Prediction device

Abstract

To provide a prediction device capable of predicting a stopping time of a vehicle at a stop with higher accuracy.SOLUTION: A prediction device 10 of one embodiment includes: a first detection unit 12 that detects waiting passengers attempting to board a vehicle V stopped at a stop; a second detection unit 14 that detects moving states of passengers existing inside the vehicle V; and a prediction unit 15 that predicts a stopping time of the vehicle V at the stop based on a detection result by the first detection unit 12 and a detection result by the second detection unit 14.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] One aspect of the present invention relates to a prediction device for predicting a vehicle stop time. [Background technology]

[0002] Patent Document 1 discloses a system that generates bus operation instructions taking into account the number of passengers waiting at bus stops. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-15612 A Summary of the Invention [Problem to be solved by the invention]

[0004] According to the mechanism of Patent Document 1, it is possible to predict the stop time of a vehicle such as a bus at each stop based on the number of waiting passengers at each stop. However, the mechanism has room for improvement in terms of improving the prediction accuracy of the stop time.

[0005] Therefore, an object of one aspect of the present invention is to provide a prediction device that can predict the dwell time of a vehicle at a bus stop with higher accuracy. [Means for solving the problem]

[0006] A prediction device according to one aspect of the present invention includes a first detection unit that detects waiting passengers who are attempting to board a vehicle stopped at a bus stop, a second detection unit that detects the movement status of passengers inside the vehicle stopped at the bus stop, and a prediction unit that predicts the stop time of the vehicle at the bus stop based on the detection results by the first detection unit and the detection results by the second detection unit.

[0007] According to a prediction device according to one aspect of the present invention, the dwell time of a vehicle at a bus stop can be predicted with greater accuracy by taking into account not only the waiting passengers detected by the first detection unit but also the movement status of passengers inside the vehicle. Effect of the Invention

[0008] According to one aspect of the present invention, it is possible to provide a prediction device that can predict the dwell time of a vehicle at a bus stop with higher accuracy. [Brief description of the drawings]

[0009] [Figure 1] FIG. 2 is a diagram illustrating an example of a functional configuration of a prediction device according to an embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of an outside-vehicle image. [Diagram 3] FIG. 2 is a diagram showing an example of an outside-vehicle image. [Figure 4] FIG. 2 is a diagram showing an example of an in-vehicle image. [Diagram 5] FIG. 2 is a diagram showing an example of an in-vehicle image. [Figure 6] 13 is a flowchart showing an example of an operation of the prediction device. [Figure 7] 7 is a flowchart showing an example of the process of step S1 in FIG. 6. [Figure 8] 7 is a flowchart showing an example of the process of step S2 in FIG. 6. [Figure 9] FIG. 2 illustrates an example of a hardware configuration of a prediction device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or corresponding elements are designated by the same reference numerals, and duplicated explanations will be omitted.

[0011] FIG. 1 is a diagram showing an example of a functional configuration of a prediction device 10 according to an embodiment. The prediction device 10 is a device that predicts the stop time at a bus stop of a vehicle V (see FIGS. 2 and 3) carrying passengers and operating along a predetermined route. An example of the vehicle V is a route bus. The vehicle V may be a manned vehicle or an unmanned autonomous vehicle. The prediction device 10 may be configured, for example, as part of a server device group (one or more computer devices) that manages the operation of the vehicle V.

[0012] As shown in FIG. 1, the prediction device 10 includes an exterior vehicle imaging unit 11, a first detection unit 12, an interior vehicle imaging unit 13, a second detection unit 14, a prediction unit 15, and a notification unit 16.

[0013] The outside-vehicle photographing unit 11 photographs the surroundings of the vehicle V stopped at a bus stop, thereby acquiring an outside image of the vehicle V stopped at the bus stop. The image acquired by the outside-vehicle photographing unit 11 may be a moving image or a still image (e.g., a plurality of images acquired periodically at a predetermined interval such as one second). The outside-vehicle photographing unit 11 may be configured, for example, with a camera or the like. For example, the outside-vehicle photographing unit 11 may be disposed so as to acquire an image of a range including the entrance E (boarding entrance) of the vehicle V stopped at the bus stop or the vicinity of the entrance E. The outside-vehicle photographing unit 11 may be attached to the vehicle V itself (e.g., the body of the vehicle V), or may be installed at each bus stop where the vehicle V is scheduled to stop.

