CN113936247A - Passenger flow state identification system of rail transit station based on streamline perception - Google Patents
Passenger flow state identification system of rail transit station based on streamline perception Download PDFInfo
- Publication number
- CN113936247A CN113936247A CN202111110065.8A CN202111110065A CN113936247A CN 113936247 A CN113936247 A CN 113936247A CN 202111110065 A CN202111110065 A CN 202111110065A CN 113936247 A CN113936247 A CN 113936247A
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- flow
- data
- detection
- streamline
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a passenger flow state identification system of a rail transit station based on streamline perception. The data server is used for storing and managing streamline sensing data, passenger flow detection data, passenger flow identification data and station passenger flow basic data; the flow line sensing server is used for carrying out station physical flow line, normal state flow line and special flow line sensing operation based on station flow basic data and transmitting an obtained flow line sensing result to the flow detection server and the data server; the passenger flow detection server is used for carrying out multi-flow-direction speed, multi-state density and multi-flow-direction flow detection based on the flow line sensing result, fixed and unfixed queue head queuing detection and transmitting the obtained passenger flow detection result to the passenger flow state identification server; and the passenger flow state identification server is used for identifying and processing the congestion state and abnormal passenger flow in a station key area based on the passenger flow detection result to obtain the congestion state and abnormal passenger flow identification result.
Description
Technical Field
The invention relates to the technical field of rail transit operation management, in particular to a passenger flow state identification system of a rail transit station based on streamline perception.
Background
Large passenger flow often appears in the rail transit station, and meanwhile abnormal passenger flow is generated due to unreasonable traveling behaviors of passengers. The passenger flow safety problem of a station can be brought by large passenger flow or abnormal passenger flow, and safety accidents are easily caused, so that the passenger flow state identification of the rail transit station is particularly important for identifying the congestion state and the abnormal state.
At present, in a passenger flow sensing system in the prior art, a video or laser dot matrix is used as a sensing data source to sense the average speed, the area density and the cross section surface flow in a certain direction.
The above-mentioned passenger flow perception system in the prior art has the following disadvantages: passenger streamlines of a rail transit station are complex and changeable, and the streamlines are different under daily peak, flat peak and emergency conditions; and the flow direction is changeable in the places such as station halls, station platforms, mixed-row stairs, roundabout fences and the like. The passenger flow perception direction of the existing passenger flow perception system is fixed, and the complexity and the changeability of the passenger flow streamline of the rail transit are not fully considered. And the physical and functional structures of the station are complex, and the real crowded state of the station cannot be accurately reflected in the modes of calculating the speed by using a fixed linear spatial position or calculating the average density by using an area and the like.
Disclosure of Invention
The embodiment of the invention provides a passenger flow state identification system of a rail transit station based on streamline perception, which provides scientific rationality of station passenger flow organization.
In order to achieve the purpose, the invention adopts the following technical scheme.
A passenger flow state identification system of a rail transit station based on flow line perception comprises a data server, a flow line perception server, a passenger flow detection server and a passenger flow state identification server which are sequentially connected;
the data server is used for storing and managing streamline sensing data, passenger flow detection data, passenger flow identification data and station passenger flow basic data;
the flow line perception server is used for carrying out station physical flow line, normal state flow line and special flow line perception operation based on station passenger flow basic data and transmitting an obtained flow line perception result to the passenger flow detection server and the data server;
the passenger flow detection server is used for detecting multi-flow speed, multi-state density and multi-flow based on a streamline sensing result, performing fixed and unfixed queue head queuing detection, and transmitting an obtained passenger flow detection result to the passenger flow state identification server;
the passenger flow state identification server is used for identifying and processing the congestion state and the abnormal passenger flow in a key area of a station based on the passenger flow detection result to obtain the identification result of the congestion state and the abnormal passenger flow.
Preferably, the data server comprises a perception data unit, a detection data unit, a passenger flow identification data unit and a station passenger flow basic data unit;
the system comprises a sensing data unit, a processing unit and a processing unit, wherein the sensing data unit is used for storing and managing streamline sensing data, and the streamline sensing data comprises original video or laser dot matrix data of each basic monitoring area and data of individual tracking and streamline sensing;
the detection data unit is used for storing and managing passenger flow detection data, and the passenger flow detection data comprises the detected characteristic data of the speed, the density, the flow and the queuing length of pedestrians in each monitoring area;
the passenger flow identification data unit is used for storing and managing passenger flow identification data, and the passenger flow identification data comprises identified congestion states and abnormal passenger flow data of each monitoring area;
the station passenger flow characteristic data unit is used for storing and managing station passenger flow basic data, and the station passenger flow basic data comprises a station physical topological structure, passenger flow organization and passenger flow state standard data.
