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

Construction hoist lift car people counting method based on multi-information fusion

A construction elevator and multi-information fusion technology, which is applied in the field of computer vision, can solve problems such as low resolution, image adhesion, and inaccurate statistics of the number of people in the construction elevator cage, and achieve good real-time performance and high algorithm recognition accuracy.

Inactive Publication Date: 2015-04-29
XIAN MAPLE TREE ELECTRONICSAL TECH DEV
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for counting the number of people in the construction elevator car based on multi-information fusion, which solves the complex background, image adhesion and low resolution of the construction elevator car in the prior art, which lead to the number of people counting in the construction elevator cage inaccurate question

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
  • Construction hoist lift car people counting method based on multi-information fusion
  • Construction hoist lift car people counting method based on multi-information fusion
  • Construction hoist lift car people counting method based on multi-information fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0068] The actual collected images of a construction site are as follows: Figure 4 , the red background is also marked in the figure, the number 1 is a yellow helmet, and the number 2 is a red helmet. Taking the red helmet as an example for analysis, Figure 5 Segment the binarized image for the image, Figure 6 It is the final analysis and processing result of the present invention. Depend on Figure 5 It can be seen that after the binary segmentation, the yellow helmet is filtered out first, and there are 6 connected domains after color extraction, among which, connected domain 4 (red door frame), connected domain 5 (red background), connected domain 6 (red background) It can be directly excluded by using the area feature; the aspect ratio of the connected domain 3 is 2, but it is excluded because the duty ratio of 0.63 does not meet the target threshold; the connected domain 1 has a duty ratio of 0.82 and an aspect ratio of 1.81. The number of targets in domain 1 is 2; ...

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 construction hoist lift car people counting method based on multi-information fusion. The method includes the steps that first, GRB color feature threshold values of a safety helmet are acquired; second, segmentation and binarization processing are performed on an image; third, background interference is removed; fourth, mathematical morphology processing is performed on the image; fifth, multiple geometric features in the image are extracted; sixth, the number of people is recognized in a multi-information fusion mode. The method effectively solves the problems caused when the number of people in a construction hoist is counted through an image processing method, is high in algorithm recognition accuracy and good in instantaneity and can meet the requirement of engineering application.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and relates to a method for counting the number of people in a construction elevator car based on multi-information fusion. Background technique [0002] With the advancement of urbanization, there are more and more high-rise buildings, and the use of construction elevators is becoming more and more frequent. In order to avoid group death and group injury accidents, the number of people carried by construction elevators is limited in China, and the safety monitoring system is required to realize the elevator cage. Statistics of the number of people inside. According to the working characteristics of the construction elevator, because the car needs to transport items or staff on different floors of the building, it cannot simply install the safety calculation device outside the door. Therefore, the easiest and feasible method is to use image recognition. There are two main algorithms for ...

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): G06K9/46G06K9/54
CPCG06V20/53
Inventor 杨静李伟
Owner XIAN MAPLE TREE ELECTRONICSAL TECH DEV
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