Anti-shielding hand key node tracking method

A key node and anti-occlusion technology, applied in the field of computer vision, can solve problems such as untraceable identification and achieve a clear restoration effect

Active Publication Date: 2018-09-14
GUANGZHOU HUANTEK CO LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention provides an anti-occlusion method for tracking key nodes of the hand, which s

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
  • Anti-shielding hand key node tracking method
  • Anti-shielding hand key node tracking method
  • Anti-shielding hand key node tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] An embodiment of the present invention provides an anti-occlusion method for tracking key nodes of a hand.

[0030] Such as Figure 1-6 As shown, an anti-occlusion hand key node tracking method provided by the embodiment of the present invention includes the training of hand key nodes and the identification of hand key nodes; wherein, the training step of the hand key nodes includes :

[0031] S1, arrange the cameras into a three-dimensional panoramic surveillance camera according to a three-dimensional pattern; then manually calibrate the parameters of each camera according to the coordinate positions of each camera; then capture a large number of image samples of hand gestures through the stereo panoramic surveillance camera for subsequent use steps to process.

[0032] S2, establish and initialize the convolutional neural network; manually mark the coordinates of the key nodes of the hand without occlusion in the hand posture image samples obtained from various per...

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 an anti-shielding hand key node tracking method. The method comprises: a panoramic camera is constructed and calibrated, a large number of hand attitude image samples are obtained, the image samples are inputted into a convolutional neural network for image pooling convolutional processing, so that the convolutional neural network is trained and is iteratively optimized; and a common camera captures real-time image information of shielded hand key nodes, real-time image identification is carried out on the trained convolutional neural network after iterative optimization, and dotted line images of hand key nodes and hand skeleton are outputted. According to the invention, the shielded images are captured in real time by the common camera and the shielded hand key nodes are identified and tracked by using the convolutional neural network after iterative optimization. Therefore, a defect that the shielded hand key nodes can not be identified and tracked in the prior art is overcome; and thus the shielded hand key nodes can be identified and tracked in a shielded state.

Description

technical field [0001] The present invention relates to the technical field of computer vision, and more specifically, relates to an anti-occlusion method for tracking key nodes of a hand. Background technique [0002] Among the current techniques for processing image data using deep neural networks, there are relatively few methods for hand motion capture, and even fewer methods for achieving relatively complete hand motion capture. [0003] Chinese patent CN201710471290.1 ​​discloses a somatosensory game interaction method and system based on deep learning and big data. It first collects action video sample data sets, then builds and trains a deep convolutional neural network model offline, and then uses the deep convolutional neural network Network model; its system includes a deep convolutional network offline training module, a real-time human-computer interaction module, and an online optimization module for a deep network model based on big data; it mainly uses ordina...

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): G06K9/00G06N3/04A63F13/213A63F13/40
CPCA63F13/213A63F13/40A63F2300/6045A63F2300/1087G06V40/28G06N3/045
Inventor 李元龙黄昌正周言明陈曦
Owner GUANGZHOU HUANTEK CO LTD
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