Estimation device and estimation method

Abstract

An estimation device (100) includes: a road information storing unit (142) that stores, for each traffic light, information about links indicating road sections in one direction of travel between a node at the center point of an intersection where a traffic light is installed and nodes on the road; and a calculation unit (152) that, on the basis of the information stored in the road information storing unit (142) and vehicle information received from a vehicle connected to the cloud and in which times and links are associated, identifies the time when the link for the same vehicle changed, and calculates the signal period of each traffic light on the basis of the identified time.

Description

Estimation device and estimation method

[0001] The present invention relates to an estimation device and an estimation method.

[0002] Information on the signal cycles of intersection traffic lights is expected to be used in a variety of fields. For example, analyzing signal cycle information can help identify the causes of past accidents and traffic congestion. Also, users can refer to signal cycle information to drive more efficiently.

[0003] Existing services for obtaining information about traffic light cycles include JARTIC (JApan Road Traffic Information Center), but the information that can be obtained from these services is limited, and it may not be possible to obtain information about the traffic light cycle of the desired traffic light.

[0004] Patent Document 1 discloses a technology that collects the "departure times" of vehicles connected to the cloud, captures the relationship between the "departure times" and the "number of acquired departure times" as a function (departure interval function), and applies an autocorrelation function to the transmission interval function to identify the period of the transmission interval function and estimate the period as the signal cycle length.

[0005] JP 2016-110392 A

[0006] However, the above-mentioned conventional technology (for example, Patent Document 1) has the problem that it is not possible to accurately estimate the signal period of a traffic light when the intersection has a complex structure or when traffic congestion occurs.

[0007] The present invention has been made in view of the above, and has an object to provide an estimation device and an estimation method that can accurately estimate the signal period of a traffic light.

[0008] In order to solve the above-mentioned problems and achieve the objectives, the estimation device is characterized by having a road information storage unit that stores, for each traffic light, information on links that indicate road sections in one direction of travel between a node at the center of an intersection where a traffic light is installed and a node on the road, and a calculation unit that identifies the time when the link of the same vehicle changed based on the information stored in the road information storage unit and vehicle information received from vehicles connected to the cloud, which corresponds time to link, and calculates the signal period of each traffic light based on the identified time.

[0009] According to the present invention, the signal period of a traffic light can be accurately estimated.

[0010] FIG. 1 is a diagram illustrating an example of the configuration of an estimation system. FIG. 2 is a diagram for explaining links. FIG. 3 is a diagram (1) illustrating an example of vehicle information transmitted by a vehicle to the estimation device. FIG. 4 is a diagram (2) illustrating an example of vehicle information transmitted by a vehicle to the estimation device. FIG. 5 is a diagram illustrating an example of the data structure of a vehicle information storage unit. FIG. 6 is a diagram illustrating an example of the data structure of a road information storage unit. FIG. 7 is a diagram for explaining processing by the estimation device. FIG. 8 is a diagram illustrating an example of a graph generated by the estimation device. FIG. 9 is a functional block diagram illustrating the configuration of the estimation device. FIG. 10 is a flowchart illustrating the processing procedure of the estimation device. FIG. 11 is a diagram illustrating an example of a complex intersection. FIG. 12 is a diagram illustrating an example of a display of the signal cycles of multiple traffic lights. FIG. 13 is a diagram illustrating an example of a computer that executes an estimation program.

[0011] Hereinafter, embodiments of the estimation device and estimation method disclosed in the present application will be described in detail with reference to the accompanying drawings. However, the present invention is not limited to these embodiments.

[0012] (Embodiment) (Estimation System) An example of an estimation system according to an embodiment will be described below. Fig. 1 is a diagram showing an example of the configuration of the estimation system.

[0013] As shown in Fig. 1, the estimation system 1 includes vehicles 10a, 10b, and 10c, and an estimation device 100. The vehicles 10a to 10c and the estimation device 100 are connected to each other via a network 5. Although Fig. 1 shows the vehicles 10a to 10c, other vehicles may also be included.

[0014] The vehicles 10a to 10c are vehicles equipped with communication devices that can connect to the network (cloud) 5. The vehicles 10a to 10c generate "vehicle information" every second and transmit the vehicle information to the estimation device 100. In the following description, the vehicles 10a to 10c will be collectively referred to as vehicle 10 where appropriate.