[0014] 2 and 3 show an example of an outside-vehicle image IM1 captured by an outside-vehicle capture unit 11 installed at a location capable of capturing an image of an entrance E (in this example, a door provided at the front part of the vehicle V) of a vehicle V stopped at a bus stop. The outside-vehicle image IM1 shown in Fig. 3 is an image captured a little later than the outside-vehicle image IM1 shown in Fig. 2 was captured.

[0015] The first detection unit 12 detects waiting passengers who are about to board the vehicle V stopped at a bus stop. For example, the first detection unit 12 detects the waiting passengers by analyzing the vehicle exterior image IM1 acquired by the vehicle exterior photographing unit 11. As an example, the first detection unit 12 detects the number of waiting passengers and the attributes of each waiting passenger based on the vehicle exterior image IM1. The attributes of the waiting passengers may be information that directly indicates the characteristics of the waiting passengers themselves, such as age (generation), sex, and body type, or may be information that indirectly indicates the characteristics of the waiting passengers from the type, presence, or absence of a specific object associated with the waiting passenger.

[0016] In this embodiment, when there is a specific object related to a waiting passenger, the first detection unit 12 detects the attributes of the waiting passenger by detecting the specific object. The attributes of the waiting passenger detected by the first detection unit 12 are used to correct (add) the time required for the waiting passenger to board the vehicle V. Examples of the specific object include a walking stick, a wheelchair, a stroller, and the like. A walking stick functions as information suggesting that the waiting passenger holding the walking stick is elderly or has difficulty walking, and will take longer to board than a standard waiting passenger. Similarly, a wheelchair or a stroller functions as information suggesting that the time required for the waiting passenger related to the specific object to board the vehicle V will be longer than the standard time required.

[0017] The first detection unit 12 detects a person or a specific object in the vehicle outside image IM1, for example, by using a known object detection method for the vehicle outside image IM1. For example, the first detection unit 12 detects (estimates) a region of a person included in the vehicle outside image IM1 by inputting the vehicle outside image IM1 to be analyzed into a machine learning model (AI model) created to detect a person. Similarly, the first detection unit 12 detects (estimates) a region of a specific object included in the vehicle outside image IM1 by inputting the vehicle outside image IM1 to be analyzed into a machine learning model (AI model) created to detect a specific object (e.g., a walking stick, a wheelchair, a stroller, etc.) registered in advance. In addition, the first detection unit 12 can track (associate) the same person or specific object between multiple frames that are consecutive in time by using a known tracking (object tracking) method for multiple frames (vehicle outside images IM1 at multiple points in time). The first detection unit 12 detects waiting passengers and specific objects by combining the above-mentioned object detection and tracking methods. An example of a processing procedure of the first detection unit 12 will be described below.

[0018] First, the first detection unit 12 detects people reflected in the vehicle outside image IM1. As an example, the first detection unit 12 detects a rectangular area (human area A) including people in the vehicle outside image IM1. In the example of Fig. 2 and Fig. 3, seven people are reflected in the vehicle outside image IM1, so seven human areas A1 to A7 are detected.

[0019] Next, the first detection unit 12 detects, as a waiting passenger, a person who is determined to be highly likely to board the vehicle V among the people captured in the vehicle exterior image IM1. For example, the first detection unit 12 may detect a waiting passenger based on a time change in the vehicle exterior image IM1. For example, the first detection unit 12 may detect, as a waiting passenger, a person who is moving so as to approach the entrance E of the stopped vehicle V. For example, the first detection unit 12 may detect (determine) as a waiting passenger a person whose moving distance approaching the entrance E of the vehicle V during a predetermined unit period (for example, the interval between the time when the vehicle exterior image IM1 in FIG. 2 was captured and the time when the vehicle exterior image IM1 in FIG. 3 was captured) is equal to or greater than a predetermined threshold.

[0020] 2 and 3, the five people corresponding to the human regions A1 to A5 are lined up in this order and moving toward the entrance E of the vehicle V. On the other hand, the two people corresponding to the human regions A6 and A7 are away from the line of the human regions A1 to A5 and are not moving toward the entrance E of the vehicle V. In such a case, the first detection unit 12 compares the outside-vehicle image IM1 in FIG. 2 with the outside-vehicle image IM1 in FIG. 3 and performs the processing as described above to detect the five people corresponding to the human regions A1 to A5 as waiting passengers.