Preferably, the flow line perception server comprises a station physical flow line unit, a normal passenger flow line perception unit and a special passenger flow line perception unit;
the station physical streamline unit is used for calculating all feasible streamline sets in each area based on station passenger flow basic data, setting a streamline state as a normal state according to station passenger flow organization data, and predicting a streamline under large passenger flow and a streamline under emergency conditions;
the normal passenger flow streamline sensing unit is used for tracking and sensing passenger flow group movement consistent with a streamline according to the normal streamline by utilizing an individual tracking technology of deep learning based on station passenger flow basic data;
the special flow line sensing unit is used for tracking and sensing passenger flow group movement consistent with the flow line according to the flow line under the conditions of large passenger flow and emergency according to the forecast based on station passenger flow basic data.
Preferably, the passenger flow detection server comprises a speed detection unit, a density detection unit, a traffic detection unit and a queuing detection unit;
the speed detection unit is used for calculating the spatial position of an individual unit time according to the spatial position of a detected object and the spatial path of a streamline path in a detection range by utilizing the streamline sensing result of the streamline server according to the video or laser dot matrix data of the detected area, and the speed of the detected passenger flow is counted by a shunting line and comprises the maximum speed, the minimum speed, the average speed and the speed variance in the direction of the shunting line;
the density detection unit is used for carrying out density calibration according to video or laser dot matrix data of a detected area, learning and detecting the density by using deep learning, counting the maximum density, the minimum density, the average density and the density variance of unit time, and dividing the gathering characteristics of the passenger flow distribution in the area into a plurality of density forms of homogeneous gathering, central gathering, front edge gathering, rear edge gathering and random gathering;
the flow detection unit is used for counting the number of people passing through the cross section in unit time by using a streamline sensing result of the streamline server according to video or laser dot matrix data of a detection area through a shunting line in a detection range;
the queuing detection unit is used for realizing the queuing detection of the fixed queue head and the non-fixed queue head; the detection method of the fixed head of the queue comprises the following steps: identifying a queuing edge through a deep learning method according to video or laser dot matrix data of a detected area, detecting whether the queuing length, the queuing width, the queuing shape, the number of queuing people and the queuing exceed a limit, and judging the order of queuing people according to a streamline if the queuing length, the queuing width, the queuing shape, the queuing number and the queuing exceed the limit length; the method for detecting the queuing of the non-fixed queue head comprises the steps of sequencing cameras of a queue passing area according to a queue flow line, traversing the detection cameras from front to back when a sequencing criterion is that the cameras pass through the front, and sequentially going backwards when the rear edge aggregation is the queuing queue head according to a camera density detection result of a space position where the detection queue is located, if the detection result is that the homogeneous aggregation is detected, increasing the queue length according to the length of the detection area, if the front edge aggregation is detected, the queue tail is the queue tail, increasing the length of the last sequential queue tail, and if the detection result is that the queue tail is of other types, not increasing the length.
Preferably, the passenger flow state identification server comprises a crowded passenger flow identification unit, an abnormal passenger flow identification unit and a passenger flow identification visual management unit;
the crowded passenger flow identification unit is used for identifying crowds by combining the station passenger flow composition and the basic passenger flow characteristics of each area according to a monitored station scene under a normal state or a predicted large passenger flow or emergency condition, wherein the crowding identification comprises the steps of identifying the crowds of a platform, a station hall and an escalator according to density and fixed queue head queuing detection results, identifying the crowds of the passengers at an entrance, a gate and a security check according to flow and the number of people queued at a fixed queue head, identifying the crowds of the passengers at a stair according to speed and density, and identifying the crowds of the passengers at a channel according to the density and the length of the queue head;
the abnormal passenger flow identification unit is used for carrying out multi-target individual tracking on the monitored area by using deep learning, clustering the flow lines tracked by the multi-target individual tracking, comparing the clustering result with the flow line sensing result in the flow sensing server, and if the results are the same, returning no abnormality; if the results are different, continuing to compare, and if the legal flow line of the corresponding scene is opposite, returning to the reverse direction; and if a plurality of different places exist, returning group harassment, and if the local streamline of the trip is relatively static, returning individual abnormity.
