A rail transit passenger flow sorting method, system and electronic equipment

Abstract

The present invention is applicable to the technical field of rail transit passenger flow sorting, and provides a rail transit passenger flow sorting method, system and electronic equipment. When a train arrives at a station, the train number is identified and the train information is obtained; according to the train information, a designated train database is matched; when passengers get on and off the train, full-body photography of the passengers is performed and the time of getting on and off the train is recorded, and full-body images of passengers getting on and off the train and full-body images of passengers getting off and off the train are obtained. By comparing the passengers entering and exiting the train, it is possible to confirm which train the passenger is riding, and the passenger's riding time and mileage can be obtained, so that in the subsequent sorting process, the passenger flow of different trains on the same line can be analyzed more accurately, thereby improving the accuracy of passenger flow sorting.

Description

Technical Field

[0001] The present invention belongs to the technical field of rail transit passenger flow sorting, and in particular relates to a rail transit passenger flow sorting method, system and electronic equipment. Background Art

[0002] In the urban rail transit network, passenger flow is the most basic, important and core element of rail transit operation management. Passenger flow classification is to obtain accurate passenger flow distribution data in the rail transit network, so as to conduct passenger flow statistics, ticket classification, operation management analysis and decision-making, or other related applications in the urban rail transit network.

[0003] After passengers enter the subway station, some passengers will stay and wait inside the subway station, resulting in the existing clearing system not knowing which specific train the passenger is taking. For example, a passenger enters the subway station at ten o'clock, but stays in the subway station for an hour and does not enter the train until eleven o'clock. This makes it difficult for the clearing system to assign the passenger to the designated train, and it is difficult to accurately calculate the passenger flow of different trains on the same line. In the subsequent clearing process, if different trains on the same line belong to different operating companies, there will be clearing confusion and unclear division of ticket revenue. Summary of the invention

[0004] The purpose of the present invention is to provide a rail transit passenger flow sorting method, aiming to solve the problems raised in the background technology.

[0005] The present invention is implemented as follows: a rail transit passenger flow sorting method, the method comprising the following steps:

[0006] When the train arrives at the station, identify the train number and obtain train information;

[0007] According to the train information, matching a designated train database;

[0008] When passengers get on and off the bus, full-body video of the passengers is taken and the time of getting on and off is recorded to obtain full-body images of passengers getting on and off the bus and the time of passengers getting on and off the bus;

[0009] Uploading the passenger boarding full-body image and the passenger boarding time as well as the passenger getting off the train full-body image and the passenger getting off time to a designated train database;

[0010] Compare the full-body image of the passenger getting off the train with several full-body images of passengers on the train in a designated train database to obtain an image comparison result;

[0011] Determine the passenger getting off the bus based on the image comparison result, and calculate the distance and time difference between the passenger getting on and getting off the bus to obtain the passenger's mileage data and the passenger's time data;

[0012] The passenger's boarding time data is compared with the preset vehicle travel time to determine whether the passenger takes the return train.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the step of matching the designated train database according to the train information includes:

[0014] Determine the train model based on the train information;

[0015] Match the specified train database according to the train model.

[0016] As a further limitation of the technical solution of the embodiment of the present invention, the step of comparing the full-body image of the passenger getting off the train with a plurality of full-body images of passengers on the train in the designated train database to obtain the image comparison result comprises:

[0017] Perform image analysis on the full-body image of passengers getting off the bus to obtain information on their clothing combinations;

[0018] The passenger clothing matching information is compared with several passenger full-body images in the designated train database to obtain image comparison results.

[0019] As a further limitation of the technical solution of the embodiment of the present invention, the step of determining the passenger getting off the bus according to the image comparison result, and calculating the distance and time difference between the passenger getting on and getting off the bus, and obtaining the passenger's mileage data and the passenger's riding time data comprises:

[0020] Determining, based on the image comparison result, that the passenger gets off the bus;

[0021] Calculate the track mileage between the passenger alighting station and the passenger boarding station to obtain the passenger mileage data;

[0022] Subtract the passenger boarding time from the passenger disembarkation time to obtain the passenger boarding time data.

