CN111064925A - Subway passenger ticket evasion behavior detection method and system - Google Patents
Subway passenger ticket evasion behavior detection method and system Download PDFInfo
- Publication number
- CN111064925A CN111064925A CN201911224925.3A CN201911224925A CN111064925A CN 111064925 A CN111064925 A CN 111064925A CN 201911224925 A CN201911224925 A CN 201911224925A CN 111064925 A CN111064925 A CN 111064925A
- Authority
- CN
- China
- Prior art keywords
- passenger
- ticket
- card swiping
- information
- behavior
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B11/00—Apparatus for validating or cancelling issued tickets
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Signal Processing (AREA)
- Devices For Checking Fares Or Tickets At Control Points (AREA)
Abstract
The invention provides a subway passenger ticket evasion behavior detection system and a method, wherein the system specifically comprises a passenger information marking module, a ticket evasion behavior detection module and a ticket evasion behavior detection module, wherein the passenger information marking module is used for identifying and marking whether a passenger is a passenger needing to purchase a ticket and takes a bus or not and whether the passenger carries an infant or not, grabbing face information and storing dynamic bus taking information of the passenger; the card swiping behavior identification module is used for judging whether a passenger swipes a card or not based on whether the intersection exists between the human skeleton motion track obtained by the depth camera and the card swiping area or not; the card swiping information reading module is used for reading the card swiping information and time of the gate machine, and the card swiping behavior is implemented while the card swiping success record is judged to be successful; and the fare evasion behavior judging and early warning module is used for combining passenger ticket purchasing mark information, card swiping behavior identification information, card swiping success record and passenger number identification fare evasion behavior and early warning. The method can automatically detect the ticket evasion behavior in the subway in real time and finish the compensation and deduction and early warning processing.
Description
Technical Field
The invention relates to the technical field of monitoring video processing, in particular to a subway passenger ticket evasion behavior detection method and system.
Background
At present, along with the continuous expansion of urbanization process, the urban rail transit system has larger and larger traffic flow, and in order to improve the transportation efficiency, an unattended automatic ticket selling and checking machine (AFC) system is widely used in the past decades, and meanwhile, the ticket evading phenomenon is increasingly severe. For individuals, the economic return obtained by the fare evasion behavior is low, and potential threats can be formed to personal safety when the gate is crossed and the passengers swipe cards are followed; for society, the behavior of ticket evasion not only disturbs the normal riding order, but also causes adverse psychological influence on surrounding passengers; from the social economic cost consideration, although the ticket evasion behavior brings about not little economic loss to subway operation management and is often prohibited, the economic loss caused by the single ticket evasion behavior is not high. Therefore, subway fare evasion behaviors need to be monitored and managed, and the method needs to be efficient.
Video monitoring is a type of management equipment widely distributed in subways, is mainly used for remote monitoring of equipment and station and hall activities and data retention, and is a common management means with low cost based on monitoring image identification of various abnormal events. The ticket evasion behavior can be monitored based on the monitoring video by utilizing the existing monitoring equipment, the cost of monitoring human resources of the ticket evasion behavior can be effectively saved by an automatic processing technology, and the method is an economical method.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: in order to overcome the defects in the prior art, the invention provides a subway passenger ticket evasion behavior detection method and system, and a method and system for automatically identifying, detecting and early warning the subway passenger ticket evasion behavior based on deep camera shooting, so that the subway passenger ticket evasion behavior can be accurately identified in real time and early warning is realized.
The technical scheme adopted for solving the technical problems is as follows: a subway passenger ticket evasion behavior detection method comprises the following steps:
first, passenger information identification. The information comprises the height characteristics of the passenger, whether the passenger carries the infant or not and the information of the face; the height characteristics refer to the condition that the passenger height standard belongs to one of three conditions of full ticket purchasing, preferential ticket purchasing and ticket purchasing no need, and are marked as a ticket purchasing passenger, a preferential ticket purchasing passenger and a ticket purchasing no need passenger; the face information is used for marking early warning and further tracking of the passengers who flee for a ticket.
Furthermore, the passenger information identification provides basis for the identification of the card swiping behavior, only the passenger marked as needing to swipe the card needs to complete the card swiping action, and basic data support is provided for the identification of the ticket evading behavior; generally, in the subway taking rules, 1 adult passenger who normally swipes a card can carry 1 ticket-free passenger for free, the marked ticket-free passenger can avoid misjudgment of the ticket evading behavior when following an arrival, and the marked passenger carries an infant and can also avoid misjudgment of the ticket evading behavior when following an arrival.
The passenger height characteristics can be realized by adopting various height detection methods, and the method is not limited uniquely. For example, the method adopted in the method is to obtain the spatial position of the top of the human head based on depth camera shooting, then compare the spatial position with the height calibration point of the ticket purchasing height in the space and judge the ticket purchasing attribute of the passenger; based on the depth difference surface separation during the depth shooting, the head of the human body is identified and the ticket purchasing attribute is judged respectively, and special situations such as holding infants and the like can also be identified.