[0015] For example, the vehicle information includes a vehicle ID (Identification), time, latitude, longitude, speed, and link ID. The vehicle ID is information that uniquely identifies a vehicle. The time is the time when the vehicle generated the vehicle information. The latitude and longitude are the location information (latitude, longitude) of the vehicle corresponding to the vehicle ID. The speed is the speed of the vehicle corresponding to the vehicle ID.

[0016] The link ID is information for identifying the link of the vehicle corresponding to the vehicle ID. For example, a road section in one direction of travel between a node at the center of an intersection where a traffic light is installed and a node on the road is defined as a "link."

[0017] FIG. 2 is a diagram for explaining links. In the example shown in FIG. 2, an intersection with a traffic light is referred to as intersection 2. The traffic light is not shown. Intersection 2 includes links L1, L2, L3, L4, L5, L6, L7, and L8. Links L1 to L8 are defined as follows:

[0018] Link L1 is a road section in one direction of travel between node n0, which is the center point of intersection 2, and node n1 on the road. Vehicles travel from south to north on the road section corresponding to link L1. Vehicles traveling on the road section of link L1 can enter any of links L3 (go straight), L6 (turn left), and L7 (turn right).

[0019] Link L2 is a road section in one direction of travel between node n0, which is the center point of intersection 2, and node n2 on the road. Vehicles travel from north to south on the road section corresponding to link L2. Vehicles traveling on the road section of link L2 can enter any of links L4 (going straight), L7 (turning left), and L6 (turning right).

[0020] Link L3 is a road section in one direction of travel between node n0 at the center of intersection 2 and node n3 on the road. In the road section corresponding to link L3, vehicles travel from south to north.

[0021] Link L4 is a road section in one direction of travel between node n0 at the center of intersection 2 and node n4 on the road. In the road section corresponding to link L4, vehicles travel from north to south.

[0022] Link L5 is a road section in one direction of travel between node n0, which is the center point of intersection 2, and node n5 on the road. Vehicles travel from west to east on the road section corresponding to link L5. Vehicles traveling on the road section of link L5 can enter any of links L7 (going straight), L3 (turning left), and L4 (turning right).

[0023] Link L6 is a road section in one direction of travel between node n0 at the center of intersection 2 and node n6 on the road. In the road section corresponding to link L6, a vehicle travels from east to west.

[0024] Link L7 is a road section in one direction of travel between node n0 at the center of intersection 2 and node n7 on the road. In the road section corresponding to link L6, a vehicle travels from west to east.

[0025] Link L8 is a road section in one direction of travel between node n0, which is the center point of intersection 2, and node n8 on the road. Vehicles travel from east to west on the road section corresponding to link L6. Vehicles traveling on the road section of link L8 can enter any of links L6 (straight ahead), L4 (left turn), and L3 (right turn).

[0026] The links L1 to L8 have been described above. Here, an example of the transition of vehicle information transmitted from the vehicles 10a to 10c to the estimation device 100 will be described. The link IDs of the links L1 to L8 are (1) to (8), respectively.

[0027] Fig. 3 is a diagram (1) illustrating an example of vehicle information transmitted by a vehicle to an estimation device. The example shown in Fig. 3 shows the transition of vehicle information when a vehicle 10a moves from link L1 to link L3 at intersection 2. The vehicle ID of vehicle 10a is assumed to be "CA." Nodes n0 to n8 are not shown in Fig. 3.

[0028] For example, when the vehicle 10a is traveling at position 1-1, it generates vehicle information D1-1 and transmits it to the estimation device 100. The vehicle information D1-1 includes a vehicle ID of "CA," a time of "September 1, 2020, 15:32:01," a latitude of "35.19 (degrees)," a longitude of "137.06 (degrees)," a speed of "14.1 (m / s)," and a link ID of "(1)."

[0029] One second after generating vehicle information D1-1, vehicle 10a moves to position 1-2. While vehicle 10a is traveling at position 1-2, vehicle 10a generates vehicle information D1-2 and transmits it to estimation device 100. In vehicle information D1-2, the following are set: vehicle ID "CA", time "September 1, 2020, 15:32:02", latitude "35.19 (degrees)", longitude "137.06 (degrees)", speed "13.9 (m / s)", and link ID "(1)".

[0030] One second after generating the vehicle information D1-2, the vehicle 10a moves to position 1-3. While the vehicle 10a is traveling at position 1-3, the vehicle 10a generates vehicle information D1-3 and transmits it to the estimation device 100. The vehicle information D1-3 includes the following settings: vehicle ID "CA", time "September 1, 2020, 15:32:03", latitude "35.19 (degrees)", longitude "137.06 (degrees)", speed "13.8 (m / s)", and link ID "(1)".