[0023] As a further limitation of the technical solution of the embodiment of the present invention, the step of comparing the passenger boarding time data with the preset vehicle travel time to determine whether the passenger takes the return train includes:

[0024] Comparing the passenger's boarding time data with the vehicle's preset travel time;

[0025] If the passenger's travel time data is greater than the vehicle's preset travel time, it is determined that the passenger is taking a return train.

[0026] A rail transit passenger flow sorting system, the system comprising: a train identification unit, a designated train database matching unit, a passenger image acquisition unit, a passenger image uploading unit, an image comparison unit, a distance and time difference calculation unit and a return train judgment unit, wherein:

[0027] The train identification unit is used to identify the train number and obtain train information when the train arrives at the station;

[0028] A designated train database matching unit is used to match a designated train database according to train information;

[0029] The passenger image acquisition unit is used to take full-body photos of passengers and record the time of getting on and off the bus when the passengers get on and off the bus, and to acquire full-body images of passengers getting on and off the bus and the time of passengers getting on and off the bus, as well as full-body images of passengers getting off and the time of passengers getting off the bus;

[0030] A passenger image uploading unit, used for uploading the passenger boarding full-body image and the passenger boarding time as well as the passenger getting off full-body image and the passenger getting off time to a designated train database;

[0031] An image comparison unit, used for comparing the full-body image of the passenger getting off the train with a number of full-body images of passengers on the train in a designated train database, to obtain an image comparison result;

[0032] A distance and time difference calculation unit, used to determine the passenger getting off the bus according to the image comparison result, and calculate the distance and time difference between the passenger getting on and getting off the bus, so as to obtain the passenger's mileage data and the passenger's time data;

[0033] The return train judgment unit is used to compare the passenger's boarding time data with the vehicle's preset travel time to judge whether the passenger takes the return train.

[0034] As a further limitation of the technical solution of the embodiment of the present invention, the image comparison unit specifically includes:

[0035] An image analysis module is used to analyze the full-body image of the passenger getting off the bus and obtain the passenger's clothing matching information;

[0036] The image comparison module is used to compare the passenger clothing matching information with several passenger full-body images in the designated train database to obtain an image comparison result.

[0037] As a further limitation of the technical solution of the embodiment of the present invention, the distance and time difference calculation unit specifically includes:

[0038] A station determination module, used for determining the passenger to get off the train based on the image comparison result;

[0039] The mileage calculation module is used to calculate the track mileage between the passenger alighting station and the passenger boarding station to obtain the passenger mileage data;

[0040] The riding time calculation module is used to obtain the passenger riding time data by subtracting the passenger boarding time from the passenger getting off time.

[0041] As a further limitation of the technical solution of the embodiment of the present invention, the return train judgment unit specifically includes:

[0042] A time comparison module, used to compare the passenger's boarding time data with the vehicle's preset travel time;

[0043] The judgment module is used to judge whether the passenger takes a return train if the passenger's travel time data is greater than the preset travel time of the vehicle.

[0044] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the rail transit passenger flow clearing method.

[0045] The present invention identifies the train number and obtains the train information when the train arrives at the station; matches the designated train database according to the train information; takes full-body photos of the passengers and records the boarding and alighting times when the passengers get on and off the train, obtains the full-body images of the passengers and the boarding time of the passengers and the alighting time of the passengers; and uploads the full-body images of the passengers and the boarding time of the passengers and the alighting time of the passengers to the designated train database. By comparing the passengers entering and exiting the train, it can be confirmed which train the passengers are riding, and the passengers' riding time and mileage can be obtained, so that in the subsequent clearing process, the passenger flow of different trains on the same line can be analyzed more accurately, thereby improving the accuracy of passenger flow clearing. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart of a method provided by an embodiment of the present invention;

[0047] Figure 2 A flowchart of matching a train database in a method provided in an embodiment of the present invention;

[0048] Figure 3 A flowchart of obtaining image comparison results in the method provided in an embodiment of the present invention;

[0049] Figure 4 A flow chart of obtaining passenger riding data in the method provided in an embodiment of the present invention;

