Real-time hand tracking method based on depth sensor

A depth sensor and hand technology, applied in the field of human-computer interaction, to achieve the effect of improving real-time performance, improving accuracy, and improving extraction efficiency

Active Publication Date: 2018-11-30
NANJING UNIV OF POSTS & TELECOMM
View PDF9 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Considering the real-time requirements, and the vision-based tracking method is more in line with the real-time requirements, the challenge of this method is to be able to accurately, robustly and efficiently detect and track various hand parameters in motion

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
  • Real-time hand tracking method based on depth sensor
  • Real-time hand tracking method based on depth sensor
  • Real-time hand tracking method based on depth sensor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] This embodiment provides a real-time hand motion tracking method based on a depth sensor, the specific process is as follows figure 1 shown, including the following steps:

[0043] Step 1: Raw data optimization;

[0044] Step 1.1: Occlusion recovery; when the hand is occluded or partially occluded, the real-time data fed back by the depth sensor will shake violently, and the reliability of the data is not high. At this time, it is necessary to predict the position of the joints that are not tracked by the depth sensor. In this paper, the combination of depth data and bone data provided by the depth sensor Kinect is used to repair the occluded hand joints. Due to the length invariance of human bones, the joint chain is composed of elbows, hands, wrists, and fingertips, and the length between each adjacent joint is calculated, that is, the length of the joint is compared with the standard human skeleton as the basis for occluded joint repair. in accordance with. Two po...

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 provides a real-time hand tracking method based on a depth sensor. The method includes: reading depth information, and using forward kinematics to complete the blocking repairing of handbone information through bone data assistance; after the optimized bone joint information is obtained, using a Kalman filtering algorithm to smooth the motion information of the tracked palm; using real-time palm coordinate information and a cascade recursive continuous regional analysis algorithm to extract the hand region from a depth image; using pixel points furthest away from the edge as thebone points of fingers, and adopting a fingertip acquiring scheme using the minimum three-dimensional geodesic distance as the geometrical characteristic and finger bone points as alternative points.By the method, the real-time tracking quality of the disordered motion of the hand without posture limitation, and real-time hand tracking is achieved. Experiment results show that the method can increase tracking accuracy.

Description

technical field [0001] The invention relates to a hand movement tracking method, in particular to a real-time hand tracking method based on a depth sensor, which belongs to the technical field of human-computer interaction. Background technique [0002] With the continuous advancement of computer and sensor technology, Human-Computer Interaction (Human-Computer Interaction) technology has developed to the human-centered Natural User Interface (NUI) interaction stage, which requires machines to communicate with users as naturally as humans. interactive. In daily life, the most common means of communication for human beings is the combination of sight, hearing and speaking, and hands play a vital role in the daily interaction process. Correspondingly, the human-computer interaction technology based on hand movement is also indispensable in the stage of natural user interface interaction, and has broad application prospects. However, since each hand has 27 degrees of freedom ...

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): G06F3/01
CPCG06F3/011G06F3/017
Inventor 陈建新林清宇周亮奚晨煊
Owner NANJING UNIV OF POSTS & TELECOMM
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