Vision detection system and method based on deep learning and storage medium

A technology of vision detection and deep learning, which is applied in the field of vision detection system based on deep learning, can solve problems such as difficult finger posture and pointing, limited system performance, complex joints, etc., and achieves reduced computational complexity, easy identification, and high judgment accuracy Effect

Active Publication Date: 2021-08-13
四川翼飞视科技有限公司
View PDF24 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such methods are based on traditional algorithms with relatively low accuracy
At the same time, due to the small target and complex joints of the finger, it is particularly difficult to accurately judge the gesture and pointing of the finger, which limits the performance of the system.
[0004] In the field of deep learning, the machine vision model based on the self-attention mechanism that has emerged in recent years has achieved excellent accuracy in many fields. square exponential growth

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
  • Vision detection system and method based on deep learning and storage medium
  • Vision detection system and method based on deep learning and storage medium
  • Vision detection system and method based on deep learning and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] A vision detection system based on deep learning, such as figure 1 As shown in the figure, it includes an identification display module, an image acquisition module, a posture evaluation module, and a result evaluation module; the identification display module is used to display the vision detection mark, and the user uses the arm to make corresponding limb movements; the image acquisition module is used to collect the user The image of the limb movements made by the arm is input to the posture evaluation module; the posture evaluation module is used to detect and collect the key points of the posture of the limb movements made by the arm; the result evaluation module judges the user's arm state according to the key points of the user's arm posture, Then, it is judged whether the user's action is consistent with the vision detection mark, and the detection result is output.

[0037] Further, the result evaluation module determines the state of the arm according to the r...

Embodiment 2

[0040] This embodiment is optimized on the basis of Embodiment 1, such as figure 2 As shown, the posture evaluation module includes a target detection sub-module and a posture detection sub-module, the target detection sub-module is used to detect the coordinate frame of the human body; the input of the posture detection sub-module is the image area corresponding to the human body, and detects the human body. The key points of the attitude, and output the coordinate information of the key points of the attitude.

[0041] Further, as image 3 As shown, the posture detection sub-module includes several alternate local attention units and result output units arranged in sequence from front to back, and the alternate local attention units are used to extract posture feature information and generate a feature map; The result output unit is used to upsample the feature map to improve the resolution of the feature map, and generate the final pose key point coordinate information fr...

Embodiment 3

[0048] A vision detection system based on deep learning, such as figure 1 As shown in the figure, it includes an identification display module, an image acquisition module, a posture evaluation module, and a result evaluation module; the identification display module is used to display the vision detection mark, and the user uses the arm to make corresponding limb movements; the image acquisition module is used to collect the user The image of the limb movements made by the arm is input to the posture evaluation module; the posture evaluation module is used to detect and collect the key points of the posture of the limb movements made by the arm; the result evaluation module judges the user's arm state according to the key points of the user's arm posture, Then, it is judged whether the user's action is consistent with the vision detection mark, and the detection result is output.

[0049] Further, as figure 2 As shown, the posture evaluation module includes a target detecti...

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 vision detection system and method based on deep learning and a storage medium. The vision detection system comprises an identification display module, an image acquisition module, a posture evaluation module and a result evaluation module. The identification display module is used for vision detection identification and a user makes corresponding limb actions through arms; the image acquisition module is used for acquiring an image of a limb action made by arms of a user and inputting the image to the posture evaluation module; the posture evaluation module is used for detecting and collecting posture key points of the limb action made by the arms; and the result evaluation module judges an arm state of the user according to the arm posture key points of the user, further judges whether the action of the user conforms to the vision detection identification or not, and outputs a detection result. The result evaluation module judges whether directions of the arm postures of the user are consistent or not according to the directions of the arm postures of the users. Compared with finger directions, targets of the arm postures are larger and easier to identify, and detection precision is higher.

Description

technical field [0001] The invention belongs to the technical field of vision detection, and in particular relates to a vision detection system, method and storage medium based on deep learning. Background technique [0002] With the advancement of science and technology and the popularity of information technology, people use mobile phones, computers, televisions and other high-tech devices for more and more time, and the risk of visual impairment caused by this also increases, especially for young people. Can not be ignored. Common vision tests are generally performed in professional institutions and are performed manually, and users cannot perform independent operations. [0003] At the same time, some intelligent vision detection systems, such as the intelligent vision detector based on image analysis disclosed in the patent CN106778597A, use the traditional algorithm detector in the field of machine vision to judge the gesture and pointing of the finger, and build the ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): A61B3/032A61B3/00G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCA61B3/032A61B3/0016G06N3/08G06V40/113G06V10/44G06N3/045G06F18/241
Inventor 桑高丽卢丽闫超韩强陶陶
Owner 四川翼飞视科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap