Method of restoring three-dimensional human body posture from unmarked monocular image in combination with height map

A technology of human body posture and height map, applied in image analysis, image data processing, instruments, etc., can solve problems such as inaccurate detection

Active Publication Date: 2016-06-01
ZHEJIANG UNIV
View PDF5 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, due to the influence of environmental factors or occlusion in real situations, the features of the image (such as human body contours, limbs or two-dimensional joint points) cannot be accurately detected, so that the recovery of three-dimensional human body posture based on monocular images becomes difficult. more challenging

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 of restoring three-dimensional human body posture from unmarked monocular image in combination with height map
  • Method of restoring three-dimensional human body posture from unmarked monocular image in combination with height map
  • Method of restoring three-dimensional human body posture from unmarked monocular image in combination with height map

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046]The core of the present invention is to add height information (that is, use a height map) in the process of identifying two-dimensional joint points, and then add timing consistency constraints in the process of recovering three-dimensional poses from two-dimensional joint points.

[0047] The following uses an embodiment to describe the implementation of the specific process, and the steps are as follows (see figure 1 ):

[0048] 1) Use the color image dataset and the height image dataset to train a two-dimensional joint point recognition model based on a deep convolutional network; given an image sequence where w and h are the width and height of the image, respectively, and d is the number of channels. The goal of two-dimensional joint point recognition is to use the RGB image and the estimated height image to calculate the position of the two-dimensional joint point on each frame image. The model used for the recognition of two-dimensional joint points is based o...

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 method of restoring a three-dimensional human body posture from an unmarked monocular image in combination with a height map. The method comprises the following steps: 1) a color image and a height image are used for training to obtain a deep convolutional network-based two-dimensional joint point recognition model; 2) a video frame image sequence and a camera parameter are inputted, and a height map corresponding to each frame of image is calculated; 3) the video frame image and the height map obtained in the second step are inputted, and the two-dimensional joint point recognition model obtained through training the first step is used to obtain two-dimensional joint point coordinates of a human body in each frame of image; and 4) the two-dimensional joint point coordinates obtained in the third step are inputted, and the human body three-dimensional posture is restored according to an optimization model. During the two-dimensional joint point recognition process, the color image and the height image are used integrally, and the two-dimensional joint point recognition accuracy is improved; and time sequence consistency constraints are added to the optimization model which can restore the three-dimensional human body posture from the two-dimensional joint point, and thus the restored three-dimensional human body posture is closer to the real human body posture.

Description

technical field [0001] The invention relates to a method for restoring a three-dimensional human body posture, in particular to a method for restoring a three-dimensional human body posture from an unmarked monocular image sequence in combination with a height map. Background technique [0002] Human 3D pose estimation has attracted the attention of many researchers because of its wide application prospects. The existing 3D human pose estimation methods can be mainly divided into methods based on monocular cameras and methods based on multi-view image sequences. Currently, single-purpose methods are receiving increasing attention from the industry. Because although the multi-view method provides more visual data, which can provide richer information for pose estimation, in reality, these data are not always available, especially in applications such as video surveillance and nursing homes. [0003] Restoring 3D human pose from a sequence of monocular images is an inherentl...

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): G06T7/00
Inventor 耿卫东杜宇刘永豪韩菲琳桂义林王镇
Owner ZHEJIANG UNIV
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