[0050] Figure 5A flow chart of determining whether a passenger takes a return train in a method provided in an embodiment of the present invention;

[0051] Figure 6 An application architecture diagram of a system provided by an embodiment of the present invention;

[0052] Figure 7 A structural block diagram of an image comparison unit in a system provided by an embodiment of the present invention;

[0053] Figure 8 A structural block diagram of a distance and time difference calculation unit in a system provided by an embodiment of the present invention;

[0054] Fig. 9 This is a structural block diagram of a return train judgment unit in a system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0056] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0057] Specifically, a rail transit passenger flow sorting method comprises the following steps:

[0058] Step S100, when a train arrives at a station, identify the train number and obtain train information;

[0059] In the embodiment of the present invention, the outer surface of each carriage of the train is affixed with the same barcode or QR code, and a number of smart cameras are installed in the platform hall of the subway, and the camera of each smart camera is aimed at the arrival area of ​​the train carriage. The number of smart cameras is the same as the number of carriages of the train. The above-mentioned smart cameras have functions such as face recognition, backlight compensation, picture adjustment and smart zoom, and the smart cameras are connected to the Internet via WIFI;

[0060] It can be understood that when a subway train arrives at the platform hall area of ​​a subway station, the smart camera captures the barcode or QR code on the train car and uploads the picture containing the barcode or QR code to the background computer. The background computer reads the barcode or QR code in the picture and extracts the train information therein. The train information includes the train model, the operating unit to which the train belongs, the train schedule, and the train speed, etc.

[0061] Furthermore, the rail transit passenger flow clearing method further comprises the following steps:

[0062] Step S200, matching a designated train database according to the train information.

[0063] In the embodiment of the present invention, when establishing a database, the backend computer shall establish different train databases according to the models of different trains and the operators to which they belong. These train databases are relatively independent, and each train database only contains the passenger data on the corresponding train. These passenger data include the full-body image of the passenger and the boarding and alighting time of the passenger. After the train arrives at the station, the backend computer can match the corresponding designated train database according to the train information.

[0064] It can be understood that by setting up multiple databases and setting up the databases independently, when the background computer identifies and reads passenger data, it only needs to perform identification and reading operations in the designated train database corresponding to the arriving train, thereby greatly reducing the computing power requirements of the background computer, thereby reducing investment costs, and the independent database setting facilitates subsequent passenger data deletion operations to ensure that passenger privacy is not leaked.

[0065] Specifically, Figure 2 A flow chart of matching a train database in the method provided by an embodiment of the present invention is shown.

[0066] Among them, in a preferred embodiment of the present invention, matching the designated train database according to the train information specifically includes the following steps:

[0067] Step 201, determining the train model according to the train information;

[0068] Step 202, matching a designated train database according to the train model.

[0069] In an embodiment of the present invention, after the background computer reads the barcode or QR code on the arriving train, it extracts the train information therein and determines the specific model of the train. The background computer then matches the specific model to the corresponding designated train database. After that, the passenger data of all passengers who take the train or get off the train obtained by the smart camera are uploaded to the designated train database.

[0070] Furthermore, the rail transit passenger flow clearing method further comprises the following steps:

[0071] Step S300, when passengers get on and off the bus, full-body video of the passengers is taken and the time of getting on and off is recorded to obtain full-body images of passengers getting on and the time of passengers getting on, as well as full-body images of passengers getting off and the time of passengers getting off.

[0072] Step S400, uploading the passenger boarding full-body image and the passenger boarding time as well as the passenger getting off the train full-body image and the passenger getting off time to a designated train database.

[0073] In an embodiment of the present invention, when passengers get on or off a train, a smart camera installed in the platform hall will take full-body photos of the passengers in motion and record the time of taking photos while taking photos. The time of taking photos is the time when the passengers get on or off the train. The smart camera will then upload the full-body images of the passengers getting on and off the train and the time when the passengers get on and off the train, as well as the full-body images of the passengers getting off and off the train, to a designated train database that matches the arriving train.

