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

Method for predicting queuing and waiting duration of passengers in airport security check

A technology of waiting time and passengers, applied in the field of artificial intelligence identification, can solve the problems that cannot be used to estimate the queuing time, is not suitable for the estimation of the estimated duration, and cannot provide immediate feedback, so as to improve the utilization rate of human resources, reduce the cost of human services, The effect of guaranteeing the accuracy of prediction

Pending Publication Date: 2020-03-13
CHENGDU KOALA URAN TECH CO LTD
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such systems typically use a single camera to capture the time of check-in and therefore cannot be used to estimate queue times
Although information related to personnel identification can be obtained, such information is historical information after leaving the team and cannot be immediately fed back to other current systems for decision-making adjustment and optimization
Other face-based systems use multiple sets of cameras to compare the face images collected at the entrance and exit, and estimate the waiting time in line, but they are not perfect, and the statistical error is large. In the actual use process, the effect is not obvious and the effect is weak.
[0006] The existing patent CN105139040B, the patent name is: a queuing state information detection method and its system, although it discloses a method of information monitoring through human body feature recognition, but it is relatively complicated, although other information of the queue can be obtained, and Taking factors such as personnel departure into consideration, although the degree of accuracy has been greatly improved, it is more complicated, the cost of use is extremely high, and the error tolerance rate is low. It is not suitable for the estimation of the estimated duration of passengers in airport security checks.

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 for predicting queuing and waiting duration of passengers in airport security check
  • Method for predicting queuing and waiting duration of passengers in airport security check
  • Method for predicting queuing and waiting duration of passengers in airport security check

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] In this embodiment, a method for estimating the waiting time of passengers at airport security check includes the following steps:

[0044] (1) Judge passengers who are waiting in line for security check;

[0045] (2) Identify the passengers who have been judged successfully, and calculate the number of passengers waiting in line for security check;

[0046] (3) Through big data analysis, get the average security check time of each passenger;

[0047] (4) Calculate the product of the number of people waiting for security check and the average security check time, which is the expected waiting time for passengers at airport security check.

[0048] Among them, the judging process of the passenger waiting in line for security check in step (1) is: dividing the queuing recognition area, and when the passenger stays in the queuing recognition area for more than 10 seconds, it is determined that the passenger is a passenger waiting for security check. The division of the queuing reco...

Embodiment 2

[0058] On the basis of the above-mentioned embodiment, this embodiment further restricts the crowd counting process when the deep learning convolutional neural network used is MCNN: Use 3 different scale convolutional networks to extract the multi-scale features of the image, and use The 1×1 convolution kernel fuses multi-scale features together. Its network structure is like figure 1 Shown. This type of model using multiple networks has many parameters and a large amount of calculations, which makes it impossible for real-time crowd counting predictions. Moreover, the multi-array network cannot extract head features of different scales as described.

[0059] Density map generation

[0060] The data set of crowd counting usually marks the position of the head, and the corresponding crowd density map needs to be generated based on the data of the head position. MCNN proposed an adaptive convolution kernel method to generate the corresponding density map.

[0061] In the process of...

Embodiment 3

[0069] On the basis of the above-mentioned embodiment, this embodiment further restricts that when the convolutional neural network used for deep learning is CP-CNN, the global and local feature information of the image is used to generate the density map of the estimated crowd image. The network structure is as follows figure 2 Shown.

[0070] The top-level sub-network means to extract and classify the features of the entire input image, and expand the classification result into an image with the same height and width as the density feature; the bottom-level sub-network does the same operation on the patch cut out of the original image , Get the local context. Finally, the global and local context features and the density map of the middle part generated from the original image are concatenated in the channel dimension. Through the global density and local density information of the crowd in an image, the entire feature is finally constrained, so that the network can adaptively...

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 for predicting queuing and waiting duration of passengers in airport security check. The method comprises the following steps: 1) judging passengers who are queuing and waiting for security check; 2) identifying the successfully judged passengers, and calculating the number of queuing passengers waiting for security check; 3) obtaining the average security check duration of each passenger through big data analysis; and 4) calculating the product of the number of people waiting for security check and the average security check duration, i.e., the predicted airport security check passenger queuing duration. The invention further provides a specific application according to the method, namely an auxiliary airport passenger security check system, which comprises a calculation and storage module, a data acquisition module and a feedback module for realizing the method. The method for predicting queuing and waiting duration is obvious for places, so that theprediction accuracy can be ensured, passengers can select a team with the least waiting time to queue conveniently, an airport internal security check system is assisted in controlling and managing security check people flow, and the method is suitable for being popularized and applied in the airport security check process.

Description

Technical field [0001] The invention relates to the field of artificial intelligence recognition technology, and specifically refers to a method and application for predicting the waiting time of passengers in airport security check. Background technique [0002] With the growing prosperity of the global economy and trade, the rapid development of the air transportation industry, and the continuous increase in airport passenger flow, airport security checks are facing great challenges. In order to improve the efficiency of airport services, multi-window parallel services or dynamic increase and decrease of windows are currently many airports. Take the means. The question of the trade-off game between passenger flow and human service resources and how to improve the efficiency of passenger flow under the premise of limited service resources require urgent research and optimization. [0003] The number of security checkpoints in the existing airport security check system is inconsis...

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): G06K9/00G06N3/04G06N3/08G06F17/18
CPCG06N3/08G06F17/18G06V20/53G06N3/045
Inventor 赵桐龙炳铖奚兴沈复民
Owner CHENGDU KOALA URAN TECH CO LTD
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