Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for detecting human body parts

A technology for detecting devices and components, which is applied in the fields of computer vision and pattern recognition, and can solve the problem of not using the information around the object.

Active Publication Date: 2019-01-08
BEIJING SAMSUNG TELECOM R&D CENT +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The object-based human body part detection method utilizes the intrinsic features and contour structure features of the object, but does not utilize the surrounding information of the object

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
  • Method and device for detecting human body parts
  • Method and device for detecting human body parts
  • Method and device for detecting human body parts

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0024] figure 1 is a flowchart showing the training process of the human body part detection method according to the present invention.

[0025] Such as figure 1 As shown, the training process of the human body part detection method according to the present invention mainly includes four stages: (110) training image data construction; (120) preprocessing; (130) training sample preparation; (140) human body part classifier training. Each of the above stages will be described separately below.

[0026] First, in the training image data construction stage (110), the training image data may be constructed by synthetic image data or real image data.

[0027] Next, in a preprocessing stage (120), the training image data is quantized and background removed. Quantization processing refers to representing raw image data as quantized depth image data for subsequent ...

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

A method and device for detecting human body parts are provided. The method includes: identifying a group of sub-images related to human body parts in an image to be detected; feature, assigning a trust level to the body part of each sub-image in the set of sub-images; sub-images with a trust level above a threshold are merged to detect the position of the body part. The method and device of the present invention can more effectively improve the real-time performance of human body part detection.

Description

technical field [0001] The present invention relates to the fields of computer vision and pattern recognition, and more specifically, to a human body part detection method and device based on multi-part context descriptors. Background technique [0002] Human pose estimation is a basic topic of computer vision technology, which is widely used in various fields such as human-computer interaction, real character animation of games and movies, 3D natural interaction, etc. Due to its academic and commercial value, the research on human pose estimation has become the focus in the field of computer vision in recent years. In particular, human body part detection is a fundamental technique in human pose estimation techniques. Human body part detection technology can provide important observation information for human body pose estimation. [0003] In human body part detection, object detection can generally be divided into two types, namely, object-based human body part detection...

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): G06K9/00G06K9/66
CPCG06T7/194G06V40/103G06V10/28G06V10/267
Inventor 刘荣张帆陈茂林金智渊崔昌圭李基彰
Owner BEIJING SAMSUNG TELECOM R&D CENT