Side ditch information generation system and side ditch information generation method

Abstract

In this side ditch information generation system, a location information acquisition unit (1) acquires location information for a probe vehicle (100), and a video acquisition unit (2) acquires a periphery video, which is a video obtained by imaging the periphery of the probe vehicle (100). On the basis of the periphery video of the probe vehicle (100) and the location information for the probe vehicle (100) when the periphery video was imaged, a side ditch presence point detection unit (3) detects side ditch presence points, which are points where a side ditch is present on a road. On the basis of the periphery video, a side ditch caution point detection unit (7) detects, from among the side ditch presence points, side ditch caution points, which are points where the probe vehicle (100) could enter the side ditch from the road. A side ditch caution point storage unit (8) stores information about the side ditch caution points.

Description

Gutter information generation system and gutter information generation method

[0001] The present disclosure relates to a road ditch information generating system and a road ditch information generating method for generating information on road ditches.

[0002] For example, Patent Document 1 listed below proposes a technology for displaying a guide indicating the location of the road or a gutter when the boundary between the road and the gutter or the like outside it cannot be seen due to snow accumulation.

[0003] International Publication No. 2021 / 029016

[0004] Even if a gutter is difficult to see, the risk of a vehicle falling into the gutter is low if a guardrail is installed between the road and the gutter. Therefore, the risk of a vehicle falling into a gutter varies from gutter to gutter. However, the technology of Patent Document 1 does not take into account the differences in risk between gutters and treats all gutters equally. As a result, guides are displayed even on roads with gutters that pose a low risk of a vehicle falling into (e.g., gutter with guardrail), which unnecessarily consumes computing resources. To solve this problem, it is necessary to identify in advance the locations of dangerous gutters (gutters where a vehicle may fall into).

[0005] The present disclosure has been made to solve the above-mentioned problems, and aims to provide a gutter information generation system that generates information indicating locations where dangerous gutter locations exist.

[0006] The gutter information generation system according to the present disclosure includes a location information acquisition unit that acquires location information of a vehicle, an image acquisition unit that acquires surrounding image, which is image captured of the area around the vehicle, a gutter presence point detection unit that detects gutter presence points, which are points where a gutter is located on a road, based on the surrounding image of the vehicle and the location information of the vehicle at the time the surrounding image was captured, a gutter caution point detection unit that detects gutter caution points, which are points where a vehicle may enter a gutter from the road, from among the gutter presence points based on the surrounding image, and a gutter caution point storage unit that stores information about the gutter caution points.

[0007] According to the road ditch information generating system according to the present disclosure, it is possible to generate information indicating locations where dangerous road ditches exist.

[0008] The objects, features, aspects, and advantages of the present disclosure will become more apparent from the following detailed description and the accompanying drawings.

[0009] 1 is a diagram showing the configuration of a side ditch information generating system according to embodiment 1. FIG. 2 is a diagram showing an example of probe information. FIG. 3 is a flowchart showing the operation of a probe device in the side ditch information generating system according to embodiment 1. FIG. 4 is a flowchart showing the operation of a server in the side ditch information generating system according to embodiment 1. FIG. 5 is a diagram showing the configuration of a side ditch information generating system according to embodiment 2. FIG. 6 is a diagram showing an example of a road on which a probe vehicle travels. FIG. 7 is a diagram showing an example of a surrounding image when the road is not flooded. FIG. 8 is a diagram showing an example of a surrounding image when the road is flooded. FIG. 9 is a diagram showing an example of an image for distinguishing between a road and a side ditch. FIG. 10 is a diagram showing an example of the hardware configuration of a probe device and a server. FIG. 11 is a diagram showing an example of the hardware configuration of a probe device and a server.

[0010] <First Embodiment> FIG. 1 is a diagram showing the configuration of a road ditch information generating system according to a first embodiment. The road ditch information generating system includes a probe device 110 mounted on a vehicle 100 and a server 200 capable of communicating with the probe device 110 via a network 300. Hereinafter, a vehicle 100 equipped with a probe device 110 will be referred to as a "probe vehicle." The road ditch information generating system may include multiple probe vehicles 100. The probe device 110 does not necessarily have to be permanently installed on the probe vehicle 100, and may be detachable from the probe vehicle 100. In this case, the probe device 110 may be an application running on a mobile terminal such as a mobile phone, smartphone, or PND (Portable Navigation Device).

