WO2017149720A1 - 混雑予測装置および混雑予測方法 - Google Patents
混雑予測装置および混雑予測方法 Download PDFInfo
- Publication number
- WO2017149720A1 WO2017149720A1 PCT/JP2016/056581 JP2016056581W WO2017149720A1 WO 2017149720 A1 WO2017149720 A1 WO 2017149720A1 JP 2016056581 W JP2016056581 W JP 2016056581W WO 2017149720 A1 WO2017149720 A1 WO 2017149720A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- prediction
- congestion
- data
- congestion prediction
- measurement
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/046—Forward inferencing; Production systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Definitions
- the present invention relates to a congestion prediction device for performing congestion prediction at the time of event holding and the method thereof.
- the event security monitoring method described in Patent Document 1 first, based on past results or data, the inflow / outflow points of transportation facilities or the like that are directly related to the traffic in the security target area such as the event venue or passage.
- the outflow data of the outlook is prepared in advance.
- a camera is installed at a peripheral point deeply related to the crowd in the security target area and takes an image.
- the event security monitoring device measures the human flow at the peripheral point by performing image processing on the captured image, and uses the actual measurement value of the human flow and the inflow / outflow data of the public prepared in advance. And predict congestion in the guarded area.
- the present invention has been made to solve the above-described problems, and eliminates the need to prepare data used for congestion prediction in advance, and enables congestion prediction at the first event or venue. With the goal.
- the congestion prediction device uses a measurement data output from a sensor that measures the number of persons who have passed through a measurement point, and predicts a future number of people passing through the measurement point to generate prediction data. And a congestion prediction processing unit that uses the prediction data generated by the prediction data generation unit to predict the future congestion state of the measurement point and generates and outputs congestion prediction data.
- the future passing number is predicted using the measurement data of the passing number at the measurement point, and the future congestion state at the measurement point is predicted using the prediction data. It is not necessary to prepare data in advance, and it becomes possible to predict congestion at the first event or venue.
- FIG. 2 is a hardware configuration diagram of the congestion prediction device according to Embodiment 1.
- FIG. It is a sequence diagram which shows the process which the congestion prediction apparatus which concerns on Embodiment 1 performs.
- 4 is a flowchart illustrating processing performed by a measurement data storage unit of the congestion prediction device according to the first embodiment.
- 6 is a flowchart illustrating processing performed by a prediction data generation unit of the congestion prediction device according to the first embodiment.
- 4 is a flowchart illustrating processing performed by an expected data storage unit of the congestion prediction device according to the first embodiment.
- 6 is a flowchart illustrating processing performed by a congestion prediction processing unit of the congestion prediction device according to the first embodiment.
- FIG. 10 is a sequence diagram illustrating processing performed by the congestion prediction device according to Embodiment 2.
- FIG. It is a flowchart which shows the process which the measurement data storage part of the congestion prediction apparatus which concerns on Embodiment 2 performs.
- 10 is a flowchart illustrating a process performed by a prediction data generation unit of the congestion prediction device according to the second embodiment.
- 10 is a flowchart illustrating a process performed by a predicted data storage unit of the congestion prediction device according to the second embodiment.
- 10 is a flowchart illustrating processing performed by a congestion prediction processing unit of the congestion prediction device according to the second embodiment.
- 10 is a flowchart illustrating processing performed by a difference calculation unit of the congestion prediction device according to the second embodiment.
- FIG. 1 is a functional configuration diagram of the congestion prediction apparatus according to Embodiment 1 of the present invention.
- This congestion prediction device predicts the congestion state of a route from a place where people occur to an event venue, such as a public transportation such as a station or a bus stop or a parking lot, at the time of an event.
- the sensor 1 is installed on the route from the place where the person is generated to the event venue, and the sensor 1 and the congestion prediction device are connected.
- the position where the sensor 1 is installed on the route from the place where people occur to the event venue is called a measurement point.
- the sensor 1 measures the number of persons passing through the measurement point in the forward or backward direction, generates time series data, and outputs the time series data to the congestion prediction device.
- the sensor 1 includes a camera, for example, and performs image processing on an image captured by the camera to measure the number of passing people.
- the time series data generated by the sensor 1 is referred to as measurement data.
- the congestion prediction device includes a measurement data storage unit 10, a prediction data generation unit 20, a prediction data storage unit 30, and a congestion prediction processing unit 40.
- the measurement data storage unit 10 stores measurement data output from the sensor 1.
- the predicted data generation unit 20 uses the measurement data stored in the measurement data storage unit 10 to generate a time-series data by predicting the number of people passing by at the measurement point, and stores the predicted data in the predicted data storage unit 30 as predicted data. Output.
- the predicted data storage unit 30 stores the predicted data output by the predicted data generation unit 20 and outputs the stored predicted data to the congestion prediction processing unit 40 as selected predicted data.
