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

A Deep Learning Hand Detection Method Based on Hand Region Prediction

A detection method and hand technology, applied in computer parts, instruments, biological neural network models, etc., can solve problems such as lack of temporal context information

Active Publication Date: 2021-04-23
UNIV OF SCI & TECH OF CHINA
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention overcomes the lack of temporal context information in single-image hand detection, alleviates the difficulty in detection of human hands caused by motion blur, occlusion, and appearance of new hands, and enhances the accuracy and robustness of the human hand detection system

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
  • A Deep Learning Hand Detection Method Based on Hand Region Prediction
  • A Deep Learning Hand Detection Method Based on Hand Region Prediction
  • A Deep Learning Hand Detection Method Based on Hand Region Prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0044] 1. If figure 1 As shown, train a deep convolutional network, use the trained deep convolutional network to detect the hand (left hand, right hand and overlapping hands) in the first frame of the video stream under complex background, including;

[0045] Obtain hand video stream datasets with complex backgrounds in a variety of different scenes, and manually calibrate the labels in the dataset. The labels include the coordinates of the uppe...

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 deep learning hand detection method based on hand region prediction. The hands are divided into left hand, right hand and overlapping hands. The detection method first trains a deep convolutional network, and uses the trained network to detect complex backgrounds The hand category and area in the first frame of the next video stream; then according to the temporal and spatial correlation of the hand generated by the inertia of the hand motion, the tracking algorithm is used to predict the hand area in the second frame, and combined with the The adjacent frame difference method obtains the hand occlusion area and the newly emerging hand area, and uses the tracking algorithm and the adjacent frame difference method to construct a mask to enhance the interesting part of the image and form a frame image with attention ; Input this image into the trained deep convolutional network for detection, and obtain accurate hand categories and regions; until the last frame, the same detection method as the second frame is adopted to realize hand detection in video streams under complex backgrounds.

Description

technical field [0001] The invention relates to a method for detecting hands in a video sequence under a complex background. The hands are divided into three categories: left hands, right hands and overlapping hands, and belong to the field of video object detection. Background technique [0002] In the existing field of human hand detection based on vision, there are mainly feature detection method, template matching method, image difference method and so on. Most of the hand detection methods use hand skin color [1,2,3,4], palm texture [5,6] and hand shape [2,4,5,6] as detection features. Due to the complex background (the picture contains a large number of skin-like areas), illumination changes, complex and changeable hand shapes, and many occlusion interferences, there has been no particularly stable and mature detection method for hands. With the development of depth cameras (Kinect sensor, Xtion sensor provided by ASUS, etc.), depth information is widely used in hand ...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06V40/107G06V20/41G06N3/045G06F18/214
Inventor 叶中付王瑾薇黄世亮
Owner UNIV OF SCI & TECH OF CHINA
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