[0031] One second after generating the vehicle information D1-3, the vehicle 10a moves to position 1-4 (moves to link L3). While the vehicle 10a is traveling at position 1-4, it generates vehicle information D1-4 and transmits it to the estimation device 100. The vehicle information D1-4 includes the following: vehicle ID "CA", time "September 1, 2020, 15:32:04", latitude "35.19 (degrees)", longitude "137.06 (degrees)", speed "13.7 (m / s)", and link ID "(3)".

[0032] One second after generating the vehicle information D1-4, the vehicle 10a moves to position 1-5. While the vehicle 10a is traveling at position 1-5, the vehicle 10a generates vehicle information D1-5 and transmits it to the estimation device 100. The vehicle information D1-5 includes the following set: vehicle ID "CA", time "September 1, 2020, 15:32:05", latitude "35.19 (degrees)", longitude "137.06 (degrees)", speed "13.8 (m / s)", and link ID "(3)".

[0033] In the example shown in Figure 3, vehicle 10a is moving (straight) from link L1 to link L3, so it can be determined that the traffic light for the north-south direction at intersection 2 is green and the traffic light for the east-west direction at intersection 2 is red. Note that in the example of Figure 3, values ​​after "35.19 (degrees)" are omitted for the latitude at each time. Similarly, values ​​after "137.06 (degrees)" are omitted for the longitude at each time.

[0034] Fig. 4 is a diagram (2) illustrating an example of vehicle information transmitted by a vehicle to an estimation device. The example shown in Fig. 4 shows the transition of vehicle information when vehicle 10b moves from link L5 to link L4 at intersection 2. The vehicle ID of vehicle 10b is assumed to be "CB." Nodes n0 to n8 are not shown in Fig. 4.

[0035] For example, when vehicle 10b is traveling at position 2-1, it generates vehicle information D2-1 and transmits it to estimation device 100. The vehicle information D2-1 includes a vehicle ID of "CB," a time of "September 1, 2020, 8:11:34," a latitude of "35.19 (degrees)," a longitude of "137.06 (degrees)," a speed of "11.8 (m / s)," and a link ID of "(5)."

[0036] One second after generating vehicle information D2-1, vehicle 10b moves to position 2-2. While vehicle 10b is traveling at position 2-2, vehicle 10b generates vehicle information D2-2 and transmits it to estimation device 100. In vehicle information D2-2, the following are set: vehicle ID "CB," time "September 1, 2020, 8:11:35," latitude "35.19 (degrees)," longitude "137.06 (degrees)," speed "11.5 (m / s)," and link ID "(5)."

[0037] One second after generating vehicle information D2-2, vehicle 10b moves to position 2-3. While vehicle 10b is traveling at position 2-3, vehicle 10b generates vehicle information D2-3 and transmits it to estimation device 100. In vehicle information D2-3, the following are set: vehicle ID "CB", time "September 1, 2020, 8:11:36", latitude "35.19 (degrees)", longitude "137.06 (degrees)", speed "11.1 (m / s)", and link ID "(5)".

[0038] One second after generating vehicle information D2-3, vehicle 10b moves to position 2-4 (moves to link L4). While vehicle 10b is traveling at position 2-4, it generates vehicle information D2-4 and transmits it to the estimation device 100. The vehicle information D2-4 includes the following settings: vehicle ID "CB", time "September 1, 2020, 8:11:37", latitude "35.19 (degrees)", longitude "137.06 (degrees)", speed "10.8 (m / s)", and link ID "(4)".

[0039] One second after generating vehicle information D2-4, vehicle 10b moves to position 2-5. While vehicle 10b is traveling at position 2-5, vehicle 10b generates vehicle information D2-5 and transmits it to the estimation device 100. In vehicle information D2-5, the following are set: vehicle ID "CB", time "September 1, 2020, 8:11:38", latitude "35.19 (degrees)", longitude "137.06 (degrees)", speed "10.6 (m / s)", and link ID "(4)".

[0040] One second after generating vehicle information D2-5, vehicle 10b moves to position 2-6. While vehicle 10b is traveling at position 2-6, it generates vehicle information D2-6 and transmits it to the estimation device 100. In vehicle information D2-6, the following are set: vehicle ID "CB", time "September 1, 2020, 8:11:39", latitude "35.19 (degrees)", longitude "137.06 (degrees)", speed "10.5 (m / s)", and link ID "(4)".