According to the technical scheme provided by the embodiment of the invention, the passenger flow congestion degree identification in different areas is carried out through multi-flow-direction speed, multi-state density and multi-flow-direction flow detection, fixed and unfixed queue head queuing detection and matching with the scene and the congestion level of equipment facilities, so that the real passenger flow congestion state of a station is more accurately reflected. Based on station normality and special flow line perception, the abnormal passenger flow is identified by matching an actual passenger flow line detection result with a scene, and the safety state of the station passenger flow is reflected more accurately.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a passenger flow state identification system of a rail transit station based on streamline sensing according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a station passenger flow identification visualization according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a station physical flow line set provided by an embodiment of the present invention;
fig. 4 is a flow chart of flow line sensing for passenger flow according to an embodiment of the present invention;
FIG. 5 is a flow chart of a fixed queue detection provided by an embodiment of the present invention;
FIG. 6 is a flow chart of non-fixed queue detection according to an embodiment of the present invention;
fig. 7 is a flow chart illustrating a process of identifying congested passenger flows according to an embodiment of the present invention;
fig. 8 is a flowchart illustrating an abnormal passenger flow identification method according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
For the convenience of understanding the embodiments of the present invention, the following description will be further explained by taking several specific embodiments as examples in conjunction with the drawings, and the embodiments are not to be construed as limiting the embodiments of the present invention.
Therefore, the invention identifies the passenger flow state of the station based on the manifold passenger flow stream line perception of the station and builds a system comprising stream line perception, characteristic detection and state identification.
Fig. 1 is a schematic structural diagram of a passenger flow state identification system of a rail transit station based on flow line sensing according to an embodiment of the present invention, and fig. 1 includes a data server, a flow line sensing server, a passenger flow detection server, and a passenger flow state identification server, which are connected in sequence.
The data server is used for storing and managing streamline sensing data, passenger flow detection data, passenger flow identification data and station passenger flow basic data;
the flow line perception server is used for carrying out station physical flow line, normal state flow line and special flow line perception operation based on station passenger flow basic data and transmitting an obtained flow line perception result to the passenger flow detection server and the data server;
the passenger flow detection server is used for detecting multi-flow speed, multi-state density and multi-flow based on a streamline sensing result, performing fixed and unfixed queue head queuing detection, and transmitting an obtained passenger flow detection result to the passenger flow state identification server;
the passenger flow state identification server is used for identifying and processing the congestion state and the abnormal passenger flow in a key area of a station based on the passenger flow detection result to obtain the identification result of the congestion state and the abnormal passenger flow.
Preferably, the data server comprises a perception data unit, a detection data unit, a passenger flow identification data unit and a station passenger flow basic data unit;
the sensing data unit stores original video or laser dot matrix data of each monitoring area and data of individual tracking and streamline sensing; the detection data unit stores the detected characteristic data of the speed, density, flow, queue length and the like of the pedestrians in each monitoring area; the passenger flow identification data unit stores and identifies the congestion state and abnormal passenger flow data of each monitoring area; the station passenger flow characteristic data unit stores station physical topological structure, passenger flow organization and passenger flow state standard data.
Preferably, the flow line perception server comprises a station physical flow line unit, a normal passenger flow line perception unit and a special passenger flow line perception unit;
the station physical streamline unit is used for calculating all feasible streamline sets in each area, and setting the streamline state as a normal state, predicting the streamline under large passenger flow and the streamline under emergency conditions according to station passenger flow organization data; the normal passenger flow streamline sensing unit is used for tracking and sensing passenger flow group movement consistent with the streamline according to the normal streamline by utilizing an individual tracking technology of deep learning; and the special flow line sensing unit tracks and senses passenger flow group movement consistent with the flow line according to the flow line predicted under the conditions of large passenger flow and emergency.