- the congestion prediction processing unit 40 uses the selected prediction data output from the prediction data storage unit 30 to predict the future congestion state of the measurement point, generates congestion prediction data, and outputs the data to the outside.
- Sensor 1 may measure only one of the number of people passing the measurement point in the forward direction or the number of people passing in the return direction, or may measure both.
- the prediction data generation unit 20 when the measurement data is obtained by measuring the number of people passing the measurement point in the outward direction, the prediction data generation unit 20 generates prediction data that predicts the number of people passing only the outward route, and the congestion prediction processing unit 40 is only for the outward route.
- Congestion prediction data is generated by predicting the congestion state. As described above, the contents of the prediction data and the congestion prediction data also change depending on whether the measurement target is the forward path or the return path.
- FIG. 2 is a hardware configuration diagram of the congestion prediction device.
- the congestion prediction apparatus includes a processor 101, a memory 102, an input interface 103, and an output interface 104.
- the input interface 103 inputs measurement data from the sensor 1 to the measurement data storage unit 10.
- the output interface 104 outputs the congestion prediction data of the congestion prediction processing unit 40 to an external device such as a display.
- the congestion prediction device includes a processing circuit for generating prediction data using the measurement data and generating congestion prediction data using the prediction data.
- the processing circuit is a processor 101 that executes a program stored in the memory 102.
- the processor 101 is also referred to as a CPU (Central Processing Unit), a processing device, an arithmetic device, a microprocessor, a microcomputer, or a DSP (Digital Signal Processor).
- Each function of the prediction data generation unit 20 and the congestion prediction processing unit 40 is realized by software, firmware, or a combination of software and firmware.
- Software or firmware is described as a program and stored in the memory 102.
- the processor 101 reads out and executes the program stored in the memory 102, thereby realizing the function of each unit. That is, when the congestion prediction device is executed by the processor 101, the step of generating the prediction data using the measurement data and the step of generating the congestion prediction data using the prediction data are executed as a result.
- the memory 102 for storing the program to become is provided. These programs can also be said to cause a computer to execute the procedures or methods of the predicted data generation unit 20 and the congestion prediction processing unit 40.
- the memory 102 includes, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Programmable EPROM), a flash memory, an SSD (Solid State Drive), or the like. It may be a volatile semiconductor memory, a magnetic disk such as a hard disk or a flexible disk, or an optical disk such as a CD (Compact Disc) or a DVD (Digital Versatile Disc).
- the measurement data storage unit 10 and the prediction data storage unit 30 in the congestion prediction device are a memory 102.
- FIG. 3 is a sequence diagram illustrating processing performed by the congestion prediction device according to the first embodiment.
- FIG. 4 is a flowchart illustrating processing performed by the measurement data storage unit 10 of the congestion prediction apparatus according to the first embodiment. The processing in steps S101 to S104 in FIG. 4 is performed in step S100 in FIG.
- the measurement data storage unit 10 confirms whether or not the measurement data is received from the sensor 1 via the input interface 103.
- the measurement data storage unit 10 proceeds to step S102 when measurement data is received (step S101 “YES”), and proceeds to step S103 when there is no reception (step S101 “NO”).
- step S102 the measurement data storage unit 10 receives and stores measurement data from the sensor 1 via the input interface 103.
- step S103 the measurement data storage unit 10 confirms whether or not there is a notification from the predicted data generation unit 20.
- the measurement data storage unit 10 proceeds to step S104 when there is a notification from the predicted data generation unit 20 (step S103 “YES”), and returns to step S101 when there is no notification (step S103 “NO”).
- the measurement data storage unit 10 selects a predetermined range of measurement data from the stored measurement data, and transmits the measurement data to the prediction data generation unit 20 as prediction measurement data.
- the predetermined range may be set in advance in the measurement data storage unit 10, or may be set from outside the congestion prediction device as necessary. For example, when the measurement data storage unit 10 receives the notification from the prediction data generation unit 20, the measurement data storage unit 10 transmits time-series data from that time point to a time point that goes back by a predetermined range to the prediction data generation unit 20 as measurement data for prediction. .
- the measurement data storage unit 10 returns to step S101 after step S104.
- FIG. 5 is a flowchart showing processing performed by the prediction data generation unit 20 of the congestion prediction apparatus according to the first embodiment. The processing in steps S201 to S206 in FIG. 5 is performed in step S200 in FIG.
- step S201 in FIG. 5 the predicted data generation unit 20 transmits a notification to the measurement data storage unit 10. This notification is for transmitting the measurement data for prediction from the measurement data storage unit 10 to the prediction data generation unit 20.
- step S202 the prediction data generation unit 20 confirms whether or not the measurement data for prediction is received from the measurement data storage unit 10.
- the prediction data generation unit 20 proceeds to step S203 when the measurement data for prediction is received (step S202 “YES”), and repeats step S202 when there is no reception (step S202 “NO”).
