JP2020004235A - Traffic condition determination system and traffic condition determination device - Google Patents

Abstract

To provide a traffic condition determination system and a traffic condition determination device that enable accurate determination of traffic congestion on a road in each lane over a wider range.SOLUTION: A traffic condition determination system is configured in that information for specifying a traveling lane and a vehicle speed of each vehicle 4 traveling on a road is acquired as traveling information; information on a captured image of a periphery of each vehicle captured by an on-vehicle camera 7 of each vehicle 4 traveling on the road is acquired as peripheral image information, and a traffic congestion condition of the road for each lane is determined based on the acquired traveling information and the acquired peripheral image information.SELECTED DRAWING: Figure 15

Description

  The present invention relates to a traffic condition determination system and a traffic condition determination device for determining a traffic congestion condition.

  2. Description of the Related Art Conventionally, as one of traveling supports when a user moves on a road, providing traffic information acquired from an external center or the like has been performed. The traffic information includes, for example, information on traffic congestion occurring on roads, road closures, accidents, lane regulations, and the like. Here, as a system for providing a user with information on the traffic congestion on the road, there are, for example, a road traffic information communication system (VICS: registered trademark) and a probe car system. Here, in the probe car system, based on the information collected from each vehicle, it is possible to specify a traffic congestion state on a wider range of roads without being limited to the main road, and to provide it to the user.

  For example, in Japanese Patent Application Laid-Open No. 2015-7902, information specifying an inter-vehicle distance to another vehicle and a vehicle position calculated based on an image captured by each vehicle traveling on a road is collected, and the collected information is collected. A technique for identifying the vehicle density on the road (that is, the degree of congestion of the road) by analyzing the road is disclosed. It also discloses calculating an inter-vehicle distance of a vehicle for each lane.

JP, 2015-7902, A (page 5-11)

  Here, in Patent Document 1, an image is taken of a relative relationship (for example, an inter-vehicle distance) between another vehicle included in an image captured by a vehicle actually traveling on a road and an imaged vehicle (hereinafter, referred to as an imaged vehicle). The information is collected from vehicles, and the vehicle density on the road is specified based on the collected information. However, the relative relationship between the imaged vehicle and the other vehicle calculated from the captured image that does not specify the traveling lane and the vehicle speed has low reliability as information, and the vehicle density of the road calculated from only such information is inaccurate. May be information. Also, the collection target is the inter-vehicle distance between another vehicle near the imaging vehicle and the imaging vehicle at the time of imaging, and in a state where the traveling lane and the vehicle speed are not specified, an accurate road in a certain section is calculated based on the inter-vehicle distance. It is also difficult to calculate the vehicle density.

  On the other hand, there is also a method of judging traffic congestion by collecting driving information (for example, vehicle speed and the like) of a vehicle that actually runs on a road. In such a method, particularly when judging traffic congestion for each lane, There was a problem that only the lane in which the vehicle actually traveled could be determined.

  The present invention has been made in order to solve the above-described conventional problems, and includes traveling information for specifying a traveling lane and a vehicle speed of each vehicle traveling on a road, and information based on a captured image in which each vehicle captures a surrounding area. It is an object of the present invention to provide a traffic condition determination system and a traffic condition determination device which can accurately determine the traffic congestion state of a road in each lane in a wider range by using both.

In order to achieve the above object, a traffic condition determination system according to the present invention includes a traveling information collection unit that collects information specifying a traveling lane and a vehicle speed of each vehicle traveling on a road as traveling information, An image information collection unit that collects, as peripheral image information, information about a captured image of the periphery of each vehicle by an imaging device provided in the vehicle, and the travel information and the image information collection unit that are collected by the travel information collection unit. Traffic congestion judging means for judging traffic congestion on the road for each lane based on the collected peripheral image information.
The “information for specifying the traveling lane of the vehicle” may be information for identifying the traveling lane itself or information for identifying the traveling lane (for example, the position coordinates of the vehicle).
Further, the “information about the captured image” may be the captured image itself, or may be data derived by performing image processing on the captured image.

  In addition, the traffic situation determination device according to the present invention includes a traveling information collection unit that collects information specifying a traveling lane and a vehicle speed of each vehicle traveling on a road as traveling information, and an imaging device provided in each vehicle traveling on the road. An image information collecting unit that collects information about a captured image of the periphery of each of the vehicles as a peripheral image information by a device, and the traveling information collected by the traveling information collecting unit and the image information collected by the image information collecting unit. Traffic congestion determining means for determining traffic congestion on the road for each lane based on the surrounding image information.

  According to the traffic condition determination system and the traffic condition determination device according to the present invention having the above-described configuration, when determining the traffic congestion state of each lane based on information collected from each vehicle traveling on the road, By using the traveling information of a vehicle whose reliability is high but the determination range is narrow and the information based on the captured image of the vehicle whose reliability as information is low but the determination range is wide, the road for each lane is used. Can be accurately determined in a wider range.

It is a schematic structure figure showing the traffic situation judging system concerning this embodiment. It is a block diagram showing composition of a traffic situation judging system concerning this embodiment. FIG. 4 is a diagram illustrating an example of probe information stored in a probe information DB. It is the figure which showed an example of the information regarding the traffic congestion situation for every lane memorize | stored in a traffic congestion information DB. FIG. 2 is a block diagram schematically illustrating a control system of the navigation device according to the embodiment. It is a flowchart of the congestion situation determination processing program according to the present embodiment. It is a flowchart of a sub-processing program of own lane processing. FIG. 5 is a diagram illustrating a method for specifying a lane in which an imaging vehicle is located. FIG. 7 is a diagram illustrating a method for specifying a traveling lane that the imaging vehicle mainly travels during imaging of the captured image. It is a flowchart of the sub-processing program of other lane density processing. It is a figure showing other vehicles detected based on a picked-up image. It is a flowchart of a sub-processing program of another lane speed processing. It is a flowchart of a sub-processing program of lane matching processing. It is a flowchart of a sub-processing program of parallel running processing. FIG. 10 is a diagram illustrating an example of determining a traffic jam determination result when traffic jam determination based on a plurality of imaging vehicles is possible for the same lane. FIG. 10 is a diagram illustrating an example of determining a traffic jam determination result when traffic jam determination based on a plurality of imaging vehicles is possible for the same lane. FIG. 10 is a diagram illustrating an example of determining a traffic jam determination result when traffic jam determination based on a plurality of imaging vehicles is possible for the same lane. FIG. 10 is a diagram illustrating an example of determining a traffic jam determination result when traffic jam determination based on a plurality of imaging vehicles is possible for the same lane.

  Hereinafter, a traffic situation determination system according to the present invention will be described in detail with reference to the drawings based on a specific embodiment. First, a schematic configuration of a traffic situation determination system 1 according to the present embodiment will be described with reference to FIGS. FIG. 1 is a schematic configuration diagram showing a traffic situation determination system 1 according to the present embodiment. FIG. 2 is a block diagram showing a configuration of the traffic situation determination system 1 according to the present embodiment.

  As shown in FIG. 1, a traffic condition determination system 1 according to the present embodiment includes a server device (traffic condition determination device) 3 provided in a probe center 2 and a navigation device as a communication (guide) terminal mounted on a vehicle 4. 5 basically. The server device 3 and the navigation device 5 are configured to be able to transmit and receive electronic data to and from each other via the communication network 6. Note that, instead of the navigation device 5, for example, a mobile phone, a smartphone, a tablet terminal, or a personal computer may be used.

  Here, the traffic situation determination system 1 according to the present embodiment constitutes a so-called probe car system. Here, the probe car system is a system that collects information using the vehicle 4 as a sensor. Specifically, the vehicle 4 transmits, to the probe center 2 via a communication device mounted in the vehicle 4 in advance together with the GPS data and the operating status of each system such as steering operation and shift position, including speed data, This is a system in which the collected data is reused as various information on the center side.

  The server device 3 provided in the probe center 2 appropriately collects and accumulates probe information (material information) including current time, traveling information, and the like from each of the vehicles 4 traveling the whole country, and stores road information from the accumulated probe information. Related information (for example, road closure information, accident information, traffic congestion information, travel time, etc.), and distributes the generated support information to the navigation device 5 and performs various processes using the support information. It is an information management server. In particular, in the present embodiment, the server device 3 collects, from each vehicle 4, the current position coordinates of the vehicle 4, the vehicle speed, and an image of the surroundings captured by the on-board camera 7 provided in the vehicle 4, and statistically or collects the collected information. By performing the analysis, data indicating the traffic congestion state for each lane is generated and distributed to the vehicle 4.