[0041] One second after generating vehicle information D2-6, vehicle 10b moves to position 2-7. While vehicle 10b is traveling at position 2-7, it generates vehicle information D2-7 and transmits it to the estimation device 100. The vehicle information D2-7 includes the following settings: vehicle ID "CB", time "September 1, 2020, 8:11:40", latitude "35.19 (degrees)", longitude "137.06 (degrees)", speed "10.3 (m / s)", and link ID "(4)".

[0042] In the example shown in Figure 4, vehicle 10b is moving (turning right) from link L5 to link L4, and therefore it can be determined that the traffic light for the north-south direction at intersection 2 is "red" and the traffic light for the east-west direction at intersection 2 is "green." Note that in the example of Figure 4, values ​​after "35.19 (degrees)" are omitted for the latitude at each time. Similarly, values ​​after "137.06 (degrees)" are omitted for the longitude at each time.

[0043] 3 and 4 , when the vehicle 10 travels through the intersection 2, the vehicle 10 generates vehicle information every second and transmits the generated vehicle information to the estimation device 100. Note that the vehicle 10 may identify the link ID in any way when generating the vehicle information. For example, the vehicle 10 has a determination table that associates link areas with link IDs, and identifies the link ID of the link on which the vehicle 10 is traveling based on the determination table and vehicle position information acquired using a GPS (Global Positioning System) function or the like.

[0044] (Estimation Device) Next, we will move on to explaining the estimation device 100 shown in Fig. 1. The estimation device 100 identifies the time when the link (link ID) of the same vehicle changed based on vehicle information received from the vehicle 10, and calculates the signal period of each traffic light based on the identified time. For example, the estimation device 100 has a vehicle information storage unit 141 and a road information storage unit 142.

[0045] Fig. 5 is a diagram showing an example of the data structure of the vehicle information storage unit. As shown in Fig. 5, the vehicle information storage unit 141 has a vehicle ID, time, latitude, longitude, speed, and link ID. The explanations regarding the vehicle ID, time, latitude, longitude, speed, and link ID are the same as those given in Figs. 3 and 4 . The estimation device 100 stores the vehicle information in the vehicle information storage unit 141 every time it receives the vehicle information from the vehicle 10. One record in the vehicle information storage unit 141 corresponds to one piece of vehicle information.

[0046] FIG. 6 is a diagram showing an example of the data structure of the road information storage unit. As shown in FIG. 6, the road information storage unit 142 has a traffic light ID, location information, and link ID configuration information. The traffic light ID is information that uniquely identifies a traffic light. The location information is location information (latitude, longitude) of the intersection where the traffic light ID is installed. The link ID configuration information is information about the link of the intersection where the traffic light ID is set. For example, if the intersection where the traffic light IDs "SIG1-1 (e.g., north-south direction)" and "SIG1-2 (e.g., east-west direction)" are set is intersection 2 shown in FIG. 2, the link ID configuration information corresponding to the traffic light IDs "SIG1-1" and "SIG1-2" includes information about the arrangement of the links L1 to L8 shown in FIG. 2, the vehicle travel direction, etc.

[0047] An example of the process by which the estimation device 100 estimates the signal period of a traffic light will be described. Fig. 7 is a diagram for explaining the process by the estimation device. As an example, Fig. 7 describes the traffic light to be processed as a traffic light (traffic light ID: SIG1-1) installed in the north-south direction of intersection 2, but the estimation device 100 estimates the signal periods of other traffic lights in the same manner.

[0048] The estimation device 100 extracts vehicle information of the vehicle 10 that has traveled through an intersection where a traffic light to be processed is installed from the vehicle information storage unit 141, and sets the vehicle information in the vehicle information list 141a. For example, the estimation device 100 extracts vehicle information in which latitude and longitude included in a predetermined area based on location information corresponding to the traffic light ID of the traffic light to be processed is set as the vehicle information of the vehicle 10 that has traveled through an intersection where a traffic light to be processed is installed.

[0049] The estimation device 100 classifies each piece of vehicle information included in the vehicle information list 141a by the same vehicle ID and sorts the classified vehicle information in chronological order. In the example shown in Fig. 7, the vehicle information list 141a includes a plurality of pieces of vehicle information each having a vehicle ID "CA" set thereto and a plurality of pieces of vehicle information each having a vehicle ID "CB" set thereto.