[0011] As shown in FIG. 1 , the probe device 110 is connected to a locator 101, a camera 102, and a communication device 103 provided in the probe vehicle 100. The locator 101 calculates the current position of the probe vehicle 100 using GNSS (Global Navigation Satellite Systems). The camera 102 captures images of the surroundings of the probe vehicle 100. Hereinafter, the image of the surroundings of the probe vehicle 100 captured by the camera 102 will be referred to as "surrounding image." The communication device 103 is a communication means for the probe vehicle 100 to communicate with the server 200.

[0012] The camera 102 may be any type, such as a front camera, a rear camera, or an in-vehicle camera. The locator 101 and the camera 102 may be built into a drive recorder of the probe vehicle 100. The communication device 103 may be a general-purpose communication device such as a mobile phone or a smartphone. Some or all of the locator 101, the camera 102, and the communication device 103 may be built into the probe device 110.

[0013] The probe device 110 includes a position information acquisition unit 1 , an image acquisition unit 2 , a gutter location detection unit 3 , and a probe information generation unit 4 .

[0014] The position information acquisition unit 1 acquires position information indicating the current position of the probe vehicle 100 from a locator 101. The image acquisition unit 2 acquires an image of the surroundings of the probe vehicle 100 from a camera .

[0015] The gutter presence point detection unit 3 detects a gutter presence point, which is a point where a gutter is present on a road, based on the peripheral image of the probe vehicle 100 and the position information of the probe vehicle 100 at the time the peripheral image was captured. Specifically, the gutter presence point detection unit 3 analyzes the peripheral image to search for a gutter on the road on which the probe vehicle 100 has traveled, and the position where the peripheral image in which the gutter is detected was captured (i.e., the position of the probe vehicle 100 at the time the peripheral image was captured) becomes the gutter presence point corresponding to that gutter.

[0016] The probe information generation unit 4 creates probe information including location information and surrounding video with the same timestamp, and the detection results of the gutter in the surrounding video, and transmits the created probe information to the server 200 via the network 300 using the communication device 103.

[0017] The server 200 is constructed in a cloud environment and has sufficient hardware resources to process probe information transmitted from a large number of probe vehicles 100. The server 200 includes a communication unit 5, a probe information storage unit 6, a ditch caution point detection unit 7, a ditch caution point storage unit 8, and a map database 9.

[0018] The communication unit 5 is a communication means for the server 200 to communicate with the probe device 110 of the probe vehicle 100. The probe information transmitted from the probe device 110 is received by the communication unit 5.

[0019] The probe information storage unit 6 stores the probe information received by the communication unit 5. FIG. 2 shows an example of the probe information stored in the probe information storage unit 6. In FIG. 2, "vehicle ID" is the identifier of the probe vehicle 100 that is the sender of the probe information. "Coordinates" is the location information included in the probe information, i.e., information on the location where the surrounding image included in the probe information was captured. "Image file" is a data file of the surrounding image included in the probe information. "Timestamp" is the timestamp of the location information and surrounding image included in the probe information. "Presence or absence of a gutter" is the detection result of a gutter in the surrounding image included in the probe information. "Danger level" will be described later.

[0020] 2 also includes probe information in which a gutter was not detected, the probe device 110 may transmit only probe information in which a gutter was detected to the server 200. This reduces the amount of probe information transmitted from the probe device 110, thereby suppressing the consumption of communication resources.

[0021] The ditch caution point detection unit 7 detects ditch caution points, which are points where a vehicle may enter a ditch from the road, from among the ditch existing points based on the surrounding image included in the probe information stored in the probe information storage unit 6. Whether a vehicle may enter a ditch can be determined, for example, by whether there is a guardrail or a fence between the road and the ditch. In this case, the ditch caution point detection unit 7 detects points where there is no guardrail or fence between the road and the ditch as ditch caution points.

[0022] Furthermore, whether or not a vehicle can enter a side ditch may be determined taking into consideration the size (width and depth) of the side ditch. The size of the side ditch can be calculated by analyzing surrounding video. Alternatively, map data including information on the size of the side ditch may be stored in the map database 9, and the side ditch caution point detection unit 7 may determine whether or not a vehicle can enter a side ditch based on the map data. Furthermore, the probe information may include point cloud data of the side ditch acquired by a millimeter-wave radar or LiDAR mounted on the probe vehicle 100, and the side ditch caution point detection unit 7 may determine whether or not a vehicle can enter a side ditch based on the point cloud data.

[0023] The ditch caution point storage unit 8 stores the ditch caution points detected by the ditch caution point detection unit 7. The map database 9 is a database in which road map data is stored. The map data in the map database 9 includes information on ditch caution points. The map database 9 updates the map data by reflecting information on ditch caution points newly stored in the ditch caution point storage unit 8 in the map data.

[0024] 3 is a flowchart showing the operation of the probe device 110. The operation of the probe device 110 will be described below based on the flowchart of FIG.

[0025] When the probe vehicle 100 starts traveling, the probe device 110 starts the operation shown in Fig. 3. First, the position information acquisition unit 1 acquires the position information of the probe vehicle 100 from the locator 101 (step S10), and the image acquisition unit 2 acquires an image of the surroundings of the probe vehicle 100 from the camera 102 (step S11).

[0026] Next, the gutter presence point detection unit 3 analyzes the surrounding image acquired in step S11 and searches for a gutter present point by searching for a gutter reflected in the surrounding image (step S12). The shooting position of the surrounding image where the gutter is detected (i.e., the position of the probe vehicle 100 at the time when the surrounding image was shot) becomes the gutter presence point corresponding to the gutter.

[0027] Next, the probe information generation unit 4 generates probe information including the location information acquired in step S10, the surrounding image acquired in step S11, and the gutter detection result in step S12 (step S13).The probe information generation unit 4 then transmits the probe information generated in step S13 to the server 200 using the communication device 103 (step S14).

[0028] 3 ends. If the probe vehicle 100 continues traveling (NO in step S15), the process returns to step S10, and the above-described process is repeated. The repetition period, i.e., the probe information generation period, may be a fixed period, such as every second, or may be a variable period designated by the server 200.

[0029] 4 is a flowchart showing the operation of the server 200. The operation of the server 200 will be described below with reference to the flowchart of FIG.

[0030] The probe information transmitted from the probe device 110 in step S14 of FIG. 3 is received by the communication unit 5 of the server 200 (step S20) and stored in the probe information storage unit 6 (step S21).

[0031] The ditch caution point detection unit 7 searches for ditch caution points, which are points where a vehicle may enter a ditch from the road, based on the surrounding image included in the probe information stored in the probe information storage unit 6 (step S22). The ditch caution points detected by the ditch caution point detection unit 7 are stored in the ditch caution point storage unit 8 (step S23).

[0032] The map database 9 updates the map data by reflecting the information on the side ditch caution points stored in the side ditch caution point storage unit 8 in step S23 in the map data (step S24).

[0033] The above process is repeatedly executed every time the communication unit 5 receives new probe information.

[0034] According to the gutter information generating system of the first embodiment, it is possible to generate information on gutter caution points, which are points where dangerous gutters that vehicles can enter exist, or map data including information on gutter caution points, from the probe information collected by the probe device 110 of the probe vehicle 100.

[0035] [Modification 1] In the first embodiment, an example has been shown in which the ditch existing point detection unit 3 is arranged in the probe device 110 mounted on the probe vehicle 100, and the ditch caution point detection unit 7 is arranged in the server 200. However, both the ditch existing point detection unit 3 and the ditch caution point detection unit 7 may be arranged in the probe device 110, or both the ditch existing point detection unit 3 and the ditch caution point detection unit 7 may be arranged in the server 200.

[0036] However, it should be noted that if both the gutter presence point detection unit 3 and the gutter caution point detection unit 7 are placed in the probe device 110, the calculation load on the probe device 110 will increase, which will require the probe device 110 to have higher performance, and this may increase the cost of the probe device 110.