[0021] Furthermore, the first detection unit 12 may detect a wheelchair in which a person corresponding to the person area A2 is riding as a specific object B related to the person. That is, when a specific object B related to a waiting passenger (in this example, the person corresponding to the person area A2) who is scheduled to board the vehicle V is reflected in the outside-vehicle image IM1, the first detection unit 12 may detect the specific object B in association with the waiting passenger.

[0022] The interior photographing unit 13 photographs the interior of the vehicle V stopped at a bus stop, thereby acquiring an interior image of the vehicle V while stopped. The image acquired by the interior photographing unit 13 may be a moving image or a still image (e.g., a plurality of images acquired periodically at a predetermined interval such as one second). The interior photographing unit 13 may be configured, for example, with a camera or the like. For example, the interior photographing unit 13 may be positioned so as to acquire an image including at least an area near the entrance E of the vehicle V. The interior photographing unit 13 is attached, for example, to the interior of the vehicle V. Figures 4 and 5 show an example of an interior image IM2 of a vehicle V stopped at a bus stop.

[0023] The second detection unit 14 detects the movement status of passengers inside the vehicle V stopped at a bus stop. For example, the second detection unit 14 detects the movement status of passengers inside the vehicle by analyzing the interior image IM2 acquired by the interior photography unit 13. As an example, the second detection unit 14 detects the number of passengers moving near the entrance E inside the vehicle V (for example, within a range within a predetermined threshold distance from a reference position indicating the entrance E) and the status of each passenger based on the interior image IM2. The status of the passengers is information indicating, for example, whether they are moving normally or whether they are experiencing trouble such as falling.

[0024] The second detection unit 14 detects the movement of passengers in the vehicle by executing the same method as the first detection unit 12 on the vehicle interior image IM2. For example, the second detection unit 14 detects (estimates) the area of ​​a person included in the vehicle interior image IM2 by inputting the vehicle interior image IM2 to be analyzed into a machine learning model (AI model) created to detect a person. In addition, the second detection unit 14 can track (associate) the same passenger between multiple frames that are consecutive in time by using a known tracking (object tracking) method for multiple frames (vehicle interior images IM2 at multiple points in time). The second detection unit 14 detects passengers moving inside the vehicle (near the entrance E in this embodiment) by combining the above-mentioned object detection and tracking methods.

[0025] Furthermore, the second detection unit 14 can estimate the posture (or posture change) of a passenger reflected in the in-vehicle image IM2 by, for example, performing a known method of pose estimation using the detection results of a person's skeletal points on the in-vehicle image IM2, and based on the estimation result, can determine whether the passenger is experiencing trouble such as a fall.

[0026] In the example of Fig. 4, the second detection unit 14 detects four passengers C who are moving near the entrance E inside the vehicle. In the example of Fig. 5, the second detection unit 14 detects three passengers C who are moving near the entrance E inside the vehicle, and also detects trouble (falling in the example of Fig. 5) for passenger C1 during movement.

[0027] The prediction unit 15 predicts the stop time of the vehicle V at the bus stop based on the detection result by the first detection unit 12 and the detection result by the second detection unit 14. In this embodiment, the stop time of the vehicle V predicted by the prediction unit 15 is the time from a certain point (prediction point) after the vehicle V stops at the bus stop to a point when all waiting passengers have boarded (i.e., the departure possible point when the vehicle V can leave the bus stop). For example, the prediction unit 15 may repeatedly execute a prediction process (for example, a series of processes shown in the flowcharts of FIG. 6 to FIG. 8) described later from a point when the entrance E opens after the vehicle V stops (i.e., the boarding start point when the waiting passengers can board) to the departure possible point. In this case, the predicted stop time can be appropriately updated based on the inside and outside conditions of the vehicle V at the latest point in time.

[0028] In this embodiment, the prediction unit 15 basically predicts the dwell time from a certain prediction time to the time when the vehicle can depart based on the number of waiting passengers detected by the first detection unit 12 at the prediction time (in the example of Figures 2 and 3, five people corresponding to human areas A1 to A5) and the number of passengers moving near the entrance E of the vehicle detected by the second detection unit 14 at the prediction time (four people in the example of Figure 4, and three people in the example of Figure 5).