Preferably, the passenger flow detection server comprises a speed detection unit, a density detection unit, a traffic detection unit and a queuing detection unit;
the speed detection unit is used for calculating the spatial position of an individual unit time according to the spatial position of a detected object and the spatial path of a streamline path in a detection range by utilizing the streamline sensing result of the streamline server according to the video or laser dot matrix of the detected area, and on the basis, the speed of the detected passenger flow, including the maximum speed, the minimum speed, the average speed and the speed variance in the direction of the shunting line, is counted by the shunting line;
the density detection unit is used for carrying out density calibration according to a video or laser dot matrix of a detected region, learning and detecting the density by utilizing deep learning, counting the maximum density, the minimum density, the average density and the density variance of unit time, and dividing the gathering characteristics of the distribution of the passenger flow in the region into a plurality of density forms of homogeneous gathering, central gathering, front edge gathering, rear edge gathering and random gathering;
the flow detection unit is used for counting the number of people passing through the cross section in unit time by using the streamline sensing result of the streamline server according to the video or laser dot matrix of the detection area through the shunting line in the detection range;
the queuing detection unit is used for realizing the queuing detection of the fixed queue head and the non-fixed queue head; the detection method of the fixed queue head comprises the steps of identifying a queuing edge through a deep learning method according to a video or laser dot matrix of a detected area, detecting the queuing length, the queuing width, the queuing shape, the number of queuing people, judging whether the queuing exceeds a limit or a limit length, and judging the order of queuing people according to a streamline; the method for detecting the queuing of the non-fixed queue head comprises the steps of sequencing the cameras of a queue passing area according to a density detection result of the cameras of the space position where a detection queue is located and a queue streamline, traversing the detection cameras from front to back when the sequencing criterion is that the cameras pass from front to back, sequentially moving backwards when the cameras are the queue head and the queue head, increasing the queue length according to the length of the detection area if homogeneous aggregation occurs, increasing the last sequential queue tail length if the cameras are the queue tail if the cameras are the front edge aggregation, and not increasing the length if the cameras are other types.
Preferably, the passenger flow state identification server comprises a crowded passenger flow identification unit, an abnormal passenger flow identification unit and a passenger flow identification visual management unit;
the system comprises a congestion passenger flow identification unit, a traffic flow identification unit and a traffic flow identification unit, wherein the congestion passenger flow identification unit is used for identifying congestion by combining the composition of station passenger flow and the basic passenger flow characteristics of each area under the condition of normal state or predicted large passenger flow or emergency according to a monitored station scene and mainly comprises the steps of identifying the passenger flow congestion of a platform, a station hall and an escalator according to density and fixed queue head queuing detection results, identifying the passenger flow congestion of an entrance, a gate and a safety inspection according to flow and the number of people who queue at a fixed queue head, identifying the passenger flow congestion of a stair according to speed and density, and identifying the passenger flow congestion of a channel according to the density and the number of people who queue at an unfixed queue head;
and the abnormal passenger flow identification unit is used for tracking multiple targets of individuals in the monitored area by using deep learning, performing streamline clustering by using a clustering method, comparing a clustering result with a streamline sensing result in the flow sensing server, and judging whether abnormal behaviors such as retrograde motion, disturbance, falling and the like occur or not according to the current station passenger flow organization scene.
Fig. 2 is a schematic diagram illustrating a station passenger flow identification visualization provided in an embodiment of the present invention, and fig. 2 is a schematic diagram illustrating: the station passenger flow identification visualization unit is divided into five modules which are respectively a station overall graph module, a key area video module, a key index time-sharing change module, a passenger flow state identification result module and a flow line checking module. The contents displayed by the modules and the functions possessed by the modules are shown in the following table.
TABLE 1 predictive visualization Unit Module functionality
Referring to fig. 3, fig. 3 is a schematic diagram of a station physical flow line set provided by an embodiment of the present invention, and on the basis of building a station network, a feasible physical flow line set includes a daily passenger flow line, a big passenger flow organization flow line and an emergency evacuation flow line which can be predicted; wherein daily passenger flow streamline includes the streamline of bringing in the station, the streamline of leaving the station, the streamline of transfer, emergent evacuation streamline and can foresee big passenger flow organization streamline, the streamline of getting in the station includes reservation/fast passage and gets in the station, the security check is brought in the station and is checked the safety check of buying tickets and come in the station, the streamline of leaving the station includes direct streamline of leaving the station and the streamline of making up tickets, the streamline of transfer includes the streamline of taking a transfer in the same station and the streamline of passageway, emergent evacuation streamline includes the streamline of leaving the station fast and keeps away the danger streamline fast, can foresee big passenger flow organization streamline and include that the streamline of detour seals with former streamline.