And secondly, identifying the card swiping behavior. Extracting video data of each gate channel based on depth camera shooting, and identifying card swiping behaviors of a human body; in the depth image, the card swiping position of the gate machine is located at a fixed position in a depth space, and the depth range of the card swiping area and the image range of the card swiping area in the depth image are marked according to the learning of the card swiping behaviors of multiple persons; and (3) identifying key skeleton points of human motion and depth track information of the key skeleton points when the key skeleton points pass through a gate channel by adopting a kinect2.0 system, judging that a card swiping action exists if the human motion track, particularly a palm track, is crossed and overlapped with a marked card swiping area, and otherwise marking a non-card swiping action for passengers, and extracting system time for implementing the card swiping action.
And thirdly, judging whether the card swiping is successful or not. When the passenger successfully swipes the card at the gate and goes out, the gate system outputs card swiping success information to the card swiping behavior identification system, wherein the card swiping success information comprises a card swiping card number and card swiping time, and whether the passenger successfully swipes the card or not is judged through comparison between the card swiping time and the card swiping behavior marking time, and the passenger card swiping information is further marked. Preferably, when the card swiping card number or the mobile payment account information and the card swiping time are determined to be successful, the card swiping card number or the mobile payment account information and the card swiping time are written into passenger mark information as dynamic information, and the account number related telephone number or the identity card information is written into the passenger mark information. Once the passenger swipes the card, the computer system automatically reads the card number and associated telephone number and tags the personal information of the passenger for judgment.
The card swiping behavior identification is the basis of the ticket evasion behavior judgment, passengers needing to take a full ticket need to swipe cards or swipe mobile phones to pay for entering the station, passengers holding preferential cards need to swipe cards for entering the station, and passengers without tickets do not need to swipe cards; when the ticket-free passenger has the card swiping behavior and successfully swipes the card, marking the trailing inbound passenger to finish the card swiping payment.
And fourthly, determining and early warning the ticket evasion behavior. And comparing the marking information of the passenger with the card swiping behavior identification information, judging whether the passenger has the ticket evading behavior, giving an early warning to the ticket evading behavior, issuing a voice warning to the passenger who does not effectively hold the ticket for the individual, and issuing a ticket evading alarm and displaying information of the face, the passenger card number and the telephone number to an operation management monitoring department.
The ticket evasion behavior comprises the following steps: marking ticket buying passengers and preferential ticket buying passengers to judge as ticket evading behaviors when no card swiping behaviors exist; marking ticket buying passengers and preferential ticket passengers to have card swiping behaviors and not to have card swiping success records to judge as ticket evading behaviors; and judging the behavior of ticket evasion by carrying more than 1 ticket-free passenger.
Preferably, the judgment of the behavior of carrying more than 1 ticket-free passenger for judging ticket evasion is realized by passenger information marking and people counting, when more than 2 ticket-free passengers exist among 2 successful passengers swiping cards, the first person swiping the cards is judged to have the behavior of ticket evasion, and all passenger face information is extracted to be used as the information marking of the ticket evasion of the passengers; when more than 1 ticket-free passenger exists among 2 passengers carrying infants and successfully swiping cards, judging that the card-swiping person has a ticket evasion behavior, and extracting face information of all passengers to mark ticket evasion information for the ticket evasion passengers; after 1 passenger who carries infants and swipes the card successfully, marking that the card swiping success of the passenger who purchases the ticket subsequently is carried out when the card swiping behavior of the 1 passenger who avoids the ticket exists and the card swiping success is successful, and marking that the passenger who carries the infants carries the passengers; and when 1 passenger carrying an infant and swipes the card successfully, the 1 ticket-free passenger and the passenger swipes the card successfully pass through the system, and the system is judged to have no ticket evasion behavior.
Further, the ticket evasion behavior early warning system executes a fare deduction program for passengers marked with the personal fare cards and the telephone numbers and sends processing prompt information to the passenger telephones; and establishing an fare evasion information base for passengers without personal riding cards and telephone numbers, wherein the fare evasion information base comprises fare evasion passenger face information, fare evasion behavior information and fare evasion process monitoring videos. The technical scheme of how the fare evasion judging and early warning system realizes the refund and deduction has various modes, and is not the concern of the invention, so the details are not described herein.
In order to realize the method of the invention, the application provides a system for detecting the ticket evading behavior of subway passengers, which specifically comprises a kinect2.0 depth camera and a 4-system processing module:
kinect2.0 degree of depth camera is installed at business turn over station floodgate machine rear for collect the motion video that the passenger passed through the floodgate machine passageway, in order to avoid the problem of sheltering from that the human body discrepancy in elevation brought, adjustment camera installation angle makes the best effective visual field cover floodgate machine passageway, and camera main shaft and floodgate machine top surface slope cross, perhaps the camera is facing to the floodgate machine passageway that needs detected to one side. Another kinect2.0 degree of depth camera is installed at floodgate machine top station room top, adopts wide angle camera, and the best field of view covers the region that gets into floodgate machine the place ahead for detect the human head top degree of depth value and the motion track point before getting into the floodgate machine by bus.
