Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A Human Recognition Method Based on Head and Shoulders Model

A human body recognition and model technology, applied in the field of target recognition, can solve problems such as large amount of calculation, achieve the effect of reducing calculation amount, enhancing reliability and stability, and reducing recognition time

Inactive Publication Date: 2017-05-17
NANJING UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Wang Chengliang and others used a mixed Gaussian model to extract the human body area, and then identified the human body in this area (Wang Chengliang, Zhou Jia, Huang Sheng. Fast moving human detection based on Gaussian mixture model and PCA-HOG[J]. Computer application research. 2012,29(6):2156-1260.), which greatly improves the recognition rate, but this method still calculates features for the whole human body, and the amount of calculation is still large

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 Human Recognition Method Based on Head and Shoulders Model
  • A Human Recognition Method Based on Head and Shoulders Model
  • A Human Recognition Method Based on Head and Shoulders Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] Such as figure 1 Shown, a kind of human body recognition method based on head shoulder model of the present invention comprises the following steps:

[0015] Step 1. Use the human head and shoulders model to select and train the SVM classifier. The specific process is:

[0016] For pedestrian databases, such as INRIA, MIT and other pedestrian databases, the human head and shoulders model in the pedestrian image is intercepted and saved as a positive sample image, and the size of the positive sample image is unified as M×M; an image of the same size is intercepted from the background image and saved It is a negative sample picture, and the size of the negative sample picture is unified as M×M; the HOG features of the saved positive sample picture and negative sample picture are calculated, and then used to train the SVM classifier.

[0017] The method for calculating the HOG feature and training the SVM classifier can be found in the literature (Navneet Dalal, Bill Trig...

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 provides a body recognizing method based on a head and shoulder model. The HOG character of the head and shoulder model is calculated and an SVM sorter is trained to take participate in sorting; the moving body target is extracted through a Gaussian mixture model, the body target outline is extracted based on the edge extracting algorithm, and the body head and shoulder model is obtained according to the body proportion relation; the HOG character of the head and shoulder model is sorted into a non-body target to be further processed. By means of the body recognizing method, the calculation amount is further reduced, and the recognizing time is shortened while the body recognizing rate is improved.

Description

technical field [0001] The invention belongs to the technical field of target recognition, and in particular relates to a human body recognition method based on a head and shoulders model. Background technique [0002] The HOG feature (Histogram of Oriented Gradients descriptor) was first proposed by Navneet Dalal and Bill Triggs, researchers at the French National Institute of Computer Technology and Control (Chris Stauffer, W E L Grimson. Adaptive background mixture models for real-time tracking[C]\\ Computer Vision and Pattern Recognition, Fort Collins, CO, Jun 23-25, 1999, 2: 1063-6919.). The currently commonly used human body recognition method is the HOG+SVM mode. Dalal extracts human body HOG features from pedestrian database samples such as INRIA and MIT and trains SVM (support vector machine) classifiers to realize human body recognition for static images. M.Kachouane, S.Sahki verified the influence of cell unit and block area size on the human body recognition eff...

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): G06K9/00G06K9/62
Inventor 顾国华刘琳孔筱芳龚文彪李娇徐富元钱惟贤
Owner NANJING UNIV OF SCI & TECH
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
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