Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Dynamic gesture recognition method

A dynamic gesture and gesture recognition technology, which is applied in the field of intelligent interaction of automobile intelligent cockpit, can solve the problems of excessive convolutional neural network model and difficulty in real-time calculation of convolutional neural network model.

Active Publication Date: 2021-06-08
CHONGQING CHANGAN AUTOMOBILE CO LTD
View PDF16 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem is that the position of the hand in the mask method is also difficult to avoid the related effects of light caused by traditional images. In addition, the convolutional neural network model constructed at the back end of the scheme is too heavy, and it is difficult for the relevant hardware equipment at the cockpit end to calculate the real time. Convolutional Neural Network Model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Dynamic gesture recognition method
  • Dynamic gesture recognition method
  • Dynamic gesture recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0043] see figure 1 , figure 2 and image 3 , the present embodiment shows a dynamic gesture recognition method, comprising the following steps:

[0044] Preliminary gesture judgment stage:

[0045] Step 1) The original hand image is recognized by the YOLO recognition model to obtain the relevant hand region of interest;

[0046] Step 2) Adjust the image size of each hand region of interest to determine the number of hands;

[0047] When it is judged that the number of hands is zero, enter the gesture tolerance process;

[0048] The gesture tolerance process is:

[0049] Judging the current state of the gesture tolerance process, if it is "Yes", the gesture recognition tolerance will gradually decrease;

[0050] If the gesture recognition tolerance drops to zero, set the gesture tolerance process status to "No", set the gesture recognition status to unrecogni...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a dynamic gesture recognition method, which comprises the following steps of: setting a starting gesture judgment stage: judging that a gesture is started when a starting gesture judgment frame is between a starting gesture judgment lower limit frame number and a starting gesture judgment upper limit frame number. In this way, before gesture recognition, judgment of gesture movement conditions is added, gesture shaking in short time and static gestures in long time are prevented from being included in gesture recognition, the recognition efficiency is improved, and meanwhile the recognition precision is improved. When an error exists in recognition of one frame of image, a tolerance redundancy process is set, the gesture recognition tolerance is gradually reduced, and the risk of overall recognition errors caused by the fact that threshold recognition, size adjustment and the like are not passed under the condition that a temporary image is blurred and shakes is avoided.

Description

technical field [0001] The invention belongs to the technical field of intelligent interaction in an automobile intelligent cockpit, and in particular relates to a dynamic gesture recognition method. Background technique [0002] The electrification, networking, sharing, and intelligence of automobiles are the current development trend of the entire automobile, which will greatly improve the sense and mode of current travel. In the process of continuous development of automobiles, the improvement of the shape of the cockpit inside the car, the functions realized by the relevant cockpit, and the human-computer interaction mode of the cockpit are the key parts for the OEM to build a smart cockpit. For a long time, the internal user interaction in the cockpit has been completed by mechanical buttons or touches on the large display screen. The relevant controls in the car are generally only controlled by the front driver. For the rear passengers, there is no actual controllable ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/32G06K9/62G06F3/01
CPCG06F3/017G06V40/28G06V10/25G06F18/24
Inventor 李梦真吴锐杨栋权郑思源
Owner CHONGQING CHANGAN AUTOMOBILE CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com