The 4 large system processing modules comprise: the system comprises a passenger information marking module, a card swiping behavior identification module, a card swiping information reading module and a ticket evasion behavior judgment and early warning module. The modules can be software or realize the functions of the modules by executing the corresponding software through hardware.
The passenger information marking module is used for identifying and marking the height characteristics of the passenger, whether the passenger carries an infant or not, the face information, the riding card information, the mobile payment account information, the telephone number information, the dynamic riding information and the like, capturing the face information and storing the dynamic riding information of the passenger. The dynamic riding information comprises passenger card swiping records and ticket evasion information.
And the card swiping behavior identification module is used for detecting whether the passenger has card swiping behavior. Judging whether the passenger swipes the card or not based on the intersection of the human skeleton motion trail obtained by the depth camera and the card swiping area; extracting video data of each gate channel based on depth camera shooting; in the depth image, the card swiping position of the gate machine is located at a fixed position in a depth space, and the depth range of the card swiping area and the image range of the card swiping area in the depth image are marked according to the learning of the card swiping behaviors of multiple persons; a kinect2.0 system is adopted to identify key skeleton points of human motion and depth track information when the key skeleton points pass through a gate channel, if the human motion track, particularly the palm track, is overlapped with a marked card swiping area in a crossing way, the card swiping action is judged to be carried out, and if not, the non-card swiping action is marked for passengers; and extracting the system time for implementing the card swiping behavior.
The card swiping information reading module is used for reading card swiping success information of the gate system, and the read information comprises card swiping card numbers or mobile payment account numbers and card swiping time, and phone numbers or identity card information related to the card numbers or the account numbers. Card number or mobile payment account information and card swiping time are used as dynamic information to be written into passenger marking information, and telephone number or identity card information related to the card number or the account is written into the passenger marking information. And further, judging whether the passenger successfully swipes the card or not by comparing the card swiping time with the card swiping behavior marking time and further marking the card swiping information of the passenger. And when the card swiping behavior is implemented, the card swiping success record is judged to be successful.
And the fare evasion behavior judgment and early warning module is used for comparing the ticket purchasing mark information, the card swiping behavior identification information, the card swiping success record and the number of passing persons of the passengers, judging whether the passengers have fare evasion behaviors or not and early warning the fare evasion behaviors.
The early warning of the ticket evasion behavior is to issue voice warning to an individual who does not effectively hold a ticket, issue ticket evasion alarm and display information of a face, a passenger card number and a telephone number to an operation management monitoring department; for the passengers marked with the personal riding cards and the telephone numbers, the system executes a riding money deduction program and sends processing prompt information to the passenger telephones; and establishing an fare evasion information base for passengers without personal riding cards and telephone numbers, wherein the fare evasion information base comprises fare evasion passenger face information, fare evasion behavior information and fare evasion process monitoring videos.
The invention has the beneficial effects that: the invention provides a subway passenger ticket evasion behavior detection system and method, which are based on whether a human motion skeleton subjected to deep image pickup has a card swiping behavior and are compared with the number of passengers who successfully swipe cards and carry ticket-free passengers, so that whether the passengers evade tickets is judged, and money compensation processing and notification are performed according to passenger marking information. The method can automatically detect the ticket evasion behavior in the subway in real time and finish the compensation and deduction and early warning processing, and the detection system is simple in device and convenient to use.
Drawings
The invention is further illustrated by the following figures and examples.
FIG. 1 is a schematic diagram of one embodiment of the present invention;
FIG. 2 is a diagram of a passenger ticketing information tag structure according to an embodiment of the present invention;
Detailed Description
The present invention will now be described in detail with reference to the accompanying drawings. This figure is a simplified schematic diagram, and merely illustrates the basic structure of the present invention in a schematic manner, and therefore it shows only the constitution related to the present invention.
As shown in fig. 1 and fig. 2, the subway passenger fare evasion behavior detection system of the present invention comprises a passenger information marking module, a card swiping behavior recognition module, a card swiping information reading module and a fare evasion behavior determination and pre-warning module, wherein,
the passenger information marking module is used for identifying and marking whether the passenger is a passenger needing ticket buying and taking a bus or not and carrying an infant, grabbing face information and storing dynamic bus taking information of the passenger;
the card swiping behavior identification module is used for judging whether a passenger swipes a card or not based on whether the intersection exists between the human skeleton motion track obtained by the depth camera and the card swiping area or not;
the card swiping information reading module is used for reading the card swiping information and time of the gate machine, and the card swiping behavior is implemented while the card swiping success record is judged to be successful;
and the fare evasion behavior judging and early warning module is used for combining passenger ticket purchasing mark information, card swiping behavior identification information, card swiping success record and passenger number identification fare evasion behavior and early warning.