- step S203 the prediction data generation unit 20 receives and stores prediction measurement data from the measurement data storage unit 10.
- the predicted data generation unit 20 uses linear approximation or the like to predict the number of passing people at a future measurement point according to the predicted data generation range, and generates predicted data.
- the predicted data generation range is a parameter that determines how many people will pass from the present to the future.
- the predicted data generation range may be set in the predicted data generation unit 20 in advance, or may be set from outside the congestion prediction device as necessary.
- step S205 the predicted data generation unit 20 transmits the predicted data generated in step S204 to the predicted data storage unit 30.
- step S206 the prediction data generation unit 20 checks whether there is a notification from the congestion prediction processing unit 40. When there is a notification from the congestion prediction processing unit 40 (step S206 “YES”), the prediction data generation unit 20 returns to step S201, and when there is no notification (step S206 “NO”), repeats this step S206.
- FIG. 6 is a flowchart illustrating processing performed by the prediction data storage unit 30 of the congestion prediction apparatus according to the first embodiment. The processing in steps S301 to S303 in FIG. 6 is performed in step S300 in FIG.
- the predicted data storage unit 30 confirms whether or not the predicted data has been received from the predicted data generation unit 20.
- the predicted data storage unit 30 proceeds to step S302 when predicted data is received (step S301 “YES”), and repeats step S301 when no predicted data is received (step S301 “NO”).
- step S302 the predicted data storage unit 30 receives and stores the predicted data from the predicted data generation unit 20.
- step S303 the predicted data storage unit 30 selects the predicted data stored in step S302, and transmits the selected predicted data to the congestion prediction processing unit 40 as selected predicted data.
- the predicted data storage unit 30 returns to step S301 after step S303.
- FIG. 7 is a flowchart showing processing performed by the congestion prediction processing unit 40 of the congestion prediction apparatus according to the first embodiment. The processing in steps S401 to S406 in FIG. 7 is performed in step S400 in FIG.
- the congestion prediction processing unit 40 confirms whether or not the selected predicted data is received from the predicted data storage unit 30.
- the congestion prediction processing unit 40 proceeds to step S402 when selection prediction data is received (step S401 “YES”), and returns to step S401 when there is no reception (step S401 “NO”).
- step S402 the congestion prediction processing unit 40 receives the selected predicted data from the predicted data storage unit 30.
- the congestion prediction processing unit 40 uses the selected prediction data received from the prediction data storage unit 30 in step S402 to execute a congestion prediction process using a technique such as multi-agent simulation, and obtains the congestion prediction data of the measurement point. Generate.
- the congestion prediction data is, for example, time series data of the flow rate and density of people around the measurement point.
- step S404 the congestion prediction processing unit 40 confirms whether the congestion prediction process has reached the time point when the congestion prediction ends.
- the congestion prediction end time is a parameter that determines how far ahead the congestion prediction is to be executed from the congestion prediction start time, and the prediction data generation range end time ⁇ congestion prediction end time.
- the congestion prediction end point may be set in advance in the congestion prediction processing unit 40, or may be set from outside the congestion prediction device as necessary.
- the congestion prediction processing unit 40 proceeds to step S405, and when not reached (step S404 “NO”), returns to step S403. Continue the congestion prediction process.
- step S405 the congestion prediction processing unit 40 outputs the congestion prediction data via the output interface 104.
- step S ⁇ b> 406 the congestion prediction processing unit 40 transmits a notification to the predicted data generation unit 20.
- This notification is for instructing the prediction data generation unit 20 to generate new prediction data, and the prediction data generation unit 20 that has received this notification notifies the measurement data storage unit 10 of the measurement for prediction. You will be requesting data.
- the congestion prediction processing unit 40 returns to step S401 after step S406.
- the congestion prediction device predicts and predicts the future number of people passing through the measurement point using the measurement data output from the sensor 1 that measures the number of people passing through the measurement point.
- a prediction data generation unit 20 that generates data
- a congestion prediction processing unit 40 that predicts the future congestion state of the measurement point using the prediction data generated by the prediction data generation unit 20 and outputs the congestion prediction data. It is a configuration.
- the forecast data used for the congestion prediction can be generated in real time, so that it is not necessary to prepare the forecast data in advance, and the congestion prediction at the first event or holding place is possible.
- Embodiment 2 the measurement data newly output by the sensor 1 during the congestion state prediction process in the congestion prediction processing unit 40 is reflected in the congestion prediction data and output.
- FIG. 8 is a functional configuration diagram of the congestion prediction apparatus according to Embodiment 2 of the present invention. 8 that are the same as or correspond to those in FIG. 1 are denoted by the same reference numerals.
- the congestion prediction apparatus according to the second embodiment has a configuration in which a difference calculation unit 50 is added to the congestion prediction apparatus according to the first embodiment illustrated in FIG.