[0074] Furthermore, the rail transit passenger flow clearing method further comprises the following steps:

[0075] Step S500, comparing the full-body image of the passenger getting off the train with several full-body images of passengers on the train in a designated train database to obtain an image comparison result.

[0076] In an embodiment of the present invention, the purpose of comparing the full-body image of a passenger getting off the train with several full-body images of passengers on the train in a designated train database is to determine the target passenger, that is, to determine the passenger who has taken the train and completed the purpose of riding. After comparing the full-body image of the passenger getting off the train with several full-body images of passengers on the train in the designated train database one by one, the two images with the highest similarity are determined, and the image comparison results are obtained. According to the image comparison results, it is determined that the passenger who has got off the train has completed the purpose of riding.

[0077] Specifically, Figure 3 A flow chart of obtaining image comparison results in the method provided by an embodiment of the present invention is shown.

[0078] Among them, in a preferred embodiment of the present invention, the whole-body image of the passenger getting off the train is compared with several whole-body images of passengers on the train in the designated train database to obtain the image comparison result, which specifically includes the following steps:

[0079] Step S501, performing image analysis on the full-body image of the passenger getting off the bus to obtain the passenger's clothing matching information;

[0080] Step S502, comparing the passenger clothing matching information with a number of passenger full-body images in a designated train database to obtain an image comparison result.

[0081] In the embodiment of the present invention, when using a smart camera to obtain full-body images of passengers getting on and off the train, due to the various limitations of the smart camera's angle and the passenger's body shape and walking posture, the smart camera cannot carefully capture the passenger's facial image and facial details. Therefore, the accuracy of determining the target passenger through facial recognition is low, and it is also easy to miss the detection problem. Therefore, in this method, after uploading the full-body images of passengers getting on and off the train obtained by the background computer to the background computer, the background computer performs image analysis on the full-body images of passengers getting on and off the train, and obtains the passenger's clothing matching information in the image. The passenger clothing matching information refers to that the background computer extracts the clothing images from the full-body images of passengers getting on and off the train separately to form a comparison image containing only the clothing images. Then, when comparing the full-body image of passengers getting off the train with multiple full-body images of passengers getting on the train in the designated train database, the comparison images extracted from different full-body images are compared, and the two images with the highest similarity are obtained to determine the target passenger.

[0082] It can be understood that by using the passenger's clothing matching information to compare the passenger's full-body images when getting on and off the bus, the target passenger can be identified more accurately, and the steps for the background computer to identify the clothing matching information are relatively simple, and the corresponding computing power requirements for the background computer are relatively low, thereby improving the accuracy of passenger identification in this application.

[0083] Furthermore, the rail transit passenger flow clearing method further comprises the following steps:

[0084] Step S600, based on the image comparison result, determine whether the passenger gets off the bus, and calculate the distance and time difference between the passenger getting on and getting off the bus, so as to obtain the passenger's mileage data and the passenger's time data.

[0085] In an embodiment of the present invention, after determining that the target passenger has gotten off the train based on the image comparison result, the distance and time difference between the subway station where the passenger got on the train and the subway station where the passenger got off the train are calculated. The time difference is the travel time data of the passenger on the train, and the distance is the passenger's mileage. The background computer can then attribute the passenger's mileage to the operator of the train to which the passenger belongs, and settle the mileage based on the passenger's mileage.

[0086] Specifically, Figure 4 A flow chart of obtaining passenger riding data in the method provided by an embodiment of the present invention is shown.

[0087] Among them, in a preferred embodiment of the present invention, the step of determining the passenger getting off the bus according to the image comparison result, and calculating the distance and time difference between the passenger getting on and getting off the bus, and obtaining the passenger's mileage data and the passenger's riding time data specifically includes the following steps:

[0088] Step S601, determining whether a passenger gets off the bus based on the image comparison result;

[0089] Step S602, calculating the track mileage between the passenger alighting station and the passenger boarding station to obtain passenger travel mileage data;

[0090] Step S603, subtract the passenger boarding time from the passenger alighting time to obtain the passenger boarding time data.

[0091] Furthermore, the rail transit passenger flow clearing method further comprises the following steps:

[0092] Step S700, comparing the passenger's boarding time data with the preset vehicle travel time to determine whether the passenger takes a return train.