As shown in fig. 1, a subway passenger ticket evasion behavior detection method includes the following steps:
s11: and the passenger information marking module is used for detecting the height of the passenger, marking the passenger ticket purchasing attribute and marking the related information of the passenger.
The passenger height detection and ticket purchasing attribute mark judges the head space position of a human body based on depth camera shooting, and then compares the head space position with a ticket purchasing height calibration point in the space to judge the ticket purchasing attribute of the passenger; meanwhile, the depth difference surface separation during the depth image pickup follows the depth cross section of the human body and the infant embracing body, the vertex of the human body is respectively identified, the ticket purchasing attribute is judged, and special situations such as the infant embracing body, the carrying of personal belongings and the like can also be identified by utilizing the human body model through comparison analysis. The passenger height characteristics can be realized by adopting various height detection methods, and the method is not limited uniquely. Fig. 2 is a passenger information mark structure diagram of a subway passenger ticket evasion behavior detection method and system device according to an embodiment of the present invention, wherein 1 wide-angle kinect2.0 camera is installed at the top of a station hall above a gate, and an optimal view field covers an area in front of the gate for detecting a human vertex depth value and a motion track point before a ride enters the gate; the identification points of the height limit value height of the ticket purchasing height are arranged on the wall surface, 4 identification points form a rectangular height detection area in space, and the height characteristic detection can be completed when people reach the front of the gate through the area; measuring the depths of 4 identification points, calculating and marking the depth value and pixel coordinate of each pixel point in the detection area in a depth camera RGB image, comparing the y coordinates of the two points when the human head top depth value and the x coordinate thereof in the RGB image are consistent with the calibration point, and when the human head top y value is larger, representing that the human height exceeds the ticket purchasing limit value; and marking the ticket purchasing attribute of the passenger after detection is finished: and the system can be used for buying tickets in full amount, buying tickets in preferential amount and not needing to buy tickets, and analyzing whether the marks carry infants or carry personal belongings or not according to the depth difference.
The passenger marking information includes: the system comprises height characteristics, ticket purchasing attributes, carrying or not carrying of infants, face information, riding card information, mobile payment account information, telephone number information and dynamic riding information, wherein the dynamic riding information comprises passenger card swiping records and ticket evasion information. The face information is captured in the height detection process, and the mobile payment account information related to the fare evasion passenger can be searched for according to face comparison when necessary; the dynamic riding information comprises daily riding record and ticket evasion behavior information of passengers, and can be used for evidence of implementation measures such as ticket card deduction and the like in the follow-up process and can also be used as credit investigation record supporting materials.
S12: and the card swiping behavior identification module is used for detecting whether the passenger has card swiping behavior. The specific measures for identifying the fare evasion behavior based on the depth camera include: (1) video data of each gate channel is extracted based on depth camera shooting, a camera is installed behind the gate of the station, the installation angle of the camera is adjusted to ensure that the gate channel is covered by the optimal effective view field, the camera is obliquely opposite to the gate channel to be detected, and in order to ensure the processing quality, the number of channels processed by the camera at the same time can be limited by shielding the view angle of the camera; (2) in a depth image of video data, a gate card swiping position is located at a fixed position in a depth space, and a depth range of a card swiping area and a position area of the card swiping area in a depth image are marked through multi-person card swiping behavior learning; (3) a kinect2.0 system is adopted to identify key skeleton points of human motion, and depth values and position information in the motion process of the key skeleton points are extracted to form a motion track; and depth track information when it passes through the gate channel; (4) if the human body movement track, particularly the palm track, is overlapped with the marked card swiping area in a crossing way, the card swiping behavior is judged to exist, otherwise, the passenger is marked with the non-card swiping behavior, and meanwhile, the system time for implementing the card swiping behavior is extracted.
S13: and the card swiping information reading module is used for reading the card swiping success information of the gate system. The specific read-in information comprises a card swiping number or a mobile payment account number, card swiping time, a card number or account number associated telephone number and identity card information. And the card swiping number or the mobile payment account information and the card swiping time are used as dynamic information to be written into passenger mark information, and the account number related telephone number or the identity card information is written into the passenger identity mark information. Preferably, whether the passenger successfully swipes the card can be judged by comparing the card swiping time with the card swiping behavior marking time, and further, card swiping record information is marked for the passenger after the card swiping is successful.
S14: and the fare evasion behavior judgment and early warning module is used for comparing passenger marking information, card swiping behavior identification information and card swiping records, judging whether the passenger has a fare evasion behavior or not and early warning the fare evasion behavior. The fare evasion determination specifically includes: (1) marking ticket buying passengers and preferential ticket buying passengers to judge as ticket evading behaviors when no card swiping behaviors exist; (2) marking ticket buying passengers and preferential ticket passengers to have card swiping behaviors and not to have card swiping success records to judge as ticket evading behaviors; (3) and judging the behavior of ticket evasion by carrying more than 1 ticket-free passenger.
