Human body image key point attitude estimation method

A human body image and pose estimation technology, applied in the field of image processing, can solve problems such as large uncertainty and unsatisfactory generation quality, achieve good results, improve detection performance, and experience large effects

Pending Publication Date: 2020-05-15
天津中科智能识别有限公司
View PDF11 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing human body image key point pose estimation generation

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
  • Human body image key point attitude estimation method
  • Human body image key point attitude estimation method
  • Human body image key point attitude estimation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0033] The human body image key point attitude estimation method of the present invention comprises the following steps:

[0034] Step S1, first perform specific data enhancement on the image training set data, and first define all possible data enhancements that can be applied to the image, as shown in the following table (the parameters correspond to the corresponding function parameters of TensorFlow):

[0035]

[0036] The present invention adopts the following specific operations:

[0037]

[0038] In the present invention, the enhanced strategy is defined as a group of disordered K sub-strategies (strategies 1-3).

[0039] During training, one of the K sub-policies is ra...

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 human body image key point posture estimation method, which comprises the following steps of: firstly, sending an image into a feature pyramid network DefectionNet based on cavity convolution for image detection, and only outputting a human body image marked by a bounding box for a human body; cutting into a predetermined format size, and carrying out data enhancement processing to form training data; training a human body image key point posture estimation model of the neural network fused with the hole convolution Dilted conv by utilizing the training data to obtaina deep neural network model capable of performing posture estimation on the human body image to obtain a human body firmware key point image; and performing human body posture estimation by using themodel. Key point generation can be performed on the input image containing the human body, and the human body key points generated in the image after the estimation processing are generated have highprecision so that skeleton geometric information of the human body can be well maintained.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for estimating key point poses of human body images. Background technique [0002] Human body image key point pose estimation refers to modeling and estimating the key points on the human skeleton from an image containing the human body. The key points of the human body are generally defined as: ankle joint, left knee joint, left hip, right hip, left knee Joints, left ankle joint, right ankle joint, upper neck, top of the head, right wrist, left elbow, left shoulder, right shoulder, right elbow, left wrist, and finally through the trained pose estimation model, perform pose estimation on the input image and output is an image containing key points of a human skeleton. [0003] Due to the flexibility of the human body, various postures and shapes will appear, and a small change in any part of the human body will produce a new posture. At the same time, the visib...

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): G06K9/00G06K9/62G06K9/32G06N3/04
CPCG06V40/103G06V10/25G06N3/045G06F18/25G06F18/214
Inventor 孙哲南赫然侯峦轩马鑫
Owner 天津中科智能识别有限公司
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