[0093] In the embodiment of the present invention, the preset vehicle travel time refers to the required travel time of a train between stations. The travel time is usually fixed, and the actual required travel time of the train deviates from the preset vehicle travel time by about a few minutes.

[0094] After the passenger enters the train, although the comparison of the above-mentioned full-body images of the passenger getting on and off the train can determine at which two stations the passenger got on and off the train, it is impossible to determine whether the passenger took the return trip of the train. If the passenger took the return trip of the train, it would occupy the passenger flow of the train, resulting in deviation in the analysis of the passenger flow by the background computer, which in turn affects the subsequent clearing calculation;

[0095] It can be understood that in this method, by comparing the passenger's riding time data with the preset vehicle travel time, if the passenger's riding time is much longer than the preset vehicle travel time, it can be determined that the passenger took the return train of the train, and according to the actual length of the passenger's riding time, it can also be analyzed how many times the target passenger took the return trip of the train, thereby improving the accuracy of the analysis of the passenger flow of passengers taking the train by this rail transit passenger flow classification method, and making the subsequent passenger flow classification more accurate;

[0096] It is understandable that after the passenger gets off the train and completes the above steps, all information containing the passenger getting off the train in the designated train database should be deleted.

[0097] Figure 5 A flow chart of determining whether a passenger takes a return train in a method provided by an embodiment of the present invention is shown.

[0098] Among them, in a preferred embodiment of the present invention, the comparison of the passenger's boarding time data with the preset vehicle travel time to determine whether the passenger takes the return train specifically includes the following steps:

[0099] Step S701, comparing the passenger's boarding time data with the vehicle's preset travel time;

[0100] Step S702: If the passenger's travel time data is greater than the preset travel time of the vehicle, it is determined that the passenger takes a return train.

[0101] Furthermore, Figure 6 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0102] Among them, in another preferred embodiment provided by the present invention, a rail transit passenger flow sorting system includes:

[0103] The train identification unit 100 is used to identify the train number and obtain train information when the train arrives at the station.

[0104] In the embodiment of the present invention, the outer surface of each carriage of the train is affixed with the same barcode or QR code, and a number of smart cameras are installed in the platform hall of the subway, and the camera of each smart camera is aimed at the arrival area of ​​the train carriage. The number of smart cameras is the same as the number of carriages of the train. The above-mentioned smart cameras have functions such as face recognition, backlight compensation, picture adjustment and smart zoom, and the smart cameras are connected to the Internet via WIFI;

[0105] It can be understood that when the subway train arrives at the platform hall area of ​​the subway station, the smart camera captures the barcode or QR code on the train car and uploads the picture containing the barcode or QR code to the background computer. The train identification unit 100 reads the barcode or QR code in the picture and extracts the train information therein. The train information includes the train model, the operating unit to which the train belongs, the train schedule, and the train speed, etc.

[0106] Furthermore, the rail transit passenger flow sorting system further includes:

[0107] A designated train database matching unit 200 is used to match a designated train database according to train information;

[0108] In the embodiment of the present invention, when establishing a database, the background computer shall establish different train databases according to the models of different trains and the operators to which they belong. These train databases are relatively independent, and each train database only contains the passenger data on the corresponding train. These passenger data include the full-body image of the passenger and the boarding and alighting time of the passenger. After the train arrives at the station, the designated train database matching unit 200 can match the corresponding designated train database according to the train information.

[0109] It can be understood that by setting up multiple databases and setting up the databases independently, when the background computer identifies and reads passenger data, it only needs to perform identification and reading operations in the designated train database corresponding to the arriving train, thereby greatly reducing the computing power requirements of the background computer, thereby reducing investment costs, and the independent database setting facilitates subsequent passenger data deletion operations to ensure that passenger privacy is not leaked.

[0110] Furthermore, the rail transit passenger flow sorting system further includes:

[0111] The passenger image acquisition unit 300 is used to take full-body photos of passengers and record the boarding and alighting times when passengers get on and off the train, and to acquire full-body images of passengers getting on and off the train and the time of passengers getting on and off the train, as well as full-body images of passengers getting off and the time of passengers getting off the train.