Preferably, the decision of the fare evasion behavior of the passengers carrying more than 1 free ticket is realized by comparing passenger information marks with people counting, the human decision of the people counting is completed by a passenger detection and marking module, and the number of the human bodies passing through a gate passage is only counted. Specifically, the fare evasion determination method includes: (1) when more than 2 ticket-free passengers exist among 2 successful passengers swiping the cards, judging that the person swiping the cards has a ticket evasion behavior, and extracting face information of all passengers to mark the ticket evasion information for the ticket evasion passengers; (2) when more than 1 ticket-free passenger exists among 2 passengers carrying infants and successfully swiping cards, judging that the card-swiping person has a ticket evasion behavior, and extracting face information of all passengers to mark ticket evasion information for the ticket evasion passengers; (3) after 1 passenger who carries infants and swipes the card successfully, marking that the card swiping success of the passenger who purchases the ticket subsequently is carried out when the card swiping behavior of the 1 passenger who avoids the ticket exists and the card swiping success is successful, and marking that the passenger who carries the infants carries the passengers; (4) and when 1 passenger carrying an infant and swipes the card successfully, the 1 ticket-free passenger and the passenger swipes the card successfully pass through the system, and the system is judged to have no ticket evasion behavior.
Preferably, the fare evasion behavior early warning method includes: (1) issuing a voice warning to the passenger who does not effectively take a ticket to the individual, and executing a fare compensation program and sending processing prompt information to the passenger telephone by the system for the passenger who marks the individual fare card and the telephone number; (2) establishing an fare evasion information base for passengers who do not mark personal riding cards, telephone numbers and associated accounts, wherein the fare evasion information base comprises fare evasion passenger face information, fare evasion behavior information and fare evasion process monitoring videos; (3) issuing ticket evasion alarm and face, passenger card number and telephone number information display to an operation management monitoring department, and prompting relevant accounts to make up for ticket money or prompting that the information is insufficient according to the passenger information and writing the information into a ticket evasion information base; (4) the operation management department can transfer the ticket evasion information base data obtained by monitoring to a public security system or a credit investigation management department according to the requirement.
The method judges whether the passenger successfully swipes the card based on the intersection of the moving human body track and the card swiping position of the space fixed position and the comparison of the card swiping records, and then combines the ticket purchasing attribute of the passenger and the number of passengers carrying the ticket-free passenger to identify the ticket evading behavior, and sends out early warning, executes the deduction and other measures. The method can automatically detect the ticket evasion behavior in the subway in real time, and meanwhile, the money deduction, the early warning processing and the information storage are completed, and the detection system is simple in device and convenient to use.
In light of the foregoing description of preferred embodiments in accordance with the invention, it is to be understood that numerous changes and modifications may be made by those skilled in the art without departing from the scope of the invention. The technical scope of the present invention is not limited to the contents of the specification, and must be determined according to the scope of the claims.
Claims (9)
1. A subway passenger ticket evasion behavior detection method is characterized in that: the method comprises the following steps:
s11: detecting and marking passenger information, and judging whether ticket buying is needed or not;
s12: recognizing and marking card swiping behaviors, recognizing key skeleton point tracks of human body movement, recognizing whether a human body swipes a card when passing through a gate channel, and marking card swiping information;
s13: reading the marked card swiping information and judging whether the passenger swipes the card successfully;
s14: and (4) determining the ticket evasion behavior and carrying out early warning by combining the marking information, the card swiping behavior data, the card swiping record and the person number identification result detection.
2. The subway passenger ticket evasion behavior detection method as claimed in claim 1, characterized in that: the passenger information in the step S11 comprises the height characteristics of the passenger, whether the passenger carries the infant and the face information or not; the passenger height characteristic refers to the passenger height standard which belongs to the three conditions of full ticket purchasing, preferential ticket purchasing and ticket purchasing no need; the face information is used for marking early warning and tracking of the fare evasion passengers.
3. The subway passenger ticket evasion behavior detection method as claimed in claim 1, characterized in that: the step S12 of recognizing the card swiping behavior and marking specifically comprises the following steps:
extracting video data of each gate channel based on depth camera shooting, and identifying card swiping behaviors of a human body; in the depth image, the card swiping position of the gate machine is located at a fixed position in a depth space, and the depth range of the card swiping area and the image range of the card swiping area in the depth image are marked according to the learning of the card swiping behaviors of multiple persons; and (3) identifying key skeleton points of human motion and depth track information of the key skeleton points when the key skeleton points pass through a gate channel by adopting a kinect2.0 system, judging that a card swiping behavior exists when the human motion track and a marked card swiping area are crossed and overlapped, otherwise, marking a non-card swiping behavior for passengers, and extracting system time for implementing the card swiping behavior.