- the function of the difference calculation unit 50 is realized by the processor 101 shown in FIG. 2 reading and executing a program stored in the memory 102.
- the difference calculation unit 50 is the prediction data having the smallest difference from the measurement data newly output by the sensor 1 during the congestion prediction process of the congestion prediction processing unit 40 from among the plurality of prediction data generated by the prediction data generation unit 20. And the congestion prediction processing unit 40 is notified.
- the predicted data having the smallest difference from the measured data is optimal predicted data that can predict the congestion state with high accuracy.
- the congestion prediction device includes a plurality of congestion prediction processing units 40.
- the plurality of congestion prediction processing units 40 generate a plurality of congestion prediction data using the plurality of prediction data generated by the prediction data generation unit 20. Then, among the plurality of congestion prediction processing units 40, the congestion prediction processing unit 40 that has executed the congestion prediction processing using the prediction data selected by the difference calculation unit 50 outputs the congestion prediction data generated by itself to the rest. The congestion prediction processing unit 40 discards the congestion prediction data.
- FIG. 9 is a sequence diagram illustrating processing performed by the congestion prediction device according to the second embodiment.
- FIG. 10 is a flowchart illustrating processing performed by the measurement data storage unit 10 of the congestion prediction device according to the second embodiment. The processing in steps S101 to S106 in FIG. 10 is performed in step S100a in FIG.
- the measurement data storage unit 10 performs the same processing as in steps S101 to S104 in FIG.
- step S105 the measurement data storage unit 10 confirms whether or not there is a notification from the congestion prediction processing unit 40.
- step S105 “YES” the measurement data storage unit 10 proceeds to step S106, and when there is no notification (step S105 “NO”), the measurement data storage unit 10 returns to step S101.
- step S ⁇ b> 106 the measurement data storage unit 10 transmits new measurement data received from the sensor 1 after the time when the measurement data for prediction is transmitted to the prediction data generation unit 20 to the difference calculation unit 50 as updated measurement data.
- the measurement data storage unit 10 returns to step S101 after step S106.
- FIG. 11 is a flowchart showing processing performed by the prediction data generation unit 20 of the congestion prediction apparatus according to the second embodiment. The processing in steps S201 to S206 in FIG. 11 is performed in step S200a in FIG.
- the predicted data generation unit 20 performs the same processing as in steps S201 to S203 in FIG.
- the predicted data generation unit 20 uses a linear approximation or the like to predict the number of passing people at a future measurement point according to the predicted data generation range, and generates a plurality of predicted data.
- the prediction data generation unit 20 may generate a plurality of prediction data by changing the approximate expression to be used, or may generate a plurality of prediction data by changing the use range of the measurement data for prediction. Good.
- the prediction data generation unit 20 generates one prediction data based on, for example, the latest five measurement data, and the ten most recent measurements. Another predicted data is generated based on the data.
- steps S205 and S206 the predicted data generation unit 20 performs the same processing as steps S205 and S206 in FIG.
- FIG. 12 is a flowchart showing processing performed by the prediction data storage unit 30 of the congestion prediction device according to the second embodiment. The processing in steps S301 to S303a in FIG. 12 is performed in step S300a in FIG.
- the predicted data storage unit 30 performs the same processing as steps S301 and S302 in FIG.
- step S303a the prediction data storage unit 30 assigns one of the plurality of prediction data stored in step S302 to one of the plurality of congestion prediction processing units 40 on a one-to-one basis, and assigns the prediction data to the assignment destination. It transmits to the congestion prediction processing unit 40.
- the prediction data transmitted to the allocation destination congestion prediction processing unit 40 is referred to as selection prediction data.
- the predicted data storage unit 30 transmits the selected predicted data to the plurality of congestion prediction processing units 40 one by one.
- the prediction data storage unit 30 also transmits the plurality of selected prediction data transmitted to the plurality of congestion prediction processing units 40 to the difference calculation unit 50.
- the predicted data storage unit 30 returns to step S301 after step S303a.
- FIG. 13 is a flowchart illustrating processing performed by the congestion prediction processing unit 40 of the congestion prediction apparatus according to the second embodiment.
- Each of the plurality of congestion prediction processing units 40 performs the processing shown in the flowchart of FIG.
- the processing in steps S401 to S414 in FIG. 13 is performed in step S400a in FIG.
- the congestion prediction processing unit 40 performs the same processing as in steps S401 to S403 in FIG.
- the congestion prediction processing unit 40 confirms whether the congestion prediction processing has reached the measurement data storage unit notification time point.
- the measurement data storage section notification time is a parameter that determines how far ahead the congestion prediction is started from when the congestion prediction is started and when the notification is transmitted to the measurement data storage section 10, and is based on the congestion prediction end time. It is the time when it is set. For example, 100 steps before the congestion prediction end point is set as the measurement data storage unit notification point.