[0112] The passenger image uploading unit 400 is used to upload the passenger boarding full-body image and the passenger boarding time as well as the passenger getting off the train full-body image and the passenger getting off time to the designated train database.

[0113] In an embodiment of the present invention, when passengers get on or off a train, the passenger image acquisition unit 300 will take a full-body photo of the passenger in motion and record the photo-taking time while taking the photo, and the photo-taking time is the time when the passenger gets on or off the train. Then, the passenger image uploading unit 400 will upload the full-body image of the passenger getting on the train and the time when the passenger gets on the train, as well as the full-body image of the passenger getting off the train and the time when the passenger gets off the train, to a designated train database that matches the arriving train.

[0114] Furthermore, the rail transit passenger flow sorting system further includes:

[0115] The image comparison unit 500 is used to compare the full-body image of the passenger getting off the train with a number of full-body images of passengers on the train in the designated train database to obtain an image comparison result.

[0116] In the embodiment of the present invention, the purpose of the image comparison unit 500 comparing the full-body image of the passenger getting off the train with several full-body images of passengers riding on the train in the designated train database is to determine the target passenger, that is, to determine the passenger who takes the train and completes the purpose of riding. After comparing the full-body image of the passenger getting off the train with several full-body images of passengers riding on the train in the designated train database one by one, the image comparison unit 500 determines the two images with the highest similarity and obtains the image comparison result, and determines whether the passenger getting off the train has completed the purpose of riding based on the image comparison result.

[0117] Specifically, Figure 7 It shows a structural block diagram of the image comparison unit 500 in the system provided by the embodiment of the present invention.

[0118] In a preferred embodiment of the present invention, the image comparison unit 500 specifically includes:

[0119] Image analysis module 501, used to analyze the full-body image of the passenger getting off the bus and obtain the passenger's clothing matching information;

[0120] The image comparison module 502 is used to compare the passenger clothing matching information with a number of passenger full-body images in the designated train database to obtain an image comparison result.

[0121] In the embodiment of the present invention, when the passenger image acquisition unit 300 is used to acquire the full-body image of the passenger getting on and off the train, due to the various limitations of the angle of the smart camera and the body shape and walking posture of the passenger, the smart camera cannot carefully capture the facial image and facial details of the passenger. Therefore, the accuracy of determining the target passenger by facial recognition is low, and it is also easy to miss the detection problem. Therefore, in the present method, after the full-body image of the passenger getting on and off the train acquired by the background computer is uploaded to the background computer, the image analysis module 501 performs image analysis on the full-body image of the passenger getting on and off the train, and obtains the passenger's clothing matching information in the image. The passenger clothing matching information refers to that the background computer extracts the clothing image from the full-body image of the passenger getting on and off the train separately to form a comparison image containing only the clothing image, and then the image comparison module 502 compares the comparison images extracted from different full-body images when comparing the full-body image of the passenger getting off the train with multiple full-body images of the passenger getting on the train in the designated train database, and obtains the two images with the highest similarity to determine the target passenger;

[0122] It can be understood that by using the passenger's clothing matching information to compare the passenger's full-body images when getting on and off the bus, the target passenger can be identified more accurately, and the steps for the background computer to identify the clothing matching information are relatively simple, and the corresponding computing power requirements for the background computer are relatively low, thereby improving the accuracy of passenger identification in this application.

[0123] Furthermore, the rail transit passenger flow sorting system further includes:

[0124] The distance and time difference calculation unit 600 is used to determine the passenger getting off the bus according to the image comparison result, and calculate the distance and time difference between the passenger getting on and getting off the bus, so as to obtain the passenger's mileage data and the passenger's time data.

[0125] In the embodiment of the present invention, after determining that the target passenger gets off the train based on the image comparison result, the distance and time difference calculation unit 600 calculates the distance and time difference between the subway station where the passenger gets on the train and the subway station where the passenger gets off the train. The time difference is the travel time data of the passenger on the train, and the distance is the passenger's mileage. The background computer can then attribute the passenger's mileage to the operator of the train to which the passenger belongs, and settle the mileage based on the passenger's mileage.