4. The subway passenger ticket evasion behavior detection method as claimed in claim 1, characterized in that: the step S13 of determining whether the card swiping is successful specifically includes the following steps:
when the passenger successfully swipes the card at the card swiping position of the gate machine, the gate machine system outputs card swiping success information to the card swiping behavior identification system, wherein the card swiping success information comprises a card swiping card number and card swiping time, and whether the passenger successfully swipes the card or not is judged by comparing the card swiping time with the card swiping behavior marking time and the passenger card swiping information is further marked;
the card swiping behavior identification is the basis of the ticket evasion behavior judgment, passengers needing to take a full ticket need to swipe cards or swipe mobile phones to pay for entering the station, passengers holding preferential cards need to swipe cards for entering the station, and passengers without tickets do not need to swipe cards; when the ticket-free passenger has the card swiping behavior and successfully swipes the card, marking the trailing inbound passenger to finish the card swiping payment.
5. The subway passenger ticket evasion behavior detection method as claimed in claim 4, characterized in that: and when the card swiping card number or the mobile payment account information and the card swiping time are judged to be successful, writing the card swiping card number or the mobile payment account information and the card swiping time into passenger marking information as dynamic information, and writing account number-associated telephone number or identity card information into the passenger marking information.
6. The subway passenger ticket evasion behavior detection method as claimed in claim 1, characterized in that: the step S14 of determining and warning the fare evasion behavior specifically includes the following steps:
comparing the marking information of the passenger with the card swiping behavior identification information, judging whether the passenger has the ticket evading behavior, giving an early warning to the ticket evading behavior, issuing a voice warning to the passenger who does not effectively hold the ticket to the individual, and issuing a ticket evading alarm and displaying the face, the passenger card number and the telephone number information to an operation management monitoring department;
the ticket evasion behavior early warning is that for passengers marked with individual riding, a system executes a riding money deduction program and sends processing prompt information to passenger telephones; and establishing an fare evasion information base for passengers without marked individual rides, wherein the fare evasion information base comprises fare evasion passenger face information, fare evasion behavior information and fare evasion process monitoring videos.
7. The subway passenger ticket evasion behavior detection method as claimed in claim 6, characterized in that: the ticket evasion behavior comprises a behavior of marking ticket purchasing passengers and judging the ticket evasion behavior when the preferential ticket passengers do not have a card swiping behavior; marking ticket buying passengers and preferential ticket passengers to have card swiping behaviors and not to have card swiping success records to judge as ticket evading behaviors; or the behavior of carrying more than 1 ticket-free passenger to judge as ticket evasion.
8. The subway passenger ticket evasion behavior detection method as claimed in claim 7, characterized in that: the judgment of the behavior of the passengers carrying more than 1 free ticket as the ticket evasion is realized through passenger information marking and people counting, when more than 2 free ticket passengers exist among 2 successful card swiping passengers, the passengers firstly swipe the cards and judge that the ticket evasion behavior exists, and all passenger face information is extracted to be used as the ticket evasion information marking of the passengers; when more than 1 ticket-free passenger exists among 2 passengers carrying infants and successfully swiping cards, judging that the card-swiping person has a ticket evasion behavior, and extracting face information of all passengers to mark ticket evasion information for the ticket evasion passengers; after 1 passenger who carries infants and swipes the card successfully, marking that the card swiping success of the passenger who purchases the ticket subsequently is carried out when the card swiping behavior of the 1 passenger who avoids the ticket exists and the card swiping success is successful, and marking that the passenger who carries the infants carries the passengers; and when 1 passenger carrying an infant and swipes the card successfully, the 1 ticket-free passenger and the passenger swipes the card successfully pass through the system, and the system is judged to have no ticket evasion behavior.
