CN111611951A - Security check people flow real-time monitoring system and method based on machine vision - Google Patents
Security check people flow real-time monitoring system and method based on machine vision Download PDFInfo
- Publication number
- CN111611951A CN111611951A CN202010459551.XA CN202010459551A CN111611951A CN 111611951 A CN111611951 A CN 111611951A CN 202010459551 A CN202010459551 A CN 202010459551A CN 111611951 A CN111611951 A CN 111611951A
- Authority
- CN
- China
- Prior art keywords
- security inspection
- module
- security
- inspection port
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000007689 inspection Methods 0.000 claims abstract description 113
- 238000005286 illumination Methods 0.000 claims abstract description 37
- 238000004458 analytical method Methods 0.000 claims abstract description 25
- 238000000605 extraction Methods 0.000 claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 238000005070 sampling Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 31
- 238000004364 calculation method Methods 0.000 claims description 19
- 239000013598 vector Substances 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a security check people flow real-time monitoring system and method based on machine vision. The system consists of a video acquisition module, a background image preprocessing module, an image semantic analysis module and a strategy generation module, and the method comprises the following steps: collecting a passenger flow volume video of a security inspection port; carrying out frame sampling on the passenger flow video, calculating the illumination intensity and the ambiguity of a sampled video picture, and obtaining a picture with qualified illumination and definition according to a set threshold range; performing target region candidate, feature extraction and classification on the pictures with qualified illumination and definition, and counting passengers identified in the pictures; and comprehensively analyzing the number of the passengers at each identified security inspection port, and giving out a reasonable evacuation suggestion or a security inspection port switching suggestion. The invention effectively helps airport staff to know the flow of people at the security inspection port in time, improves the security inspection efficiency by methods of reasonably untwining, opening and closing the security inspection port and the like, and can save the security inspection time of passengers and optimize the experience of the passengers.
Description
Technical Field
The invention relates to the field of airport people flow security check monitoring, in particular to a security check people flow real-time monitoring system and method based on machine vision.
Background
With the progress of information technology, the domestic aviation and tourism industry is rapidly developed, and passengers who go out by taking airplanes are correspondingly and greatly increased. The problem that follows is whether the relevant supporting facilities and services can be satisfied by the passengers, so that the passengers can be more conveniently provided. In the security inspection link, airport service personnel usually cannot pay attention to the condition that passengers waiting for inspection are at a security inspection port in time, and the conditions that passengers at a certain security inspection port are too many and the switch of the security inspection port is not timely and unreasonable can be caused.
The existing passenger checking guide is manually monitored by airport service personnel, the flexibility and the real-time performance are not good enough, the experience of passenger going out is greatly reduced due to overlong waiting time, and the service quality of an airport is not well affected, so that passengers suspect the service of the airport. If the passenger detection waiting condition can be monitored in real time and the detection waiting and evacuation can be conducted, the airport security check efficiency can be greatly improved, and the travel experience of the passengers can be well improved.
Therefore, a security inspection people flow real-time monitoring system based on machine vision is urgently needed to be provided, the number of people waiting for inspection of passengers at each security inspection port can be monitored in real time, an intelligent reasonable passenger guiding strategy waiting for inspection and a security inspection port switching strategy are provided after comprehensive analysis, manpower labor of airport service personnel is liberated, and passenger traveling experience is improved.
Disclosure of Invention
The invention provides a real-time monitoring system and a real-time monitoring method for the flow of security check people based on machine vision, which at least solve the problems that in the related technology, too many security check port passengers exist, the opening and closing of the security check port are untimely and unreasonable, and the real-time monitoring and the waiting and checking dispersion cannot be realized.
According to one aspect of the invention, a security inspection people flow real-time monitoring system based on machine vision is provided, which comprises: a video acquisition module, a background image preprocessing module, an image semantic analysis module and a strategy generation module, wherein,
the video acquisition module is used for acquiring the passenger flow volume video of the security inspection port and transmitting the passenger flow volume video to the background image preprocessing module;
the background image preprocessing module is used for performing frame sampling on the passenger flow video, calculating the illumination intensity and the ambiguity of a sampled video picture, and transmitting the picture with the illumination and the ambiguity within a set threshold range to the image semantic analysis module;
the image semantic analysis module is used for performing target region candidate, feature extraction and classification on the pictures transmitted by the background image preprocessing system, counting passengers identified in the pictures and transmitting the passengers to the strategy generation module;
the strategy generation module comprehensively analyzes the number of passengers at each security inspection port identified by the image semantic analysis system and provides reasonable evacuation suggestions or switch security inspection port suggestions.