Referring to fig. 4, fig. 4 is a flow chart of passenger flow streamline sensing provided by the embodiment of the present invention, in which multiple target individual tracking is performed in a sensing area, similarity calculation is performed on a curve obtained by tracking and various streamlines in the sensing area, and when the similarity reaches a certain threshold, consistency matching is satisfied, and classification of the streamlines where the identified tracking curves are located is output.
Referring to fig. 5, fig. 5 is a flowchart of a fixed queue detection according to an embodiment of the present invention, where detection is performed from a fixed queue head position, a maximum boundary of a queue in a monitoring area is input first, then edge recognition is performed in the maximum boundary to obtain a shape and a length of the queue, and it is determined whether a queue tail is reached according to the length of the queue, if the queue tail is not reached, an adjacent monitoring area is checked according to a queue direction, and if the queue tail is reached, the detection is ended.
Referring to fig. 6, fig. 6 is a flowchart of a non-fixed queuing detection method according to an embodiment of the present invention, in which a queue detection method for a non-fixed head of a queue includes sorting cameras in a region where the queue passes according to a queue flow line, traversing the detection cameras from front to back, and according to a detection result of a density of the cameras at a spatial position where the detection queue is located, when a head of the queuing queue appears after a rear edge aggregation, sequentially going backward, if a homogeneous aggregation is detected, increasing a length according to a detection region, and if a front edge aggregation appears, increasing a length of a tail of the queue, if another type is detected, increasing a length of a tail of the queue finally sequentially, and if another type is detected, not increasing the length.
Referring to fig. 7, fig. 7 is a flow chart of identifying congested passenger flows according to an embodiment of the present invention, where: normal peak leveling/peak, holiday/large-scale activity, emergency evacuation scene, reading the congestion level standard of different areas, selecting proper detection indexes according to the characteristics of different areas, and carrying out congestion identification, specifically comprising: the method comprises the steps of identifying passenger flow congestion of a platform, a station hall and an escalator according to density and fixed queue head queuing detection results, identifying passenger flow congestion of an entrance, a gate and security inspection according to flow and the number of people who queue at the fixed queue head, identifying passenger flow congestion of a stair according to speed and density, and identifying passenger flow congestion of a channel according to density and non-fixed queue head queuing length;
referring to fig. 8, fig. 8 is a flow chart for identifying abnormal passenger flows, which is provided by the embodiment of the present invention, and is configured to perform multi-target individual tracking on a monitored area by using deep learning, perform clustering on streamlines tracked by the multi-target individual tracking, compare a clustering result with a streamline sensing result in a traffic sensing server, and return no abnormality if the results are the same. If the results are different, continuing to compare, and if the result is opposite to the legal streamline of the corresponding scene, returning to the reverse direction; if the number of the places is different, group harassment is returned, and if the local streamline of the trip is relatively static, the abnormality such as falling of the individual is returned.
In summary, the effective effects of the embodiments of the present invention are as follows:
(1) through multi-flow-direction speed, multi-state density, multi-flow-direction flow detection, fixed and unfixed queue head queuing detection and matching with the scene and the equipment facility congestion level, passenger flow congestion degree identification in different areas is carried out, and the real passenger flow congestion state of a station is reflected more accurately.
(2) Based on station normality and special flow line perception, the abnormal passenger flow is identified by matching an actual passenger flow line detection result with a scene, and the safety state of the station passenger flow is reflected more accurately.
Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (5)
1. A passenger flow state identification system of a rail transit station based on flow line perception is characterized by comprising a data server, a flow line perception server, a passenger flow detection server and a passenger flow state identification server which are sequentially connected;
the data server is used for storing and managing streamline sensing data, passenger flow detection data, passenger flow identification data and station passenger flow basic data;
the flow line perception server is used for carrying out station physical flow line, normal state flow line and special flow line perception operation based on station passenger flow basic data and transmitting an obtained flow line perception result to the passenger flow detection server and the data server;
the passenger flow detection server is used for detecting multi-flow speed, multi-state density and multi-flow based on a streamline sensing result, performing fixed and unfixed queue head queuing detection, and transmitting an obtained passenger flow detection result to the passenger flow state identification server;
the passenger flow state identification server is used for identifying and processing the congestion state and the abnormal passenger flow in a key area of a station based on the passenger flow detection result to obtain the identification result of the congestion state and the abnormal passenger flow.