  Here, the on-vehicle camera 7 is configured by a camera using a solid-state imaging device such as a CCD, and is attached to a bumper of the vehicle 4, a back side of a rearview mirror, a door mirror, and the like, and can capture an image of the environment around the vehicle 4. Is set to the optical axis direction. The number of in-vehicle cameras 7 may be singular or plural. For example, the in-vehicle camera 7 captures an image of the surrounding environment ahead of the traveling direction of the vehicle when the vehicle 4 is traveling. Note that the image pickup range may be the side or the rear, not the front in the traveling direction of the vehicle 4.

  On the other hand, the navigation device 5 is mounted on the vehicle 4 and displays a map around the position of the vehicle based on the stored map data, displays the current position of the vehicle on a map image, and displays a set guidance route. This is an in-vehicle device that provides travel guidance along. The navigation device 5 also guides the user about the information on the traffic congestion for each lane received from the server device 3. The details of the navigation device 5 will be described later.

  In addition, the communication network 6 includes a number of base stations located all over the country and a communication company that manages and controls each base station, and connects the base stations and the communication company with each other by wire (optical fiber, ISDN, etc.) or wirelessly. It is configured by connecting. Here, the base station has a transceiver (transmitter / receiver) for communicating with the navigation device 5 and an antenna. The base station performs wireless communication between the communication companies, while relaying the communication of the navigation device 5 located at the terminal of the communication network 6 and within the range (cell) where the radio wave of the base station can reach with the server device 3. Have a role to do.

  The vehicle 4 from which information is to be collected and the vehicle 4 from which information on the traffic congestion status for each lane generated based on the collected information need not be the same vehicle, but different vehicles. It may be. In addition, the distribution of the information on the traffic congestion state for each lane need not always be performed to the vehicle 4, and may be performed to, for example, a mobile phone, a smartphone, a tablet terminal, or a personal computer.

  Next, the configuration of the server device 3 constituting the traffic situation determination system 1 will be described in more detail with reference to FIG.

  The server device 3 includes a server control ECU 11, a map information DB 12 as information recording means connected to the server control ECU 11, a probe information DB 13, a congestion information DB 14, and a center communication device 15, as shown in FIG. It is structured.

  The server control ECU 11 (electronic control unit) is an electronic control unit that controls the entire server device 3, and is used as a working memory when the CPU 21 performs various arithmetic processing as the arithmetic device and the control device. In addition to the RAM 22, a control program, a ROM 23 in which a congestion situation determination processing program (see FIG. 6) described later and the like are recorded, and an internal storage device such as a flash memory 24 for storing a program read from the ROM 23. . The server control ECU 11 constitutes various means as a processing algorithm together with an ECU of the navigation device 5 described later. For example, the traveling information collecting means collects, as the traveling information, information for specifying the traveling lane and the vehicle speed of each vehicle traveling on the road. The image information collecting means collects, as peripheral image information, information on a captured image of the periphery of each vehicle captured by an imaging device provided in each vehicle traveling on the road. The traffic congestion determining means determines the traffic congestion state of the road for each lane based on the traveling information collected by the traveling information collecting means and the peripheral image information collected by the image information collecting means.

  The map information DB 12 is storage means for storing map information registered based on externally input data and input operations, divided into areas (for example, every 20 km square). The map information DB 12 has basically the same configuration as the map information stored in the navigation device 5 described below, and includes various information necessary for route search, route guidance, and map display including the road network. It is composed of For example, it includes link data relating to roads (links), node data relating to node points, intersection data relating to each intersection, point data relating to points such as facilities, and the like. In particular, the link data includes information on the position coordinates of both ends of the link, the structure of the lanes included in the link (the number of lanes, the width of the lane, the point where the number of lanes increases / decreases in the middle of the link, etc.).

  The probe information DB 13 is storage means for cumulatively storing probe information collected from each of the vehicles 4 traveling throughout the country. In the present embodiment, the probe information collected from the vehicle 4 includes, in particular, (a) a captured image captured by the vehicle-mounted camera 7 provided in the vehicle, and (b) a vehicle at the time of capturing each frame included in the captured image. (C) the link on which the vehicle currently travels and the time of entry into the link. However, the probe information does not necessarily need to include all of the information on (a) to (c), and may include, for example, only information on (a) and (b). When the determination of the traffic congestion state is performed only for a specific link (for example, an entrance link to an intersection), probe information may be collected only from vehicles traveling on the corresponding link.

  FIG. 3 is a diagram showing an example of the probe information stored in the probe information DB 13. As shown in FIG. 3, the probe information includes a vehicle ID for identifying the vehicle of the transmission source, information related to the above (a) to (c), and the like. For example, when the vehicle 4 with ID “A” enters the link with ID “100001” at 9:01:30, the probe information shown in FIG. 3 includes the captured image together with the captured image captured by the vehicle traveling on the link. The current position and the vehicle speed of the vehicle during the imaging are stored in frame units. Similarly, other probe information is stored. Note that the captured image shown in FIG. 3 describes the ID of the captured image. However, if there is a vehicle ID, a travel link, and a link entry time, the captured image can be specified, and therefore it is not necessary to assign an ID to the captured image. There is no.

  On the other hand, the traffic congestion information DB 14 is a storage unit that cumulatively stores information (distribution information) on traffic congestion status for each lane generated by statistically or analyzing the probe information stored in the probe information DB 13. In the present embodiment, the traffic congestion state is determined in, for example, two stages of “vacant” and “congested”, but may be determined in three stages of “vacant”, “congested”, and “congested”, or four or more stages. . In addition, the traffic congestion state may be specified based on the average vehicle speed and travel time. The details of the traffic jam determination process will be described later.

  FIG. 4 is a diagram showing an example of information related to the traffic congestion state for each lane stored in the traffic congestion information DB 14. As shown in FIG. 4, the information on the traffic congestion state for each lane includes information for specifying the date and time when the traffic congestion state was determined, information for specifying the link and the lane, and the traffic congestion state for the determined lane (“vacant” or "Congestion"). Specifically, “statistical date and time”, “link ID”, and “lane No. And "degree of congestion" correspond. In addition, "Lane No. ] Defines, for example, 1, 2, 3,... From the left for a plurality of lanes included in the link. For example, if the link ID is “100001” and the lane No. If it is “1”, it indicates the leftmost lane of the link ID “100001”. In the example shown in FIG. 4, the information on the traffic congestion status for each lane also includes the information on the lane determined as “vacant”, but only the information on the lane determined as “congestion” is included. Is also good. Further, “unknown” may be stored for a lane in which the traffic congestion state cannot be determined.

  Then, the server device 3 distributes the information on the traffic congestion state for each lane stored in the traffic congestion information DB 14 to the navigation device 5 in response to a request from the navigation device 5. On the other hand, the navigation device 5 to which the information on the traffic congestion status for each lane is distributed guides the user to the distributed traffic congestion status for each lane and performs a route search to the destination in consideration of the distributed traffic congestion status. .

  The center communication device 15 is a communication device for communicating with an external traffic information center such as the vehicle 4 or a VICS (Vehicle Information and Communication System) center via the communication network 6. In the present embodiment, probe information and distribution information are transmitted to and received from each vehicle 4 via the center communication device 15.

  Next, a schematic configuration of the navigation device 5 mounted on the vehicle 4 will be described with reference to FIG. FIG. 5 is a block diagram showing the navigation device 5 according to the present embodiment.

  As shown in FIG. 5, the navigation device 5 according to the present embodiment includes a current position detection unit 31 that detects a current position of a vehicle on which the navigation device 5 is mounted, a data recording unit 32 in which various data are recorded, A navigation ECU 33 that performs various arithmetic processes based on the input information, an operation unit 34 that receives an operation from a user, a liquid crystal display 35 that displays a map around the vehicle, information about a traffic jam, and the like to the user. , A speaker 36 for outputting voice guidance relating to route guidance, a DVD drive 37 for reading a DVD as a storage medium, and a communication module 38 for communicating with an information center such as the probe center 2 or a VICS center. ing. The navigation device 5 is connected to an in-vehicle camera 7 installed on a vehicle equipped with the navigation device 5 via an in-vehicle network such as CAN.