[0126] Specifically, Figure 8 It shows a structural block diagram of the distance and time difference calculation unit 600 in the system provided by the embodiment of the present invention.

[0127] In a preferred embodiment of the present invention, the distance and time difference calculation unit 600 specifically includes:

[0128] A station determination module 601 is used to determine the passenger to get off the train based on the image comparison result;

[0129] The mileage calculation module 602 is used to calculate the track mileage between the passenger alighting station and the passenger boarding station to obtain the passenger mileage data;

[0130] The riding time calculation module 603 is used to obtain the passenger riding time data by subtracting the passenger boarding time from the passenger getting off time.

[0131] Furthermore, the rail transit passenger flow sorting system further includes:

[0132] The return train determination unit 700 is used to compare the passenger's boarding time data with the preset vehicle travel time to determine whether the passenger takes the return train.

[0133] In the embodiment of the present invention, the preset vehicle travel time refers to the required travel time of a train between stations. The travel time is usually fixed, and the actual required travel time of the train deviates from the preset vehicle travel time by about a few minutes.

[0134] After the passenger enters the train, although the comparison of the above-mentioned full-body images of the passenger getting on and off the train can determine at which two stations the passenger got on and off the train, it is impossible to determine whether the passenger took the return trip of the train. If the passenger took the return trip of the train, it would occupy the passenger flow of the train, resulting in deviation in the analysis of the passenger flow by the background computer, which in turn affects the subsequent clearing calculation;

[0135] It can be understood that in the present method, by comparing the passenger's travel time data with the preset vehicle travel time, if the passenger's travel time is much longer than the preset vehicle travel time, and the return train judgment unit 700 can judge that the passenger has taken the return train of this train, and based on the actual length of the passenger's travel time, the return train judgment unit 700 can also analyze how many return trips the target passenger has taken on this train, thereby improving the accuracy of the analysis of the passenger flow of passengers taking the train by this rail transit passenger flow sorting method, and making the subsequent passenger flow sorting more accurate.

[0136] Specifically, Fig. 9 The structure block diagram of the return train judgment unit in the system provided by the embodiment of the present invention is shown.

[0137] Among them, in the preferred embodiment provided by the present invention, the return train judgment unit 700 specifically includes:

[0138] The time comparison module 701 is used to compare the passenger's boarding time data with the vehicle's preset travel time;

[0139] The judgment module 702 is used to judge whether the passenger takes a return train if the passenger's travel time data is greater than the preset travel time of the vehicle.

[0140] An electronic device, which may be a computer, comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the rail transit passenger flow clearing method.

[0141] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0142] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0143] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0144] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0145] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A rail transit passenger flow sorting method, characterized in that: The method comprises the following steps: When the train arrives at the station, identify the train number and obtain train information; According to the train information, matching a designated train database; The step of matching a designated train database according to the train information comprises: Determine the train model based on the train information; Match the specified train database according to the train model; When passengers get on and off the bus, full-body video of the passengers is taken and the time of getting on and off is recorded to obtain full-body images of passengers getting on and off the bus and the time of passengers getting on and off the bus; When establishing a database, different train databases should be established according to different train models and operators. These train databases are relatively independent, and each train database only contains the passenger data on the corresponding train. These passenger data include the full-body image of the passenger and the time when the passenger boarded and got off the train. After the train arrives at the station, the corresponding designated train database is matched according to the train information. Uploading the passenger boarding full-body image and the passenger boarding time as well as the passenger getting off the train full-body image and the passenger getting off time to a designated train database; Compare the full-body image of the passenger getting off the train with several full-body images of passengers on the train in a designated train database to obtain an image comparison result; Determine the passenger getting off the bus based on the image comparison result, and calculate the distance and time difference between the passenger getting on and getting off the bus to obtain the passenger's mileage data and the passenger's time data; The passenger's boarding time data is compared with the preset vehicle travel time to determine whether the passenger takes the return train.