- the measurement data storage unit notification time point may be set in the congestion prediction processing unit 40 in advance, or may be set from outside the congestion prediction device as necessary.
- the congestion prediction processing unit 40 proceeds to step S412 when the congestion prediction processing has reached the measurement data storage unit notification time (step S411 “YES”), and proceeds to step S403 when the congestion prediction processing has not reached (step S411 “NO”). Return to continue the congestion prediction process.
- step S412 the congestion prediction processing unit 40 transmits a notification to the measurement data storage unit 10. This notification is for transmitting updated measurement data from the measurement data storage unit 10 to the difference calculation unit 50.
- step S413 and step S404 following this step S413 the congestion prediction processing unit 40 performs the same processing as in step S403 and step S404 in FIG.
- the congestion prediction processing unit 40 proceeds to step S414, and when not reached (step S404 “NO”), returns to step S413. Continue the congestion prediction process.
- step S414 the congestion prediction processing unit 40 confirms whether or not there is a notification from the difference calculation unit 50.
- step S414 “YES” the congestion prediction processing unit 40 proceeds to step S405, and when there is no notification (step S414 “NO”), the congestion prediction processing unit 40 returns to step S401.
- the congestion prediction processing unit 40 performs the same processing as steps S405 and S406 of FIG.
- FIG. 14 is a flowchart illustrating processing performed by the difference calculation unit 50 of the congestion prediction device according to the second embodiment. The processing in steps S501 to S506 in FIG. 14 is performed in step S500 in FIG.
- step S501 of FIG. 14 the difference calculating unit 50 confirms whether or not a plurality of selected predicted data has been received from the predicted data storage unit 30.
- the difference calculation unit 50 proceeds to step S502 when a plurality of selection prediction data is received (step S501 “YES”), and repeats step S501 when there is no reception (step S501 “NO”).
- step S502 the difference calculating unit 50 receives a plurality of selected predicted data from the predicted data storage unit 30.
- step S503 the difference calculation unit 50 confirms whether or not the updated measurement data is received from the measurement data storage unit 10.
- the difference calculation unit 50 proceeds to step S504 when the update measurement data is received (step S503 “YES”), and repeats step S503 when there is no reception (step S503 “NO”).
- step S504 the difference calculation unit 50 receives the updated measurement data from the measurement data storage unit 10.
- step S505 the difference calculation unit 50 uses the method such as the sum of absolute differences to update each of the plurality of selected predicted data received from the predicted data storage unit 30 and the updated measurement data received from the measurement data storage unit 10. And the selected predicted data having the smallest difference from the updated measurement data is selected as the optimal predicted data.
- step S506 the difference calculation unit 50 selects the congestion prediction processing unit 40 performing the congestion prediction process using the optimal prediction data selected in step S505 from the plurality of congestion prediction processing units 40, and the congestion A notification is transmitted to the prediction processing unit 40.
- This notification is for causing the congestion prediction processing unit 40 to output optimal congestion prediction data from a plurality of congestion prediction data.
- the difference calculation unit 50 returns to step S501 after step S506.
- the plurality of congestion prediction processing units 40 perform a plurality of congestion prediction processes in parallel.
- one congestion prediction processing unit 40 performs a plurality of congestion prediction processes in order. May be.
- the congestion prediction device is based on the measurement data newly output by the sensor 1 during the congestion state prediction process from the plurality of prediction data generated by the prediction data generation unit 20. It is the structure provided with the difference calculation part 50 which selects the prediction data with the smallest difference.
- the congestion prediction processing unit 40 generates a plurality of congestion prediction data using the plurality of prediction data generated by the prediction data generation unit 20, and the prediction selected by the difference calculation unit 50 among the plurality of congestion prediction data. In this configuration, congestion prediction data generated using the data is output. Thereby, the optimal congestion prediction data with high prediction accuracy can be output.
- any combination of each embodiment, any component of each embodiment can be modified, or any component of each embodiment can be omitted.
- the congestion prediction apparatus in the said description was the structure which estimates congestion of one measurement point using one sensor 1, even if it is the structure which predicts congestion of several measurement points using several sensors 1. Good.
- the congestion prediction device does not require preparation of data in advance, it is particularly suitable for predicting the congestion state at the first event or venue.
- 1 sensor 10 measurement data storage unit, 20 prediction data generation unit, 30 prediction data storage unit, 40 congestion prediction processing unit, 50 difference calculation unit, 101 processor, 102 memory, 103 input interface, 104 output interface.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
Description
実施の形態1.