Hereinafter, each component of the navigation device 5 will be described in order.
The current position detection unit 31 includes a GPS 41, a vehicle speed sensor 42, a steering sensor 43, a gyro sensor 44, and the like, and can detect a current vehicle position, a direction, a vehicle traveling speed, a current time, and the like. . Here, particularly, the vehicle speed sensor 42 is a sensor for detecting the moving distance and the vehicle speed of the vehicle, generates a pulse according to the rotation of the driving wheel of the vehicle, and outputs a pulse signal to the navigation ECU 33. Then, the navigation ECU 33 calculates the rotation speed and the moving distance of the driving wheels by counting the generated pulses. It is not necessary for the navigation device 5 to include all of the four types of sensors, and the navigation device 5 may include only one or a plurality of types of sensors.

  The data recording unit 32 reads a hard disk (not shown) as an external storage device and a recording medium, a map information DB 45, a travel history DB 46, a distribution information DB 47, a predetermined program, and the like recorded on the hard disk. A recording head (not shown) which is a driver for writing predetermined data. Note that the data recording unit 32 may be constituted by an optical disk such as a flash memory, a memory card, a CD, or a DVD instead of the hard disk. Further, the map information DB 45, the travel history DB 46, and the distribution information DB 47 may be stored in an external server, and the navigation device 5 may acquire the information by communication.

  Here, the map information DB 45 includes, for example, link data relating to roads (links), node data relating to node points, search data used for processing relating to route search and change, facility data relating to facilities, and maps for displaying maps. This is storage means for storing display data, intersection data relating to each intersection, search data for searching for points, and the like.

  The travel history DB 46 is a storage unit that accumulates and stores travel information of the vehicle 4 and images captured by the in-vehicle camera 7. In this embodiment, particularly, the position coordinates and the vehicle speed of the vehicle at the time of capturing each frame included in the captured image are stored. Note that the current position of the vehicle 4 may be detected using the GPS 41 or the vehicle speed sensor 42, but it is desirable to specify the current position in detail using a high-accuracy location technology. The travel information and the captured image stored in the travel history DB 46 are transmitted to the server device 3 as needed as probe information.

  The distribution information DB 47 is a storage unit that stores distribution information (information related to traffic congestion for each lane) distributed from the server device 3.

  On the other hand, a navigation ECU (electronic control unit) 33 is an electronic control unit that controls the entire navigation device 5, and includes a CPU 51 as an arithmetic device and a control device, and a working memory when the CPU 51 performs various arithmetic processes. And an internal storage device such as a RAM 52 storing route data when a route is searched, a ROM 53 storing a control program, and a flash memory 54 storing a program read from the ROM 53. Have.

  The operation unit 34 is operated, for example, when inputting a departure point as a travel start point and a destination as a travel end point, and includes a plurality of operation switches (not shown) such as various keys and buttons. Then, the navigation ECU 33 performs control to execute various corresponding operations based on a switch signal output when each switch is pressed or the like. Note that the operation unit 34 can be configured by a touch panel provided on the front surface of the liquid crystal display 35. Further, it can be constituted by a microphone and a voice recognition device.

  In addition, the liquid crystal display 35 displays a map image including roads, traffic information, operation guidance, operation menus, key guidance, guidance information along a guidance route (scheduled traveling route), news, weather forecast, time, mail, and television. A program or the like is displayed. Further, in the present embodiment, particularly when congestion information is to be provided, guidance is provided for the traffic congestion status for each lane. For example, the congested lane and the other lanes are displayed on the liquid crystal display 35 in different colors. Incidentally, instead of the liquid crystal display 35, a HUD or an HMD may be used.

  In addition, the speaker 36 outputs voice guidance for guiding travel along a guidance route (planned travel route) based on an instruction from the navigation ECU 33 and guidance of traffic information. Further, in the present embodiment, particularly when congestion information is to be provided, guidance is provided for the traffic congestion status for each lane. For example, the voice guidance that "the left (center, right) lane is congested" is output.

  The DVD drive 37 is a drive that can read data recorded on a recording medium such as a DVD or a CD. Then, reproduction of music and video, updating of the map information DB 45, and the like are performed based on the read data. Note that a card slot for reading and writing a memory card may be provided instead of the DVD drive 37.

  The communication module 38 is a communication device for receiving traffic information, weather information, and the like transmitted from a traffic information center, for example, a VICS center or another external center, and corresponds to, for example, a mobile phone or a DCM. Also, a vehicle-to-vehicle communication device that performs communication between vehicles and a road-to-vehicle communication device that performs communication with a roadside device are included. It is also used to transmit and receive probe information and distribution information to and from the server device 3.

  Next, a traffic jam situation determination processing program executed in the server device 3 included in the traffic situation decision system 1 having the above configuration will be described with reference to FIG. FIG. 6 is a flowchart of the congestion situation determination processing program according to the present embodiment. Here, the congestion state determination processing program is executed after a predetermined time (for example, one minute) has elapsed since the previous execution of the program, and determines the congestion state for each lane based on the probe information transmitted from each vehicle 4. It is a program. 6, 7, 10, and 12 to 14 are stored in the RAM 22 or the ROM 23 provided in the server device 3 and executed by the CPU 21.

  First, in step (hereinafter abbreviated as S) 1, the CPU 21 reads from the probe information DB 13 probe information newly collected from each vehicle from the previous processing time to the current processing time (that is, within the last minute). . It should be noted that the probe information collected from the vehicle includes “an image captured by the on-board camera 7 provided in the vehicle”, “position coordinates and vehicle speed of the vehicle at the time of capturing each frame included in the captured image”, “vehicle information”. The current traveling link and the entry time to the link are included (see FIG. 3). The “link that the vehicle currently travels” may not be included in the probe information. Also in that case, by performing the map matching process using the position coordinates of the vehicle included in the probe information and the map information of the server device 3, it is possible to specify the link on which the vehicle travels on the server device 3 side. is there.

  The probe information may be such that the probe information acquired during the traveling of the link is distributed to the server device 3 at a timing when the vehicle reaches the end point of the link, or may be transmitted at a predetermined time interval (for example, one minute). At intervals, the probe information acquired during that time may be distributed to the server device 3.

  Next, in S2, the CPU 21 acquires intersection information. Note that S2 is executed only when the determination of the traffic congestion state is performed only for the entry link to the specific intersection, and the position information of the target intersection, the link ID of the link connected to the intersection, and the like are acquired. On the other hand, when the traffic jam determination target is not limited to only the entrance link to a specific intersection (for example, when all the links in the whole country are targeted), the process of S2 is unnecessary.

  Subsequently, in S3, the CPU 21 acquires link information of a link to be determined as a traffic congestion state. Specifically, information on the position coordinates of both ends of the link, the structure of the lane included in the link (the number of lanes, the width of the lane, the point where the lane is increased or decreased in the middle of the link, etc.) is acquired. If the determination of the traffic congestion state is not limited to a specific link (that is, if the link is to be performed for all links in the whole country), link information on all the links in the whole country is acquired. However, only the link information of “the link where the vehicle currently travels” included in the probe information acquired in S1 may be acquired.

  Thereafter, in S4, the CPU 21 performs a process of dividing the data on the probe information acquired in S1 in order to reduce the processing time. The number of divisions is, for example, two, but may be divided into three or more. When dividing, the difference between the data amounts of the divided data is made as small as possible.

For example, data is divided by the following processing.
First, the number of data (corresponding to the number of frames of a captured image) is counted for each vehicle (hereinafter, referred to as an imaging vehicle) from which probe information is collected, and the imaging vehicles are sorted in ascending order of the number of data. Then, the probe information acquired in S1 is divided by the probe information collected from the odd-numbered imaging vehicles and the probe information collected from the even-numbered imaging vehicles. Thereafter, processing is performed on the divided probe information. However, the process of S4 may be omitted.

  Next, in S5, the CPU 21 executes a later-described own lane process (FIG. 7). The own lane process is a process of determining the traffic congestion state of the lane in which the imaging vehicle has traveled based on the probe information acquired in S1 described above, in particular, the traveling information of the imaging vehicle, as described later.

