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

Indoor unattended rapid detection method capable of resisting human body posture interference

A technology of human posture and detection method, applied in the direction of neural learning method, instrument, biological neural network model, etc., to achieve effective training, meet real-time and accurate early warning requirements, and good generalization ability

Pending Publication Date: 2021-02-19
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the shortcomings of the existing human body detection algorithm, the present invention provides an indoor unattended rapid detection method that is resistant to human body posture interference

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
  • Indoor unattended rapid detection method capable of resisting human body posture interference
  • Indoor unattended rapid detection method capable of resisting human body posture interference
  • Indoor unattended rapid detection method capable of resisting human body posture interference

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] Indoor unattended rapid detection method against human body posture interference, such as figure 1 shown, including the following steps:

[0032] S1. Data collection stage: collect images and calibrate them to generate original training sets;

[0033] Collect a large number of images of indoor duty personnel from the surveillance video of the actual scene, and use a rectangular frame to calibrate the human body in the image. It is required that the rectangular frame can completely and accurately frame the human body; at the same time, the upper left corner of the rectangular frame is recorded in the image. The location coordinates (x 0, the y 0 ) and the width and height (w, h) of the rectangular frame, the coordinates of the lower right corner of the rectangular frame (x 1 ,y 1 ), where x 1 =x 0 +w,y 1 =y 0 +h; The original training set is obtained through the above operations. The original training set includes the collected pictures and corresponding rectang...

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 an indoor unattended operation rapid detection method capable of resisting human body posture interference. The method comprises the following steps: collecting and calibratingimages, and generating an original training set; preprocessing the images to generate a comprehensive amplification training set; randomly selecting a picture of a non-human-body common object with the category number of n as data to pre-train a multi-classification model for object detection, and obtaining a model parameter initialization value; initializing partial parameters of the human bodydetection model according to the model parameters obtained by pre-training, and changing the classification structure of the human body detection model into binary classification; taking the obtainedcomprehensive amplification training set as an input training set, and training the human body detection model after the classification structure is changed; and obtaining a to-be-detected image, preprocessing the to-be-detected image, training the completed human body detection model, and completing indoor unattended rapid detection resisting human body posture interference. According to the invention, the problem of human body posture interference can be overcome to a great extent.

Description

technical field [0001] The invention relates to the field of computer intelligent safety monitoring, in particular to an indoor unattended rapid detection method that resists human body posture interference. Background technique [0002] With the advent of the era of big data and intelligence, surveillance video, as the core part of the intelligent surveillance system, has been receiving extensive attention. The massive data in the video screen can be analyzed and retrieved at high speed with the help of the powerful computing power of the computer processor, and the key information in the video can be extracted according to the requirements, marked and processed, and then corresponding events and alarm information can be formed according to the processing results. Before the emergence of video analysis technology, the processing of a large number of videos was still mainly screened and checked manually, and its efficiency was relatively low (A. Kolarow et al., "APFel: The i...

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): G06K9/00G06K9/32G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/53G06V10/25G06N3/047G06N3/044G06F18/214
Inventor 黄翰林国盛李刚杨忠明
Owner SOUTH CHINA 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