[0029] The prediction unit 15 may also predict the dwell time based on the attributes of the waiting passenger detected by the first detection unit 12. As described above, in this embodiment, the prediction unit 15 predicts the dwell time based on the attributes of the waiting passenger (information indicating that the waiting passenger corresponding to the person area A2 has a disability in his / her legs and needs to move in a wheelchair in the example of Fig. 2 and Fig. 3) estimated from the specific object B (wheelchair in the example of Fig. 2 and Fig. 3) detected by the first detection unit 12 in association with the waiting passenger. In addition, when a trouble related to the movement of the passenger C is detected by the second detection unit 14, the prediction unit 15 may predict the dwell time based on the trouble (a fall of the passenger C1 in the example of Fig. 5).

[0030] The notification unit 16 notifies the operation manager of the vehicle V or a user of the vehicle V (for example, a user waiting for the arrival of the vehicle V at a stop ahead of the stop where the vehicle V is stopped, etc.) of the stop time predicted by the prediction unit 15. For example, the notification by the notification unit 16 may be executed via an email, application, website, etc. that can be viewed by the operation manager or the registered user. However, the notification method is not limited to the above, and any notification form may be used as long as the operation manager or the user can know the prediction result. In addition, the notification unit 16 may notify information generated based on the stop time predicted by the prediction unit 15 (for example, the expected arrival time of the vehicle V at a stop ahead of the stop where the vehicle V is stopped). In this case, it can be said that the stop time predicted by the prediction unit 15 is substantially notified to the operation manager or the user. In addition, in the case where the prediction process by the prediction unit 15 is repeatedly executed from the boarding start time to the departure possible time as in the present embodiment, the notification unit 16 may notify the prediction result (stop time) every time the prediction process is executed. According to the above configuration, it is possible to provide the latest information to the operation manager or users while appropriately updating the predicted stop time.

[0031] Next, an example of the operation of the prediction device 10 (an example of a prediction method) will be described with reference to Fig. 6. The process of Fig. 6 is started at an arbitrary prediction time point after the time point when the vehicle V stops at a certain bus stop, and is repeatedly executed at a predetermined processing interval until the vehicle V departs from the bus stop. That is, the process of Fig. 6 shows a series of processes executed at one prediction time point.

[0032] In step S1, the prediction unit 15 calculates a ride time that is expected to be required until all waiting passengers detected in the vehicle exterior image IM1 at the time of prediction have boarded the vehicle. Hereinafter, an example of the process in step S1 will be described with reference to FIG.

[0033] In step S11, the vehicle exterior photographing unit 11 acquires a vehicle exterior image IM1 at the prediction time point.

[0034] In step S12, the first detection unit 12 analyzes the vehicle outside image IM1 acquired in step S11. As described above, when detecting a person approaching the entrance E by tracking (object tracking) as a waiting passenger, the first detection unit 12 may also use the vehicle outside image IM1 acquired prior to the current time (the current prediction time) as an analysis target in step S12. In the example of Fig. 2 and Fig. 3, the analysis process in step S12 detects five waiting passengers corresponding to the human regions A1 to A5, and detects a specific object B related to the human region A2.

[0035] If waiting passengers are detected in step S12 (step S13: YES), the prediction unit 15 calculates (predicts) the boarding time based on the detected number of waiting passengers (step S14). As an example, the prediction unit 15 may calculate the boarding time by multiplying the number of waiting passengers by a predetermined average required time per person (e.g., 5 seconds). In the examples of Figs. 2 and 3, the prediction unit 15 calculates 25 seconds (5 seconds x 5 people) as the boarding time. If no waiting passengers are detected in step S12 (step S12: NO), the processing of the subsequent steps shown in the flowchart of Fig. 7 may be skipped, and the boarding time may be set to "0 seconds."