9. A subway passenger behavior of fleing a bill detecting system which characterized in that: comprises a passenger information marking module, a card swiping behavior identification module, a card swiping information reading module and a ticket evasion behavior judging and early warning module, wherein,
the passenger information marking module is used for identifying and marking whether the passenger is a passenger needing ticket buying and taking a bus or not and carrying an infant, grabbing face information and storing dynamic bus taking information of the passenger;
the card swiping behavior identification module is used for judging whether a passenger swipes a card or not based on whether the intersection exists between the human skeleton motion track obtained by the depth camera and the card swiping area or not;
the card swiping information reading module is used for reading the card swiping information and time of the gate machine, and the card swiping behavior is implemented while the card swiping success record is judged to be successful;
and the fare evasion behavior judging and early warning module is used for combining passenger ticket purchasing mark information, card swiping behavior identification information, card swiping success record and passenger number identification fare evasion behavior and early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911224925.3A CN111064925B (en) | 2019-12-04 | 2019-12-04 | Subway passenger ticket evasion behavior detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911224925.3A CN111064925B (en) | 2019-12-04 | 2019-12-04 | Subway passenger ticket evasion behavior detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111064925A true CN111064925A (en) | 2020-04-24 |
| CN111064925B CN111064925B (en) | 2021-05-04 |
Family
ID=70299712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911224925.3A Active CN111064925B (en) | 2019-12-04 | 2019-12-04 | Subway passenger ticket evasion behavior detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111064925B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200828A (en) * | 2020-09-03 | 2021-01-08 | 浙江大华技术股份有限公司 | Detection method and device for ticket evasion behavior and readable storage medium |
| CN113014870A (en) * | 2021-02-20 | 2021-06-22 | 同济大学 | Subway gate passage ticket evasion identification method based on passenger posture rapid estimation |
| CN113159009A (en) * | 2021-06-25 | 2021-07-23 | 华东交通大学 | Intelligent monitoring and identifying method and system for preventing ticket evasion at station |
| CN113297954A (en) * | 2021-05-21 | 2021-08-24 | 中铁第四勘察设计院集团有限公司 | Ticket checking method and system for tramcar, computer equipment and readable medium |
| CN114387715A (en) * | 2022-01-12 | 2022-04-22 | 深圳市锐宝智联信息有限公司 | Face recognition gate, gate control method, terminal device and storage medium |
| CN114613024A (en) * | 2022-03-23 | 2022-06-10 | 成都智元汇信息技术股份有限公司 | Method, device and system for pushing face recognition picture based on action data |
| CN114694217A (en) * | 2022-03-23 | 2022-07-01 | 成都智元汇信息技术股份有限公司 | Method, device and system for pushing face passing label based on action data |
| CN115482612A (en) * | 2021-06-15 | 2022-12-16 | 咪付(深圳)网络技术有限公司 | Ticket checking identification method, identification terminal and gate |
| CN117392585A (en) * | 2023-10-24 | 2024-01-12 | 广州广电运通智能科技有限公司 | Gate traffic detection method and device, electronic equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040183717A1 (en) * | 2003-03-17 | 2004-09-23 | Conley Joseph Gerard | Cosmic background radiation abnomality detector |
| CN102663833A (en) * | 2012-05-16 | 2012-09-12 | 天津市天元新泰科技发展有限公司 | Method for identifying traffic events for special gate of urban railway transit |
| CN103197762A (en) * | 2013-03-29 | 2013-07-10 | 宁凯 | Somatosensory external device capable of expanding recognizing distance and human height recognizing method |
| CN103605967A (en) * | 2013-11-26 | 2014-02-26 | 东华大学 | Subway fare evasion prevention system and working method thereof based on image recognition |
| CN103778704A (en) * | 2014-02-11 | 2014-05-07 | 上海理工大学 | Intelligent identification method for gate accidents of urban mass transit |
| CN103942865A (en) * | 2014-04-18 | 2014-07-23 | 上海交通大学 | Subway ticket evasion preventing system based on ultrasonic sensor and design method thereof |
| CN104805784A (en) * | 2015-03-30 | 2015-07-29 | 苏州华兴致远电子科技有限公司 | Gate fare evasion detection system and gate fare evasion detection method |
| CN105447466A (en) * | 2015-12-01 | 2016-03-30 | 深圳市图灵机器人有限公司 | Kinect sensor based identity comprehensive identification method |
| CN107025418A (en) * | 2016-01-29 | 2017-08-08 | 广州地铁集团有限公司 | Anti- detection method of stealing a ride, detecting system and its system based on image procossing |
| CN108629334A (en) * | 2018-06-01 | 2018-10-09 | 西京学院 | A kind of bus based on Face datection is stolen a ride verifying attachment and the method for inspection |
| US20190197316A1 (en) * | 2017-12-27 | 2019-06-27 | Bornfreedom Power P | Video-related system, method and device |
| CN111460924A (en) * | 2020-03-16 | 2020-07-28 | 上海师范大学 | Gate ticket-passing behavior detection method based on target detection |
-
2019
- 2019-12-04 CN CN201911224925.3A patent/CN111064925B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040183717A1 (en) * | 2003-03-17 | 2004-09-23 | Conley Joseph Gerard | Cosmic background radiation abnomality detector |
| CN102663833A (en) * | 2012-05-16 | 2012-09-12 | 天津市天元新泰科技发展有限公司 | Method for identifying traffic events for special gate of urban railway transit |