Optionally, the background image preprocessing module includes: the system comprises an image illumination intensity index calculation module, a ambiguity index calculation module and the like, wherein:
the illumination intensity index calculation module is used for reading the picture into a program which is an RGB three-dimensional matrix, and obtaining an illumination intensity index through matrix calculation, wherein an experience threshold value is 30;
the ambiguity and other index calculation module is used for taking a picture reading program as an RGB three-dimensional matrix, calculating the ambiguity index of the picture through a Laplacian operator, and the experience threshold value is 70;
and the background image preprocessing module filters the pictures with unqualified picture quality according to a specified threshold value, and the pictures with qualified quality are backwards transmitted to the image semantic analysis module.
Optionally, the image semantic analysis module includes: target location module, feature extraction module, classifier and counter, wherein:
the target positioning module is used for extracting a target candidate region from the transmitted qualified picture and determining a passenger candidate region image of a certain security check port by combining a gradient histogram with the shape of a security check channel;
the feature extraction module is used for representing the RGB matrix of the candidate area image into a one-dimensional feature vector through a convolutional neural network model;
the classifier carries out secondary classification according to the feature vector output by the feature extraction module and judges whether the image is a human image or not;
and the counter counts all the image candidate frames judged as people, so that the people flow information corresponding to the security inspection port on the current image can be obtained.
Optionally, the policy generation module includes: security check mouth switch strategy module and passenger evacuation strategy module, wherein: .
The security inspection port switching strategy module is used for suggesting a new security inspection port if the number of people at all security inspection ports exceeds a threshold value, and suggesting closing of a plurality of security inspection ports if the number of people at all security inspection ports is lower than the threshold value;
and the passenger evacuation strategy module is used for recommending evacuation of the passengers at the crowded security inspection port if the unbalanced number index at the security inspection port exceeds a threshold value.
Optionally, the value of the RGB three-dimensional matrix is 0 to 255.
According to another aspect of the invention, a security check people flow real-time monitoring method based on machine vision is also provided, which comprises the following steps:
step 1, collecting a passenger flow volume video of a security inspection port;
step 2, carrying out frame sampling on the passenger flow volume video, calculating the illumination intensity and the ambiguity of a sampled video picture, and obtaining a picture with qualified illumination and definition according to a set threshold range;
step 3, performing target area candidate, feature extraction and classification on the pictures with qualified illumination and definition, and counting passengers identified in the pictures;
and 4, comprehensively analyzing the number of passengers at each identified security inspection port, and giving out a reasonable evacuation suggestion or a security inspection port switching suggestion.
Optionally, the step 2 specifically includes:
step 21, taking the picture reading program as an RGB three-dimensional matrix, and obtaining an illumination intensity index through matrix calculation, wherein an empirical threshold value is 30;
step 22, taking the picture reading program as an RGB three-dimensional matrix, and calculating the ambiguity index of the picture through a Laplacian operator, wherein the experience threshold is 70;
and 23, filtering out the pictures with unqualified picture quality according to a specified threshold value to obtain the pictures with qualified illumination and definition.
Optionally, the step 3 includes:
step 31, extracting target candidate regions of the pictures with qualified illumination and definition, and determining passenger candidate region images of a certain security inspection opening by combining a gradient histogram with the shape of a security inspection channel;
step 32, representing the RGB matrix of the candidate area image into a one-dimensional characteristic vector through a convolutional neural network model;
step 33, performing secondary classification according to the feature vectors output by the feature extraction module, and judging whether the images are human images or not;
and step 34, counting all image candidate frames judged as people, and obtaining the people flow information corresponding to the security inspection port on the current image.