[0036] If a specific object is detected in step S12 (step S15: YES), the prediction unit 15 adds a time corresponding to the detected specific object to the boarding time (step S16). That is, the prediction unit 15 may add an extra time estimated to be required to the boarding time calculated in step S14, taking into consideration the attributes of the waiting passenger estimated based on the detected specific object. As an example, the prediction unit 15 adds an extra time (e.g., 30 seconds) estimated to be required for a waiting passenger in a wheelchair to board the vehicle V, compared to a walking passenger. In the example of FIG. 2 and FIG. 3, a wheelchair in which a person corresponding to the person area A2 boards is detected as the specific object B, so the prediction unit 15 adds a time (30 seconds) corresponding to the specific object B to the boarding time calculated in step S14 (25 seconds). As a result, 55 seconds is calculated as the boarding time expected until all waiting passengers waiting to board at the time of prediction are completed. Note that, if a specific object is not detected in step S12, the process of step S15 is skipped.

[0037] In step S2, the prediction unit 15 calculates an added time according to the inside-vehicle situation. An example of the process in step S2 will be described below with reference to FIG.

[0038] In step S21, the vehicle interior photographing unit 13 acquires a vehicle interior image IM2 at the prediction time point.

[0039] In step S22, the second detection unit 14 analyzes the in-vehicle image IM2 acquired in step S21. When detecting passengers moving near the entrance E by tracking (object tracking), the second detection unit 14 may also use the in-vehicle image IM2 acquired prior to the current time (the current prediction time) as an analysis target in step S22. In the example of FIG. 4, four passengers C are detected by the analysis process in step S22. On the other hand, in the example of FIG. 5, three passengers C are detected, five waiting passengers corresponding to the human areas A1 to A5 are detected, and trouble (falling) during the movement of passenger C1 is detected.

[0040] If a moving passenger C is detected near the entrance E in step S22 (step S23: YES), the prediction unit 15 calculates the added time based on the number of detected passengers (step S24). For example, if the vicinity of the entrance E is crowded with moving passengers C, it is considered that it takes a certain amount of time for the passenger C who boarded the vehicle V to move to an empty seat, an aisle, or the like at the back of the vehicle. Therefore, as an example, the prediction unit 15 may calculate the added time by multiplying the number of passengers C detected near the entrance E by a predetermined added time per person (for example, 1 second). In the example of FIG. 4, the prediction unit 15 calculates 4 seconds (1 second x 4 people) as the added time. On the other hand, in the example of FIG. 5, the prediction unit 15 calculates 3 seconds (1 second x 3 people) as the added time. If a moving passenger is not detected near the entrance E in step S22 (step S23: NO), the processing of each subsequent step shown in the flowchart of FIG. 8 is skipped, and the added time may be set to "0 seconds."

[0041] If a trouble related to the movement of passengers is detected in step S22 (step S25: YES), the prediction unit 15 adds a time corresponding to the detected trouble to the added time (step S26). That is, the prediction unit 15 may add an extra time estimated to be required until the movement of the passenger C in the car (or the passenger who will soon get into the car) is completed due to the detected trouble to the added time calculated in step S24. As an example, when a trouble of the passenger C falling down occurs, the prediction unit 15 adds an extra time (for example, 15 seconds) that is estimated to be required in advance for the content of the trouble. In the example of FIG. 4, since no trouble has occurred, the determination result of step S25 is "NO", and the processing of step S26 is skipped. On the other hand, in the example of FIG. 5, since a trouble of one passenger C1 falling down occurs, the determination result of step S25 is "YES". As a result, in step S26, "15 seconds" that is predetermined for the content of the trouble (falling down) is added to the added time calculated in step S24.

[0042] In step S3, the prediction unit 15 predicts the stop time (in this embodiment, the time from the prediction time to the departure possible time) based on the boarding time calculated in step S1 and the added time calculated in step S2. For example, the prediction unit 15 calculates the sum of the boarding time and the added time as the predicted stop time.

[0043] In step S4, the notification unit 16 notifies the operation manager of the vehicle V or the user of the vehicle V of the stop time predicted by the prediction unit 15 in step S3.

[0044] As described above, the processing procedures shown in the flowcharts of Figures 6 to 8 are merely examples, and the manner of prediction processing of the stop time by the prediction device 10 is not limited to the above processing procedures. For example, some of the processing shown in the flowcharts of Figures 6 to 8 may be deleted, other processing may be added, or the order of some of the processing may be changed. For example, the processing of step S1 in Figure 6 may be executed after the processing of step S2, or may be executed in parallel with the processing of step S2.