図1は、この発明の実施の形態1に係る混雑予測装置の機能構成図である。この混雑予測装置は、イベント開催時、駅もしくはバス停留所等の公共交通機関または駐車場等、人が発生する場所からイベント会場までの経路の混雑状態を予測するものである。人が発生する場所からイベント会場までの経路にはセンサ1が設置され、センサ1と混雑予測装置とが接続される。
混雑予測装置における計測データ記憶部10および予想データ記憶部30は、メモリ102である。
図3は、実施の形態1に係る混雑予測装置が行う処理を示すシーケンス図である。図4は、実施の形態1に係る混雑予測装置の計測データ記憶部10が行う処理を示すフローチャートである。この図4のステップS101~S104における処理は、図3のステップS100において実施される。
計測データ記憶部10は、ステップS104の後、ステップS101へ戻る。
予想データ記憶部30は、ステップS303の後、ステップS301へ戻る。
混雑予測処理部40は、ステップS406の後、ステップS401へ戻る。
実施の形態2では、混雑予測処理部40における混雑状態の予測処理中にセンサ1が新たに出力した計測データを、混雑予測データに反映して出力するようにする。
実施の形態2に係る混雑予測装置は、図1に示した実施の形態1に係る混雑予測装置に対して差異算出部50が追加された構成である。この差異算出部50の機能は、図2に示されたプロセッサ101がメモリ102に格納されたプログラムを読み出して実行することにより実現される。
図9は、実施の形態2に係る混雑予測装置が行う処理を示すシーケンス図である。図10は、実施の形態2に係る混雑予測装置の計測データ記憶部10が行う処理を示すフローチャートである。この図10のステップS101~S106における処理は、図9のステップS100aにおいて実施される。
計測データ記憶部10は、ステップS106の後、ステップS101へ戻る。
予想データ記憶部30は、ステップS303aの後、ステップS301へ戻る。
差異算出部50は、ステップS506の後、ステップS501へ戻る。
また、上記説明における混雑予測装置はひとつのセンサ1を用いてひとつの計測地点を混雑予測する構成であったが、複数のセンサ1を用いて複数の計測地点を混雑予測する構成であってもよい。
Claims (4)
- 計測地点を通過した人物の人数を計測するセンサが出力した計測データを用いて、前記計測地点における未来の通過人数を予想して予想データを生成する予想データ生成部と、
前記予想データ生成部が生成した前記予想データを用いて、前記計測地点の未来の混雑状態を予測して混雑予測データを生成し出力する混雑予測処理部とを備える混雑予測装置。 - 前記混雑予測処理部は、前記混雑状態の予測処理中に前記センサが新たに出力した計測データを、前記混雑予測データに反映して出力することを特徴とする請求項1記載の混雑予測装置。
- 前記予想データ生成部が生成した複数の予想データの中から、前記混雑状態の予測処理中に前記センサが新たに出力した計測データとの差異が最も小さい予想データを選択する差異算出部を備え、
前記混雑予測処理部は、前記予想データ生成部が生成した前記複数の予想データを用いて複数の混雑予測データを生成し、当該複数の混雑予測データのうち、前記差異算出部が選択した前記予想データを用いて生成した混雑予測データを出力することを特徴とする請求項2記載の混雑予測装置。 - 予想データ生成部が、計測地点を通過した人物の人数を計測するセンサが出力した計測データを用いて、前記計測地点における未来の通過人数を予想して予想データを生成する予想データ生成ステップと、
混雑予測処理部が、前記予想データ生成ステップで生成された前記予想データを用いて、前記計測地点の未来の混雑状態を予測して混雑予測データを生成し出力する混雑予測処理ステップとを備える混雑予測方法。
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/069,680 US20190027029A1 (en) | 2016-03-03 | 2016-03-03 | Congestion prediction device and congestion prediction method |
CN201680082378.8A CN108701334B (zh) | 2016-03-03 | 2016-03-03 | 拥挤预测装置和拥挤预测方法 |
PCT/JP2016/056581 WO2017149720A1 (ja) | 2016-03-03 | 2016-03-03 | 混雑予測装置および混雑予測方法 |
JP2016548399A JP6062124B1 (ja) | 2016-03-03 | 2016-03-03 | 混雑予測装置および混雑予測方法 |
SG11201805249RA SG11201805249RA (en) | 2016-03-03 | 2016-03-03 | Congestion prediction device and congestion prediction method |
TW105124048A TWI611378B (zh) | 2016-03-03 | 2016-07-29 | 混亂預測裝置以及混亂預測方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2016/056581 WO2017149720A1 (ja) | 2016-03-03 | 2016-03-03 | 混雑予測装置および混雑予測方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017149720A1 true WO2017149720A1 (ja) | 2017-09-08 |
Family
ID=57800029
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2016/056581 WO2017149720A1 (ja) | 2016-03-03 | 2016-03-03 | 混雑予測装置および混雑予測方法 |
Country Status (6)
Country | Link |
---|---|
US (1) | US20190027029A1 (ja) |
JP (1) | JP6062124B1 (ja) |
CN (1) | CN108701334B (ja) |
SG (1) | SG11201805249RA (ja) |
TW (1) | TWI611378B (ja) |