Optionally, the step 4 includes:
step 41, if the number of all the security inspection ports exceeds a threshold value, suggesting to newly add the security inspection ports, and if the number of all the security inspection ports is lower than the threshold value, suggesting to close a plurality of security inspection ports;
and step 42, if the unbalanced number index of the people at the security inspection port exceeds a threshold value, recommending evacuation of passengers at the crowded security inspection port.
Optionally, the value of the RGB three-dimensional matrix is 0 to 255.
According to the invention, based on the image data returned by the airport cameras of different positions near the airport security check channel, the computer vision target detection algorithm is combined, the real-time performance and the accuracy are considered, the people flow of each security check port is monitored in real time, the strategy is generated according to the crowd distribution analysis, the airport staff is effectively helped to know the people flow of the security check port in time, the security check efficiency is improved by methods of reasonably relieving and opening and closing the security check port, the passenger security check time can be saved, and the passenger experience is optimized.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a block diagram of a real-time monitoring system for the flow of a security check person based on machine vision according to the present invention;
FIG. 2 is a general flow chart of the security inspection people flow real-time monitoring system based on machine vision according to the present invention;
FIG. 3 is a flow chart of preprocessing video stream data of a security inspection people flow real-time monitoring system based on machine vision;
FIG. 4 is a process of extracting candidate areas from video stream data at a security inspection port of a security inspection people flow real-time monitoring system based on machine vision according to the present invention;
FIG. 5 is an image feature extraction process of a candidate area of a security inspection people flow real-time monitoring system based on machine vision according to the present invention;
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In this embodiment, a system for monitoring a flow of a security check person in real time based on machine vision is provided, as shown in fig. 1, including: a video acquisition module, a background image preprocessing module, an image semantic analysis module and a strategy generation module, wherein,
the video acquisition module is used for acquiring the passenger flow volume video of the security inspection port and transmitting the passenger flow volume video to the background image preprocessing module;
the background image preprocessing module is used for carrying out frame sampling on the passenger flow video, calculating the illumination intensity and the ambiguity of a sampled video picture, and transmitting the picture with the illumination and the ambiguity within a set threshold range to the image semantic analysis module;
the image semantic analysis module is used for performing target region candidate, feature extraction and classification on the pictures transmitted by the background image preprocessing system, counting passengers identified in the pictures and transmitting the passengers to the strategy generation module;
and the strategy generation module is used for comprehensively analyzing the number of passengers at each security inspection port identified by the image semantic analysis system and giving a reasonable evacuation suggestion or a switch security inspection port suggestion.
Wherein, background image preprocessing module includes: the system comprises an image illumination intensity index calculation module, a ambiguity index calculation module and the like, wherein:
the illumination intensity index calculation module is used for reading the picture into a program which is an RGB three-dimensional matrix (the numerical value is 0-255), and obtaining an illumination intensity index through matrix calculation, wherein the experience threshold value is 30;
the ambiguity index calculation module is used for taking an image reading program as an RGB three-dimensional matrix (the numerical value is 0-255), calculating the ambiguity index of the image through a Laplacian operator, and the empirical threshold value is 70;
and the background image preprocessing module filters the pictures with unqualified picture quality according to a specified threshold value, and the pictures with qualified quality are backwards transmitted to the image semantic analysis module.
Wherein, the image semantic analysis module includes: target location module, feature extraction module, classifier and counter, wherein:
the target positioning module is used for extracting a target candidate region from the transmitted qualified picture and determining a passenger candidate region image of a certain security check port by combining a gradient histogram with the shape of a security check channel;
the feature extraction module is used for representing the RGB matrix of the candidate area image into a one-dimensional feature vector through a convolutional neural network model;
the classifier carries out secondary classification according to the feature vector output by the feature extraction module and judges whether the image is a human image or not;
and the counter counts all the image candidate frames judged as people, so that the people flow information corresponding to the security inspection port on the current image can be obtained.
Wherein, the strategy generation module comprises: security check mouth switch strategy module and passenger evacuation strategy module, wherein: .