[0045] According to the prediction device 10 described above, the stop time of the vehicle at the stop can be predicted with higher accuracy by considering not only the waiting passengers at the stop detected by the first detection unit 12 but also the movement status of passengers inside the vehicle V. That is, in the example of Fig. 6, the stop time with higher accuracy can be obtained by considering not only the boarding time (step S1) based on the number of waiting passengers waiting to board outside the stopped vehicle V but also the added time (step S2) based on the movement status of passengers inside the stopped vehicle V.

[0046] Furthermore, by including the notification unit 16, the prediction device 10 can provide useful information to the operation manager of the vehicle V or the user of the vehicle V. That is, the operation manager can be given an opportunity to check whether the operation of the vehicle V is on schedule or not, and to adjust the operation if it is not on schedule. Also, for example, information can be provided to a user waiting for the arrival of the vehicle V at a future stop to understand whether the vehicle V is likely to arrive on schedule or is likely to be delayed.

[0047] Further, the prediction unit 15 predicts the stop time based on the attributes of the waiting passenger detected by the first detection unit 12. In this embodiment, the prediction unit 15 predicts the stop time based on the attributes of the waiting passenger (information indicating that the passenger is disabled and cannot walk in the above example) estimated from a specific object (specific object B indicating a wheelchair in the examples of Figs. 2 and 3) detected by the first detection unit 12 in association with the waiting passenger. According to the above configuration, the stop time (in this embodiment, the boarding time in step S1 of Fig. 6, among the elements constituting the stop time) can be predicted with higher accuracy based on the attributes of the waiting passenger. Note that, in the above embodiment, the attributes of the waiting passenger are detected based on the specific object of the waiting passenger, but the attributes of the waiting passenger may be detected based on information such as the posture and facial expression of the waiting passenger. For example, when it is detected that the waiting passenger is "elderly", the average required time applied to the waiting passenger (average required time used to calculate the boarding time in step S14 of Fig. 7) may be longer than the standard average required time per person (5 seconds in this embodiment).

[0048] Furthermore, when a trouble related to passenger movement is detected by the second detection unit 14, the prediction unit 15 predicts the stop time based on the trouble. In this embodiment (examples of Figs. 5 and 8), when a fall trouble of passenger C1 is detected, 15 seconds corresponding to the trouble is added to the additional time. With the above configuration, it is possible to more accurately predict the stop time based on the type and presence / absence of a movement trouble within the vehicle, taking into account delays and the like caused by the trouble.

[0049] The prediction device of the present disclosure has the following configuration.

[0050] [1] A first detection unit that detects a waiting passenger who is about to board a vehicle stopped at a bus stop; A second detection unit that detects a movement state of a passenger present in the vehicle stopped at the bus stop; a prediction unit that predicts a stop time of the vehicle at the bus stop based on a detection result by the first detection unit and a detection result by the second detection unit; A prediction device comprising:

[0051] [2] The prediction device of [1], further comprising a notification unit that notifies an operation manager of the vehicle or a user of the vehicle of the stop time predicted by the prediction unit.

[0052] [3] A prediction device according to [1] or [2], wherein the prediction unit predicts the stop time based on attributes of the waiting passengers detected by the first detection unit.

[0053] [4] The prediction device of [3], wherein the prediction unit predicts the stop time based on attributes of the waiting passenger estimated from a specific object detected in association with the waiting passenger by the first detection unit.

[0054] [5] The prediction device according to any one of [1] to [4], wherein the prediction unit predicts the stop time based on a trouble regarding the movement of the passengers when the second detection unit detects the trouble.

[0055] Moreover, the block diagrams used in the description of the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized by using one device that is physically or logically combined, or may be realized by using two or more devices that are physically or logically separated and directly or indirectly connected (for example, by using wires, wirelessly, etc.). The functional blocks may be realized by combining the one device or the multiple devices with software.

[0056] Functions include, but are not limited to, judging, determining, assessing, calculating, processing, deriving, investigating, searching, verifying, receiving, sending, outputting, accessing, resolving, selecting, choosing, establishing, comparing, anticipating, expecting, regarding, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assigning.

[0057] For example, the prediction device 10 according to an embodiment of the present disclosure may function as a computer that performs the prediction method of the present disclosure. Fig. 9 is a diagram showing an example of a hardware configuration of the prediction device 10 according to an embodiment of the present disclosure. The prediction device 10 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0058] In the following description, the term "apparatus" can be replaced with a circuit, a device, a unit, etc. The hardware configuration of the prediction apparatus 10 may be configured to include one or more of the devices shown in FIG. 9, or may be configured to exclude some of the devices.