[0050] The estimation device 100 identifies the link ID configuration information corresponding to the traffic light (traffic light ID: SIG1-1, north-south direction) based on the road information storage unit 142.

[0051] The estimation device 100 scans multiple pieces of vehicle information for which the vehicle ID "CA" is set, starting from the beginning, and identifies the time at which the link ID changed. In the example shown in FIG. 7 , in the vehicle information list 141a, the link ID changed from (1) to (3) at the time "September 1, 2020, 15:32:04." Furthermore, from the link ID configuration information corresponding to the traffic light (traffic light ID: SIG1-1), it can be seen that the signal of the traffic light (traffic light ID: SIG1-1, north-south direction) is "green" (see, for example, FIG. 3 ).

[0052] In this case, the estimation device 100 registers the time "September 1, 2020, 15:32:04" in the green light time list 143. By registering the time "September 1, 2020, 15:32:04" in this way in the green light time list 143, it is recorded that a green light was observed once at the time "September 1, 2020, 15:32:04." Furthermore, with respect to times not registered in the green light time list 143, it is indicated that a green light was observed zero times.

[0053] Meanwhile, the estimation device 100 scans multiple pieces of vehicle information for which the vehicle ID "CB" is set, starting from the top, and identifies the time at which the link ID changed. In the example shown in FIG. 7 , in the vehicle information list 141a, the link ID changed from (5) to (4) at the time "September 1, 2020, 8:11:37." Furthermore, from the link ID configuration information corresponding to the traffic light (traffic light ID: SIG1-1), it can be seen that the signal of the traffic light (traffic light ID: SIG1-1, north-south direction) is "red" (see, for example, FIG. 4 ).

[0054] In this case, the estimation device 100 registers the time "September 1, 2020, 8:11:37" in the red light time list 144. By registering the time "September 1, 2020, 8:11:37" in this way in the red light time list 144, it is recorded that a red light was observed once at the time "September 1, 2020, 8:11:37." Furthermore, with respect to times that are not registered in the red light time list 144, it is indicated that a red light was observed zero times.

[0055] The estimation device 100 repeatedly executes the process described in FIG. 7 for multiple pieces of vehicle information for other vehicle IDs, thereby registering the times when a green light was observed in the green light time list 143 and the times when a red light was observed in the red light time list 144.

[0056] Next, the estimation device 100 generates a numeric sequence "greenCounts[sec]" of the number of times a green light is observed for each predetermined observation time (sec) based on the green light time list 143. The numeric sequence "greenCounts[sec]" corresponds to the first numeric sequence. The estimation device 100 generates a numeric sequence "redCounts[sec]" of the number of times a red light is observed for each predetermined observation time (sec) based on the red light time list 144. The numeric sequence "redCounts[sec]" corresponds to the second numeric sequence. In this embodiment, the predetermined observation time is set to "1 second."

[0057] The estimation device 100 calculates totalCounts [sec] based on equation (1).

[0058]

[0059] The estimation device 100 calculates the autocorrelation (autocorr) based on equation (2). In equation (2), MAX_CYCLE indicates the maximum period. For example, MAX_CYCLE is "200 seconds" by default. The estimation device 100 searches for the period diff that maximizes the autocorrelation (autocorr) while changing the value of the period diff within the range from MIN_SPLIT × 2 to MAX_CYCLE. MIN_SPLIT indicates the minimum split value. For example, MIN_SPLIT is "10 seconds" by default. For each period diff, the estimation device 100 calculates the sum of products of totalCounts from the observation time sec to set + diff, and determines this as the autocorrelation (autocorr).

[0060]

[0061] In the process of calculating the autocorrelation autocorr while changing the value of the period diff, the estimation device 100 identifies the period diff when the autocorrelation autocorr is maximized as “bestDiff.” The estimation device 100 identifies the autocorrelation autocorr corresponding to “bestDiff” as “bestAutocorr.”

[0062] Furthermore, in the process of calculating the autocorrelation (autocorr) while changing the value of the period (diff), the estimation device 100 updates "bestDiff" and "bestAutocorr" when "conditions A1 and A2 are satisfied" or "conditions A1 and A3 are satisfied."