  Subsequently, in S6, the CPU 21 executes another lane density processing (FIG. 10) described later. In addition, the other lane density processing performs the image processing on the captured image captured by the imaging vehicle in the probe information acquired in S1 as described later, so that the vehicle density in the lanes other than the lane in which the imaging vehicle travels is performed. Is calculated, and the traffic congestion state of the lane is determined from the calculated vehicle density.

  Further, in S7, the CPU 21 executes another lane speed processing (FIG. 12) described later. In the other lane speed processing, as described later, the vehicle travels in a lane other than the lane in which the imaging vehicle traveled by performing image processing on the captured image captured by the imaging vehicle, among the probe information acquired in S1 described above. This is a process of calculating the traveling speed of the other vehicle and determining the traffic congestion state of the lane in which the other vehicle travels from the calculated traveling speed of the other vehicle.

  Thereafter, in S8, the CPU 21 performs a data integration process. In the data integration process, the results of the congestion determination in steps S5 to S7 are classified into links and lanes, and the results of the congestion determination for the same link and the same lane are linked (integrated). .

  Subsequently, in S9, the CPU 21 executes a later-described lane matching process (FIG. 13). The lane matching process is a process of comparing the number of lanes in which the traffic congestion is determined in S5 to S7 with the number of lanes on the actual map information to determine whether or not they match, as described later. is there.

  Further, in S10, the CPU 21 executes a parallel running process (FIG. 14) described later. In the parallel running process, as described later, when there are two or more traffic jam determination results for the same link and the same lane, the final traffic jam is determined using the priority of the determination and the like. Processing. Then, by performing the parallel running process, the final traffic congestion state for each lane is specified.

  Thereafter, in S11, as a result of performing the parallel running process in S10, the CPU 21 stores in the congestion information DB 14 information on the congestion status for each of the finally specified lanes.

  Then, in S12, the CPU 21 distributes the information on the traffic congestion status for each lane stored in the traffic congestion information DB 14 to the navigation device 5 of the vehicle 4 that has made the request. In addition, distribution may be performed to the navigation devices 5 of all the vehicles 4 in a communicable state regardless of the presence or absence of the distribution request. In addition, the distribution of the information on the traffic congestion state for each lane need not always be performed to the vehicle 4, and may be performed to, for example, a mobile phone, a smartphone, a tablet terminal, or a personal computer.

  The navigation device 5 to which the information regarding the traffic congestion status for each lane is distributed can guide the user to the traffic congestion status for each lane distributed, and can perform a route search to a destination in consideration of the distributed traffic congestion status. It becomes.

  Next, a sub-process of the own lane process executed in S5 will be described with reference to FIG. FIG. 7 is a flowchart of a sub-processing program of the own lane processing.

  The subsequent processing of S21 to S28 is performed for each link for which the traffic congestion state is to be determined, and for each imaging vehicle for which the probe information has been collected in S1. Further, the processing of S21 to S23 is performed for each frame included in the captured image captured by the imaging vehicle to be processed on the link to be processed. Then, the process proceeds to S6 after the processes of S21 to S28 are completed for all the corresponding links and imaging vehicles.

  First, in S21, the CPU 21 counts up the number N of frames. Note that the initial value of the frame number N is set to 0, and the frame number N is initialized when the process of S27 or S28 is executed. The counted number N of the current frames is stored in the flash memory 24 or the like.

  Next, in S22, the CPU 21 extracts the vehicle speed at the time of imaging the frame to be processed for the imaging vehicle to be processed from the probe information acquired in S1, and substitutes the value of the extracted vehicle speed into the vehicle speed addition value S. to add. Note that the initial value of the vehicle speed addition value S is set to 0, and is initialized when the process of S27 or S28 is executed. The added current vehicle speed value S is stored in the flash memory 24 or the like.

  Subsequently, in S23, the CPU 21 extracts, from the probe information acquired in S1, the position coordinates of the processing target imaging vehicle at the time of imaging of the processing target frame. Thereafter, by matching the extracted position coordinates with the map information provided in the server device 3 on the basis of the lane, the lane in which the imaging vehicle to be processed is located at the time of capturing the frame to be processed is specified. The map information includes information for specifying the structure of the lane in the link. For example, as shown in FIG. 8, when the imaging vehicle travels on a link including two lanes 61 and 62, and when the position coordinates 63 match the left lane 61, the imaging vehicle captures an image of a frame to be processed. It is specified that the vehicle is located on the lane 61 at the time, and the lane 61 is counted up. Note that the count-up value for each lane is initialized when the process of S27 or S28 is executed. The current value counted up for each lane is stored in the flash memory 24 or the like.

  Then, after performing the processes of S21 to S23 on all the frames included in the captured image captured by the imaging vehicle to be processed in the link to be processed, the process proceeds to S24.

  In S24, the CPU 21 reads the value of the final vehicle speed addition value S added in S22 from the flash memory 24, and divides the value by the final frame number N counted in S21. As a result, the average vehicle speed during the imaging of the captured image of the imaging vehicle to be processed is calculated.

  Next, in S25, the CPU 21 reads the count value for each lane counted in S23 from the flash memory 24, and specifies the lane with the highest count value. As a result, the lane in which the imaging vehicle to be processed mainly travels during the imaging of the captured image (hereinafter, referred to as the traveling lane) is specified. For example, as shown in FIG. 9, when the imaging vehicle travels on a link including two lanes 61 and 62, when the position coordinates 63 are matched on the left lane 61 and the right lane 62, respectively, Since the number of times of matching of the lane 62 is larger, the traveling lane in which the imaging vehicle to be processed mainly travels during the imaging of the captured image is specified as the lane 62.

  Subsequently, in S26, the CPU 21 determines whether or not the average vehicle speed calculated in S24 is equal to or higher than a threshold. Note that the threshold value may be a fixed value (for example, 10 km / h) or may be changed depending on the type of road (for example, 40 km / h for an expressway and 10 km / h for a general road).

  When it is determined that the average vehicle speed calculated in S24 is equal to or higher than the threshold (S26: YES), the process proceeds to S27. On the other hand, if it is determined that the average vehicle speed calculated in S24 is lower than the threshold (S26: NO), the process proceeds to S28.

  In S27, the CPU 21 determines that the traffic congestion state of the traveling lane of the imaging vehicle specified in S25 among the lanes included in the link to be processed is “vacant (non-congestion)”.

  On the other hand, in S28, the CPU 21 determines that the traffic congestion state of the traveling lane of the imaging vehicle identified in S25 among the lanes included in the link to be processed is “congestion”. The determination results in S27 and S28 are temporarily stored in the flash memory 24.

  After that, the process proceeds to S6 after the processes of S21 to S28 are completed for all the corresponding links and the imaging vehicles. That is, the traveling lane is specified for each link and each imaging vehicle, and congestion determination of the traveling lane is performed.

  Next, a sub-process of the other lane density process executed in S6 will be described with reference to FIG. FIG. 10 is a flowchart of a sub-processing program of the other lane density processing.

  The subsequent processes of S31 to S37 are performed for each link for which the traffic congestion state is to be determined and for each imaging vehicle for which the probe information has been collected in S1. Then, the process proceeds to S7 after the processes of S31 to S37 are completed for all the corresponding links and imaging vehicles.

  First, in S31, the CPU 21 calculates the traveling distance of the imaging vehicle to be processed on the link to be processed. The link length of the link to be processed may be regarded as the traveling distance of the imaging vehicle, or the actual traveling distance may be calculated from the history of the position coordinates of the imaging vehicle included in the probe information.

  Note that the subsequent processing of S32 and S33 is performed for each vehicle (hereinafter, referred to as another vehicle) included in the captured image captured by the processing target imaging vehicle on the link to be processed. However, other vehicles located on the traveling lane of the imaging vehicle are excluded from the processing target. The detection of other vehicles included in the imaged vehicle is performed by, for example, the following method.

  First, the CPU 21 performs image processing on each frame included in the captured image, and detects each other vehicle included in each frame. The detection of another vehicle from the image is performed by, for example, a matching process using a feature point. Thereafter, the identity of the other vehicle is determined from the shape and color of the vehicle detected between the preceding and succeeding frames, and the same ID is assigned to the same other vehicle. The “number of assigned IDs” = “the number of detected other vehicles”, and the subsequent processes of S32 and S33 are performed for each of the other vehicles to which the ID has been assigned (that is, for each ID of the other vehicle).

  For example, in the example illustrated in FIG. 11, in the link including three lanes, FIG. 12 is a diagram illustrating an example of a detection mode of another vehicle when the imaging vehicle 65 runs on the center lane. In the example shown in FIG. 11, while the vehicle is traveling on the link, first, at the point A, other vehicles are detected in the left lane and the right lane, respectively. For example, an ID “0001” is assigned to another vehicle detected in the left lane, and an ID “1001” is assigned to another vehicle detected in the right lane. Thereafter, when the imaging vehicle 65 arrives at the point B, the other vehicle having the ID “1001” detected in the right lane is once in a non-detection state, and then, when the vehicle reaches the point C, a new lane is added to the right lane. Another vehicle is detected. For example, an ID “1002” is assigned to a new other vehicle detected in the right lane. In the meantime, another vehicle with ID “0001” is continuously detected in the left lane. Thereafter, when the imaging vehicle 65 reaches the point D, the other vehicle having the ID “0001” detected in the left lane and the other vehicle having the ID “1002” detected in the right lane temporarily become the non-detection state. After that, when the vehicle reaches the point E, another new vehicle is detected in the left lane. For example, an ID “0002” is assigned to a new other vehicle detected in the left lane. Thereafter, when the imaging vehicle 65 reaches the point F, a new other vehicle is detected in the right lane. For example, an ID “1003” is assigned to a new other vehicle detected in the right lane. Next, when the imaging vehicle 65 reaches the point G, the other vehicle having the ID “1003” that has been detected in the right lane is temporarily in a non-detection state, and is further detected in the left lane when the imaging vehicle 65 reaches the point H. The vehicle other than the ID “0002” is also in the non-detection state. In the example shown in FIG. 11, as a result, two other vehicles having IDs “0001” and “0002” are detected in the left lane, and three other vehicles having IDs “1001”, “1002” and “1003” are detected in the right lane. The other vehicle in the vehicle is detected.

  Then, in S32, the CPU 21 determines whether or not the vehicle speed of the imaging vehicle when detecting another vehicle to be processed is equal to or lower than a predetermined speed. Note that the vehicle speed during the time when the imaging vehicle captures the captured image is included in the probe information acquired in S1. The predetermined speed serving as the criterion in S32 may be a fixed value (for example, 5 km / h) or may be changed depending on the type of road (for example, 20 km / h for an expressway and 5 km / h for a general road). .

  If it is determined that the vehicle speed of the imaging vehicle when detecting another vehicle to be processed is higher than the predetermined speed (S32: NO), the process proceeds to S33.

  In S33, the CPU 21 counts up the number T of other vehicles detected separately for each lane. The initial value of the number T of other vehicles is set to 0, and is initialized when the processing of S36 or S37 is executed. The counted number T of other vehicles is stored in the flash memory 24 or the like after being divided for each lane.

  On the other hand, when it is determined that the vehicle speed of the imaging vehicle when detecting another vehicle to be processed is equal to or lower than the predetermined speed (S32: YES), a special case such as that the imaging vehicle is stopped waiting for a signal is used. It is estimated that there is a situation, and it is determined that it is difficult to accurately count the number of vehicles of other vehicles from the captured image. Therefore, the other vehicle to be processed is changed without performing the count-up in S33, and the process returns to S32.

  Next, in S34, the CPU 21 reads out the final number T of other vehicles counted for each lane as a result of performing the processes of S32 and S33. Then, the read number T of other vehicles is divided by a value (for example, a value obtained by dividing the traveling distance [m] by 100, or 5 when the traveling distance is 500 m, 5) according to the traveling distance calculated in S31. For the link to be processed, the number of other vehicles per unit distance (for example, 100 m) per lane, that is, the density of other vehicles per lane is calculated. The density of other vehicles for each lane calculated in S34 is one of the parameters for specifying the traffic flow for each lane. The traffic flow indicates the flow (including speed and density) of vehicles traveling on the road.

  Subsequently, in S35, the CPU 21 determines, for each lane, whether or not the number of other vehicles per unit distance calculated in S34 is equal to or greater than a threshold. Note that the threshold value may be a fixed value (for example, 20 vehicles / 100 m) or may be changed depending on the type of road (for example, 10 vehicles / 100 m on a highway, 20 vehicles / 100 m on a general road).

  When it is determined that the number of other vehicles per unit distance calculated in S34 is equal to or greater than the threshold (S35: YES), the process proceeds to S36. On the other hand, when it is determined that the number of other vehicles per unit distance calculated in S34 is less than the threshold (S35: NO), the process proceeds to S37.

  In S36, the CPU 21 determines that the traffic congestion state of the lane in which the number of other vehicles per unit distance is equal to or larger than the threshold value is “congestion” among the lanes included in the link to be processed.

  On the other hand, in S37, the CPU 21 determines that the traffic congestion state of the lane in which the number of other vehicles per unit distance is smaller than the threshold value among the lanes included in the link to be processed is “vacant (non-congestion)”. . Note that the processing of S35 to S37 is performed on all the lanes included in the link to be processed (however, lanes that are not included in the captured image and the traveling lanes of the captured vehicle are excluded). The information is temporarily stored in the flash memory 24.

  After that, the process proceeds to S7 after the processes of S31 to S37 are completed for all the corresponding links and imaging vehicles. That is, traffic congestion determination for lanes other than the traveling lane is performed based on the captured image for each link and each captured vehicle.

  Next, a sub-process of the other lane speed process executed in S7 will be described with reference to FIG. FIG. 12 is a flowchart of a sub-processing program of another lane speed processing.

  The subsequent processing of S41 to S50 is performed for each link for which the traffic congestion state is to be determined, and for each imaging vehicle for which the probe information has been collected in S1. Further, the subsequent processing of S41 to S45 is performed for each frame included in the captured image and for each other vehicle detected in each frame. However, other vehicles located on the traveling lane of the imaging vehicle are excluded from the processing target. The detection of another vehicle from the captured image is performed by, for example, a matching process using a feature point. Then, after the processes of S41 to S50 are completed for all the corresponding links and the imaging vehicles, the process proceeds to S8.

  First, in S41, the CPU 21 calculates a distance from an imaged vehicle to another vehicle at the time of imaging of a frame to be processed. Note that the distance from the imaging vehicle to another vehicle may be a linear distance or a distance along the traveling direction of the road. The distance from the imaging vehicle to the other vehicle is calculated based on the position of the other vehicle in the frame by performing image processing on the frame to be processed and identifying the position of the other vehicle in the frame. You. In addition, when calculating the distance along the traveling direction of the road, it is preferable to calculate the distance after correcting the captured image to a top view by performing ortho-transform.

  Next, in S42, the CPU 21 determines whether the distance from the imaged vehicle to the other vehicle at the time of imaging the frame to be processed is equal to or less than a predetermined distance. The predetermined distance serving as the determination reference in S42 is an upper limit distance at which an error falls within an allowable range when calculating a relative speed of another vehicle with respect to the captured vehicle from the captured image in S44 described later, for example, 20 m. .

  Then, when it is determined that the distance from the imaged vehicle to the other vehicle at the time of imaging the frame to be processed is equal to or less than the predetermined distance (S42: YES), the process proceeds to S43. On the other hand, when it is determined that the distance from the imaging vehicle to the other vehicle at the time of imaging of the frame to be processed is longer than the predetermined distance (S42: NO), the relative speed of the other vehicle is accurately calculated from the captured image. It is found to be difficult to calculate. Therefore, the other vehicle or frame to be processed is changed without performing the processes of S43 to S45 described later, and the process returns to S41.

  In S43, the CPU 21 calculates an average distance to another vehicle. Specifically, among the frames captured earlier than the frame to be processed, a predetermined number (for example, one or two) of frames having the latest imaging time are targeted for the other vehicle calculated in S41. The respective distances are read out, and the average value of the distance calculated this time in S41 and the read distance is calculated as the average distance to another vehicle.

Next, in S44, the CPU 21 calculates the relative speed of another vehicle with respect to the imaged vehicle at the time of imaging the frame to be processed. Specifically, the distance from the imaging vehicle to the other vehicle at the time of imaging of the frame to be processed is D (f + 1), and the distance from the imaging vehicle to the other vehicle at the time of imaging of the immediately preceding frame is D (f + 1). f) Assuming that the frame rate is 1 / Δt, the relative speed Va of the other vehicle with respect to the imaging vehicle is calculated by the following equation (1). It is desirable that D (f + 1) and D (f) be the average distance calculated in S43. Va = (D (f + 1) −D (f)) / Δt (.) 1)

Thereafter, in S45, the CPU 21 calculates the absolute speed of the other vehicle at the time of capturing the frame to be processed. Specifically, assuming that the absolute speed of the imaged vehicle at the time of capturing the frame to be processed is V (f + 1), the absolute speed v (f + 1) of the other vehicle at the time of capturing the frame to be processed is V (f + 1). It is calculated by the following equation (2).
v (f + 1) = V (f + 1) + Va (2)

  Then, for all the frames included in the captured image, the process proceeds to S46 after the absolute velocities of all the other vehicles in the frames are calculated.

  In S46, the CPU 21 calculates a traveling distance of the imaging vehicle to be processed on the link to be processed. The link length of the link to be processed may be regarded as the traveling distance of the imaging vehicle, or the actual traveling distance may be calculated from the history of the position coordinates of the imaging vehicle included in the probe information.

  In S47, the CPU 21 calculates, for each lane included in the link to be processed, the average vehicle speed of another vehicle traveling in the lane. Specifically, the CPU 21 first adds the absolute speeds calculated for each of the other vehicles and for each frame in S45 in units of other vehicles to which the same ID is assigned, and includes the corresponding other vehicle. Divided by the number of frames to be processed. Thereby, the average vehicle speed for each other vehicle is calculated. Note that the assignment of the ID to the other vehicle is the same as the above-described other lane density processing (FIG. 10), and thus description thereof is omitted (see FIG. 11). Thereafter, the average vehicle speed of the other vehicles traveling in the lane is classified for each lane and divided by the number of other vehicles. As a result, the average vehicle speed of another vehicle traveling in the lane is calculated for each lane. The average vehicle speed of the other vehicles for each lane calculated in S47 is one of the parameters for specifying the traffic flow for each lane.

  Subsequently, in S48, the CPU 21 determines, for each lane, whether or not the average vehicle speed of the other vehicle calculated in S47 is equal to or higher than a threshold. Note that the threshold value may be a fixed value (for example, 10 km / h) or may be changed depending on the type of road (for example, 40 km / h for an expressway and 10 km / h for a general road).

  When it is determined that the average vehicle speed of the other vehicle calculated in S47 is equal to or higher than the threshold (S48: YES), the process proceeds to S49. On the other hand, when it is determined that the average vehicle speed of the other vehicle calculated in S47 is less than the threshold (S48: NO), the process proceeds to S50.

  In S49, the CPU 21 determines that the traffic congestion state of the lane in which the average vehicle speed of the other vehicle is determined to be equal to or higher than the threshold among the lanes included in the link to be processed is “vacant (non-congestion)”.

  On the other hand, in S50, the CPU 21 determines that the traffic congestion state of the lane in which the average vehicle speed of the other vehicle is less than the threshold among the lanes included in the link to be processed is “congestion”. The processing of S48 to S50 is performed for all the lanes included in the link to be processed (except for the lanes not included in the captured image, the lanes where no other vehicles exist, and the traveling lanes of the captured vehicle). This is performed, and the determination result is temporarily stored in the flash memory 24.

  After that, the process proceeds to S8 after the processes of S41 to S50 are completed for all the corresponding links and imaging vehicles. That is, traffic congestion determination for lanes other than the traveling lane is performed based on the captured image for each link and each captured vehicle.

  Next, a sub-process of the lane matching process executed in S9 will be described with reference to FIG. FIG. 13 is a flowchart of a sub-processing program of the lane matching processing.

  Subsequent processes in S51 and S52 are performed for each link for which the traffic congestion state is determined. Then, after the processes of S51 and S52 are completed for all the corresponding links, the process proceeds to S10.

  First, in S51, the CPU 21 counts the number of lanes for which the traffic congestion state has been determined in S5 to S7 in the link to be processed. Next, the actual number of lanes of the road corresponding to the link to be processed is read from the map information of the server device 3. Note that the map information includes information for specifying the number of lanes of the road for each link in advance, and the actual number of lanes means the number of lanes included in the map information. Then, it is determined whether or not the number of lanes in which the traffic congestion status is determined in S5 to S7 described above matches the actual number of lanes read from the map information or is smaller than the actual number of lanes. Note that not all the lanes of the road are included in the captured image captured by the imaging vehicle. Therefore, even when the exact congestion state is determined, the number of lanes for which the congestion state has been determined is not the actual number of lanes. If the number is smaller than the number of lanes, it may occur.

  Then, the number of lanes in which the traffic congestion state is determined in S5 to S7 is equal to the actual number of lanes read from the map information, or the actual number of lanes is read. When it is determined that the number is smaller (S51: YES), the process returns to S51 after switching the link to be processed. On the other hand, when it is determined that the number of lanes in which the traffic congestion status is determined in S5 to S7 is larger than the actual number of lanes read from the map information (S51: NO), the traffic congestion status is determined. It can be estimated that a lane that should not exist for some reason is recognized when making the determination. Therefore, in S52, the CPU 21 performs correction to delete the lane determination result that does not correspond to the actual lane in order to match the actual lane number, that is, the lane number included in the map information. Specifically, for example, if the number of lanes included in the map information is three, and the number of lanes for which the traffic congestion state is determined is four, the number of lanes included in the map information is three. It has three lanes to match. It should be noted that, other than deleting the number of lanes to match the number of lanes included in the map information, the determination of the congestion state of this link may not be performed, or the data may be excluded and the determination of the congestion state may be performed. .

  Next, a sub-process of the parallel running process executed in S10 will be described with reference to FIG. FIG. 14 is a flowchart of a sub-processing program of the parallel running process.

  Subsequent processing in S61 to S68 is performed for each link (hereinafter, referred to as a traffic congestion determination link) including a lane determined to be “congested” by the traffic congestion determination in any of S5 to S7, and The judgment is performed for each lane. Then, the process proceeds to S11 after the processes of S61 to S68 are completed for all the corresponding traffic jam determination links and traffic jam determination lanes.

  First, in S61, the CPU 21 initializes each parameter of a traffic jam flag, a temporary flag, and an inter-lane distance L. The parameters of the traffic jam flag, the temporary flag, and the distance L between the lanes are stored in the flash memory 24 or the like.

  The subsequent processing of S62 to S67 is performed for each traveling lane of the imaging vehicle that has traveled on the traffic congestion determination link to be processed. The traveling lane of the imaging vehicle is specified in the own lane process (FIG. 7).

  In S62, the CPU 21 calculates the distance between the traveling lane to be processed and the traffic congestion determination lane to be processed. Then, the calculated distance is substituted as the inter-lane distance L. The inter-lane distance L is calculated assuming that the distance between adjacent lanes is "1". That is, if the traveling lane to be processed is adjacent to the traffic congestion determination lane to be processed, the inter-lane distance L is “1”. When only one other lane is interposed between the traveling lane to be processed and the traffic congestion determination lane to be processed, the inter-lane distance L is “2”.

  Next, in S63, the CPU 21 determines that the traffic congestion determination lane to be processed is “congested” by the traffic congestion determination (S5 to S7) using the traveling information or the captured image of the imaging vehicle traveling in the processing lane. Is determined. In the traffic jam determination processing of S5 to S7, traffic jam determination is performed for each imaging vehicle.

  When the traffic congestion determination lane to be processed is determined to be "congested" by the traffic congestion determination (S5 to S7) using the traveling information or the captured image of the imaging vehicle traveling in the processing lane (S63: YES) )), “Congestion” is assigned to the temporary flag (S64). On the other hand, the traffic congestion determination lane to be processed is determined to be "vacant (non-congestion)" by the traffic congestion determination (S5 to S7) using the traveling information or the captured image of the imaging vehicle traveling in the processing lane. If there is (S63: NO), "empty (non-congestion)" is substituted for the temporary flag (S65).

  Thereafter, in S66, the CPU 21 reads the current inter-lane distance L substituted in S62, and the current inter-lane distance L is equal to or less than the minimum value of the inter-lane distance L substituted from the initialization in S61 to the present time. It is determined whether or not.

  When it is determined that the current inter-lane distance L is equal to or less than the minimum value of the inter-lane distance L substituted from the time after the initialization in S61 to the present time (S66: YES), the current temporary flag is added to the congestion flag. (Congestion or vacancy) is substituted (S67).

  On the other hand, if it is determined that the current inter-lane distance L is larger than the minimum value of the inter-lane distance L substituted from the time after the initialization in S61 to the present time (S66: NO), the congestion flag is changed. Without returning to S62.

  Then, after performing the processes of S62 to S67 on the traveling lanes of all the imaging vehicles traveling on the traffic congestion determination link to be processed, the process proceeds to S68.

  In S68, the traffic congestion state of the traffic congestion determination lane to be processed is finally determined based on the content of the current traffic congestion flag. Therefore, if the traffic congestion flag is "vacant (non-congestion)" at the time of S68, even if the traffic congestion determination lane is once determined to be congested in S5 to S7, the traffic congestion lane finally becomes "vacant (non-congestion)". Is determined.

  After that, the process proceeds to S11 after the processes of S61 to S68 are completed for all the corresponding traffic jam determination links and traffic jam determination lanes.

  As a result of performing the parallel running process shown in FIG. 14, when the traffic congestion determination based on the traveling information and the traffic congestion determination based on the captured image information are possible for the same lane, the determination result of the traffic congestion determination based on the traveling information has priority. Will be used. For example, as shown in FIG. 15, this is a case where two imaging vehicles 65 and 66 have respectively traveled in the center lane and the right lane of the same link, and the imaging vehicle 65 is traveling based on the traveling information. When the center lane is determined to be “congested” and the imaging vehicle 66 determines the center lane located on the left side of the own vehicle to be “non-congested” based on the captured image, the determination result of the imaging vehicle 65 has priority. Will be done. That is, the central lane is determined to be “congested”.

  In addition, as a result of performing the parallel running process shown in FIG. 14, when it is possible to determine the congestion based on a plurality of imaging vehicles for the same lane, the imaging vehicle traveling in a lane closer to the determination target lane Will be used with priority. For example, as shown in FIG. 16, the case where two imaging vehicles 65 and 66 are traveling in the leftmost lane and the rightmost lane of the same link, respectively, and the imaging vehicle 65 The second lane from the left located on the left side of the vehicle on which the vehicle is traveling is determined to be “non-congested”, and the imaging vehicle 66 determines the second lane from the left located on the left side of the vehicle based on the captured image as “congested”. ], The determination result of the imaging vehicle 65 traveling in the lane closest to the second lane from the left is prioritized. That is, the second lane from the left is determined as “non-congestion”.

  Further, when it is possible to determine the traffic congestion based on a plurality of imaging vehicles for the same lane, it is also possible to preferentially use the determination result of the traffic congestion determination based on the imaging vehicle that entered late by the link including the lane to be determined. good. For example, as shown in FIG. 17, two imaging vehicles 65 and 66 are traveling on the leftmost lane and the second lane from the right of the same link, respectively, and the imaging vehicle 65 is based on the captured image. The second lane from the left located on the left side of the vehicle on which the own vehicle is traveling is determined to be “non-congested”, and the imaging vehicle 66 determines the second lane from the left located on the left side of the own vehicle based on the captured image. When it is determined that the traffic is “congested”, the determination result of the imaging vehicle 65 having the late entry time to the link has priority. That is, the second lane from the left is determined as “non-congested”.

  In addition, when the traffic congestion determination based on a plurality of imaging vehicles is possible for the same lane, and when two or more different determination results are included, the determination result with a larger number of determined imaging vehicles is determined as the traffic jam determination result. May be used in priority. For example, as shown in FIG. 18, when three imaging vehicles 65, imaging vehicles 66, and imaging vehicles 67 respectively travel on the same link, the imaging vehicle 65 changes the second lane from the left based on the captured image. The image capturing vehicle 66 determines that the traffic lane is the second traffic lane based on the captured image, and determines that the traffic lane is the second traffic lane based on the captured image. ], The number of imaging vehicles determined to be “congested” is greater than the number of imaging vehicles determined to be “non-congested”, so that the determination results of imaging vehicles 66 and 67 determined to be “congested” have priority. Will be done. That is, the second lane from the left is determined to be “traffic jam”.

  Also, among the determination results of the traffic congestion determinations performed in S5 to S7, the weight of the traffic congestion determination may be set according to the priority level instead of employing the determination result with the highest priority. That is, the weighting is set to be heavier as the determination result has higher priority. Thus, when there are a large number of determination results, it is possible to determine a more appropriate determination result in consideration of the large number of determination results.

  As described in detail above, the traffic situation determination system 1 and the server device 3 according to the present embodiment collect information as to the traveling lane and the vehicle speed of each vehicle 4 traveling on the road as traveling information (S1). The information on the captured image of the periphery of each vehicle is collected by the on-board camera 7 of each vehicle 4 traveling on the road as peripheral image information (S1), and the collected traveling information and the collected peripheral image information are collected. The traffic congestion state of the road is determined for each lane on the basis of the information (S5 to S10). By using the information based on the captured image of the vehicle having a wide possible range, it is possible to accurately determine the traffic congestion state of the road for each lane in a wider range.

It should be noted that the present invention is not limited to the above-described embodiment, and various improvements and modifications can be made without departing from the spirit of the present invention.
For example, in the present embodiment, captured images captured by the respective vehicles 4 are collected as probe information collected from the respective vehicles 4, but image processing on the captured images is performed by the respective vehicles 4, and is derived by image processing on the captured images. Data (for example, distance to another vehicle, speed of another vehicle, etc.) may be collected as probe information.

  In the present embodiment, the position coordinates of each vehicle 4 are collected as probe information collected from each vehicle 4. However, map matching with respect to the position coordinates is performed by each vehicle 4, and the travel of the vehicle 4 specified by the map matching is performed. Lanes may be collected as probe information.

  In the present embodiment, the traveling speed and the density of another vehicle traveling in a lane other than the traveling lane are calculated based on the information on the captured image collected from each vehicle 4, and the calculated traveling speed of the other vehicle is calculated. (S6, S7), if the traffic flow in the lane can be specified, parameters other than the traveling speed of the other vehicle and the density of the other vehicle are calculated. You may. For example, the travel time of the link may be calculated.

  Further, in the present embodiment, the execution subject of the traffic congestion state determination processing program shown in FIG. 6 is the server device 3, but the configuration may be such that the navigation device 5 executes the program. Further, the server device 3 and the navigation device 5 may be configured to partially execute each. When the navigation device 5 executes the congestion status determination processing program, it is desirable to acquire the traveling information and the captured image of the other vehicle via the server device 3 or to acquire the information by inter-vehicle communication. Further, when the navigation device 5 executes a part of the congestion situation determination processing program, for example, the processes of S5 to S8 can be performed by the navigation device 5 of each vehicle.

  Further, instead of the navigation device 5, the traffic condition determination system 1 can be configured by another device having a function of guiding traffic congestion information and a function of performing a route search process using the traffic congestion information. For example, a vehicle-mounted device other than the navigation device 5, a mobile phone, a smartphone, a tablet terminal, a personal computer, and the like are possible.

  In addition, although the embodiment embodying the traffic situation determination system according to the present invention has been described above, the traffic situation determination system can also have the following configuration, and in that case, the following effects are obtained.

For example, the first configuration is as follows.
The traveling information collecting means (21) for collecting information for specifying the traveling lane and the vehicle speed of each vehicle (4) traveling on the road as traveling information, and the imaging device (7) provided in each vehicle traveling on the road. Image information collecting means (21) for collecting, as peripheral image information, information about a captured image of the periphery of each vehicle; and the traveling information collected by the traveling information collecting means and the image information collected by the image information collecting means. Traffic congestion determining means (21) for determining traffic congestion on a road for each lane based on the surrounding image information.
According to the traffic condition determination system having the above configuration, when determining the traffic congestion status of the road for each lane based on the information collected from each vehicle traveling on the road, the reliability as the information is high, but the determination is possible. By using the travel information of vehicles with a narrow range and the information based on the captured image of a vehicle with low reliability as information but a wide range that can be determined, the traffic congestion status of the road for each lane can be accurately over a wider range. Can be determined.

The second configuration is as follows.
The traffic congestion determination unit (21) is configured to perform traffic on a lane around an imaging vehicle, which is a vehicle that has captured the captured image, based on the peripheral image information collected by the image information collection unit (21). A flow is specified, and a traffic congestion state of a road is determined for each lane based on the driving information collected by the driving information collecting means and the specified traffic flow of the lane.
According to the traffic situation determination system having the above configuration, the traffic flow in the lane other than the lane in which the vehicle travels can be specified by using the captured image of the periphery of the vehicle. It is also possible to determine the traffic congestion on the road with relatively high reliability for lanes.

The third configuration is as follows.
The traffic congestion determining means (21) specifies a traveling speed and a density of a vehicle traveling on the lane as a traffic flow of the lane.
According to the traffic situation determination system having the above configuration, the traveling speed and the density of the vehicle in the lanes other than the lane in which the vehicle travels can be specified by using the captured image of the periphery of the vehicle. It is possible to determine the traffic congestion state of the road with relatively high reliability even for lanes other than the lane on which the vehicle travels.

The fourth configuration is as follows.
The congestion determination means (21) gives priority to the determination result of the congestion determination based on the traveling information when the congestion determination based on the traveling information and the congestion determination based on the peripheral image information are possible for the same lane. Used.
According to the traffic situation determination system having the above configuration, when determining the traffic congestion state of the road for each lane based on information collected from each vehicle traveling on the road, different traffic congestion determination results for the same lane Even in the case of overlapping, the result of the traffic congestion determination with high reliability as information can be preferentially used, so that the traffic congestion state of the road for each lane can be more accurately determined.

The fifth configuration is as follows.
Map information acquisition means (21) for acquiring map information (12) including information on the number of lanes of a road; and the number of lanes of the road for which the congestion state has been determined by the congestion determination means is the number of lanes of the same road in the map information. And a judgment result correcting means (21) for correcting the judgment result of the traffic congestion judging means so as to match the number of lanes of the same road in the map information when the traffic does not match.
According to the traffic situation determination system having the above configuration, when determining the traffic congestion state of the road for each lane based on information collected from each vehicle traveling on the road, the number of lanes of the road where the traffic congestion state is determined Even when the actual number of lanes does not match, it is possible to adapt to the actual lane by correcting the determination result.

The sixth configuration is as follows.
The traveling information collecting means (21) collects a history of coordinates indicating a current position of a vehicle (4) traveling on a road as information for specifying a traveling lane.
According to the traffic situation determination system having the above configuration, the traffic flow in the lane in which the vehicle has traveled can be specified by using the travel information of the vehicle. The situation can be determined.

The seventh configuration is as follows.
The traffic congestion determination means (21) determines a traffic congestion state of a road for each lane on a per-imaging vehicle basis, which is a vehicle that has captured the captured image, based on the peripheral image information regarding the captured image captured by the captured vehicle. I do.
According to the traffic condition determination system having the above-described configuration, it is possible to determine the traffic congestion condition of the road for each lane using information collected from each of the vehicles traveling on the road. Therefore, based on the information collected from each vehicle, it is possible to determine the traffic congestion state of the road in each lane in a wider range.

The eighth configuration is as follows.
The congestion determination means (21) is configured to determine whether or not the traffic congestion is determined based on a plurality of imaging vehicles in the same lane, based on the imaging vehicle traveling in a lane closer to the determination target lane. The judgment result is used with priority.
According to the traffic situation determination system having the above configuration, when determining the traffic congestion state of the road for each lane based on information collected from each vehicle traveling on the road, different traffic congestion determination results for the same lane Even in the case of overlapping, the result of the traffic congestion determination with high reliability as information can be preferentially used, so that the traffic congestion state of the road for each lane can be more accurately determined.

The ninth configuration is as follows.
When the traffic congestion determination means (21) is capable of performing traffic congestion determination based on a plurality of imaging vehicles for the same lane, the determination result of the traffic congestion determination based on the imaging vehicle that has entered late by a link including the lane to be determined. Is used with priority.
According to the traffic situation determination system having the above configuration, when determining the traffic congestion state of the road for each lane based on information collected from each vehicle traveling on the road, different traffic congestion determination results for the same lane Even in the case of overlapping, the result of the traffic jam determination having high reliability as information can be preferentially used, so that the traffic jam status of the road for each lane can be more accurately determined.

The tenth configuration is as follows.
The congestion determination means (21) is capable of determining congestion based on a plurality of imaging vehicles for the same lane, and determining that the number of determined imaging vehicles is larger when including two or more different determination results. The result is used in preference to the result of the traffic jam determination.
According to the traffic condition determination system having the above configuration, when determining the traffic congestion status of the road for each lane based on information collected from each vehicle traveling on the road, different traffic congestion determination results for the same lane Even in the case of overlapping, the result of the traffic jam determination having high reliability as information can be preferentially used, so that the traffic jam status of the road for each lane can be more accurately determined.

DESCRIPTION OF SYMBOLS 1 Traffic condition judgment system 2 Probe center 3 Server device 4 Vehicle 5 Navigation device 7 In-vehicle camera 11 Server control ECU
12 map information DB
12 Probe information DB
13 Traffic information DB
21 CPU
22 RAM
23 ROM
24 Flash memory 65, 66, 67 Imaging vehicle

Claims (11)

Traveling information collecting means for collecting information for specifying a traveling lane and a vehicle speed of each vehicle traveling on the road as traveling information,
Image information collecting means for collecting information about a captured image of the periphery of each vehicle by an imaging device provided for each vehicle traveling on the road as peripheral image information,
Traffic congestion determining means for determining a traffic congestion state of a road for each lane based on the driving information collected by the driving information collecting means and the peripheral image information collected by the image information collecting means. Judgment system. The traffic congestion determination means,
Based on the peripheral image information collected by the image information collecting means, the traffic flow of the lane is specified for a lane around the imaging vehicle that is the vehicle that captured the captured image,
The traffic condition determination system according to claim 1, wherein a traffic congestion condition of a road is determined for each lane based on the travel information collected by the travel information collection unit and the traffic flow of the specified lane.   The traffic condition determination system according to claim 2, wherein the congestion determination unit specifies a traveling speed and a density of the vehicle traveling in the lane as a traffic flow in the lane.   The traffic congestion determination unit may use the determination result of the traffic congestion determination based on the traveling information with priority when the traffic congestion determination based on the traveling information and the traffic congestion determination based on the surrounding image information are possible for the same lane. The traffic situation determination system according to any one of claims 1 to 3. Map information acquisition means for acquiring map information including information on the number of lanes of the road;
When the number of lanes of the road for which the congestion state is determined by the congestion determination means does not match the number of lanes of the same road in the map information, the congestion determination means of the congestion determination means matches the number of lanes of the same road in the map information. The traffic condition determination system according to claim 1, further comprising: a determination result correction unit configured to correct a determination result.   The traffic condition determination system according to any one of claims 1 to 5, wherein the travel information collecting means collects a history of coordinates indicating a current position of the vehicle traveling on the road as information for specifying a travel lane.   The traffic congestion determination unit determines a traffic congestion state of a road for each lane based on the peripheral image information on a captured image captured by the captured vehicle in units of a captured vehicle that captures the captured image. The traffic situation determination system according to any one of claims 1 to 6.   The congestion determination means, when it is possible to determine the congestion based on a plurality of imaging vehicles for the same lane, the determination result of the congestion determination based on the imaging vehicle traveling in a lane closer to the determination target lane The traffic condition determination system according to claim 7, which is used with priority.   The congestion determination means, when the traffic congestion determination based on a plurality of imaging vehicles is possible for the same lane, priority is given to the determination result of the traffic congestion determination based on the imaging vehicle that entered late by link including the lane to be determined. The traffic condition determination system according to claim 7, wherein the traffic condition determination system is used.   The traffic congestion determination means can perform traffic congestion determination based on a plurality of imaging vehicles for the same lane, and when two or more types of different determination results are included, determine that the number of determined imaging vehicles is larger. The traffic condition determination system according to claim 7, wherein the traffic condition determination system is used in preference to a determination result of the determination. Traveling information collecting means for collecting information for specifying a traveling lane and a vehicle speed of each vehicle traveling on the road as traveling information,
Image information collecting means for collecting information about a captured image of the periphery of each vehicle by an imaging device provided for each vehicle traveling on the road as peripheral image information,
Traffic congestion determining means for determining a traffic congestion state of a road for each lane based on the driving information collected by the driving information collecting means and the peripheral image information collected by the image information collecting means. Judgment device.

Images