[0037] On the other hand, if both the gutter presence point detection unit 3 and the gutter caution point detection unit 7 are placed on the server 200, the calculation load on the probe device 110 will be reduced, which will contribute to reducing the cost of the probe device 110. However, it should be noted that since the probe device 110 cannot detect gutter locations, it is not possible to transmit only probe information in which a gutter has been detected to the server 200 in order to reduce the consumption of communication resources, for example.

[0038] [Variation 2] The ditch caution point detection unit 7 may determine the danger level of a ditch based on the width and depth of the ditch, and may add information about the danger level of the ditch (corresponding to the "danger level" in Figure 2) to the information about the ditch caution point.

[0039] Any method for determining the danger level may be used. For example, among the gutter caution points, points with wider or deeper gutters may be determined to have a high danger level. Specifically, a gutter that is narrow enough to cause a vehicle to derail may be assigned a danger level of "1," a gutter that is wider than the width of the vehicle may be assigned a danger level of "3," and a gutter that is wider than the width of the vehicle and deeper than the height of the vehicle door may be assigned a danger level of "5."

[0040] In addition, in sections where guardrails are present, there is no risk of the vehicle falling into a gutter, and the driver may not be paying attention to the gutter. Therefore, it is considered that there is a relatively high possibility of the vehicle falling into the gutter immediately after the guardrail ends. Therefore, among the gutter caution points, the points where the guardrail ends may be judged to have a higher risk level than other points.

[0041] The gutter caution spot detection unit 7 may obtain information from the network 300 such as the number of accidents occurring at gutter caution spots, traffic volume, and the presence or absence of caution warning signs (signs warning people to be careful of gutters), and may determine the danger level based on this information.

[0042] The gutter caution point detection unit 7 may acquire weather forecast information from the network 300 and determine the current real-time danger level of a gutter based on the weather forecast. For example, the danger level of a gutter in an area where rain is forecast may be higher than usual because there is a high possibility of flooding.

[0043] [Variation 3] The ditch caution spot detection unit 7 may determine the priority of installing a new guardrail or fence for a ditch caution spot where the ditch danger level is above a certain level, and may assign priority information to the information about the ditch caution spot. This priority is determined based on at least one of the danger level, the number of accidents that have occurred at the ditch caution spot, traffic volume, the presence or absence of a guardrail, and the presence or absence of a caution warning sign.

[0044] It is expected that information on the priority of installing new guardrails or fences will be provided to companies that perform construction work on gutters, guardrails, etc., local governments (such as city halls), etc. It is also conceivable that the company or local government may operate the server 200.

[0045] [Modification 4] Analysis using machine learning or deep learning may be introduced into the process executed by the gutter caution point detection unit 7.

[0046] For example, the gutter caution point detection unit 7 may learn the characteristics of images of gutters that vehicles may enter from past surrounding images, and based on the learning results, determine whether or not a vehicle may enter a gutter in a newly obtained surrounding image.

[0047] For example, the gutter warning point detection unit 7 may learn the relationship between the characteristics of gutter images and the danger level from past surrounding images, and based on the learning results, determine the danger level of the gutter in the newly obtained surrounding image.

[0048] [Variation 5] Locator 101 may be a high-precision locator with centimeter-level (sub-meter-level) accuracy. Camera 102 may be a high-performance camera capable of capturing video with high resolution (e.g., 4K, 8K, or higher resolution), high frame rate (e.g., 24 fps or higher), and wide range (e.g., HDR). Furthermore, the map data stored in map database 9 may be high-precision map data including road shape data for each lane. If these are made more sophisticated, it will be possible to detect ditch caution points with higher accuracy, and it will be possible to create map data that more accurately reflects the detection results of ditch caution points.

[0049] Second Embodiment In a second embodiment, an example of utilizing the probe information and information on cautionary spots for ditches stored in the server 200 will be described.

[0050] 5 is a diagram showing the configuration of a road ditch information generation system according to embodiment 2. The configuration of the road ditch information generation system according to embodiment 2 is obtained by adding an information distribution unit 10, a danger area map creation unit 11, and a submerged feature storage unit 12 to the server 200 in addition to the configuration of embodiment 1 (FIG. 1). It is not necessary for all of these units to be added to the server 200; only some of these units may be added.

[0051] The information distribution unit 10 distributes various types of information stored in the server 200. Examples of the information to be distributed include information on ditch caution points stored in the ditch caution point storage unit 8, map data (map data including information on ditch caution points) stored in the map database 9, video data included in the probe information stored in the probe information storage unit 6, and information generated by a danger area map creation unit 11 and an impounded feature storage unit 12 (described later). Possible destinations for the information include vehicles (including the probe vehicle 100), companies (for example, companies that perform construction work on ditches, guardrails, etc.), and local governments (such as city halls), but there are no restrictions on the destinations.

[0052] The danger area map creation unit 11 identifies areas where there are points where caution is needed regarding roadside ditches that may be flooded (hereinafter referred to as "danger areas") based on the map data in the map database 9, and creates a danger area map showing the location or extent of the danger areas. Whether a point is at risk of flooding may be determined from information such as the presence or frequency of flooding in the past, or from information such as the size of the roadside ditches and the surrounding topography.

[0053] The danger area map may include information on the danger level of gutters within each danger area (see Variation 2 of Embodiment 1). Furthermore, the danger area map creation unit 11 may create a real-time danger area map that indicates danger areas that are currently at risk of flooding, based on weather forecast information.

[0054] The submerged feature storage unit 12 detects features with a certain height or more as submerged features that are not submerged even when flooded, based on the probe information stored in the probe information storage unit 6, specifically, the image of the area around the probe vehicle 100 and the position information of the probe vehicle 100 when the image of the area was captured, and stores the positions of the submerged features. Examples of submerged features include utility poles, buildings, and large billboards. Information on the positions of the submerged features is distributed to the vehicle by the information distribution unit 10, and can be used in the vehicle's driving assistance device or navigation system to estimate the vehicle's position and drivable area when roads are flooded. The positions of the submerged features may also be displayed on a map displayed by the vehicle's navigation system.

[0055] <Embodiment 3> In embodiment 3, an example of vehicle driving assistance provided by the side ditch information generating system is shown. Vehicle driving assistance may be provided by an on-board device (including the probe device 110) provided in each vehicle, or may be provided by the server 200. Furthermore, driving assistance for multiple vehicles may be provided collectively by the server 200. In the following, it is assumed that the vehicle whose driving is assisted by the side ditch information generating system is the probe vehicle 100, but the vehicle may be a vehicle other than the probe vehicle 100.

[0056] For example, if there is a dangerous area (an area where there is a caution point for a side ditch that may be flooded) ahead of the probe vehicle 100, the side ditch information generating system may suggest to the driver of the probe vehicle 100 to detour around the dangerous area. Furthermore, the side ditch information generating system may issue a warning to the driver of the probe vehicle 100 to notify the driver of the existence of the dangerous area via a drive recorder, a car navigation system, or a smartphone of the driver of the probe vehicle 100.

[0057] In addition, if the location where the probe vehicle 100 is traveling is flooded, the gutter information generating system may display, on the display device of the probe vehicle 100, a surrounding image taken at the location when it was not flooded.

[0058] For example, assume that the probe vehicle 100 is traveling on a road R1 shown in Fig. 6. A center line C1 and outer roadway lines (hereinafter simply referred to as "outer lines") E1 and E2 are drawn on the road R1, and gutters G1 and G2 are provided on both sides of the road R1. When the road R1 is not flooded, the camera 102 captures a surrounding image (hereinafter referred to as a forward image) as shown in Fig. 7.

[0059] However, when the road R1 is flooded, the road R1, center line C1, outer lines E1 and E2, and ditches G1 and G2 are submerged, and the surrounding image captured by the camera 102 makes these features unclear, as shown in Figure 8. In this case, the ditches information generating system acquires the surrounding image (Figure 7) of the road R1 before it was submerged, which is stored as probe information in the probe information storage unit 6, and displays it on the display device of the probe vehicle 100. The driver of the probe vehicle 100 can recognize the width of the road R1 and the positions of the center line C1, outer lines E1 and E2, and ditches G1 and G2 by looking at the image on the display device.

[0060] In addition, if the location where the probe vehicle 100 is traveling is flooded, the gutter information generation system may superimpose an image to distinguish between the road and the gutter at that location on the road at that location using a transparent display device.

[0061] A transmissive display device is a type of display device that displays information directly in the driver's field of vision by displaying it on the windshield or a transparent screen that the driver can see through. A head-up display, for example, is a transmissive display device. In a transmissive display device, the view seen by the driver through the windshield becomes the background of the screen, so an image can be displayed superimposed on the actual view.

[0062] For example, when the probe vehicle 100 travels along a flooded road R1 ( FIG. 6 ), the roadside ditch information generating system extracts the edges of the road R1, the center line C1, the outer lines E1 and E2, and the side ditches G1 and G2 from the surrounding image of the road R1 before it was submerged ( FIG. 7 ), which is stored as probe information in the probe information storage unit 6, creates an image that highlights these, and displays it on the transmissive display device of the probe vehicle 100. To the driver, as shown in FIG. 9 , the image highlighting the edges of the road R1, the center line C1, the outer lines E1 and E2, and the side ditches G1 and G2 appears superimposed on their respective positions. This allows the driver to accurately recognize the width of the road R1 and the positions of the center line C1, the outer lines E1 and E2, and the side ditches G1 and G2. If it is only necessary to distinguish between the road and the side ditches, the image highlighting the center line C1 may be omitted.

[0063] In addition, if the location where the probe vehicle 100 is traveling is flooded, the gutter information generation system may use a road surface illumination device to project an image onto the road (or the water surface on the road) at that location to distinguish between the road and the gutter at that location.

[0064] The road surface illumination device is a display device that projects an image onto the road surface, and like a transmission type display device, can display an image superimposed on an actual scene. By projecting an image similar to that shown in Figure 9 onto the road surface, the transmission type display device allows the driver to accurately recognize the width of the road R1, the center line C1, the outer lines E1 and E2, and the positions of the side ditches G1 and G2.

[0065] Even if the above-described driving assistance is performed by the side ditch information generating system, there is still a possibility that the probe vehicle 100 falls into a side ditch. Therefore, the side ditch information generating system may be provided with a function to detect the probe vehicle 100 falling into a side ditch, so that when the probe vehicle 100 is detected to have fallen into a side ditch, the side ditch information generating system may send a message requesting rescue to pre-registered contact points (for example, a fire department, the driver's family, etc.).

[0066] The function of detecting whether the probe vehicle 100 has fallen into a road ditch can be realized, for example, by measuring the angular velocity of the probe vehicle 100 with an inertial measurement unit (IMU) and detecting an abnormal angular velocity value. The IMU provided in the drive recorder may be used. The message may be transmitted by an in-vehicle device provided in each vehicle, or by the server 200 that has received a notification of the fall from the in-vehicle device.

[0067] <Hardware Configuration Example> The probe device 110 and the server 200 constituting the road ditch information generating system are realized by, for example, a processing circuit 50 shown in FIG. 10 . That is, the probe device 110 includes a processing circuit 50 for acquiring position information of the probe vehicle 100, acquiring a surrounding image that is an image of the area around the probe vehicle 100, and detecting a road ditch presence point, which is a point where a road ditch is present, based on the surrounding image of the probe vehicle 100 and the position information of the probe vehicle 100 at the time the surrounding image was captured. The server 200 also includes a processing circuit 50 for detecting a road ditch caution point, which is a point where the probe vehicle 100 may enter a road ditch, from the road ditch presence points based on the surrounding image, and storing information about the road ditch caution point. The processing circuit 50 may be dedicated hardware or may be configured using a processor (also called a central processing unit (CPU), processing device, arithmetic device, microprocessor, microcomputer, or DSP (Digital Signal Processor)) that executes a program stored in memory.

[0068] When the processing circuitry 50 is dedicated hardware, the processing circuitry 50 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof. The functions of the components of the probe device 110 and the server 200 may be realized by individual processing circuits, or the functions may be collectively realized by a single processing circuit.

[0069] The probe device 110 and the server 200 can also be realized by, for example, a processor 51 and a memory 52 shown in FIG. 11 . In this case, the functions of the components of the probe device 110 and the server 200 are realized by software or the like (software, firmware, or a combination of software and firmware). The software or the like is written as a program and stored in the memory 52. ​​The processor 51 realizes the functions of each part by reading and executing the program stored in the memory 52. ​​That is, the probe device 110 includes the memory 52 for storing a program that, when executed by the processor 51, results in the following processes: acquiring position information of the probe vehicle 100; acquiring a surrounding image that is an image of the periphery of the probe vehicle 100; and detecting a gutter presence point that is a point where a gutter is present on a road based on the surrounding image of the probe vehicle 100 and the position information of the probe vehicle 100 at the time the surrounding image was captured. The server 200 also includes a memory 52 for storing a program that ultimately executes a process of detecting, from among the gutter locations based on the surrounding image, gutter caution locations where the probe vehicle 100 may enter a gutter from the road, and a process of storing information about the gutter caution locations. In other words, these programs can be said to cause a computer to execute the procedures and methods of the operation of the components of the probe device 110 and the server 200.

[0070] Here, the memory 52 may be, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), or an EEPROM (Electrically Erasable Programmable Read Only Memory), a HDD (Hard Disk Drive), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, a DVD (Digital Versatile Disc), and a drive device for such a disk, or any other storage medium that will be used in the future.

[0071] The above describes a configuration in which the functions of the components of the probe device 110 and the server 200 are realized either by hardware or software, etc. However, this is not a limitation, and the probe device 110 and the server 200 may be configured such that some of the components are realized by dedicated hardware and other components are realized by software, etc. For example, it is possible to realize the functions of some of the components by the processing circuit 50 as dedicated hardware, and to realize the functions of other components by the processing circuit 50 as the processor 51 reading and executing a program stored in the memory 52.

[0072] As described above, the probe device 110 and the server 200 can realize the above-described functions by hardware, software, or a combination of these.

[0073] It is possible to freely combine the embodiments, and to modify or omit the embodiments as appropriate.

[0074] The above description is illustrative in all respects, and it is understood that countless variations not illustrated can be envisioned.

[0075] 100 Probe vehicle, 101 Locator, 102 Camera, 103 Communication device, 110 Probe device, 200 Server, 300 Network, 1 Location information acquisition unit, 2 Image acquisition unit, 3 Ditch presence point detection unit, 4 Probe information generation unit, 5 Communication unit, 6 Probe information storage unit, 7 Ditch caution point detection unit, 8 Ditch caution point storage unit, 9 Map database, 10 Information distribution unit, 11 Danger area map creation unit, 12 Submerged feature storage unit, 13 Report processing unit, 50 Processing circuit, 51 Processor, 52 Memory, R1 Road, C1 Center line, E1 Outer line, E2 Outer line, G1 Ditch, G2 Ditch.

Claims

1. A ditch information generation system comprising: a location information acquisition unit that acquires location information of a vehicle; an image acquisition unit that acquires surrounding image, which is image captured of the area around the vehicle; a gutter presence point detection unit that detects gutter presence points, which are points where a gutter is located on a road, based on the surrounding image of the vehicle and the location information of the vehicle at the time the surrounding image was captured; a gutter caution point detection unit that detects gutter caution points, which are points where the vehicle may enter the gutter from the road, from among the gutter presence points based on the surrounding image; and a gutter caution point storage unit that stores information about the gutter caution points.

2. The gutter information generating system according to claim 1, further comprising an information distribution unit that distributes information about the gutter caution points.

3. The gutter information generating system according to claim 1, wherein the position information acquisition unit, the image acquisition unit, and the gutter presence point detection unit are arranged in the vehicle, the gutter caution point detection unit and the gutter caution point storage unit are installed in a server capable of communicating with the vehicle, and the surrounding image of the vehicle, the position information, and the information on the gutter presence point are transmitted from the vehicle to the server as probe information.

4. The gutter information generating system according to claim 1, wherein the location information acquisition unit acquires the location information of the vehicle from a locator of the vehicle's drive recorder, and the image acquisition unit acquires the image of the surroundings of the vehicle from a camera of the drive recorder.

5. The road ditch information generation system according to claim 1, wherein the road ditch caution spot detection unit detects a spot where there is no guardrail or fence between the road and the road ditch as the road ditch caution spot.

6. The gutter information generation system described in claim 1, wherein the gutter caution point detection unit learns the characteristics of images of gutters that the vehicle may enter from past images of the surrounding area, and determines whether the vehicle may enter a gutter in the newly obtained surrounding image based on the learning results.

7. The gutter information generation system according to claim 1, wherein the gutter caution point detection unit determines the danger level of the gutter based on the width and depth of the gutter, and adds information about the danger level of the gutter to information about the gutter caution point.

8. The gutter information generating system according to claim 7, wherein the gutter caution point detection unit determines the current danger level of the gutter based on weather forecast information.

9. The gutter information generation system described in claim 7, wherein the gutter caution point detection unit learns the relationship between the characteristics of the gutter image and the danger level from past surrounding images, and determines the danger level of the gutter in the newly obtained surrounding image based on the learning results.

10. The gutter information generation system according to claim 1, further comprising a danger area map creation unit that creates a danger area map that indicates danger areas, which are areas where the gutter caution points that are at risk of flooding exist.

11. The gutter information generation system according to claim 10, wherein the danger area map creation unit creates a danger area map indicating danger areas that are currently at risk of flooding based on weather forecast information.

12. The gutter information generation system according to claim 7, wherein the gutter caution spot detection unit determines the priority of installing a new guardrail or fence for the gutter caution spot where the danger level of the gutter is above a certain level based on at least one of the number of accidents, traffic volume, the presence or absence of a guardrail, and the presence or absence of a caution warning sign, and assigns the priority information to the information about the gutter caution spot.

13. The road ditch information generating system according to claim 10, which, if the dangerous area is ahead of the vehicle, suggests to the driver of the vehicle that they take a detour around the dangerous area.

14. The gutter information generating system according to claim 10, wherein if the dangerous area is located ahead of the vehicle, a warning is given to the driver via the vehicle's drive recorder, car navigation system, or the driver's smartphone.

15. The road ditch information generating system according to claim 1, wherein, when the location where the vehicle is traveling is flooded, the surrounding image captured at the location when it was not flooded is displayed on the vehicle's display device.

16. The gutter information generation system according to claim 1, wherein, if the location where the vehicle is traveling is flooded, an image for distinguishing between the road and the gutter at that location is superimposed on the road at that location using a transparent display device.

17. The gutter information generation system according to claim 1, wherein, if the location where the vehicle is traveling is flooded, an image for distinguishing between the road and the gutter at that location is projected onto the road at that location using a road surface illumination device.

18. The gutter information generating system according to claim 1, wherein, when it detects that the vehicle has fallen into a gutter, a message requesting rescue is sent to a pre-registered contact.

19. A drainage ditch information generation system as described in claim 1, further comprising an impermeable feature memory unit that detects features having a height above a certain level as impermeable features based on the image of the surroundings of the vehicle and the position information of the vehicle at the time the image of the surroundings was taken, and stores the positions of the impermeable features.

20. A method for generating side ditch information, in which a position information acquisition unit of the side ditch information generation system acquires position information of a vehicle, an image acquisition unit of the side ditch information generation system acquires surrounding image which is image captured of the area around the vehicle, a side ditch existence point detection unit of the side ditch information generation system detects side ditch existence points which are points where a side ditch is located on a road based on the surrounding image of the vehicle and the position information of the vehicle at the time the surrounding image was captured, a side ditch caution point detection unit of the side ditch information generation system detects side ditch caution points which are points where the vehicle may enter the side ditch from the road based on the surrounding image, and a side ditch caution point storage unit of the side ditch information generation system stores information about the side ditch caution points.

Images