[0059] Each function in the prediction device 10 is realized by loading a specific software (program) onto hardware such as a processor 1001 and a memory 1002, causing the processor 1001 to perform calculations, control communication via a communication device 1004, and control at least one of reading and writing of data in the memory 1002 and the storage 1003.

[0060] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured with a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, and the like.

[0061] Moreover, the processor 1001 reads out a program (program code), a software module, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to the read out programs. As the program, a program that causes a computer to execute at least a part of the operations described in the above-mentioned embodiment is used. For example, each functional unit (e.g., the prediction unit 15, etc.) of the prediction device 10 may be realized by a control program stored in the memory 1002 and operated in the processor 1001, and other functional blocks may be similarly realized. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may be transmitted from a network via a telecommunication line.

[0062] The memory 1002 is a computer-readable recording medium, and may be configured by at least one of, for example, a Read Only Memory (ROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), a Random Access Memory (RAM), and the like. The memory 1002 may be called a register, a cache, a main memory (primary storage device), and the like. The memory 1002 can store an executable program (program code), a software module, and the like for implementing a prediction method according to an embodiment of the present disclosure.

[0063] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, and the like. Storage 1003 may be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0064] The communication device 1004 is hardware (transmission / reception device) for performing communication between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0065] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0066] In addition, each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0067] Furthermore, the prediction device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0068] Although the present embodiment has been described in detail above, it is clear to those skilled in the art that the present embodiment is not limited to the embodiment described in this specification. The present embodiment can be implemented as a modified or altered form without departing from the spirit and scope of the present invention defined by the description of the claims. Therefore, the description in this specification is intended to be illustrative and does not have any limiting meaning on the present embodiment.

[0069] The order of the steps, sequences, flow charts, etc. of each aspect / embodiment described in this disclosure may be changed unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0070] The input and output information may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information may be overwritten, updated, or added to. The output information may be deleted. The input information may be transmitted to another device.

[0071] The determination may be based on a value represented by a single bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0072] Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched according to execution. In addition, notification of specific information (e.g., notification that "X is the case") is not limited to being done explicitly, but may be done implicitly (e.g., not notifying the specific information).

[0073] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0074] Additionally, software, instructions, information, etc. may be transmitted or received over a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired and / or wireless technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave, etc.), then these wired and / or wireless technologies are included within the definition of transmission media.

[0075] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0076] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0077] The names used for the above-mentioned parameters are not limiting in any way. Furthermore, the formulas etc. using these parameters may differ from those explicitly disclosed in this disclosure. The various information elements may be identified by any suitable names, and the various names assigned to these various information elements are not limiting in any way.

[0078] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0079] Any reference to an element using a designation such as "first," "second," etc., used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must precede the second element in some way.

[0080] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Further, when used in this disclosure, the term "or" is not intended to be an exclusive or.

[0081] In this disclosure, where articles have been added due to translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0082] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different." [Explanation of symbols]

[0083] 10... prediction device, 11... exterior vehicle imaging unit, 12... first detection unit, 13... interior vehicle imaging unit, 14... second detection unit, 15... prediction unit, 16... notification unit, V... vehicle.

Claims

1. a first detection unit that detects a waiting passenger who is about to board a vehicle stopped at a bus stop; A second detection unit that detects a movement state of a passenger present in the vehicle stopped at the bus stop; a prediction unit that predicts a stop time of the vehicle at the bus stop based on a detection result by the first detection unit and a detection result by the second detection unit; A prediction device comprising:

2. The prediction device according to claim 1 , further comprising a notification unit that notifies an operation manager of the vehicle or a user of the vehicle of the stop time predicted by the prediction unit.

3. The prediction device according to claim 1 , wherein the prediction unit predicts the stop time based on an attribute of the waiting passenger detected by the first detection unit.

4. The prediction device according to claim 3 , wherein the prediction unit predicts the stop time based on an attribute of the waiting passenger estimated from a specific object detected by the first detection unit in association with the waiting passenger.

5. The prediction device according to claim 1 , wherein, when a trouble related to the movement of the passengers is detected by the second detection unit, the prediction unit predicts the stop time based on the trouble.

Images