2. The rail transit passenger flow sorting method according to claim 1, characterized in that: The step of comparing the full-body image of the passenger getting off the train with a plurality of full-body images of passengers on the train in the designated train database to obtain an image comparison result comprises: Perform image analysis on the full-body image of passengers getting off the bus to obtain information on their clothing combinations; The passenger clothing matching information is compared with several passenger full-body images in the designated train database to obtain image comparison results.

3. The rail transit passenger flow sorting method according to claim 1, characterized in that: The steps of determining the passenger getting off the bus according to the image comparison result, calculating the distance and time difference between the passenger getting on and getting off the bus, and obtaining the passenger's mileage data and the passenger's riding time data include: Determining, based on the image comparison result, that the passenger gets off the bus; Calculate the track mileage between the passenger alighting station and the passenger boarding station to obtain the passenger mileage data; Subtract the passenger boarding time from the passenger disembarkation time to obtain the passenger boarding time data.

4. The rail transit passenger flow sorting method according to claim 1, characterized in that: The step of comparing the passenger's boarding time data with the preset vehicle travel time to determine whether the passenger is taking a return train comprises: Comparing the passenger's boarding time data with the vehicle's preset travel time; If the passenger's travel time data is greater than the vehicle's preset travel time, it is determined that the passenger is taking a return train.

5. A rail transit passenger flow sorting system, characterized in that: The system comprises: a train identification unit, a designated train database matching unit, a passenger image acquisition unit, a passenger image upload unit, an image comparison unit, a distance and time difference calculation unit and a return train judgment unit, wherein: The train identification unit is used to identify the train number and obtain train information when the train arrives at the station; A designated train database matching unit is used to match a designated train database according to train information; Determine the train model based on the train information; Match the specified train database according to the train model; The passenger image acquisition unit is used to take full-body photos of passengers and record the time of getting on and off the bus when the passengers get on and off the bus, and to acquire full-body images of passengers getting on and off the bus and the time of passengers getting on and off the bus, as well as full-body images of passengers getting off and the time of passengers getting off the bus; When establishing a database, different train databases should be established according to different train models and operators. These train databases are relatively independent, and each train database only contains the passenger data on the corresponding train. These passenger data include the full-body image of the passenger and the time when the passenger boarded and got off the train. After the train arrives at the station, the corresponding designated train database is matched according to the train information. A passenger image uploading unit, used for uploading the passenger boarding full-body image and the passenger boarding time as well as the passenger getting off full-body image and the passenger getting off time to a designated train database; An image comparison unit, used for comparing the full-body image of the passenger getting off the train with a number of full-body images of passengers on the train in a designated train database, to obtain an image comparison result; A distance and time difference calculation unit, used to determine the passenger getting off the bus according to the image comparison result, and calculate the distance and time difference between the passenger getting on and getting off the bus, so as to obtain the passenger's mileage data and the passenger's time data; The return train judgment unit is used to compare the passenger's boarding time data with the vehicle's preset travel time to judge whether the passenger takes the return train.

6. The rail transit passenger flow sorting system according to claim 5, characterized in that: The image comparison unit specifically includes: An image analysis module is used to analyze the full-body image of the passenger getting off the bus and obtain the passenger's clothing matching information; The image comparison module is used to compare the passenger clothing matching information with several passenger full-body images in the designated train database to obtain image comparison results.

7. The rail transit passenger flow sorting system according to claim 5, characterized in that: The distance and time difference calculation unit specifically includes: A station determination module, used for determining the passenger to get off the train based on the image comparison result; The mileage calculation module is used to calculate the track mileage between the passenger alighting station and the passenger boarding station to obtain the passenger mileage data; The riding time calculation module is used to obtain the passenger riding time data by subtracting the passenger boarding time from the passenger getting off time.

8. The rail transit passenger flow sorting system according to claim 5, characterized in that: The return train judgment unit specifically includes: A time comparison module, used to compare the passenger's boarding time data with the vehicle's preset travel time; The judgment module is used to judge whether the passenger takes a return train if the passenger's travel time data is greater than the preset travel time of the vehicle.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the rail transit passenger flow sorting method as claimed in any one of claims 1 to 4.

Images