| CN103197762A (en) * | 2013-03-29 | 2013-07-10 | 宁凯 | Somatosensory external device capable of expanding recognizing distance and human height recognizing method |
| CN103605967A (en) * | 2013-11-26 | 2014-02-26 | 东华大学 | Subway fare evasion prevention system and working method thereof based on image recognition |
| CN103778704A (en) * | 2014-02-11 | 2014-05-07 | 上海理工大学 | Intelligent identification method for gate accidents of urban mass transit |
| CN103942865A (en) * | 2014-04-18 | 2014-07-23 | 上海交通大学 | Subway ticket evasion preventing system based on ultrasonic sensor and design method thereof |
| CN104805784A (en) * | 2015-03-30 | 2015-07-29 | 苏州华兴致远电子科技有限公司 | Gate fare evasion detection system and gate fare evasion detection method |
| CN105447466A (en) * | 2015-12-01 | 2016-03-30 | 深圳市图灵机器人有限公司 | Kinect sensor based identity comprehensive identification method |
| CN107025418A (en) * | 2016-01-29 | 2017-08-08 | 广州地铁集团有限公司 | Anti- detection method of stealing a ride, detecting system and its system based on image procossing |
| US20190197316A1 (en) * | 2017-12-27 | 2019-06-27 | Bornfreedom Power P | Video-related system, method and device |
| CN108629334A (en) * | 2018-06-01 | 2018-10-09 | 西京学院 | A kind of bus based on Face datection is stolen a ride verifying attachment and the method for inspection |
| CN111460924A (en) * | 2020-03-16 | 2020-07-28 | 上海师范大学 | Gate ticket-passing behavior detection method based on target detection |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200828A (en) * | 2020-09-03 | 2021-01-08 | 浙江大华技术股份有限公司 | Detection method and device for ticket evasion behavior and readable storage medium |
| CN113014870A (en) * | 2021-02-20 | 2021-06-22 | 同济大学 | Subway gate passage ticket evasion identification method based on passenger posture rapid estimation |
| CN113014870B (en) * | 2021-02-20 | 2022-09-20 | 同济大学 | Subway gate passage ticket evasion identification method based on passenger posture rapid estimation |
| CN113297954A (en) * | 2021-05-21 | 2021-08-24 | 中铁第四勘察设计院集团有限公司 | Ticket checking method and system for tramcar, computer equipment and readable medium |
| CN115482612A (en) * | 2021-06-15 | 2022-12-16 | 咪付(深圳)网络技术有限公司 | Ticket checking identification method, identification terminal and gate |
| CN113159009A (en) * | 2021-06-25 | 2021-07-23 | 华东交通大学 | Intelligent monitoring and identifying method and system for preventing ticket evasion at station |
| CN114387715A (en) * | 2022-01-12 | 2022-04-22 | 深圳市锐宝智联信息有限公司 | Face recognition gate, gate control method, terminal device and storage medium |
| CN114613024A (en) * | 2022-03-23 | 2022-06-10 | 成都智元汇信息技术股份有限公司 | Method, device and system for pushing face recognition picture based on action data |
| CN114694217A (en) * | 2022-03-23 | 2022-07-01 | 成都智元汇信息技术股份有限公司 | Method, device and system for pushing face passing label based on action data |
| CN117392585A (en) * | 2023-10-24 | 2024-01-12 | 广州广电运通智能科技有限公司 | Gate traffic detection method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111064925B (en) | 2021-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111064925B (en) | Subway passenger ticket evasion behavior detection method and system | |
| CN101276499B (en) | Intelligent monitoring apparatus of ATM equipment based on all-directional computer vision | |
| US20110194733A1 (en) | System and method for optical license plate matching | |
| CN104574954B (en) | A kind of vehicle auditing method, control device and system based on free streaming system | |
| US20140369566A1 (en) | Perimeter Image Capture and Recognition System | |
| JPH01319898A (en) | Toll collecting device | |
| MX2010005149A (en) | Security systems. | |
| CN104029680A (en) | Lane departure warning system and method based on monocular camera | |
| CN108583592A (en) | A kind of subway service on buses or trains job information acquisition intelligent detecting method | |
| CN105374091A (en) | Intelligent security check self-service customs clearance method, system and equipment | |
| JP2018022366A (en) | Parking lot management system | |
| JP2021096878A (en) | Information processing apparatus, information processing method, program, and information processing system | |
| CN111161430A (en) | Real-name self-service ticket selling and checking integrated device and method | |
| CN101692281A (en) | Safety monitoring method, safety monitoring device and automatic teller machine (ATM) system | |
| CN114627526A (en) | Fusion duplicate removal method and device based on multi-camera snapshot image and readable medium | |
| WO2014102047A1 (en) | Method for combatting fraud, and corresponding system | |
| JP2010108166A (en) | Tracking device, tracking method and tracking program | |
| CN104899574A (en) | In-out event detection method and system | |
| CN113901946A (en) | Abnormal behavior detection method and device, electronic equipment and storage medium | |
| CN114821490A (en) | Airport departure layer illegal vehicle automatic identification method based on deep learning | |
| CN101576960A (en) | Method and system for detecting foreign materials | |
| KR20210066081A (en) | Parking management system capable of recognizing thai car number and the method there of | |
| CN115641728B (en) | ETC charge auditing method, ETC charge auditing system, electronic equipment and medium | |
| TWI617997B (en) | Intelligent object detection assistance system and method | |
| CN107689085A (en) | A kind of ticket-checking system of urban track traffic |
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 |