The security inspection port switching strategy module is used for suggesting a new security inspection port if the number of people at all security inspection ports exceeds a threshold value, and suggesting closing of a plurality of security inspection ports if the number of people at all security inspection ports is lower than the threshold value;
and the passenger evacuation strategy module is used for recommending evacuation of the passengers at the crowded security inspection port if the unbalanced number index at the security inspection port exceeds a threshold value.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in a plurality of processors.
In this embodiment, a method for monitoring a flow of a security inspector in real time based on machine vision is further provided, as shown in fig. 2, including:
step 1, collecting a passenger flow volume video of a security inspection port;
step 2, carrying out frame sampling on the passenger flow volume video, calculating the illumination intensity and the ambiguity of a sampled video picture, and obtaining a picture with qualified illumination and definition according to a set threshold range;
step 3, performing target area candidate, feature extraction and classification on the pictures with qualified illumination and definition, and counting passengers identified in the pictures;
and 4, comprehensively analyzing the number of passengers at each identified security inspection port, and giving out a reasonable evacuation suggestion or a security inspection port switching suggestion.
As shown in fig. 3, the step 2 specifically includes:
step 21, taking the picture reading program as an RGB three-dimensional matrix (the numerical value is 0-255), and obtaining an illumination intensity index through matrix calculation, wherein an empirical threshold value is 30;
step 22, taking the picture reading program as an RGB three-dimensional matrix (the numerical value is 0-255), and calculating the ambiguity index of the picture through a Laplacian operator, wherein the empirical threshold value is 70;
and 23, filtering out the pictures with unqualified picture quality according to a specified threshold value to obtain the pictures with qualified illumination and definition.
Wherein the step 3 comprises:
step 31, as shown in fig. 4, extracting a target candidate region from the picture with qualified illumination and definition, and determining a passenger candidate region image of a certain security inspection opening by using a gradient histogram in combination with the shape of a security inspection channel;
step 32, as shown in fig. 5, characterizing the RGB matrix of the candidate area image into a one-dimensional eigenvector by a convolutional neural network model;
step 33, performing secondary classification according to the feature vectors output by the feature extraction module, and judging whether the images are human images or not;
and step 34, counting all image candidate frames judged as people, and obtaining the people flow information corresponding to the security inspection port on the current image.
Wherein the step 4 comprises: step 41, if the number of all the security inspection ports exceeds a threshold value, suggesting to newly add the security inspection ports, and if the number of all the security inspection ports is lower than the threshold value, suggesting to close a plurality of security inspection ports; and step 42, if the unbalanced number index of the people at the security inspection port exceeds a threshold value, recommending evacuation of passengers at the crowded security inspection port. As shown in the figure, the number of passengers in each security inspection channel is calculated and is transmitted into the strategy generation module, if the number of passengers in each security inspection port exceeds the threshold value, a message is sent to newly open the security inspection port, if the distribution of the passengers in the security inspection port is not balanced, the message is sent to reasonably dredge the crowded security inspection port, and if the number of passengers in the security inspection port is sparse, the message is sent to properly close the security inspection port.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
In order that the description of the embodiments of the invention will be more apparent, reference is now made to the preferred embodiments for illustration.
In terms of hardware, the security inspection people flow real-time monitoring system based on machine vision provided by the preferred embodiment comprises a plurality of cameras which are installed at an airport security inspection port and used for collecting passenger people flow images, and a server or a computer runs a security inspection people flow real-time monitoring program and is required to be equipped with a large-capacity hard disk. The camera used for monitoring the people flow image is connected with the server or the computer through an optical cable or in a wireless mode.
The video acquisition module is installed in the camera of the near different positions of airport security check passageway, gathers the passenger flow volume video of every security check mouth in real time. The image preprocessing module of the security check people flow real-time monitoring program that passenger flow volume video transmission was gone to server or computer, at first the video stream information picture that the image preprocessing module should check video acquisition transmission comes meets the requirements, filters out the picture that does not meet the requirements, and the picture that meets the requirements is transmitted to the image semantic analysis module of security check people flow real-time monitoring program, specifically is: the picture reading program is an RGB three-dimensional matrix (the numerical value is 0-255), the illumination intensity index is obtained through matrix calculation, and the empirical threshold value is 30; the picture reading program is an RGB three-dimensional matrix (the numerical value is 0-255), the ambiguity index of the picture is calculated through a Laplacian operator, the experience threshold value is 70, the picture which does not meet the requirement is filtered through a reasonable threshold value, and the picture which meets the requirement is transmitted to an image semantic analysis module of a security check people flow real-time monitoring program.