2. The system of claim 1, wherein the data server comprises a perception data unit, a detection data unit, a passenger flow identification data unit and a station passenger flow basic data unit;
the system comprises a sensing data unit, a processing unit and a processing unit, wherein the sensing data unit is used for storing and managing streamline sensing data, and the streamline sensing data comprises original video or laser dot matrix data of each basic monitoring area and data of individual tracking and streamline sensing;
the detection data unit is used for storing and managing passenger flow detection data, and the passenger flow detection data comprises the detected characteristic data of the speed, the density, the flow and the queuing length of pedestrians in each monitoring area;
the passenger flow identification data unit is used for storing and managing passenger flow identification data, and the passenger flow identification data comprises identified congestion states and abnormal passenger flow data of each monitoring area;
the station passenger flow characteristic data unit is used for storing and managing station passenger flow basic data, and the station passenger flow basic data comprises a station physical topological structure, passenger flow organization and passenger flow state standard data.
3. The system of claim 1, wherein the flow line sensing server comprises a station physical flow line unit, a normal passenger flow line sensing unit and a special passenger flow line sensing unit;
the station physical streamline unit is used for calculating all feasible streamline sets in each area based on station passenger flow basic data, setting a streamline state as a normal state according to station passenger flow organization data, and predicting a streamline under large passenger flow and a streamline under emergency conditions;
the normal passenger flow streamline sensing unit is used for tracking and sensing passenger flow group movement consistent with a streamline according to the normal streamline by utilizing an individual tracking technology of deep learning based on station passenger flow basic data;
the special flow line sensing unit is used for tracking and sensing passenger flow group movement consistent with the flow line according to the flow line under the conditions of large passenger flow and emergency according to the forecast based on station passenger flow basic data.
4. The system according to claim 1, wherein the passenger flow detection server comprises a speed detection unit, a density detection unit, a flow detection unit and a queue detection unit;
the speed detection unit is used for calculating the spatial position of an individual unit time according to the spatial position of a detected object and the spatial path of a streamline path in a detection range by utilizing the streamline sensing result of the streamline server according to the video or laser dot matrix data of the detected area, and the speed of the detected passenger flow is counted by a shunting line and comprises the maximum speed, the minimum speed, the average speed and the speed variance in the direction of the shunting line;
the density detection unit is used for carrying out density calibration according to video or laser dot matrix data of a detected area, learning and detecting the density by using deep learning, counting the maximum density, the minimum density, the average density and the density variance of unit time, and dividing the gathering characteristics of the passenger flow distribution in the area into a plurality of density forms of homogeneous gathering, central gathering, front edge gathering, rear edge gathering and random gathering;
the flow detection unit is used for counting the number of people passing through the cross section in unit time by using a streamline sensing result of the streamline server according to video or laser dot matrix data of a detection area through a shunting line in a detection range;
the queuing detection unit is used for realizing the queuing detection of the fixed queue head and the non-fixed queue head; the detection method of the fixed head of the queue comprises the following steps: identifying a queuing edge through a deep learning method according to video or laser dot matrix data of a detected area, detecting whether the queuing length, the queuing width, the queuing shape, the number of queuing people and the queuing exceed a limit, and judging the order of queuing people according to a streamline if the queuing length, the queuing width, the queuing shape, the queuing number and the queuing exceed the limit length; the method for detecting the queuing of the non-fixed queue head comprises the steps of sequencing cameras of a queue passing area according to a queue flow line, traversing the detection cameras from front to back when a sequencing criterion is that the cameras pass through the front, and sequentially going backwards when the rear edge aggregation is the queuing queue head according to a camera density detection result of a space position where the detection queue is located, if the detection result is that the homogeneous aggregation is detected, increasing the queue length according to the length of the detection area, if the front edge aggregation is detected, the queue tail is the queue tail, increasing the length of the last sequential queue tail, and if the detection result is that the queue tail is of other types, not increasing the length.
