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

Semi-supervised three-dimensional point cloud gesture key point detection method

A technology of three-dimensional point cloud and detection method, which is applied in the field of pattern recognition, can solve problems such as not necessarily applicable and heavy workload, and achieve the effects of improving practicability, improving recognition accuracy, and optimizing processing methods

Active Publication Date: 2020-02-04
SUN YAT SEN UNIV
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above recognition process often requires a large number of training samples, resulting in a huge workload, and for specific scenarios, the existing labeled samples may not be applicable

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
  • Semi-supervised three-dimensional point cloud gesture key point detection method
  • Semi-supervised three-dimensional point cloud gesture key point detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The accompanying drawings are for illustrative purposes only, and should not be construed as limiting the present invention; in order to better illustrate this embodiment, certain components in the accompanying drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product; for those skilled in the art It is understandable that some well-known structures and descriptions thereof may be omitted in the drawings. The positional relationship described in the drawings is for illustrative purposes only, and should not be construed as limiting the present invention.

[0042] Such as figure 1 As shown, the present invention provides a semi-supervised three-dimensional point cloud gesture key point detection method, comprising the following steps:

[0043] Step 1. Build the RGB-D gesture dataset:

[0044] S11. Build a two-dimensional hand key point detection model;

[0045] S12. Carry out hand key point detection model training based on the...

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 belongs to the field of pattern recognition in the field of computer vision, and particularly relates to a semi-supervised three-dimensional point cloud gesture key point detection method, which can be used for obtaining accurate three-dimensional key point information by utilizing unlabeled data. According to the method for generating the three-dimensional point cloud to recognize the gesture key points based on the TOF module, compared with a two-dimensional image, the recognition precision of the three-dimensional point cloud is greatly improved for a complex scene and an environment with poor light conditions. The processing mode of the point cloud data is optimized, the hand point cloud is smoothed and then sampled, and the precision is higher than that of smoothing after sampling.

Description

technical field [0001] The invention belongs to the field of pattern recognition under the field of computer vision, and more specifically relates to a semi-supervised method for detecting key points of gestures in a three-dimensional point cloud. Background technique [0002] In recent years, with the development of computer technology and the advent of the 5G era, convenient human-computer interaction is the mainstream of future social development. Gesture recognition can be applied to many fields, such as AR, VR, vehicle systems, smart homes, industrial detection etc. From the perspective of data sources, gesture recognition technology can be divided into methods based on data gloves and vision. The initial gesture recognition mainly uses various wearable devices that are in direct contact with the hand for data collection. Through the data gloves containing many sensors, various information required for gesture recognition can be obtained very accurately. In addition, ...

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): G06K9/00G06K9/34G06K9/62G06T7/136
CPCG06T7/136G06T2207/10028G06V40/107G06V10/267G06F18/241
Inventor 何金钰朝红阳
Owner SUN YAT SEN UNIV
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