The image semantic analysis module performs target area candidate, feature extraction and classification on the transmitted pictures, passengers identified in the pictures are counted, the pictures are transmitted to a strategy generation module of a security inspection people flow real-time monitoring program, the target candidate area extraction is performed on the transmitted qualified pictures, a gradient histogram is used for carrying out frame selection on high-probability targets by combining a security inspection candidate area, the selected candidate frame pictures are input to a convolutional neural network, one-dimensional feature vectors of the candidate areas are obtained through affine transformation, the generated feature vectors are subjected to secondary classification, whether the pictures are passenger images or not is judged, counting is performed if the pictures are the passenger images, and non-passenger images are filtered and not counted. And finally, a strategy generation module of the safety inspection people flow real-time monitoring program comprehensively analyzes the number of passengers at each safety inspection port and provides a reasonable evacuation suggestion or a switch safety inspection port suggestion.
In summary, according to the invention, based on the video image acquired by the security check port camera, the people flow distribution information obtained after the analysis processing is generated, and the reasonable evacuation suggestion or the security check port opening and closing suggestion are generated, so that the airport staff can be effectively helped to know the flow condition of people at the security check port in time, the security check efficiency is improved by the methods of reasonable evacuation, security check port opening and closing and the like, meanwhile, the security check time of passengers can be saved, and the passenger experience is optimized.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The utility model provides a security inspection people flow real-time monitoring system based on machine vision which characterized in that includes: a video acquisition module, a background image preprocessing module, an image semantic analysis module and a strategy generation module, wherein,
the video acquisition module is used for acquiring the passenger flow volume video of the security inspection port and transmitting the passenger flow volume video to the background image preprocessing module;
the background image preprocessing module is used for performing frame sampling on the passenger flow video, calculating the illumination intensity and the ambiguity of a sampled video picture, and transmitting the picture with the illumination and the ambiguity within a set threshold range to the image semantic analysis module;
the image semantic analysis module is used for performing target region candidate, feature extraction and classification on the pictures transmitted by the background image preprocessing system, counting passengers identified in the pictures and transmitting the passengers to the strategy generation module;
the strategy generation module comprehensively analyzes the number of passengers at each security inspection port identified by the image semantic analysis system and provides reasonable evacuation suggestions or switch security inspection port suggestions.
2. The machine vision-based security inspection people flow real-time monitoring system of claim 1, wherein the background image preprocessing module comprises: the system comprises an image illumination intensity index calculation module, a ambiguity index calculation module and the like, wherein:
the illumination intensity index calculation module is used for reading the picture into a program which is an RGB three-dimensional matrix, and obtaining an illumination intensity index through matrix calculation, wherein an experience threshold value is 30;
the ambiguity and other index calculation module is used for taking a picture reading program as an RGB three-dimensional matrix, calculating the ambiguity index of the picture through a Laplacian operator, and the experience threshold value is 70;
and the background image preprocessing module filters the pictures with unqualified picture quality according to a specified threshold value, and the pictures with qualified quality are backwards transmitted to the image semantic analysis module.
3. The machine vision-based security inspection people flow real-time monitoring system of claim 1, wherein the image semantic analysis module comprises: target location module, feature extraction module, classifier and counter, wherein:
the target positioning module is used for extracting a target candidate region from the transmitted qualified picture and determining a passenger candidate region image of a certain security check port by combining a gradient histogram with the shape of a security check channel;
the feature extraction module is used for representing the RGB matrix of the candidate area image into a one-dimensional feature vector through a convolutional neural network model;
the classifier carries out secondary classification according to the feature vector output by the feature extraction module and judges whether the image is a human image or not;
and the counter counts all the image candidate frames judged as people, so that the people flow information corresponding to the security inspection port on the current image can be obtained.
4. The machine-vision-based security inspection people flow real-time monitoring system of claim 1, wherein the policy generation module comprises: security check mouth switch strategy module and passenger evacuation strategy module, wherein: .