[0063] Condition A1: bestAutocorr<autocorr Condition A2: bestAutocorr×1.2<autocorr Condition A3: bestDiff+5>diff

[0064] That is, the estimation device 100 updates the maximum autocorrelation and the period if the current maximum autocorrelation bestAutocorr is smaller than the calculated autocorrelation autocorr and the current autocorrelation autocorr is greater than 1.2 times bestAutocorr or the difference in periods is 5 or more. This makes it possible to prevent false detection of two periods, three periods, etc.

[0065] The estimation device 100 estimates the period "bestDiff" of the search result as the signal period of the traffic light to be processed (for example, traffic light ID: SIG1-1, north-south traffic light).

[0066] The estimation device 100 generates a graph that visualizes the traffic light signal period based on the estimated signal period. FIG. 8 is a diagram showing an example of a graph generated by the estimation device. The vertical axis of graph G1 corresponds to date. The horizontal axis of graph G1 corresponds to time. In graph G1, T1 is the search result signal period (bestDiff). T1-1 indicates the length of the green signal period within the signal period. T1-2 indicates the length of the red signal period within the signal period. The estimation device 100 displays graph G1 on a display device or the like.

[0067] The estimation device 100 may specify the length T1-1 of the green light and the length T1-2 of the red light in any way. For example, the estimation device 100 plots a first mark on the graph G1 at a position corresponding to the time (date + time) when the green light was observed, based on the green light time list 143. The estimation device 100 plots a second mark on the graph G1 at a position corresponding to the time (date + time) when the red light was observed, based on the red light time list 144.

[0068] The estimating device 100 searches for boundaries between the plotted first marks and the plotted second marks within T1 set on the graph G1, and sets lengths T1-1 and T1-2 based on the boundaries found. Alternatively, the estimating device 100 may display the plotted first marks and the plotted second marks to the user and accept the user's specification of lengths T1-1 and T1-2.

[0069] As described above, the estimation device 100 according to this embodiment identifies the time when the link (link ID) of the same vehicle changed based on the vehicle information received from the vehicle 10, and calculates the signal period of each traffic light based on the identified time. This makes it possible to accurately estimate the signal period of a traffic light even when the intersection has a complex structure or when congestion occurs.

[0070] (Configuration Example of Estimation Device) Next, a configuration example of the estimation device 100 that executes the above processing will be described. Fig. 9 is a functional block diagram showing the configuration of the estimation device. As shown in Fig. 9, the estimation device 100 has a communication control unit 110, an input unit 120, a display unit 130, a storage unit 140, and a control unit 150.

[0071] The communication control unit 110 is realized by a NIC (Network Interface Card) or the like, and controls communication between the vehicle 10 connected to the network 5 and the control unit 150. For example, the communication control unit 110 receives vehicle information from the vehicle 10.

[0072] The input unit 120 is realized using input devices such as a keyboard, a mouse, etc. A user operates the input unit 120 to input various pieces of information to the control unit 150.

[0073] The display unit 130 is an output device that outputs information acquired from the control unit 160, and is realized by a display device such as a liquid crystal display, a printing device such as a printer, etc. For example, the display unit 130 displays the signal cycle of each traffic light and a graph.

[0074] The memory unit 140 includes a vehicle information storage unit 141, a road information storage unit 142, a green light time list 143, and a red light time list 144. The memory unit 140 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0075] The vehicle information storage unit 141 stores the vehicle information received from the vehicle 10. The description of the vehicle information storage unit 141 is the same as that described with reference to FIG.

[0076] The road information storage unit 142 stores information about links at intersections where traffic lights are installed. The road information storage unit 142 is the same as that described with reference to FIG.

[0077] The green light time list 143 is a list that stores information about the time when the link of a vehicle 10 that entered an intersection while the corresponding traffic light was green changed. The explanation of the green light time list 143 is the same as that explained in FIGS. 3 and 7.

[0078] The red light time list 144 is a list that stores information about the time when the link of a vehicle 10 that entered an intersection while the corresponding traffic light was red changed. The explanation of the red light time list 144 is the same as that explained in FIGS. 4 and 7.

[0079] Next, the description will move on to the control unit 150. The control unit 150 includes an acquisition unit 151, a calculation unit 152, and a generation unit 153. The control unit 150 is a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit).

[0080] The acquisition unit 151 acquires vehicle information from the vehicle 10 via the communication control unit 110, and stores the acquired vehicle information in the vehicle information storage unit 141. The acquisition unit 151 repeatedly executes the above process every time it acquires vehicle information from the vehicle 10.