WO (1) | WO2017149720A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2022034358A (ja) * | 2020-08-18 | 2022-03-03 | 東日本旅客鉄道株式会社 | 混雑予測装置、混雑予測システム、混雑予測方法及び混雑予測プログラム |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6905888B2 (ja) * | 2017-07-25 | 2021-07-21 | 日本電信電話株式会社 | 流量予測装置、方法、及びプログラム |
JP6933992B2 (ja) | 2018-03-26 | 2021-09-08 | 株式会社日立ソリューションズ | 人流予測装置および人流予測プログラム |
CN111785016A (zh) * | 2020-05-27 | 2020-10-16 | 诠航科技有限公司 | 一种闸道口机器人以及基于闸道口机器人的交通预警系统 |
CN111551187B (zh) * | 2020-06-04 | 2021-09-24 | 福建江夏学院 | 一种基于捕食搜索策略的行车路线规划方法及系统 |
CN111724592B (zh) * | 2020-06-12 | 2022-11-25 | 重庆大学 | 一种基于收费数据与卡口数据的高速公路交通拥堵检测方法 |
CN112382099B (zh) * | 2021-01-15 | 2021-04-13 | 腾讯科技(深圳)有限公司 | 交通路况预测方法、装置、电子设备及存储介质 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004178358A (ja) * | 2002-11-28 | 2004-06-24 | Meidensha Corp | イベント警備監視方法及びイベント警備監視装置 |
JP2011248429A (ja) * | 2010-05-24 | 2011-12-08 | Nippon Telegr & Teleph Corp <Ntt> | 情報提示システム、情報提示装置、および情報提示プログラム |
JP2015207041A (ja) * | 2014-04-17 | 2015-11-19 | 株式会社ニコン | 混雑度推定サーバ、および混雑度推定システム |
Family Cites Families (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3521637B2 (ja) * | 1996-08-02 | 2004-04-19 | オムロン株式会社 | 通過人数計測装置及びそれを用いた入退場者数管理システム |
JP4399283B2 (ja) * | 2004-01-30 | 2010-01-13 | 三菱電機株式会社 | 駅混雑度推定システム |
JP4508840B2 (ja) * | 2004-11-15 | 2010-07-21 | 三菱電機株式会社 | 列車運行管理システム |
JP2007145210A (ja) * | 2005-11-29 | 2007-06-14 | Nippon Telegr & Teleph Corp <Ntt> | 列車混雑度提供システム、混雑度算出器、およびプログラム |
US20070208498A1 (en) * | 2006-03-03 | 2007-09-06 | Inrix, Inc. | Displaying road traffic condition information and user controls |
JP4982143B2 (ja) * | 2006-09-27 | 2012-07-25 | クラリオン株式会社 | 交通状況予測装置 |
CN100583171C (zh) * | 2008-09-04 | 2010-01-20 | 上海交通大学 | 基于客流预测和自适应仿真的拥挤预警系统 |
CN102050366B (zh) * | 2009-11-05 | 2013-02-13 | 上海三菱电梯有限公司 | 人数检测装置及方法 |
JP5520203B2 (ja) * | 2010-12-01 | 2014-06-11 | 株式会社日立製作所 | 混雑度推定装置 |
CN102096813A (zh) * | 2011-02-10 | 2011-06-15 | 北京邮电大学 | 单目摄像机垂直视角下基于Blob的行人计数方法 |
CN102142192B (zh) * | 2011-04-28 | 2014-05-28 | 北京市劳动保护科学研究所 | 基于组合多步预测的行人交通拥堵预警方法及系统 |
JP5615312B2 (ja) * | 2012-03-26 | 2014-10-29 | 株式会社デンソーアイティーラボラトリ | 渋滞予測方法及び渋滞予測装置 |
CN102801775A (zh) * | 2012-04-17 | 2012-11-28 | 杭州群核信息技术有限公司 | 一种实时处理远程监控信息的云计算平台 |
JP6212290B2 (ja) * | 2013-06-05 | 2017-10-11 | 株式会社日立製作所 | エレベーターシステムの群管理制御方法 |
CN103714698B (zh) * | 2013-12-26 | 2016-09-21 | 苏州清研微视电子科技有限公司 | 基于距离图像的公交车辆客流量统计系统及方法 |
WO2015162670A1 (ja) * | 2014-04-21 | 2015-10-29 | 三菱電機株式会社 | 列車走行予測装置および列車走行予測方法 |
CN104050809B (zh) * | 2014-06-03 | 2016-07-20 | 北京航天福道高技术股份有限公司 | 交通状况自动分析预测方法 |
CN104050808B (zh) * | 2014-06-03 | 2016-05-18 | 北京航天福道高技术股份有限公司 | 公路交通堵塞定位搜寻方法 |
US10136249B2 (en) * | 2015-07-24 | 2018-11-20 | Hitachi, Ltd. | Information distribution apparatus and method |
CN105224999A (zh) * | 2015-09-10 | 2016-01-06 | 北京市交通信息中心 | 基于afc数据的城市轨道交通实时客流预测方法及系统 |
CN105279572B (zh) * | 2015-09-16 | 2017-02-08 | 北京城建设计发展集团股份有限公司 | 城市轨道交通客流密集度指数计算与发布系统 |
-
2016
- 2016-03-03 JP JP2016548399A patent/JP6062124B1/ja active Active