5. The system according to claim 1, wherein the passenger flow status recognition server comprises a crowded passenger flow recognition unit, an abnormal passenger flow recognition unit and a passenger flow recognition visualization management unit;
the crowded passenger flow identification unit is used for identifying crowds by combining the station passenger flow composition and the basic passenger flow characteristics of each area according to a monitored station scene under a normal state or a predicted large passenger flow or emergency condition, wherein the crowding identification comprises the steps of identifying the crowds of a platform, a station hall and an escalator according to density and fixed queue head queuing detection results, identifying the crowds of the passengers at an entrance, a gate and a security check according to flow and the number of people queued at a fixed queue head, identifying the crowds of the passengers at a stair according to speed and density, and identifying the crowds of the passengers at a channel according to the density and the length of the queue head;
the abnormal passenger flow identification unit is used for carrying out multi-target individual tracking on the monitored area by using deep learning, clustering the flow lines tracked by the multi-target individual tracking, comparing the clustering result with the flow line sensing result in the flow sensing server, and if the results are the same, returning no abnormality; if the results are different, continuing to compare, and if the legal flow line of the corresponding scene is opposite, returning to the reverse direction; and if a plurality of different places exist, returning group harassment, and if the local streamline of the trip is relatively static, returning individual abnormity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111110065.8A CN113936247B (en) | 2021-09-18 | 2021-09-18 | Rail transit station passenger flow state identification system based on streamline perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111110065.8A CN113936247B (en) | 2021-09-18 | 2021-09-18 | Rail transit station passenger flow state identification system based on streamline perception |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113936247A true CN113936247A (en) | 2022-01-14 |
| CN113936247B CN113936247B (en) | 2023-08-01 |
Family
ID=79276460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111110065.8A Active CN113936247B (en) | 2021-09-18 | 2021-09-18 | Rail transit station passenger flow state identification system based on streamline perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113936247B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114581846A (en) * | 2022-03-03 | 2022-06-03 | 北京城建设计发展集团股份有限公司 | Method and device for monitoring holographic passenger flow of subway station in real time and computer equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105404850A (en) * | 2015-10-21 | 2016-03-16 | 中南大学 | Station passenger flow monitoring system, station passenger flow monitoring method, station passenger flow control system and station passenger flow control method |
| US20160379049A1 (en) * | 2015-04-29 | 2016-12-29 | Beijing Kuangshi Technology Co., Ltd. | Video monitoring method, video monitoring system and computer program product |
| CN109801474A (en) * | 2019-02-22 | 2019-05-24 | 北京启安智慧科技有限公司 | A kind of the Regional Risk analysis method and system of urban safety |
| CN110481606A (en) * | 2019-08-23 | 2019-11-22 | 上海电气自动化设计研究所有限公司 | The metro passenger flow of view-based access control model identification technology guides system and method |
| CN110942411A (en) * | 2019-11-20 | 2020-03-31 | 北京城建设计发展集团股份有限公司 | Subway station passenger flow grading alarm method based on regional linkage |
| CN111368650A (en) * | 2020-02-18 | 2020-07-03 | 北京交通大学 | Crowd crowding behavior identification method based on track data |
| WO2021023310A1 (en) * | 2019-08-07 | 2021-02-11 | 中兴通讯股份有限公司 | Method for estimating and presenting passenger flow, system, and computer readable storage medium |
| CN113159393A (en) * | 2021-03-30 | 2021-07-23 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Passenger station passenger flow awareness early warning method and device, electronic equipment and storage medium |
-
2021
- 2021-09-18 CN CN202111110065.8A patent/CN113936247B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160379049A1 (en) * | 2015-04-29 | 2016-12-29 | Beijing Kuangshi Technology Co., Ltd. | Video monitoring method, video monitoring system and computer program product |
| CN105404850A (en) * | 2015-10-21 | 2016-03-16 | 中南大学 | Station passenger flow monitoring system, station passenger flow monitoring method, station passenger flow control system and station passenger flow control method |
