centered interaction method, but the current driver control platform for public transportation vehicles often requires more command operations to be completed, and the control scr...

AI Technical Summary

Problems solved by technology

Complex on-board operating equipment not only improves the driving safety and comfort of the vehicle, but also increases the amount and complexity of the driver's operations

[0003] At present, human-computer interaction technology is gradually changing from a computer-centered to a human-centered interaction method, but the current driver control platform for public transportation vehicles often requires more command operations to be completed, and the control screen and buttons The setting is more complicated, and some buttons are arranged under the steering wheel or far away, which is not convenient for drivers to use

Images