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

3D body posture estimation algorithm for single depth image

A technology of depth image and human body posture, applied in the field of computer vision, can solve the problem of lack of labels and achieve the effect of improving the results of part classification and recognition

Active Publication Date: 2018-06-12
BEIJING UNIV OF TECH
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] 1. Considering that the existing depth image database lacks the pixel-based labels we need, it is not suitable for this experiment. Therefore, we solve the problem of a large amount of data required for the training process by synthesizing the depth image database. In the experiment, we will The depth image is normalized to 225*300

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
  • 3D body posture estimation algorithm for single depth image
  • 3D body posture estimation algorithm for single depth image
  • 3D body posture estimation algorithm for single depth image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The present invention will be described in detail below with reference to the drawings and specific embodiments.

[0061] The technical block diagram of the present invention is shown in Figure 1. We first use the background subtraction method to remove the background of the depth image, and only retain the depth human body information. Then in the training phase, based on the part fusion, the larger parts are divided into smaller parts, and features are extracted, and then the part classification model is trained through random forest, as shown in Figure 1(a); in the testing phase, As shown in Figure 1(b), the image features of the test stage are first extracted, and then the body parts of the image are recognized through the part classification model, and the corresponding parts of the recognition are merged into large parts through the part fusion idea, so as to obtain the fused random forest Preliminary classification results, using the multi-level random forest integ...

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 3D body posture estimation algorithm for a single depth image. The method comprises the steps: proposing an improved feature extraction method, and guiding the depth gradientfeature extraction through the comprehensive utilization of the part size information and distance transformation information, thereby greatly improving the expression capability of the extracted features; proposing an error classification processing mechanism-multistage random forest integration algorithm for removing part wrong classified points in order to solve a wrong classification problemin the random forest part classification, and obtaining a more accurate part recognition result; adaptively removing the interference points in the part again through the improved PDA, a position weight threshold processing method and the recognized part size information, and obtaining a more accurate main direction vector; and finally obtaining a posture estimation result through a human body part configuration relation. The method improves the accuracy of a part classification model, can effectively remove the wrong classified interference points in the recognized part, improves the part recognition accuracy, and finally obtains a more accurate 3D body posture estimation result.

Description

Technical field [0001] The invention relates to the field of computer vision, in particular to a 3D human pose estimation algorithm for a single depth image. Background technique [0002] Image-based human pose estimation is an important research hotspot in the field of computer vision, among which human motion and behavior analysis based on this have been widely used in video surveillance, behavior analysis, and human-computer interaction. Human body pose estimation is a process that can automatically locate each joint position from a video or image through an estimation algorithm, and estimate the human body pose according to the configuration relationship of human body parts. However, in the actual environment, due to the complexity of human body structure and movement posture, different body types, clothing, skin color, etc. are also different, which pose a challenge to accurately predict the quality of posture. The pixels in the depth image record distance information, whic...

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): G06K9/62G06T7/50
CPCG06T7/50G06F18/24133G06F18/254
Inventor 蔡轶珩王雪艳孔欣然马杰李媛媛
Owner BEIJING UNIV OF TECH
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