- 2016-03-03 US US16/069,680 patent/US20190027029A1/en not_active Abandoned
- 2016-03-03 SG SG11201805249RA patent/SG11201805249RA/en unknown
- 2016-03-03 CN CN201680082378.8A patent/CN108701334B/zh active Active
- 2016-03-03 WO PCT/JP2016/056581 patent/WO2017149720A1/ja active Application Filing
- 2016-07-29 TW TW105124048A patent/TWI611378B/zh active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004178358A (ja) * | 2002-11-28 | 2004-06-24 | Meidensha Corp | イベント警備監視方法及びイベント警備監視装置 |
JP2011248429A (ja) * | 2010-05-24 | 2011-12-08 | Nippon Telegr & Teleph Corp <Ntt> | 情報提示システム、情報提示装置、および情報提示プログラム |
JP2015207041A (ja) * | 2014-04-17 | 2015-11-19 | 株式会社ニコン | 混雑度推定サーバ、および混雑度推定システム |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2022034358A (ja) * | 2020-08-18 | 2022-03-03 | 東日本旅客鉄道株式会社 | 混雑予測装置、混雑予測システム、混雑予測方法及び混雑予測プログラム |
JP7175072B2 (ja) | 2020-08-18 | 2022-11-18 | 東日本旅客鉄道株式会社 | 混雑予測システム、混雑予測方法及び混雑予測プログラム |
Also Published As
Publication number | Publication date |
---|---|
CN108701334B (zh) | 2022-08-26 |
JPWO2017149720A1 (ja) | 2018-03-15 |
SG11201805249RA (en) | 2018-09-27 |
US20190027029A1 (en) | 2019-01-24 |
TW201732748A (zh) | 2017-09-16 |
TWI611378B (zh) | 2018-01-11 |
CN108701334A (zh) | 2018-10-23 |
JP6062124B1 (ja) | 2017-01-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6062124B1 (ja) | 混雑予測装置および混雑予測方法 | |
JP7042905B2 (ja) | 逆センサモデルを生成する方法および装置、ならびに障害物を検出するための方法 | |
WO2009038561A1 (en) | System and method for threat propagation estimation | |
JP2009064433A (ja) | 共同体に基づく信用のための方法及び装置 | |
JP2015172850A (ja) | 駅混雑予測装置及び駅混雑情報提供システム | |
EP3862990A1 (en) | Information processing method, and information processing system | |
TW201729960A (zh) | 基於立體視覺的隨機地圖產生和貝氏更新 | |
US10467888B2 (en) | System and method for dynamically adjusting an emergency coordination simulation system | |
JP2018022413A (ja) | 混雑予測装置、混雑予測方法及び混雑予測プログラム | |
WO2020116022A1 (ja) | センサシステム、センサシステムの制御方法、及び制御装置 | |
WO2016075931A1 (ja) | 避難予測システム、避難予測方法及びコンピュータ読み取り可能記録媒体 | |
WO2019171552A1 (ja) | 光モジュールの寿命予測方法および寿命予測装置 | |
JP5002733B2 (ja) | 在室人数推定装置及び在室人数推定方法 | |
JP4908541B2 (ja) | 在室人数推定装置及び在室人数推定方法 | |
JP2019021047A (ja) | 情報処理装置、制御方法およびプログラム | |
CN109754115B (zh) | 数据预测的方法、装置、存储介质及电子设备 | |
JP2018095142A (ja) | 車載制御装置 | |
JP2023032184A (ja) | 追尾装置 | |
JP2008165362A (ja) | 旅行時間算出装置、プログラム、および記録媒体 | |
JP2009069080A (ja) | 被測定物の将来温度推定方法、装置、及びコンピュータプログラム | |
JP2016211877A (ja) | 下水流入量予測装置 | |
JP2020149282A (ja) | データ予測装置、データ予測方法、及びデータ予測プログラム | |
WO2018131311A1 (ja) | センシングシステム、センサノード装置、センサ測定値処理方法及びプログラム | |
WO2022013928A1 (ja) | エレベーターの停止予測システム | |
JP2023043006A (ja) | 予測装置、予測方法及び予測プログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2016548399 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 11201805249R Country of ref document: SG |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16892560 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16892560 Country of ref document: EP Kind code of ref document: A1 |