The security inspection port switching strategy module is used for suggesting a new security inspection port if the number of people at all security inspection ports exceeds a threshold value, and suggesting closing of a plurality of security inspection ports if the number of people at all security inspection ports is lower than the threshold value;
and the passenger evacuation strategy module is used for recommending evacuation of the passengers at the crowded security inspection port if the unbalanced number index at the security inspection port exceeds a threshold value.
5. The machine-vision-based real-time security inspector flow monitoring system of claim 2, wherein the RGB three-dimensional matrix values are 0-255.
6. A safety inspection people flow real-time monitoring method based on machine vision is characterized by comprising the following steps:
step 1, collecting a passenger flow volume video of a security inspection port;
step 2, carrying out frame sampling on the passenger flow volume video, calculating the illumination intensity and the ambiguity of a sampled video picture, and obtaining a picture with qualified illumination and definition according to a set threshold range;
step 3, performing target area candidate, feature extraction and classification on the pictures with qualified illumination and definition, and counting passengers identified in the pictures;
and 4, comprehensively analyzing the number of passengers at each identified security inspection port, and giving out a reasonable evacuation suggestion or a security inspection port switching suggestion.
7. The machine vision-based security inspection people flow real-time monitoring method according to claim 6, wherein the step 2 specifically comprises:
step 21, taking the picture reading program as an RGB three-dimensional matrix, and obtaining an illumination intensity index through matrix calculation, wherein an empirical threshold value is 30;
step 22, taking the picture reading program as an RGB three-dimensional matrix, and calculating the ambiguity index of the picture through a Laplacian operator, wherein the experience threshold is 70;
and 23, filtering out the pictures with unqualified picture quality according to a specified threshold value to obtain the pictures with qualified illumination and definition.
8. The machine vision-based security inspector flow real-time monitoring method of claim 6, wherein the step 3 comprises:
step 31, extracting target candidate regions of the pictures with qualified illumination and definition, and determining passenger candidate region images of a certain security inspection opening by combining a gradient histogram with the shape of a security inspection channel;
step 32, representing the RGB matrix of the candidate area image into a one-dimensional characteristic vector through a convolutional neural network model;
step 33, performing secondary classification according to the feature vectors output by the feature extraction module, and judging whether the images are human images or not;
and step 34, counting all image candidate frames judged as people, and obtaining the people flow information corresponding to the security inspection port on the current image.
9. The machine vision-based security inspector flow real-time monitoring method of claim 6, wherein the step 4 comprises:
step 41, if the number of all the security inspection ports exceeds a threshold value, suggesting to newly add the security inspection ports, and if the number of all the security inspection ports is lower than the threshold value, suggesting to close a plurality of security inspection ports;
and step 42, if the unbalanced number index of the people at the security inspection port exceeds a threshold value, recommending evacuation of passengers at the crowded security inspection port.
10. The machine-vision-based real-time monitoring method for the flow of the security check people, according to claim 7, is characterized in that the RGB three-dimensional matrix value is 0-255.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010459551.XA CN111611951A (en) | 2020-05-27 | 2020-05-27 | Security check people flow real-time monitoring system and method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010459551.XA CN111611951A (en) | 2020-05-27 | 2020-05-27 | Security check people flow real-time monitoring system and method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111611951A true CN111611951A (en) | 2020-09-01 |
Family
ID=72200475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010459551.XA Pending CN111611951A (en) | 2020-05-27 | 2020-05-27 | Security check people flow real-time monitoring system and method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111611951A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114114448A (en) * | 2021-11-22 | 2022-03-01 | 青岛民航凯亚***集成有限公司 | Early warning system and method for preventing missing detection in airport security inspection |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105763853A (en) * | 2016-04-14 | 2016-07-13 | 北京中电万联科技股份有限公司 | Emergency early warning method for stampede accident in public area |