| CN109801474A (en) * | 2019-02-22 | 2019-05-24 | 北京启安智慧科技有限公司 | A kind of the Regional Risk analysis method and system of urban safety |
| WO2021023310A1 (en) * | 2019-08-07 | 2021-02-11 | 中兴通讯股份有限公司 | Method for estimating and presenting passenger flow, system, and computer readable storage medium |
| CN110481606A (en) * | 2019-08-23 | 2019-11-22 | 上海电气自动化设计研究所有限公司 | The metro passenger flow of view-based access control model identification technology guides system and method |
| CN110942411A (en) * | 2019-11-20 | 2020-03-31 | 北京城建设计发展集团股份有限公司 | Subway station passenger flow grading alarm method based on regional linkage |
| CN111368650A (en) * | 2020-02-18 | 2020-07-03 | 北京交通大学 | Crowd crowding behavior identification method based on track data |
| CN113159393A (en) * | 2021-03-30 | 2021-07-23 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Passenger station passenger flow awareness early warning method and device, electronic equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| FEI DOU ET AL: ""Research on Passenger Inflow Control Optimization and Simulation in Urban Rail Transit Station"", 《THE 3RD INTERNATIONAL CONFERENCE ON ELECTRICAL AND INFORMATION TECHNOLOGIES FOR RAIL TRANSPORTATION 2017》, pages 71 - 76 * |
| JIAJIA XU ET AL: ""Crowded treading warning system for urban rail transit stations based on video detection technology"", 《IOP CONFERENCE SERIES: EARTH AND ENVIRONMENT SCIENCE》, pages 1 - 5 * |
| 俞益等: ""智能视频图像分析系统在城市轨道交通中的应用探索"", 《中国安防》, no. 6, pages 73 - 76 * |
| 郭建媛: ""城市轨道交通网络客流调控方法"", 《中国博士学位论文全文数据库（工程科技Ⅱ辑）》, no. 2, pages 033 - 28 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114581846A (en) * | 2022-03-03 | 2022-06-03 | 北京城建设计发展集团股份有限公司 | Method and device for monitoring holographic passenger flow of subway station in real time and computer equipment |
| CN114581846B (en) * | 2022-03-03 | 2024-02-20 | 北京城建设计发展集团股份有限公司 | Real-time monitoring method and device for holographic passenger flow of subway station and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113936247B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Park et al. | Real-time prediction of secondary incident occurrences using vehicle probe data | |
| US10943204B2 (en) | Realtime video monitoring applied to reduce customer wait times | |
| Pande et al. | Comprehensive analysis of the relationship between real-time traffic surveillance data and rear-end crashes on freeways | |
| Pande et al. | Assessment of freeway traffic parameters leading to lane-change related collisions | |
| US10552687B2 (en) | Visual monitoring of queues using auxillary devices | |
| Tageldin et al. | Models to evaluate the severity of pedestrian-vehicle conflicts in five cities | |
| CN108289203B (en) | Video monitoring system for rail transit | |
| JP5992681B2 (en) | Unusual condition detection system for congestion | |
| EP3437955B1 (en) | Train disembarking passenger number prediction system, congestion visualization and evaluation system, and riding capacity calculation system | |
| CN109979197B (en) | Method and system for constructing highway traffic time map based on fusion data | |
| CN108091132A (en) | A kind of traffic flow forecasting method and device | |
| Shirazi et al. | A typical video-based framework for counting, behavior and safety analysis at intersections | |
| CN112116263B (en) | Traffic intersection risk level assessment method and device, electronic equipment and storage medium | |
| CN113936465A (en) | Traffic incident detection method and device | |
| Liu et al. | Traffic state spatial-temporal characteristic analysis and short-term forecasting based on manifold similarity | |
| Tageldin et al. | Automated analysis and validation of right-turn merging behavior | |
| CN113936247A (en) | Passenger flow state identification system of rail transit station based on streamline perception | |
| Guerrieri et al. | Real-time social distance measurement and face mask detection in public transportation systems during the COVID-19 pandemic and post-pandemic Era: Theoretical approach and case study in Italy | |
| Zheng et al. | Toward real-time congestion measurement of passenger flow on platform screen doors based on surveillance videos analysis | |
| Xie et al. | Advancing crowd forecasting with graphs across microscopic trajectory to macroscopic dynamics | |
| Jadhav et al. | Road accident analysis and prediction of accident severity using machine learning | |
| CN110941278B (en) | Dynamic safety analysis method in station | |
| Essa | Calibration and validation of traffic microsimulation models for safety evaluation using automated video-based conflict analysis | |
| Liu et al. | Intelligent video analysis system for railway station | |
| WO2020139283A2 (en) | Bubble eye system |
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 |