[0081] The calculation unit 152 identifies the time when the link for the same vehicle changed based on the vehicle information stored in the vehicle information storage unit 141 and the information in the road information storage unit 142, and calculates the signal period (bestDiff) of each traffic light based on the identified time. The processing by the calculation unit 152 is similar to the processing described in Fig. 7. The calculation unit 152 may output the signal period of each traffic light to the display unit 130 for display.

[0082] The calculation unit 152 may select multiple traffic lights in order from a pre-set traffic light list and calculate the signal periods of the selected traffic lights in order, or may accept the designation of a specific traffic light from the input unit 120, etc., and calculate the signal period of the designated traffic light.

[0083] The generation unit 153 generates a graph that visualizes the signal periods of traffic lights based on the signal periods calculated by the calculation unit 152. For example, the generation unit 153 generates the graph G1 shown in Fig. 8. The generation unit 153 outputs information about the generated graph to the display unit 130 for display.

[0084] (Processing Procedure of Estimation Device) Next, a description will be given of an example of the processing procedure of the estimation device 100. Fig. 10 is a flowchart showing the processing procedure of the estimation device.

[0085] 10 , the calculation unit 152 of the estimation device 100 selects a traffic light for which a signal period is to be calculated (step S101). The calculation unit 152 acquires vehicle information of a vehicle that has entered the intersection of the selected traffic light from the vehicle information storage unit 141 (step S102).

[0086] The calculation unit 152 acquires link ID configuration information for the selected traffic light from the road information storage unit 142 (step S103). Based on the acquired vehicle information and link ID configuration information, the calculation unit 152 identifies the time when the link ID of the same vehicle changed (step S104).

[0087] The calculation unit 152 registers the identified time in the green light time list 143 or the red light time list 144 (step S105). The calculation unit 152 generates a numerical sequence of the number of times a green light is observed (greenCounts[sec]) based on the green light time list 143 (step S106).

[0088] The calculation unit 152 generates a numerical sequence (redCounts[sec]) of the number of times a red light has been observed based on the red light time list 144 (step S107). The calculation unit 152 calculates totalCounts[sec] based on the numerical sequence (greenCounts[sec]) and the numerical sequence (redCounts[sec]) (step S108).

[0089] The calculation unit 152 calculates the autocorrelation (autocorr) while changing the value of the period (diff) based on Equation (2) and identifies the period (bestDiff) that results in bestAutocorr (step S109).The calculation unit 152 estimates the period (bestDiff) that results in bestAutocorr as the signal period of the traffic light (step S110).

[0090] The generating unit 153 of the estimation device 100 generates a graph based on the signal period of the traffic light (step S111), and outputs the generated graph to the display unit 130 (step S112).

[0091] (Effects of the Estimation Device) According to the estimation device 100 of this embodiment, the signal period of a traffic light can be accurately estimated.

[0092] For example, when multiple starts are measured within an intersection section due to traffic congestion, waiting to turn right or left, etc., the conventional technique using the autocorrelation of the start interval function may result in erroneous detection of the cycle length. In contrast, the estimation device 100 extracts only one point (time) at which the link ID changes, so the possibility of erroneous detection is small.

[0093] The estimation device 100 can identify the direction in which a vehicle enters or leaves an intersection by tracking changes in link ID, making it possible to estimate the signal period and arrow time period of a complex intersection such as that shown in Fig. 11. Fig. 11 is a diagram showing an example of a complex intersection. For example, the estimation device 100 can estimate the signal period of each traffic light installed at the intersection 2a shown in Fig. 11 in the same manner as above by setting multiple links and identifying the time when the link ID in the vehicle information transmitted from the vehicle 10 changes.

[0094] The estimation device 100 estimates the signal period along with the date and time at each intersection. By comparing the signal period with the signal periods of traffic lights at preceding and following intersections, the offset value of the signal period can be calculated, enabling detailed reproduction of vehicle behavior over a wide range of areas. FIG. 12 illustrates an example display of the signal periods of multiple traffic lights. The horizontal axis of graph G2 in FIG. 12 corresponds to time, while the vertical axis represents traffic lights 2-1 to 2-6. The green and red signal periods calculated from the signal periods of traffic lights 2-1, 2-2, 2-3, 2-4, 2-5, and 2-6 are shown. The black portions of graph G2 indicate red signal periods. The estimation device 100 may transmit the information of graph G2 to the vehicle 10 and display it. This allows the driver of the vehicle 10 to drive at a speed that avoids running red lights. In the example shown in FIG. 12, driving at a speed between 30 and 50 km per hour allows the vehicle 10 to drive without running red lights.

[0095] (Other Configuration Examples) In the above-described embodiment, the vehicle 10 sets the link ID of the link on which the vehicle is traveling in the vehicle information using a determination table, but this is not limited to this. For example, the estimation device 100 may have a determination table and determine the link ID based on the vehicle's position information (latitude and longitude) set in the vehicle information and the determination table.

[0096] (Estimation Program) Next, an example of a computer that executes the estimation program will be described. Fig. 13 is a diagram showing an example of a computer that executes the estimation program. The computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0097] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1031. The disk drive interface 1040 is connected to a disk drive 1041. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1041. The serial port interface 1050 is connected to a mouse 1051 and a keyboard 1052, for example. The video adapter 1060 is connected to a display 1061, for example.

[0098] Here, the hard disk drive 1031 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. The various pieces of information described in the above embodiments are stored in the hard disk drive 1031 or memory 1010, for example.

[0099] The estimation program is stored in the hard disk drive 1031 as a program module 1093 in which instructions to be executed by the computer 1000 are written. Specifically, the program module 1093 in which processes for executing the acquisition unit 151, calculation unit 152, and generation unit 153 described in the above embodiment are written is stored in the hard disk drive 1031.

[0100] Data used for information processing by the estimation program is stored as program data 1094, for example, in the hard disk drive 1031. Then, the CPU 1020 reads the program module 1093 and the program data 1094 stored in the hard disk drive 1031 into the RAM 1012 as necessary, and executes each of the above-described procedures.

[0101] The program module 1093 and program data 1094 related to the estimation program are not limited to being stored in the hard disk drive 1031, and may be stored in a removable storage medium, for example, and read by the CPU 1020 via the disk drive 1041. Alternatively, the program module 1093 and program data 1094 related to the estimation program may be stored in another computer connected via a network such as a LAN or a WAN (Wide Area Network), and read by the CPU 1020 via the network interface 1070.

[0102] Although the present invention has been described above as an embodiment, the present invention is not limited to the descriptions and drawings that form part of the disclosure of the present invention. In other words, other embodiments, examples, and operational techniques that can be made by those skilled in the art based on the present invention are all included in the scope of the present invention.

[0103] REFERENCE SIGNS LIST 100 Estimation device 110 Communication control unit 120 Input unit 130 Display unit 140 Memory unit 141 Vehicle information storage unit 142 Road information storage unit 143 Green light time list 144 Red light time list 150 Control unit 151 Acquisition unit 152 Calculation unit 153 Generation unit

Claims

1. An estimation device, comprising: a road information storage unit that stores, for each traffic signal, information on a link indicating a road section in one traveling direction between a node at the center point of an intersection where the traffic signal is installed and a node on the road; and a calculation unit that identifies a time when the link of the same vehicle has changed based on the information stored in the road information storage unit and vehicle information received from a vehicle connected to the cloud, the vehicle information associating a time with a link, and calculates a signal cycle of each traffic signal based on the identified time.

2. The estimation device according to claim 1, further comprising a generation unit that generates a graph visualizing the signal cycle of each traffic signal based on the signal cycle of each traffic signal.

3. The calculation unit identifies a first numerical sequence indicating the number of observations of a green signal at predetermined time intervals based on a first time when the link of a first vehicle that has entered the intersection according to the green signal has changed while the traffic signal is green, and identifies a second numerical sequence indicating the number of observations of a red signal at the predetermined time intervals based on a second time when the link of a second vehicle that has entered the intersection according to the green signal in a direction intersecting the red signal direction has changed while the traffic signal is red, and calculates the signal cycle of each traffic signal based on the first numerical sequence and the second numerical sequence. The estimation device according to claim 1 or 2.

4. An estimation method executed by an estimation device, the estimation device having a storage device that stores, for each traffic signal, information on a link indicating a road section in one traveling direction between a node at the center point of an intersection where the traffic signal is installed and a node on the road, the method including: a step of identifying a time when the link of the same vehicle has changed based on the information stored in the storage device and vehicle information received from a vehicle connected to the cloud, the vehicle information associating a time with a link; and a step of calculating a signal cycle of each traffic signal based on the identified time.

Images