| US20170286780A1 (en) * | 2016-03-18 | 2017-10-05 | Shenzhen University | Method and system for calculating passenger crowdedness degree |
| CN109272153A (en) * | 2018-09-10 | 2019-01-25 | 合肥巨清信息科技有限公司 | A kind of tourist attraction stream of people early warning system |
| CN110059642A (en) * | 2019-04-23 | 2019-07-26 | 北京海益同展信息科技有限公司 | Facial image screening technique and device |
| CN110879990A (en) * | 2019-11-22 | 2020-03-13 | 成都考拉悠然科技有限公司 | Method for predicting queuing waiting time of security check passenger in airport and application thereof |
| CN111191610A (en) * | 2019-12-31 | 2020-05-22 | 河海大学常州校区 | People flow detection and processing method in video monitoring |
-
2020
- 2020-05-27 CN CN202010459551.XA patent/CN111611951A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170286780A1 (en) * | 2016-03-18 | 2017-10-05 | Shenzhen University | Method and system for calculating passenger crowdedness degree |
| CN105763853A (en) * | 2016-04-14 | 2016-07-13 | 北京中电万联科技股份有限公司 | Emergency early warning method for stampede accident in public area |
| CN109272153A (en) * | 2018-09-10 | 2019-01-25 | 合肥巨清信息科技有限公司 | A kind of tourist attraction stream of people early warning system |
| CN110059642A (en) * | 2019-04-23 | 2019-07-26 | 北京海益同展信息科技有限公司 | Facial image screening technique and device |
| CN110879990A (en) * | 2019-11-22 | 2020-03-13 | 成都考拉悠然科技有限公司 | Method for predicting queuing waiting time of security check passenger in airport and application thereof |
| CN111191610A (en) * | 2019-12-31 | 2020-05-22 | 河海大学常州校区 | People flow detection and processing method in video monitoring |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114114448A (en) * | 2021-11-22 | 2022-03-01 | 青岛民航凯亚***集成有限公司 | Early warning system and method for preventing missing detection in airport security inspection |
| CN114114448B (en) * | 2021-11-22 | 2023-11-24 | 青岛民航凯亚***集成有限公司 | Early warning system and method for airport security check leakage prevention |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110826538A (en) | Abnormal off-duty identification system for electric power business hall | |
| CN112183471A (en) | Automatic detection method and system for standard wearing of epidemic prevention mask of field personnel | |
| CN104504377B (en) | A kind of passenger on public transport degree of crowding identifying system and method | |
| CN108304816B (en) | Identity recognition method and device, storage medium and electronic equipment | |
| EP4012606A1 (en) | Method for estimating and presenting passenger flow, system, and computer readable storage medium | |
| CN107038449B (en) | Method and device for identifying fraudulent user | |
| CN109840982B (en) | Queuing recommendation method and device and computer readable storage medium | |
| CN110647855A (en) | Subway station passenger flow statistical method based on face recognition | |
| CN111353338B (en) | Energy efficiency improvement method based on business hall video monitoring | |
| CN109543542A (en) | A kind of determination method whether particular place personnel dressing standardizes | |
| WO2023179099A1 (en) | Image detection method and apparatus, and device and readable storage medium | |
| CN112132071A (en) | Processing method, device and equipment for identifying traffic jam and storage medium | |
| CN115719475B (en) | Three-stage trackside equipment fault automatic detection method based on deep learning | |
| CN110602446A (en) | Garbage recovery reminding method and system and storage medium | |
| CN115065798A (en) | Big data-based video analysis monitoring system | |
| CN112926483A (en) | Standard cabinet state indicator lamp identification monitoring method, device and system | |
| CN111611951A (en) | Security check people flow real-time monitoring system and method based on machine vision | |
| CN113822110B (en) | Target detection method and device | |
| CN114519879A (en) | Human body data archiving method, device, equipment and storage medium | |
| CN111582278B (en) | Portrait segmentation method and device and electronic equipment | |
| CN114360064B (en) | Office place personnel behavior lightweight target detection method based on deep learning | |
| Zhang et al. | Fault detection of overhead contact systems based on multi-view Faster R-CNN | |
| CN113392770A (en) | Typical violation behavior detection method and system for transformer substation operating personnel | |
| CN114330477A (en) | Power equipment defect detection system and method based on mixed reality equipment | |
| CN112733610A (en) | Power transmission line image recognition detection method based on unmanned aerial vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |