CN113570644B - Airport passenger positioning method, airport passenger positioning device, electronic equipment and medium - Google Patents
Airport passenger positioning method, airport passenger positioning device, electronic equipment and medium Download PDFInfo
- Publication number
- CN113570644B CN113570644B CN202111132797.7A CN202111132797A CN113570644B CN 113570644 B CN113570644 B CN 113570644B CN 202111132797 A CN202111132797 A CN 202111132797A CN 113570644 B CN113570644 B CN 113570644B
- Authority
- CN
- China
- Prior art keywords
- target
- passenger
- image
- counter
- target passenger
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000007689 inspection Methods 0.000 claims abstract description 85
- 238000001514 detection method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 230000000903 blocking effect Effects 0.000 claims description 4
- 230000001815 facial effect Effects 0.000 claims description 4
- 239000013598 vector Substances 0.000 description 7
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The application provides an airport passenger positioning method, an airport passenger positioning device, electronic equipment and a medium, wherein the method comprises the following steps: responding that a target passenger meets a preset positioning condition, selecting target security inspection information matched with travel information of the target passenger from registered security inspection information, and matching the target security inspection information from a corresponding first counter image according to the target security inspection information to obtain a half-body image of the target passenger; tracking the target passenger through the counter camera based on the half-body image of the target passenger and the designated area of the pre-defined counter area, determining a target security check image, and matching the target security check image to obtain a whole-body image of the target passenger; tracking the target passenger through a waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determine the position of the target passenger; passengers can be more accurately positioned.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an airport passenger positioning method, apparatus, electronic device, and medium.
Background
With the rapid development of science and technology, the living standard of people is continuously improved, and more travel modes can be selected by people. The travel by taking the plane is one of the most convenient travel modes.
In practice, aircraft cannot take off on time in many situations. For example, passengers cannot board the aircraft on time. When the passengers can not board the airplane on time, the airport needs to remind the passengers to board the airplane quickly.
Currently, the ways to look for passengers are: taking a face image obtained in a security inspection area as a reference, and positioning the position of the late boarding passenger through face matching; searching for late boarding passengers in a linkage manner through regional broadcasting; the search of the late boarding passenger is carried out through a ticket buying telephone. The three modes can not effectively, quickly and accurately locate and search the passengers.
Disclosure of Invention
In view of the above, an object of the present invention is to provide an airport passenger positioning method, apparatus, electronic device and medium, which can realize accurate positioning of passengers based on the existing monitoring environment of an airport.
In a first aspect, an embodiment of the present application provides a method for positioning passengers in an airport, where the airport includes a counter area, a security checkpoint area, and a waiting area; the passenger registers security check information in the counter area and waits for taking a corresponding flight in the terminal area after passing through the security check area; the counter area is provided with a counter camera which is used for shooting a counter image and recording shooting time; the security inspection region is provided with a security inspection camera which is used for shooting a security inspection image and recording shooting time; the waiting area is provided with a waiting camera which is used for shooting waiting images and recording shooting time; the method comprises the following steps:
responding that a target passenger meets a preset positioning condition, selecting target security inspection information matched with travel information of the target passenger from registered security inspection information, and matching the target security inspection information from a corresponding first counter image according to the target security inspection information to obtain a half-body image of the target passenger;
tracking the target passenger through the counter camera based on the half-body image of the target passenger and the designated area of the pre-defined counter area, determining a target security check image, and matching the target security check image to obtain a whole-body image of the target passenger;
and tracking the target passenger through a waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determine the position of the target passenger.
In a preferred technical solution of the present application, the travel information includes first personal identification data and first flight data; the security inspection information comprises second personal identity data, second flight data, security inspection time and security inspection positions; the step of selecting target security check information matched with the trip information of the target passenger from the registered security check information, and obtaining a half-body image of the target passenger from a corresponding first counter image in a matching manner according to the target security check information comprises the following steps:
determining the security check time and the security check position of the target passenger through the matching of the first personal identity data and the first flight data and the second personal identity data and the second flight data;
and taking an image shot by a camera of a target counter at the security check position at the security check time as a first counter image, and selecting a half-body image of the target passenger from the first counter image.
In a preferred embodiment of the present invention, the selecting the bust image of the target passenger from the first counter image includes:
detecting mask information of a passenger delimiting a detection area in the first counter image and facial obstruction information of the passenger;
and determining the target passenger according to the size of the mask pixel value of the passenger and the existence of the blocking object on the face of the passenger, and extracting the half-body image of the target passenger.
In a preferred technical solution of the present application, the determining a target security inspection image by tracking the target passenger with the counter camera based on the bust image of the target passenger and the designated area of the pre-defined counter area includes:
acquiring a second counter image shot by the counter camera at a preset time interval and shooting time corresponding to the second counter image;
determining the time when the target passenger arrives at the designated area by matching the half-body image of the target passenger with the passenger in the designated area in the second counter image;
predicting the time period of the target passenger appearing at the security inspection opening according to the time of the target passenger arriving at the designated area, the distance between the designated area and the security inspection opening and the walking speed of the target passenger;
and taking the image shot by the security check camera in the predicted time period as a target security check image.
In a preferred technical solution of the present application, the obtaining of the whole-body image of the target passenger by matching from the target security inspection image includes:
calculating the similarity between the whole-body image of each passenger in the target security inspection image and the half-body image of the target passenger;
and selecting the whole-body image of the passenger larger than the preset similarity threshold as the whole-body image of the target passenger.
In a preferred technical solution of the present application, the tracking, based on the whole-body image of the target passenger, of the target passenger by using a waiting camera to obtain a track of the target passenger and determine a position of the target passenger includes:
if two continuous positions corresponding to any passenger in the waiting images of the continuous frames shot by the waiting camera meet a preset condition, acquiring the position corresponding to each passenger in the waiting images of the continuous frames;
determining the target passenger from the passengers appearing in the waiting images according to the matching degree of the whole-body image of the target passenger and each passenger in the waiting images;
and setting the positions of the target passengers in the waiting images of different frames as the tracks of the target passengers, and determining the positions of the target passengers according to the tracks of the target passengers.
In the technical scheme of the present application, the two continuous positions include a first actual position and a second actual position, and whether two continuous positions corresponding to any passenger in the waiting images of the continuous frames shot by the waiting camera satisfy a preset condition is determined in the following manner:
determining the predicted position of any passenger in the next frame of waiting image according to the motion state of the passenger at the first actual position;
and if the distance between the predicted position and the second actual position is smaller than or equal to a distance threshold value, two continuous positions corresponding to the passenger meet a preset condition.
In a preferred technical scheme of the application, the number of the waiting areas is multiple, each waiting camera respectively shoots the corresponding waiting area, and the arrangement sequence of the waiting cameras is determined according to the path planning of an airport; the tracking of the target passenger through a waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determine the position of the target passenger comprises the following steps:
based on the whole-body image of the target passenger, each waiting camera respectively tracks the target passenger in a corresponding waiting area to obtain the track of the target passenger in the waiting area;
integrating the track of the target passenger in each waiting area into the whole track of the target passenger according to the arrangement sequence;
and determining the position of the target passenger according to the overall track of the target passenger.
In a second aspect, an embodiment of the present application provides an airport passenger positioning device, where the airport includes a counter area, a security checkpoint area, and a waiting area; the passenger registers security check information in the counter area and waits for taking a corresponding flight in the terminal area after passing through the security check area; the counter area is provided with a counter camera which is used for shooting a counter image and recording shooting time; the security inspection region is provided with a security inspection camera which is used for shooting a security inspection image and recording shooting time; the waiting area is provided with a waiting camera which is used for shooting waiting images and recording shooting time; the device comprises:
the system comprises a half-body image matching module, a first counter image matching module and a second counter image matching module, wherein the half-body image matching module is used for responding that a target passenger meets a preset positioning condition, selecting target security check information matched with trip information of the target passenger from registered security check information, and matching the target security check information with a corresponding first counter image according to the target security check information to obtain a half-body image of the target passenger;
the whole-body image matching module is used for tracking the target passenger through the counter camera based on the half-body image of the target passenger and the designated area of the pre-defined counter area, determining a target security inspection image, and matching the target security inspection image to obtain a whole-body image of the target passenger;
and the position determining module is used for tracking the target passenger through a waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determining the position of the target passenger.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor, when executing the computer program, implements the steps of the above-mentioned airport passenger positioning method.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the above-mentioned airport passenger positioning method.
The technical scheme provided by the embodiment of the application can have the following beneficial effects: according to the method, a target passenger meets preset positioning conditions in response, target security inspection information matched with trip information of the target passenger is selected from registered security inspection information, and a half-body image of the target passenger is obtained through matching from a corresponding first counter image according to the target security inspection information; then tracking the target passenger through the counter camera based on the half-body image of the target passenger and the designated area of the pre-defined counter area, determining a target security check image, and matching the target security check image to obtain a whole-body image of the target passenger; finally, tracking the target passenger through a waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determine the position of the target passenger; passengers can be more accurately positioned.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flow chart illustrating an airport passenger positioning method according to an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating a process of extracting a half-length image according to an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating an airport passenger locating device provided by an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
The late boarding passenger is one of the causes of flight delay, and about 240 people are average late boarding or non-boarding passengers per day at a large airport with only one terminal. The active search method for late boarding passengers mainly focuses on the following points:
(1) taking a face image obtained in a security inspection area as a reference, and positioning the position of the late boarding passenger through face matching;
(2) searching for late boarding passengers in a linkage manner through regional broadcasting;
(3) the search of the late boarding passenger is carried out through a ticket buying telephone.
Among the three main flow solutions mentioned above, there are the following problems:
the first scheme belongs to active searching and depends on face images of passengers, but existing cameras in a waiting area of an airport are difficult to obtain the face images, the positions of the face cameras can be limited only to channels, elevator entrances and the like, and the positions of the passengers are difficult to accurately position.
The second solution is broadcast-based, with limited broadcast areas, which tend to be difficult to catch the attention of late boarding passengers.
The third scheme is mainly telephone notification, and according to statistics, the accuracy of the telephone reserved for ticket purchasing of the passenger is about 60%, and the passenger often cannot receive reminding information or the telephone.
The three schemes can remind part of late boarding passengers to a certain extent, but cannot effectively, quickly and accurately locate and search the passengers.
Based on this, the embodiments of the present application provide an airport passenger positioning method, apparatus, electronic device and medium, which are described below by embodiments.
The existing airport comprises a counter area, a security inspection area and a waiting area; the passenger registers security check information in a counter area and waits for taking a corresponding flight in a terminal area after passing through a security check port area; the counter area is provided with a counter camera which is used for shooting a counter image and recording shooting time; a security check camera is arranged in the security check area and used for shooting security check images and recording shooting time; and a waiting camera is arranged in the waiting area and used for shooting waiting images and recording shooting time.
When a passenger buys an air ticket, the passenger needs to register own travel information on a server; the travel information comprises first personal identity data and first flight data; the first personal identity data comprises the name, the identity card number and the like of the passenger; the first flight data includes a flight date to be purchased by the passenger, a flight number in the flight date, and the like.
Upon arrival at the flight date, the passenger travels to the airport with the relevant materials. After arriving at the airport, the terminal needs to pass through a counter area, and security check information is registered in the counter area, wherein the security check information comprises second personal identity data, second flight data, security check time and a security check position; the second personal identification data comprises the name, the identification card number, the big-end photo and the like of the passenger; the second flight data includes a flight date to be purchased by the traveler, a flight number in the flight date, and the like; the security position is the specific direction of the passenger security check and can be a corresponding passage number when the passenger enters the counter area.
And after the passenger smoothly passes the security check, the passenger enters a waiting area to wait for boarding.
Fig. 1 is a schematic flow chart illustrating an airport passenger positioning method provided by an embodiment of the present application, wherein the method includes steps S101-S103; specifically, the method comprises the following steps:
s101, responding that a target passenger meets a preset positioning condition, selecting target security inspection information matched with trip information of the target passenger from registered security inspection information, and matching the target security inspection information from a corresponding first counter image according to the target security inspection information to obtain a half-body image of the target passenger;
s102, tracking the target passenger through a counter camera based on the half-body image of the target passenger and the designated area of the pre-defined counter area, determining a target security check image, and matching the target security check image to obtain a whole-body image of the target passenger;
s103, tracking the target passenger through the waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determine the position of the target passenger.
The method and the device realize tracking of the target passenger in the track of the waiting area based on the existing monitoring environment of the airport, and can realize accurate positioning of the target passenger.
Some embodiments of the present application are described in detail below. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
S101, responding that the target passenger meets a preset positioning condition, selecting target security check information matched with the trip information of the target passenger from the registered security check information, and matching the target security check information from the corresponding first counter image to obtain a half-body image of the target passenger.
Responding that the target passenger meets the preset positioning conditions, wherein the preset positioning conditions comprise at least one of the following conditions: and when the departure time of the current time and the target flight reaches a preset range, receiving a positioning request aiming at the target passenger. When the actual takeoff time of the target flight to be taken at the current time reaches a preset range or a certain key passenger needs to be searched, the crew member can send the passenger positioning condition corresponding to the target flight to the server. And the server acquires the travel information of the target passenger waiting for taking the target flight from the passenger ticket purchasing database according to the passenger positioning condition corresponding to the target flight.
After the server acquires the travel information of the target passenger, target security inspection information matched with the travel information of the target passenger is selected from the registered security inspection information, wherein the matching means that the target security inspection information and the travel information are the same passenger information.
The travel information comprises first personal identity data and first flight data, and the security inspection information comprises second personal identity data, second flight data, security inspection time and security inspection positions.
According to the method and the device, the first personal identity data and the first flight data are matched with the second personal identity data and the second flight data, the security check information is determined to be target security check information of the target passenger, and the security check time and the security check position included in the target security check information are the security check time and the security check position of the target passenger.
In order to quickly acquire an image including a target passenger, the image captured by a target counter camera at a security check position of the target passenger at the security check time of the target passenger is used as a first counter image, namely the first counter image includes the target passenger, and the first counter image is selected as the half-body image of the target passenger.
As shown in fig. 2, in the present application, in order to improve the extraction efficiency when selecting the half-body image of the target traveler from the first counter image, the first counter image is defined with a detection area.
S201, detecting mask information of a passenger in a first counter image for defining a detection area and facial shelter information of the passenger;
s202, according to the size of the mask pixel value of the passenger and the existence of the blocking object on the face of the passenger, the target passenger is determined, and the half-body image of the target passenger is extracted.
When the method is specifically implemented, the passenger identity information is matched with the half-length picture in combination with the airport business process;
obtaining information of the late boarding passenger, including flight number, identification card number and name, as shown in the following table:
obtaining security inspection information, including the following information:
the check-in time and the check-in channel of the late boarding passenger can be obtained by matching the flight number, the flight date, the name and the identification card number: the overdetection time is as follows: 9:03: 50; an over-detection channel: DE 06;
the method comprises the steps of obtaining a counter image containing a late boarding passenger, defining an ROI (region of interest) in the counter image, detecting the pedestrian in the ROI by using EfficientNet, and obtaining a half-body picture of the passenger according to the passing time 9:03: 50.
Many times, when the half-body pictures of the ROI area of the verification counter are obtained, 2 or 3 persons can be detected at the same time, wherein the persons mainly hold children or queue relatively closely, and pedestrians who queue behind can enter the ROI area.
In view of the above, the mask of the traveler inside the ROI area detection frame is mainly extracted and distinguished from whether or not the traveler wears a mask, and in general, when the traveler with the pixel rank 2 that the mask occupies is taken and the non-wearing mask is detected, the traveler is considered to be a bust to look for the traveler. If no mask is worn, the passenger with the largest image pickup element occupies the half-body photograph of the passenger to be searched.
S102, tracking the target passenger through the counter camera based on the half-body image of the target passenger and the designated area of the pre-defined counter area, determining a target security check image, and matching the target security check image to obtain a whole-body image of the target passenger.
The present application aims to find a position of a target passenger and to determine the position of the target passenger more accurately, and uses an already obtained target passenger half-body photograph to obtain a full-body photograph of the target passenger based on a tracking and similarity matching technique, and determines the position of the target passenger using the full-body photograph of the target passenger.
When a passenger is in a counter area, due to reasons such as shielding of a counter, the passenger can only acquire the half-body image of the passenger in most of time, and when the passenger arrives at a security check area, the whole-body image of the passenger can be completely acquired, so that the method and the device can acquire the whole-body image of the target passenger from the security check image.
In order to determine the security check image containing the target passenger, the time of the target passenger appearing in the security check image is predicted, and therefore the target security check image containing the target passenger is obtained.
The application comprises the following steps: acquiring a second counter image shot by a counter camera at a preset time interval and shooting time corresponding to the second counter image;
matching the half-body image of the target passenger with the passenger in the designated area in the second counter image to determine the time when the target passenger reaches the designated area;
predicting the time period of the target passenger appearing at the security inspection port according to the time of the target passenger reaching the designated area, the distance between the designated area and the security inspection port and the walking speed of the target passenger;
and taking the image shot by the security inspection camera in the predicted time period as a target security inspection image.
After the target security inspection image determined by the target passenger is determined, the whole-body image of the target passenger needs to be obtained from the target security inspection image in a matching mode.
The method comprises the steps of calculating the similarity between a whole-body image of each passenger in a target security inspection image and a half-body image of the target passenger;
and selecting the whole-body image of the passenger larger than the preset similarity threshold as the whole-body image of the target passenger.
In specific implementation, the method is based on the whole body photograph acquisition based on the combination of tracking and similarity matching technology.
The passenger is tracked by taking the acquired half-length photograph position as a tracking starting point and a matched template, and the passenger is tracked mainly by using a detection and similarity matching method. Detecting the pedestrian number N every 10 frames, extracting the mask features of the pedestrian in order to eliminate the influence of the background features, and using the full-connection layer features of the network as the matching features of the pedestrian.
I.e., T, T +10, … …, T +10n frames are detected and a mask is acquired until they are tracked to the out-of-counter area and the time they are out of the counter area is recorded.
The similarity matching algorithm used in the tracking is mainly Pearson correlation coefficient which is mainly used for degreeA linear correlation between two variables is measured. Calculating the quotient of covariance and standard deviation of the feature vectors extracted from T, T +10 frames, wherein the matrix vector of each pedestrian feature layer of the T frame is X, the matrix vector of each pedestrian feature layer of the T +10 frame is Y, and the similarity between the two vectors
Is defined as:
and setting a corresponding threshold value, wherein the threshold value is mainly obtained through experimental statistics of a large amount of experimental data, and taking the highest similarity as a tracking result under the condition of meeting a certain threshold value.
Tracking the position of the passenger leaving the counter area, recording the appearance time of the passenger, and setting the final appearance time of the passenger to be 9:05: 10.
Detecting pedestrians appearing in the video of the security inspection gateway area after 9:05:10, wherein the time period of the appearance of the detected late boarding passengers is as follows according to the general walking speed of adults: and 9:05:10-9:06:10, and detecting the passengers appearing in the video of the security inspection passage port in the time period.
And matching the detected pedestrian with the acquired half-body photo, wherein the highest similarity is the full-body photo of the passenger waiting to check for the late boarding.
S103, tracking the target passenger through the waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determine the position of the target passenger.
According to the method and the device, when the target passenger is tracked through the waiting camera based on the whole body image of the target passenger, some irrelevant waiting images are removed through preset conditions in order to improve matching efficiency.
If two continuous positions corresponding to any passenger in the waiting images of the continuous frames shot by the waiting camera meet a preset condition, acquiring the position corresponding to each passenger in the waiting images of the continuous frames;
determining target passengers from the passengers appearing in the waiting images according to the matching degree of the whole-body image of the target passengers and each passenger in the waiting images;
and taking the positions of the target passengers in the waiting images of different frames as the tracks of the target passengers, and determining the positions of the target passengers according to the tracks of the target passengers.
According to the method and the device, the target passenger is determined from the waiting images meeting the preset conditions, the positions of the target passenger appearing in the waiting images of different frames are combined into the track of the target passenger, and the position appearing at the last in the track of the target passenger is used as the position of the target passenger.
According to the motion state of any passenger at the first actual position, the predicted position of the passenger in the next frame of waiting image is determined;
and if the distance between the predicted position and the second actual position is smaller than or equal to the distance threshold, two continuous positions corresponding to the passenger meet the preset condition.
According to the method, when a plurality of waiting areas are arranged in the airport, each waiting camera respectively shoots the corresponding waiting area, and the arrangement sequence of the waiting cameras is determined according to the path planning of the airport; the location of the target passenger is determined by:
based on the whole-body image of the target passenger, each waiting camera respectively tracks the target passenger in the corresponding waiting area to obtain the track of the target passenger in the waiting area;
integrating the tracks of the target passengers in each waiting area into the whole track of the target passengers according to the arrangement sequence;
and determining the position of the target passenger according to the overall track of the target passenger.
In specific implementation, the obtained picture of the whole passenger is input in the step, pedestrian detection is carried out on the selected cameras according to the region and time sequence, the characteristic of the appearing passenger is extracted mainly by the re-recognition basic network, and the characteristic of the continuous position of the appearing passenger is tracked to obtain the characteristic of the continuous position of the appearing passenger.
In the main tracking mode in the step, the acquisition of a plurality of position characteristics of the tracked pedestrian is realized by using similarity and spatial position information, namely Kalman filtering.
Let the position coordinate (detection frame) of the passenger detected at time T be PTAt a running speed VTAcceleration of μTThen the state transition detected at time T +1 is expressed as:
the above formula can be applied to predict the state of a detected passenger at the next location, thereby applying spatial features to the tracking to improve the accuracy of the tracking.
Meanwhile, by adding a distance measurement mode, the number of distance pixel points for detecting that the passenger walks to T +1 from T moment is assumed to be a, and the feature vector X of the passenger at T moment isiAnd the feature vector Y of the passenger at the moment T +1iThe following condition is satisfied:
continuously measuring the similarity between feature vectors of pedestrians detected at T and T +1 by using a Pearson correlation coefficient, and finally realizing the tracking of passengers to be detected and the output of continuous position features by combining state prediction features, distance features and similarity features, wherein the feature expression of tracking continuous positions is as follows:
in actual use, 10 positions of continuous occurrences of the tracked pedestrian are generally taken as matching objects.
Matching the detected and tracked features Z of the continuous positions of each pedestrian by using the acquired whole body illumination features as templates and the Pearson correlation coefficient as similarity measureiIf the similarity of 10 continuous positions is in the set threshold range, the person is considered to be the latest login sought by the personAn airplane passenger.
In practical application, in order to avoid false detection caused by the influence of the distance of a camera or light, if the similarity of 7 or more positions reaches a set threshold value, the passenger to be searched is considered.
Compared with the prior art, the invention has the following beneficial effects:
based on the existing monitoring environment of the airport, the track and position description of late boarding passengers or important attention personnel in the waiting area can be realized, and the accurate positioning of the positions of the late boarding passengers or the important attention personnel can be realized.
The pedestrian detection precision can reach 95% on average, the accuracy rate of the position positioning of the late boarding passengers can reach 84% on average, and the proposal of the scheme or the method can be expanded to the description of the track and the position of the passengers focused on by the whole terminal building.
Fig. 3 shows a schematic structural diagram of an airport passenger positioning device provided in an embodiment of the present application, where the device includes:
the system comprises a half-length image matching module, a first counter image matching module and a second counter image matching module, wherein the half-length image matching module is used for responding that a target passenger meets a preset positioning condition, selecting target security check information matched with trip information of the target passenger from registered security check information, and matching the target security check information with a corresponding first counter image according to the target security check information to obtain a half-length image of the target passenger;
the whole-body image matching module is used for tracking the target passenger through the counter camera based on the half-body image of the target passenger and the designated area of the pre-defined counter area, determining a target security check image and matching the target security check image to obtain a whole-body image of the target passenger;
and the position determining module is used for tracking the target passenger through the waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determining the position of the target passenger.
The half-body image matching module is used for responding that the target passenger meets the preset positioning condition, selecting target security check information matched with the trip information of the target passenger from the registered security check information, and matching the half-body image of the target passenger from the corresponding first counter image according to the target security check information, and comprises the following steps:
the travel information comprises first personal identity data and first flight data; the safety inspection information comprises second personal identity data, second flight data, safety inspection time and a safety inspection position; selecting target security check information matched with the trip information of the target passenger from the registered security check information, and matching the target security check information with a corresponding first counter image to obtain a half-body image of the target passenger, wherein the method comprises the following steps:
determining the security check time and the security check position of the target passenger through the matching of the first personal identity data and the first flight data with the second personal identity data and the second flight data;
and taking an image shot by a camera at the security check position at the security check time of the target counter as a first counter image, and selecting a half-body image of the target passenger from the first counter image.
Selecting a target passenger's half-body image from a first counter image, comprising:
detecting mask information of a passenger delimiting a detection area in a first counter image and facial obstruction information of the passenger;
a target passenger is identified based on the size of the mask pixel value of the passenger and the presence or absence of a blocking object on the face of the passenger, and a half-body image of the target passenger is extracted.
The whole-body image matching module is used for tracking the target passenger through the counter camera based on the half-body image of the target passenger and the designated area of the pre-defined counter area, determining the target security check image and matching the target security check image to obtain the whole-body image of the target passenger, and comprises the following steps:
based on the bust image of the target passenger and the designated area of the pre-defined counter area, the target passenger is tracked through the counter camera, and the target security inspection image is determined, which comprises the following steps:
acquiring a second counter image shot by a counter camera at a preset time interval and shooting time corresponding to the second counter image;
matching the half-body image of the target passenger with the passenger in the designated area in the second counter image to determine the time when the target passenger reaches the designated area;
predicting the time period of the target passenger appearing at the security inspection port according to the time of the target passenger reaching the designated area, the distance between the designated area and the security inspection port and the walking speed of the target passenger;
and taking the image shot by the security inspection camera in the predicted time period as a target security inspection image.
Obtaining a whole-body image of the target passenger from the target security inspection image in a matching way, wherein the whole-body image comprises the following steps:
calculating the similarity between the whole-body image of each passenger in the target security inspection image and the half-body image of the target passenger;
and selecting the whole-body image of the passenger larger than the preset similarity threshold as the whole-body image of the target passenger.
The position determination module is used for tracking the target passenger through the waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determine the position of the target passenger, and comprises:
based on the whole-body image of the target passenger, the target passenger is tracked through the waiting camera, the track of the target passenger is obtained, and the position of the target passenger is determined, which comprises the following steps:
if two continuous positions corresponding to any passenger in the waiting images of the continuous frames shot by the waiting camera meet a preset condition, acquiring the position corresponding to each passenger in the waiting images of the continuous frames;
determining target passengers from the passengers appearing in the waiting images according to the matching degree of the whole-body image of the target passengers and each passenger in the waiting images;
and taking the positions of the target passengers in the waiting images of different frames as the tracks of the target passengers, and determining the positions of the target passengers according to the tracks of the target passengers.
The two continuous positions comprise a first actual position and a second actual position, and whether the two continuous positions corresponding to any passenger in the waiting images of the continuous frames shot by the waiting camera meet the preset conditions or not is judged in the following mode:
determining the predicted position of any passenger in the next frame of waiting image according to the motion state of the passenger at the first actual position;
and if the distance between the predicted position and the second actual position is smaller than or equal to the distance threshold, two continuous positions corresponding to the passenger meet the preset condition.
The number of the waiting areas is multiple, each waiting camera respectively shoots the corresponding waiting area, and the arrangement sequence of the waiting cameras is determined according to the path planning of the airport; based on the whole-body image of the target passenger, the target passenger is tracked through the waiting camera, the track of the target passenger is obtained, and the position of the target passenger is determined, which comprises the following steps:
based on the whole-body image of the target passenger, each waiting camera respectively tracks the target passenger in the corresponding waiting area to obtain the track of the target passenger in the waiting area;
integrating the tracks of the target passengers in each waiting area into the whole track of the target passengers according to the arrangement sequence;
and determining the position of the target passenger according to the overall track of the target passenger.
As shown in fig. 4, an embodiment of the present application provides an electronic device for executing the airport passenger positioning method in the present application, the device includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the airport passenger positioning method when executing the computer program.
In particular, the memory and the processor may be general-purpose memory and processor, which are not limited in particular, and the airport passenger location method described above can be performed when the processor runs a computer program stored in the memory.
Corresponding to the airport passenger positioning method in the present application, the present application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor performs the steps of the airport passenger positioning method described above.
In particular, the storage medium can be a general-purpose storage medium, such as a removable disk, a hard disk, or the like, on which a computer program can be executed when being executed, which can perform the above-mentioned airport passenger location method.
In the embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other ways. The above-described system embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and there may be other divisions in actual implementation, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In other words, the shown or discussed coupling or direct coupling or communication connection between each other includes an indirect coupling or communication connection between systems or units through some communication interfaces, including electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, that is, may be located in one place, or may also be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (including a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus once an item is defined in one figure, it need not be further defined and explained in subsequent figures, and moreover, the terms "first", "second", "third", etc. are used merely to distinguish one description from another and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope disclosed in the present application; such modifications, changes or substitutions do not depart from the spirit and scope of the present disclosure, which should be construed in light of the above teachings. Are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An airport passenger positioning method is characterized in that an airport comprises a counter area, a security inspection area and a waiting area; the passenger registers security check information in the counter area and waits for taking a corresponding flight in the terminal area after passing through the security check area; the counter area is provided with a counter camera which is used for shooting a counter image and recording shooting time; the security inspection region is provided with a security inspection camera which is used for shooting a security inspection image and recording shooting time; the waiting area is provided with a waiting camera which is used for shooting waiting images and recording shooting time; the travel information comprises first personal identity data and first flight data; the security inspection information comprises second personal identity data, second flight data, security inspection time and security inspection positions; the method comprises the following steps:
responding that a target passenger meets a preset positioning condition, selecting target security inspection information matched with travel information of the target passenger from registered security inspection information, and matching the target security inspection information from a corresponding first counter image according to the target security inspection information to obtain a half-body image of the target passenger;
tracking the target passenger through the counter camera based on the half-body image of the target passenger and the designated area of the pre-defined counter area, determining a target security check image, and matching the target security check image to obtain a whole-body image of the target passenger;
tracking the target passenger through a waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determine the position of the target passenger;
the step of selecting target security check information matched with the trip information of the target passenger from the registered security check information, and obtaining a half-body image of the target passenger from a corresponding first counter image in a matching manner according to the target security check information comprises the following steps:
determining the security check time and the security check position of the target passenger through the matching of the first personal identity data and the first flight data and the second personal identity data and the second flight data;
and taking an image shot by a camera of a target counter at the security check position at the security check time as a first counter image, and selecting a half-body image of the target passenger from the first counter image.
2. The method of claim 1, wherein said extracting the target passenger's bust image from the first counter image comprises:
detecting mask information of a passenger delimiting a detection area in the first counter image and facial obstruction information of the passenger;
and determining the target passenger according to the size of the mask pixel value of the passenger and the existence of the blocking object on the face of the passenger, and extracting the half-body image of the target passenger.
3. The method of claim 1, wherein determining a target security inspection image by tracking the target passenger with the counter camera based on the target passenger's bust image and a designated area of a pre-defined counter area comprises:
acquiring a second counter image shot by the counter camera at a preset time interval and shooting time corresponding to the second counter image;
determining the time when the target passenger arrives at the designated area by matching the half-body image of the target passenger with the passenger in the designated area in the second counter image;
predicting the time period of the target passenger appearing at the security inspection opening according to the time of the target passenger arriving at the designated area, the distance between the designated area and the security inspection opening and the walking speed of the target passenger;
and taking the image shot by the security check camera in the predicted time period as a target security check image.
4. The method of claim 1, wherein the matching of the target passenger's whole-body image from the target security inspection image comprises:
calculating the similarity between the whole-body image of each passenger in the target security inspection image and the half-body image of the target passenger;
and selecting the whole-body image of the passenger larger than the preset similarity threshold as the whole-body image of the target passenger.
5. The method of claim 1, wherein the tracking the target passenger through a waiting camera based on the whole-body image of the target passenger, obtaining a track of the target passenger, and determining the position of the target passenger comprises:
if two continuous positions corresponding to any passenger in the waiting images of the continuous frames shot by the waiting camera meet a preset condition, acquiring the position corresponding to each passenger in the waiting images of the continuous frames;
determining the target passenger from the passengers appearing in the waiting images according to the matching degree of the whole-body image of the target passenger and each passenger in the waiting images;
and taking the positions of the target passengers in the waiting images of different frames as the tracks of the target passengers, and determining the positions of the target passengers according to the tracks of the target passengers.
6. The method according to claim 5, wherein the two continuous positions comprise a first actual position and a second actual position, and whether the two continuous positions corresponding to any passenger in the waiting images of the consecutive frames shot by the waiting camera meet the preset condition is judged by the following method:
determining the predicted position of any passenger in the next frame of waiting image according to the motion state of the passenger at the first actual position;
and if the distance between the predicted position and the second actual position is smaller than or equal to a distance threshold value, two continuous positions corresponding to the passenger meet a preset condition.
7. The method according to claim 1, wherein the number of the waiting areas is multiple, each waiting camera respectively shoots the corresponding waiting area, and the arrangement sequence of the waiting cameras is determined according to the path planning of an airport; the tracking of the target passenger through a waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determine the position of the target passenger comprises the following steps:
based on the whole-body image of the target passenger, each waiting camera respectively tracks the target passenger in a corresponding waiting area to obtain the track of the target passenger in the waiting area;
integrating the track of the target passenger in each waiting area into the whole track of the target passenger according to the arrangement sequence;
and determining the position of the target passenger according to the overall track of the target passenger.
8. An airport passenger positioning device is characterized in that the airport comprises a counter area, a security inspection area and a waiting area; the passenger registers security check information in the counter area and waits for taking a corresponding flight in the terminal area after passing through the security check area; the counter area is provided with a counter camera which is used for shooting a counter image and recording shooting time; the security inspection region is provided with a security inspection camera which is used for shooting a security inspection image and recording shooting time; the waiting area is provided with a waiting camera which is used for shooting waiting images and recording shooting time; the travel information comprises first personal identity data and first flight data; the security inspection information comprises second personal identity data, second flight data, security inspection time and security inspection positions; the device comprises:
the system comprises a half-body image matching module, a first counter image matching module and a second counter image matching module, wherein the half-body image matching module is used for responding that a target passenger meets a preset positioning condition, selecting target security check information matched with trip information of the target passenger from registered security check information, and matching the target security check information with a corresponding first counter image according to the target security check information to obtain a half-body image of the target passenger;
the whole-body image matching module is used for tracking the target passenger through the counter camera based on the half-body image of the target passenger and the designated area of the pre-defined counter area, determining a target security inspection image and matching the target security inspection image to obtain a whole-body image of the target passenger;
the position determining module is used for tracking the target passenger through a waiting camera based on the whole-body image of the target passenger to obtain the track of the target passenger and determining the position of the target passenger;
the half-length image matching module is used for selecting target security check information matched with the trip information of the target passenger from the registered security check information, and matching the target security check information with a corresponding first counter image to obtain a half-length image of the target passenger according to the target security check information, and comprises:
determining the security check time and the security check position of the target passenger through the matching of the first personal identity data and the first flight data and the second personal identity data and the second flight data;
and taking an image shot by a camera of a target counter at the security check position at the security check time as a first counter image, and selecting a half-body image of the target passenger from the first counter image.
9. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the steps of the method of airport passenger location according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for locating airport passengers according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111132797.7A CN113570644B (en) | 2021-09-27 | 2021-09-27 | Airport passenger positioning method, airport passenger positioning device, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111132797.7A CN113570644B (en) | 2021-09-27 | 2021-09-27 | Airport passenger positioning method, airport passenger positioning device, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113570644A CN113570644A (en) | 2021-10-29 |
| CN113570644B true CN113570644B (en) | 2021-11-30 |
Family
ID=78174764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111132797.7A Active CN113570644B (en) | 2021-09-27 | 2021-09-27 | Airport passenger positioning method, airport passenger positioning device, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113570644B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117830958B (en) * | 2024-03-04 | 2024-06-11 | 罗普特科技集团股份有限公司 | Passenger clearance and weather detection management method and device and electronic equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324024A (en) * | 2011-09-06 | 2012-01-18 | 苏州科雷芯电子科技有限公司 | Airport passenger recognition and positioning method and system based on target tracking technique |
| CN106539581A (en) * | 2016-12-07 | 2017-03-29 | 中国民用航空总局第二研究所 | Controller's fatigue detection method and system based on probabilistic method |
| JP2017078952A (en) * | 2015-10-20 | 2017-04-27 | 株式会社エクサ | System for tracking passengers in airport |
| CN109840407A (en) * | 2018-12-24 | 2019-06-04 | 航天信息股份有限公司 | Intelligent personnel's verification system and method |
| CN110443177A (en) * | 2019-07-29 | 2019-11-12 | 上海工程技术大学 | A kind of airport indoor locating system based on recognition of face |
| CN112069920A (en) * | 2020-08-18 | 2020-12-11 | 武汉大学 | Cross-domain pedestrian re-identification method based on attribute feature driven clustering |
| CN112084824A (en) * | 2019-06-14 | 2020-12-15 | 杭州海康威视数字技术股份有限公司 | Passenger reminding method and device, electronic equipment and storage medium |
| CN212208397U (en) * | 2020-04-24 | 2020-12-22 | 民航成都电子技术有限责任公司 | Security inspection system |
| CN113436229A (en) * | 2021-08-26 | 2021-09-24 | 深圳市金大智能创新科技有限公司 | Multi-target cross-camera pedestrian trajectory path generation method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7634662B2 (en) * | 2002-11-21 | 2009-12-15 | Monroe David A | Method for incorporating facial recognition technology in a multimedia surveillance system |
-
2021
- 2021-09-27 CN CN202111132797.7A patent/CN113570644B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324024A (en) * | 2011-09-06 | 2012-01-18 | 苏州科雷芯电子科技有限公司 | Airport passenger recognition and positioning method and system based on target tracking technique |
| JP2017078952A (en) * | 2015-10-20 | 2017-04-27 | 株式会社エクサ | System for tracking passengers in airport |
| CN106539581A (en) * | 2016-12-07 | 2017-03-29 | 中国民用航空总局第二研究所 | Controller's fatigue detection method and system based on probabilistic method |
| CN109840407A (en) * | 2018-12-24 | 2019-06-04 | 航天信息股份有限公司 | Intelligent personnel's verification system and method |
| CN112084824A (en) * | 2019-06-14 | 2020-12-15 | 杭州海康威视数字技术股份有限公司 | Passenger reminding method and device, electronic equipment and storage medium |
| CN110443177A (en) * | 2019-07-29 | 2019-11-12 | 上海工程技术大学 | A kind of airport indoor locating system based on recognition of face |
| CN212208397U (en) * | 2020-04-24 | 2020-12-22 | 民航成都电子技术有限责任公司 | Security inspection system |
| CN112069920A (en) * | 2020-08-18 | 2020-12-11 | 武汉大学 | Cross-domain pedestrian re-identification method based on attribute feature driven clustering |
| CN113436229A (en) * | 2021-08-26 | 2021-09-24 | 深圳市金大智能创新科技有限公司 | Multi-target cross-camera pedestrian trajectory path generation method |
Non-Patent Citations (2)
| Title |
|---|
| 《人脸检测在机场离港旅客识别系统中的应用研究》;李丹;《中国优秀博硕士学位论文全文数据库 (硕士) 信息科技辑》;20060115(第01期);第I138-193页 * |
| 《基于航班离港时刻主导的单航班离港旅客聚集模型》;邢志伟 等;《电子科技大学学报》;20150930;第44卷(第05期);第719-724页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113570644A (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10776627B2 (en) | Human flow analysis method, human flow analysis apparatus, and human flow analysis system | |
| JP5851651B2 (en) | Video surveillance system, video surveillance method, and video surveillance device | |
| JP4852765B2 (en) | Estimating connection relationship between distributed cameras and connection relationship estimation program | |
| US20160191865A1 (en) | System and method for estimating an expected waiting time for a person entering a queue | |
| US20180096209A1 (en) | Non-transitory computer-readable storage medium, event detection apparatus, and event detection method | |
| JP2022168070A (en) | person detection system | |
| JP2018067755A (en) | Detection data management device | |
| JP2017174343A (en) | Customer attribute extraction device and customer attribute extraction program | |
| WO2022078134A1 (en) | People traffic analysis method and system, electronic device, and readable storage medium | |
| CN113570644B (en) | Airport passenger positioning method, airport passenger positioning device, electronic equipment and medium | |
| JPWO2019220589A1 (en) | Video analysis device, video analysis method, and program | |
| JPWO2020138348A1 (en) | Information processing equipment, information processing methods and programs | |
| Denman et al. | Automatic surveillance in transportation hubs: No longer just about catching the bad guy | |
| CN114581990A (en) | Intelligent running test method and device | |
| Farhadmanesh et al. | Automated video-based air traffic surveillance system for counting general aviation aircraft operations at non-towered airports | |
| Islam et al. | Correlating belongings with passengers in a simulated airport security checkpoint | |
| Perko et al. | Airborne based high performance crowd monitoring for security applications | |
| CN110287957A (en) | A kind of localization method and positioning device of low slow Small object | |
| NL2029136B1 (en) | Vision-based sports timing and identification system | |
| EP3901820A2 (en) | Event analysis system and event analysis method | |
| TW201944325A (en) | Analysis system | |
| JP7264283B2 (en) | Image processing device, person search system, image processing method, and image processing program | |
| KR20130104018A (en) | A count system of coming and going using image analysis and method thereof | |
| WO2022113148A1 (en) | Server device, system, control method of server device, and storage medium | |
| JP7196681B2 (en) | Determination device, determination method and program |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |