Feature identification device, feature identification method, and feature identification computer program

Abstract

To specify a sort of a lane separation facility appropriately.SOLUTION: A feature specifying device stores in a storage unit, passage information for indicating whether a position is included in a confrontation traffic section and lane separation facility information for indicating a sort of lane separation facility which separates a road at that position by a traveling direction, associated with each position on a road; and depending on whether a predetermined position on a road has the lane separation facility information associated with it and whether the predetermined position is included in the confrontation traffic section based on the passage information, a feature specifying device specifies the sort of the lane separation facility based on an image taken of the lane separation facility at the predetermined position, using a first algorithm capable of specifying the sort of the lane separation facility based on an image taken of the lane separation facility, or a second algorithm capable of specifying a separation pole and a separation wire rope of the lane separation facility with a higher degree of certainty than the first algorithm.SELECTED DRAWING: Figure 6

Description

[Technical field]

[0001] The present disclosure relates to a feature identification device, a feature identification method, and a feature identification computer program for identifying a type of feature depicted in an image. [Background technology]

[0002] There is known a map generating device that collects images of the surroundings of a vehicle, which are acquired by a sensor mounted on the vehicle, and generates a high-precision map that shows the surroundings with high accuracy using information on the surroundings detected from the images. The generated high-precision map is used for automatic driving control of the vehicle. The surroundings include lane separation facilities that separate the roads around the vehicle according to the driving direction.

[0003] The map generating device described in Patent Document 1 detects candidate median strip information from a street view image corresponding to a target road, and modifies the candidate median strip information based on a preset modification policy.

[0004] In the map data update system described in Patent Document 1, an in-vehicle terminal obtains map data for update from a map update server and updates the map data of the in-vehicle terminal. When there is update data after the start of a temporary road change, the map update server instructs the update data to be temporarily used and distributes the update data. When there is update data after the end of the temporary road change, the map update server instructs the use of map data before the start of the temporary road change. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2021-99489 Summary of the Invention [Problem to be solved by the invention]

[0006] Lane separation facilities include, for example, separation poles, separation wire ropes, and guard rails. Separation poles are multiple poles arranged at a predetermined interval, and no wire ropes are installed. Separation wire ropes are multiple poles arranged at a predetermined interval, and wire ropes are installed. Guard rails are multiple poles arranged at a predetermined interval, and rail-shaped steel materials are installed. In opposing traffic sections such as temporary service sections, separation poles or separation wire ropes are often installed as lane separation facilities.

[0007] In such two-way traffic sections, separator poles are less effective at preventing vehicles from slipping into the oncoming lane in the event of an accident than separator wire ropes or guardrails. In two-way traffic sections, it is preferable to appropriately identify the type of lane separation equipment, and when the lane separation equipment is a separator pole, to maintain safety similar to that when the lane separation equipment is not a separator pole, for example, by using driving control that makes it more difficult for vehicles to slip into the oncoming lane.

[0008] In order to identify the type of lane separation equipment from the surrounding images, especially whether it is a separation pole or a separation wire rope, it is necessary to detect the presence or absence of the wire rope. However, since the wire rope is generally long and thin with a diameter of about 18 mm, it is difficult to properly detect it from the image.

[0009] An object of the present disclosure is to provide a feature identification device that can appropriately identify the type of lane division facility. [Means for solving the problem]

[0010] The gist of the present disclosure is as follows.

[0011] (1) A map storage unit that stores, in association with each position on a road, traffic information indicating whether the position is included in a two-way traffic section, and lane separation facility information indicating at least whether the lane separation facility that separates the road according to the direction of travel at that position is a separation pole consisting of multiple poles arranged at a predetermined interval and no wire rope installed, a separation wire rope consisting of multiple poles arranged at a predetermined interval and the wire rope installed, or something other than that; an identification unit that, when the lane separation equipment information is not associated with a predetermined position on the road and it is determined based on the traffic information that the predetermined position is not included in the oncoming traffic section, identifies a type of the lane separation equipment based on an image of the lane separation equipment at the predetermined position using a first algorithm capable of identifying a type of the lane separation equipment based on an image of the lane separation equipment, and, when the lane separation equipment information is not associated with the predetermined position and it is determined based on the traffic information that the predetermined position is included in the oncoming traffic section, identifies a type of the lane separation equipment based on an image of the lane separation equipment at the predetermined position using a second algorithm capable of identifying the separation pole and the separation wire rope of the lane separation equipment with a higher degree of certainty than the first algorithm; A feature identification device comprising:

[0012] (2) The identification unit executes, as the first algorithm, at least a detection process for detecting an object from the image by inputting the image into a pre-trained detector, and a first identification process for identifying the type of the lane separation facility based on the detected object, and, as the second algorithm, at least a second identification process for extending each of the three or more lines so that they are continuous from one to the other of the adjacent poles when a difference in spacing between adjacent lines among the three or more extended lines is smaller than a predetermined error threshold, identifying the lane separation facility as the separation wire rope,

[0013] (3) In the case where the lane dividing facility information is associated with the specified location, the identification unit identifies the type of the lane dividing facility based on an image of the lane dividing facility taken at the specified location by a third algorithm including the detection process, the first identification process, and a type determination process for determining whether the type of the lane dividing facility identified in the first identification process is the same as the type represented in the lane dividing facility information.

[0014] (4) In the case where the lane separation facility information is associated with the specified location, the identification unit identifies the type of the lane separation facility based on an image of the lane separation facility taken at the specified location by a third algorithm including the detection process, the first identification process, and an appearance determination process for determining whether the object detected by the detection process has a standard appearance of the type of lane separation facility represented in the lane separation facility information associated with the specified location. This is the feature identification device described in (2) or (3) above.

[0015] (5) A memory unit stores, in association with each position on a road, traffic information indicating whether the position is included in a two-way traffic section and lane separation facility information indicating at least whether the lane separation facility that separates the road according to the direction of travel at that position is a separation pole consisting of multiple poles arranged at a predetermined interval and no wire rope installed, a separation wire rope consisting of multiple poles arranged at a predetermined interval and the wire rope installed, or something other than that, if the lane separation facility information is not associated with a predetermined position on the road and it is determined based on the traffic information that the predetermined position is not included in the oncoming traffic section, a first algorithm capable of identifying a type of the lane separation facility based on an image of the lane separation facility is used to identify a type of the lane separation facility based on an image of the lane separation facility at the predetermined position; if the lane separation facility information is not associated with the predetermined location and it is determined based on the traffic information that the predetermined location is included in the oncoming traffic section, a second algorithm is used to identify the type of the lane separation facility based on an image of the lane separation facility taken at the predetermined location, the second algorithm being capable of identifying the separation pole and the separation wire rope of the lane separation facility with a higher degree of certainty than the first algorithm; A method for identifying a feature, comprising:

[0016] (6) When lane separation equipment information is not associated with a predetermined position on a road and the predetermined position is determined not to be included in the oncoming traffic section based on traffic information indicating for each position on the road whether the position is included in the oncoming traffic section, a first algorithm capable of identifying the type of lane separation equipment based on an image of the lane separation equipment is used to identify the type of lane separation equipment based on an image of the lane separation equipment at the predetermined position, and the lane separation equipment information is information at least indicating whether the lane separation equipment that separates the road by driving direction at each position on the road is a separation pole that is a plurality of poles arranged at a predetermined interval and has no wire rope installed, a separation wire rope that has the wire rope installed on a plurality of poles arranged at a predetermined interval, or something other than the above; if the lane separation facility information is not associated with the predetermined location and it is determined based on the traffic information that the predetermined location is included in the oncoming traffic section, identifying a type of the lane separation facility based on an image of the lane separation facility at the predetermined location using a second algorithm that can identify the separation pole and the separation wire rope of the lane separation facility with a higher degree of certainty than the first algorithm; A computer program for identifying geographical features that causes a computer to execute the above.

[0017] According to the feature identification device according to the present disclosure, it is possible to appropriately identify the type of lane division facility. [Brief description of the drawings]

[0018] [Figure 1] FIG. 1 is a schematic diagram illustrating a first example of a lane separation facility. [Diagram 2] FIG. 11 is a schematic diagram illustrating a second example of a lane separation facility. [Diagram 3] 1 is a schematic configuration diagram of a vehicle on which a feature identification device is mounted. [Figure 4] FIG. 2 is a hardware configuration diagram of the feature identifying device. [Diagram 5] FIG. 2 is a functional block diagram of a processor included in the feature identifying device. [Figure 6] 13 is a flowchart of a feature identification process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] The feature identification device that can appropriately identify the type of lane division facility will be described in detail below with reference to the drawings. The feature identification device stores traffic information and lane division facility information in a map storage unit in association with each position on a road.

[0020] The traffic information is information indicating whether or not a given position on a road is included in a two-way traffic section. The lane separation information is information indicating at least whether the lane separation equipment that separates the road for each direction of travel at a given position on a road is a separation pole, a separation wire pole, or something else. A separation pole is a lane separation equipment consisting of multiple poles arranged at a predetermined interval and no wire rope is installed. A separation wire rope is a lane separation equipment consisting of multiple poles arranged at a predetermined interval and a wire rope installed on them.

[0021] FIG. 1 is a schematic diagram illustrating a first example of a lane separation facility, and FIG. 2 is a schematic diagram illustrating a second example of a lane separation facility.

[0022] FIG. 1 shows a road having a lane L11 defined by lane markings LL11 and LL12, and a lane L12 defined by lane markings LL13 and LL14, the lane L11 having a different running direction from the lane L11. The lanes L11 and L12 are separated according to their running directions by poles P11-P15 and wire ropes WR1-WR3 installed on the poles P11-P15. FIG. 1 shows a standard separation wire rope, which is a lane separation facility separating the lanes L11 and L12. In the standard separation wire rope, the poles P11-P15 have a height of, for example, about 1000 mm, and are installed at intervals of, for example, 4000 mm.

[0023] Fig. 2 shows a road having a lane L21 defined by lane dividing lines LL21 and LL22, and a lane L22 defined by lane dividing lines LL23 and LL24, the lane L21 having a different running direction from the lane L21. The lanes L21 and L22 are separated by poles P21-P23 according to their running directions. Fig. 2 shows a standard separation pole, which is a lane separation facility separating the lanes L21 and L22. In the standard separation pole, the height of the poles P21-P23 is, for example, about 650 mm, and they are installed at intervals of, for example, 10,000 mm.

[0024] The feature identification device determines whether lane separation facility information is associated with a predetermined position on a road. The feature identification device also determines whether the predetermined position is included in an oncoming traffic section based on traffic information.

[0025] When lane dividing facility information is not associated with the predetermined location and it is determined that the predetermined location is not included in the oncoming traffic section, the feature identification device identifies the type of the lane dividing facility based on an image of the lane dividing facility taken at the predetermined location by a first algorithm. The first algorithm is an algorithm capable of identifying the type of the lane dividing facility based on an image of the lane dividing facility.

[0026] If no lane separation facility information is associated with the predetermined location and it is determined that the predetermined location is included in a two-way traffic section, the feature identification device uses a second algorithm to identify the type of the lane separation facility based on an image of the lane separation facility captured at the predetermined location. The second algorithm is an algorithm that can identify separation poles and separation wire ropes of the lane separation facility with a higher degree of certainty than the first algorithm.

[0027] FIG. 3 is a schematic configuration diagram of a vehicle on which a feature identification device is mounted.

[0028] The vehicle 1 has a peripheral camera 2, a GNSS (Global Navigation Satellite System) receiver 3, a storage device 4, and a feature identification device 5. The peripheral camera 2, the GNSS receiver 3, the storage device 4, and the feature identification device 5 are communicatively connected via an in-vehicle network that complies with a standard such as a controller area network.

[0029] The surrounding camera 2 is an example of a sensor for generating a surrounding image according to the surrounding conditions of the vehicle 1. The surrounding camera 2 has a two-dimensional detector configured with an array of photoelectric conversion elements sensitive to visible light, such as a CCD or C-MOS, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. The surrounding camera 2 is disposed, for example, at the front upper part of the vehicle interior, facing forward. The surrounding camera 2 photographs the surrounding conditions of the vehicle 1 through the windshield or rear window at a predetermined photographing period (for example, 1 / 30 second to 1 / 10 second), and outputs a surrounding image showing the surrounding conditions. The surrounding image is an example of an image photographed of a lane separation facility.

[0030] The GNSS receiver 3 is an example of a positioning sensor, which receives GNSS signals from GNSS satellites at predetermined intervals by a GNSS antenna (not shown) and determines the self-position of the vehicle 1 based on the received GNSS signals. The GNSS receiver 3 outputs a positioning signal representing the positioning result of the self-position of the vehicle 1 based on the GNSS signals to the feature identification device 5 via the in-vehicle network at predetermined intervals.

[0031] The storage device 4 is an example of a map storage unit, and includes, for example, a non-volatile semiconductor memory or a hard disk device. The storage device 4 stores map information including traffic information and lane division facility information in association with each position on the road.

[0032] The traffic information is information that indicates whether each position on a road is included in a two-way traffic section, and is represented by, for example, the coordinates of the start point and the end point of the two-way traffic section.

[0033] The lane separation facility information is information that indicates the type of lane separation facility that separates the road for each driving direction at each position on the road. The types of lane separation facilities include at least separation poles and separation wire ropes. The separation poles are multiple poles arranged at a predetermined interval and have no wire rope installed. The separation wire rope is a wire rope installed on multiple poles arranged at a predetermined interval.

[0034] The feature identification device 5 is an ECU (Electronic Control Unit) having a communication interface circuit, a memory, and a processor. The feature identification device 5 receives a peripheral image from the peripheral camera 2 via the communication interface, and identifies the type of lane separation facility shown in the peripheral image.

[0035] The feature identification device 5 acquires a peripheral image from the peripheral camera 2 via the communication interface circuit. The feature identification device 5 inputs the peripheral image to a classifier that has been trained in advance to detect features from images, and identifies the type of lane separation facility based on the object detected from the peripheral image.

[0036] 4 is a schematic diagram of the hardware of the feature identifying device 5. The feature identifying device 5 comprises a communication interface 51, a memory 52, and a processor 53.

[0037] The communication interface 51 is an example of a communication unit, and has a communication interface circuit for connecting the feature identification device 5 to an in-vehicle network. The communication interface 51 supplies the received data to the processor 53. In addition, the communication interface 51 outputs the data supplied from the processor 53 to the outside.

[0038] The memory 52 is another example of a map storage unit, and includes a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 52 temporarily stores map information read from the storage device 4. The memory 52 also stores various data used in processing by the processor 53, such as the processing contents executed as the first algorithm and the second algorithm. The memory 52 also stores various application programs, such as a computer program for identifying features that causes a computer to execute a feature identification method.

[0039] The processor 53 is an example of a control unit, and includes one or more processors and their peripheral circuits. The processor 53 may further include other arithmetic circuits, such as a logic arithmetic unit, a numerical arithmetic unit, or a graphics processing unit.

[0040] FIG. 5 is a functional block diagram of the processor 53 included in the feature identifying device 5.

[0041] The processor 53 of the feature identifying device 5 has an identifying unit 531 as a functional block. The identifying unit 531 is a functional module implemented by a program executed on the processor 53. A computer program that realizes the functions of the identifying unit 531 of the processor 53 may be provided in a form recorded on a computer-readable portable recording medium such as a semiconductor memory, a magnetic recording medium, or an optical recording medium. Alternatively, each of these units of the processor 53 may be implemented in the feature identifying device 5 as an independent integrated circuit, microprocessor, or firmware.

[0042] The identification unit 531 refers to the map information stored in the storage device 4 and determines whether lane dividing facility information is associated with a predetermined position on the road where the lane dividing facility is photographed. The identification unit 531 also refers to the traffic information included in the map information stored in the storage device 4 and determines whether the predetermined position is included in an oncoming traffic section.

[0043] The identification unit 531 identifies the type of the lane separation facility based on a surrounding image of the lane separation facility captured at a predetermined position. In identifying the type of the lane separation facility, the identification unit 531 uses different algorithms depending on whether lane separation facility information is associated with the predetermined position and whether the predetermined position is determined to be included in a two-way traffic section.

[0044] When it is determined that no lane separation facility information is associated with the predetermined position and that the predetermined position is not included in the oncoming traffic section, the identification unit 531 identifies the type of the lane separation facility based on the surrounding image by a first algorithm. The first algorithm is an algorithm that can identify the type of the lane separation facility based on an image of the lane separation facility.

[0045] The first algorithm includes, for example, a detection process for detecting an object area and a type from an image, and a first identification process for identifying the type of the lane separation facility based on the detected type.

[0046] The identification unit 531 executes the detection process by inputting the image to a classifier. The classifier can be a convolutional neural network (CNN) having multiple convolution layers connected in series from the input side to the output side, which has been trained in advance to detect areas and types of predetermined objects and features from an image. The CNN is trained in advance according to a predetermined learning method such as backpropagation using a large number of images depicting objects used in lane separation facilities such as poles and wire ropes, and features such as lane markings, and the types of the objects, as teacher data, so that the CNN operates as a classifier that detects areas and types of features such as objects used in lane separation facilities and lane markings.

[0047] In the first identification process, when a wire rope and a pole are detected from the peripheral image, the identification unit 531 identifies the type of the lane separation facility as a separation wire rope. In addition, in the first identification process, when a wire rope is not detected from the peripheral image and a pole is detected, the identification unit 531 identifies the type of the lane separation facility as a separation pole.

[0048] If no lane separation facility information is associated with the predetermined position and it is determined that the predetermined position is included in a two-way traffic section, the identification unit 531 identifies the type of lane separation facility based on the surrounding image by a second algorithm. The second algorithm is an algorithm that can identify separation poles and separation wire ropes of lane separation facilities with a higher degree of certainty than the first algorithm.

[0049] The second algorithm includes, for example, a detection process similar to the first algorithm and a second identification process.

[0050] In the second identification process, the identification unit 531 determines whether multiple poles are detected by the detection process, and if multiple poles are detected, determines whether three or more lines extending from one adjacent pole to the other among the multiple detected poles are detected.

[0051] When three or more lines extending from one of the adjacent poles to the other are detected, the specifying unit 531 extends each of the three or more lines so that they continue from one of the adjacent poles to the other.

[0052] Furthermore, the identification unit 531 judges whether or not the difference in the intervals between adjacent lines among the extended three or more lines is smaller than a predetermined error threshold. If it is judged that the difference in the intervals between the adjacent lines is smaller than the predetermined error threshold, the identification unit 531 identifies the type of the lane separation facility as a separating wire rope. The error threshold is set, for example, as a ratio (for example, ±10%) of the difference between the interval between two adjacent lines among the three or more lines and the interval between the other two adjacent lines, and is stored in advance in the memory 52. ​​One of the two adjacent lines and one of the other two adjacent lines may be the same line.

[0053] The type of lane separation facility identified by the first algorithm or the second algorithm can be used for automatic driving control of the vehicle 1 by a driving control device (not shown) mounted on the vehicle 1. For example, when the type of lane separation facility is identified as a separation pole, the driving control device controls the driving of the vehicle 1 so that the speed of the vehicle 1 is lower than when the type of lane separation facility is identified as a separation wire rope.

[0054] When lane division facility information is associated with a predetermined position, the identification unit 531 identifies the type of the lane division facility based on the surrounding image by the third algorithm.

[0055] The third algorithm includes, for example, a detection process and a first identification process similar to the first algorithm, and a type determination process that determines whether the type of lane division facility identified in the first identification process is the same as the type represented in the lane division facility information associated with a specified location.

[0056] If it is determined in the type determination process that the type of the lane separation facility identified in the first identification process is not the same as the type represented in the lane separation facility information, the identification unit 531 identifies the lane separation facility information associated with the position as the lane separation facility information that should be updated.

[0057] The third algorithm may include, instead of or in addition to the type determination process, an appearance determination process that determines whether an object detected in the detection process has the standard appearance of a lane separation facility of the type represented in the lane separation facility information associated with a specified location.

[0058] Standard appearances (e.g., pole heights and installation intervals) of lane separation facilities for each type, such as separation wire ropes and separation poles, are stored in advance in the memory 52. ​​The identification unit 531 estimates the actual height of the area determined to be a pole, for example, based on the ratio of the length of a horizontal straight line passing through the lower end of the area determined to be a pole divided by a pair of areas determined to be lane dividing lines, and the actual interval of the lane dividing lines stored in advance in the memory 52. ​​The identification unit 531 also estimates the actual length of the interval of the area determined to be a pole, for example, based on the length of a horizontal straight line passing through the lower end of one of the areas determined to be a pole divided by a pair of areas determined to be lane dividing lines, the length of a horizontal straight line passing through the lower end of another area adjacent to the one area divided by a pair of areas determined to be lane dividing lines, the actual interval of the lane dividing lines stored in advance in the memory 52, and shooting parameters such as the focal length of the imaging optical system of the peripheral camera 2 stored in advance in the memory 52.

[0059] In the appearance determination process, the identification unit 531 determines whether or not the object detected in the detection process has a standard appearance for each type of lane separation facility stored in the memory 52. ​​When it is determined that the object identified in the detection process does not have the standard appearance of the lane separation facility of the type represented in the lane separation facility information associated with a predetermined position, the identification unit 531 identifies the lane separation facility information associated with the position as lane separation facility information that should be updated.

[0060] The lane division equipment information to be updated, identified by the type determination process or the appearance determination process in the third algorithm, is transmitted to a map information management server (not shown) via a data communication module (not shown) that communicates with external devices via the communication interface 51 and the communication network. When the number or ratio of lane division equipment information to be updated exceeds a predetermined update threshold, the map information management server creates map information with the lane division equipment information updated.

[0061] The detection process of the first to third algorithms may include pre-processing including binarization of an image and thinning of the binarized image. The identification unit 531 can perform the pre-processing by applying a known binarization filter and thinning filter to the surrounding image.

[0062] 6 is a flowchart of the feature identification process. The processor 53 of the feature identification device 5 executes the feature identification process shown in FIG. 6 every time an image of a lane separation facility is input.

[0063] First, the specification unit 531 of the processor 53 determines whether or not lane division facility information is associated with a predetermined position on a road where an image of the lane division facility is captured (step S1).

[0064] When it is determined that the lane separation facility information is not associated with the predetermined position (step S1: N), the specification unit 531 determines whether or not the predetermined position is included in an oncoming traffic section (step S2).

[0065] If it is determined that the specified position is not included in the oncoming traffic section (step S2: N), the identification unit 531 identifies the type of lane separation facility based on the image using the first algorithm (step S3), and terminates the feature identification process.

[0066] If it is determined that the specified position is included in the oncoming traffic section (step S2: Y), the identification unit 531 identifies the type of lane separation facility based on the image using the second algorithm (step S4), and ends the feature identification process.

[0067] If it is determined that lane separation facility information is associated with a specified location (step S1: Y), the identification unit 531 uses the third algorithm to identify the type of lane separation facility based on the image (step S5), and terminates the feature identification process.

[0068] By executing the feature identification process in this manner, the feature identification device 5 can appropriately identify the type of the lane division facility.

[0069] In the present embodiment, an example has been described in which the feature identification device is mounted on a vehicle as an ECU. However, the embodiment of the feature identification device is not limited to this. For example, the feature identification device may be implemented as a server capable of receiving a surrounding image from a vehicle. In this case, the surrounding image may be transmitted from the vehicle to the server via a communication network, or may be transmitted via a data medium. The type of lane separation facility identified by the feature identification device implemented as a server can be used to create map information by a map information management server. The created map information is distributed, for example, via a communication network and stored in the storage device 4 of the vehicle 1, and used for automatic driving control of the vehicle 1.

[0070] It should be understood that those skilled in the art can make various changes, substitutions, and alterations thereto without departing from the spirit and scope of the present disclosure. [Explanation of symbols]

[0071] 4. Storage Devices 5 Feature identification device 52 Memory 53 Processors 531 Specific part

Claims

1. a map storage unit that stores, in association with each position on a road, traffic information indicating whether the position is included in a two-way traffic section, and lane separation facility information indicating at least whether the lane separation facility that separates the road according to the traveling direction at the position is a separation pole that is a plurality of poles arranged at a predetermined interval and has no wire rope installed, a separation wire rope that is a plurality of poles arranged at a predetermined interval and has the wire rope installed, or other lane separation facility; an identification unit that, when the lane separation equipment information is not associated with a predetermined position on the road and it is determined based on the traffic information that the predetermined position is not included in the oncoming traffic section, identifies a type of the lane separation equipment based on an image of the lane separation equipment at the predetermined position using a first algorithm capable of identifying a type of the lane separation equipment based on an image of the lane separation equipment, and, when the lane separation equipment information is not associated with the predetermined position and it is determined based on the traffic information that the predetermined position is included in the oncoming traffic section, identifies a type of the lane separation equipment based on an image of the lane separation equipment at the predetermined position using a second algorithm capable of identifying the separation pole and the separation wire rope of the lane separation equipment with a higher degree of certainty than the first algorithm; A feature identification device comprising:

2. 2. The feature identification device according to claim 1, wherein the identification unit executes, as the first algorithm, at least a detection process for detecting an object from the image by inputting the image into a pre-trained detector, and a first identification process for identifying the type of the lane separation facility based on the detected object, and executes, as the second algorithm, at least the detection process, and a second identification process for, if a plurality of the poles are detected by the detection process, and three or more lines are detected extending from one of the adjacent poles to the other among the plurality of detected poles, extending each of the three or more lines so that they are continuous from one of the adjacent poles to the other, and identifying the lane separation facility as the separation wire rope if a difference in spacing between adjacent lines among the extended three or more lines is smaller than a predetermined error threshold.

3. 3. The feature identification device of claim 2, wherein, when the lane dividing facility information is associated with the specified location, the identification unit identifies the type of the lane dividing facility based on an image of the lane dividing facility taken at the specified location by a third algorithm including the detection process, the first identification process, and a type determination process that determines whether the type of the lane dividing facility identified in the first identification process is the same as the type represented in the lane dividing facility information.

4. The feature identification device of claim 2, wherein, when the lane separation facility information is associated with the specified location, the identification unit identifies the type of lane separation facility based on an image of the lane separation facility taken at the specified location by a third algorithm including the detection process, the first identification process, and an appearance determination process for determining whether the object detected by the detection process has a standard appearance of the type of lane separation facility represented in the lane separation facility information associated with the specified location.

5. a storage unit stores, in association with each position on a road, traffic information indicating whether the position is included in a two-way traffic section, and lane separation facility information indicating at least whether the lane separation facility that separates the road according to the traveling direction at the position is a separation pole that is a plurality of poles arranged at a predetermined interval and has no wire rope installed, a separation wire rope that is a plurality of poles arranged at a predetermined interval and has the wire rope installed, or other lane separation facility information; if the lane separation facility information is not associated with a predetermined position on the road and it is determined based on the traffic information that the predetermined position is not included in the oncoming traffic section, a type of the lane separation facility is identified based on an image of the lane separation facility at the predetermined position using a first algorithm capable of identifying the type of the lane separation facility based on an image of the lane separation facility; if the lane separation facility information is not associated with the predetermined location and it is determined based on the traffic information that the predetermined location is included in the oncoming traffic section, a second algorithm is used to identify the type of the lane separation facility based on an image of the lane separation facility taken at the predetermined location, the second algorithm being capable of identifying the separation pole and the separation wire rope of the lane separation facility with a higher degree of certainty than the first algorithm; A method for identifying a feature, comprising:

6. When lane separation equipment information is not associated with a predetermined position on a road, and when it is determined that the predetermined position is not included in the oncoming traffic section based on traffic information indicating for each position on the road whether the position is included in the oncoming traffic section, a first algorithm capable of identifying the type of lane separation equipment based on an image of the lane separation equipment is used to identify the type of the lane separation equipment based on an image of the lane separation equipment at the predetermined position, and the lane separation equipment information is information at least indicating whether the lane separation equipment that separates the road by driving direction at each position on the road is a separation pole that is a plurality of poles arranged at a predetermined interval and has no wire rope installed, a separation wire rope that has the wire rope installed on a plurality of poles arranged at a predetermined interval, or something other than the above; if the lane separation facility information is not associated with the predetermined location and it is determined based on the traffic information that the predetermined location is included in the oncoming traffic section, identifying a type of the lane separation facility based on an image of the lane separation facility at the predetermined location using a second algorithm that can identify the separation pole and the separation wire rope of the lane separation facility with a higher degree of certainty than the first algorithm; A computer program for identifying geographical features that causes a computer to execute the above.

Images