Information processing device, road identification method, road identification program

Abstract

To provide an information processor capable of identifying roads on map information to which road signs correspond.SOLUTION: An information processor includes: a storage unit for storing map information including road information; an acquisition unit for acquiring a captured image including at least a road sign; an extraction unit for extracting a road sign in the captured image; a calculation unit for calculating an inclination of the extracted road sign with respect to a candidate road to which the road sign may correspond; and an identification unit for identifying that regulations of the road sign are applied to which road on the map information, based on the inclination calculated by the calculation unit.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an information processing device that creates map information, a road identification method, and a road identification program.

Background Art

[0002] Various road signs are installed on roads. In some cases, a plurality of road signs are installed on a single support pole, and a driver driving a vehicle may not be able to instantly recognize each road sign immediately. Therefore, causing a navigation device or the like to provide guidance about road signs can reduce the burden on the driver. To achieve this, it is desirable that in the map information used by the navigation device, it is clearly set which road each road sign is accurately installed for. However, manually verifying that each road sign is accurately set in the map information is a complicated task. Patent Document 1 discloses a technology for road sign recognition in which a driving assistance device extracts the outline of a road sign from a captured image, and when it is determined based on the aspect ratio that the inclination angle of the road sign relative to the own vehicle is within a preset range, the road sign is recognized as being installed facing the own vehicle.

Prior Art Literature

Patent Literature

[0003]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0004] By the way, in the case of the above-mentioned Patent Document 1, there is a problem that depending on the imaging conditions of the captured image, it may not be possible to accurately recognize whether the road sign is installed for the road on which the own vehicle is traveling.

[0005] Therefore, the present invention has been made in view of the above problems, and aims to provide an information processing device, a road identification method, and a road identification program that can identify which road corresponds to a road sign. [Means for solving the problem]

[0006] To solve the above problems, an information processing device according to one aspect of the present invention includes a storage unit for storing map information including road information, an acquisition unit for acquiring an image including at least road signs, an extraction unit for extracting road signs from the image, a calculation unit for calculating the inclination of the extracted road signs with respect to a candidate road that the road sign may correspond to, and an identification unit for identifying which road on the map information the regulations of the road signs apply to based on the inclination calculated by the calculation unit.

[0007] To solve the above problems, a road identification method according to one aspect of the present invention involves a computer that can access a storage unit that stores map information including road information, performing an acquisition step of acquiring an image containing at least road signs; an extraction step of extracting road signs from the image; a calculation step of calculating the inclination of the extracted road signs with respect to a candidate road that the road signs may correspond to; and an identification step of identifying which roads on the map information the regulations of the road signs apply to, based on the inclination calculated in the calculation step.

[0008] To solve the above problems, a road identification program according to one aspect of the present invention provides a computer that can access a storage unit that stores map information including road information, and includes an acquisition function to acquire an image containing at least road signs, an extraction function to extract road signs from the image, a calculation function to calculate the inclination of the extracted road signs with respect to a candidate road that the road sign may correspond to, and an identification function to identify which road on the map information the regulations of the road signs apply to based on the inclination calculated by the calculation function.

[0009] Furthermore, in the above-mentioned information processing device, the storage unit may store road sign installation standard information that associates angle information to be installed relative to the road for each type of road sign, and the identification unit may identify the road on the map information to which the road sign regulations apply based on the inclination calculated by the calculation unit and the road sign installation standard information.

[0010] Furthermore, in the above-mentioned information processing device, the acquisition unit may acquire images of the area outside the vehicle while the vehicle is in motion as captured images.

[0011] Furthermore, in the above-mentioned information processing device, the identification unit may identify road areas in the captured image, determine which of the identified road areas a road sign corresponds to based on the boundary shape of the identified road areas, and determine which roads on the map information the regulations of the road signs apply to.

[0012] Furthermore, in the above-mentioned information processing device, the acquisition unit may acquire multiple captured images of road signs taken from different directions, the calculation unit may calculate the inclination of the road signs included in the multiple captured images, and the identification unit may identify the road on the map information to which the road sign regulations apply based on the multiple inclinations calculated by the calculation unit.

[0013] Furthermore, the above-mentioned information processing device may also include a registration unit that associates road sign information with roads on map information identified by the identification unit and registers that information. [Effects of the Invention]

[0014] An information processing device according to one aspect of the present invention can identify which road on map information corresponds to which road, based on the type of road sign included in the captured image and the installation angle at which the road sign should be installed relative to the road. [Brief explanation of the drawing]

[0015] [Figure 1] This is a block diagram showing an example of the configuration of an information processing device. [Figure 2]This is a data conceptual diagram showing an example of a data configuration of road sign installation standard information. [Figure 3] (a) is an example of a captured image. (b) is a partially enlarged view of the captured image. (c) is a diagram showing a part of map information. [Figure 4] (a) is another example of a captured image. (b) is an example of a captured image captured from an angle different from that of the captured image in (a). [Figure 5] (a) is another example of a captured image. (b) is a diagram explaining the association of road signs. [Figure 6] This is a flowchart showing an example of the operation of the information processing device. [Figure 7] This is a block diagram showing another configuration example of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, an information processing device according to an aspect of the present invention will be described in detail with reference to the drawings.

[0017] Embodiment Configuration of Information Processing Device An information processing device according to an aspect of the present invention (see 100 in FIG. 1) includes: a storage unit (see 104 in FIG. 1) that stores map information including road information; an acquisition unit (see 105 in FIG. 1) that acquires a captured image including at least a road sign; an extraction unit (see 105 in FIG. 1) that extracts the road sign from the captured image; a calculation unit (see 105 in FIG. 1) that calculates an inclination of the extracted road sign with respect to a candidate road to which the road sign may correspond; and a specifying unit (see 105 in FIG. 1) that specifies which road on the map information the regulation of the road sign is applied to, based on the inclination calculated by the calculation unit. The information processing device may also include a registration unit (see 105 in FIG. 1) that associates and registers road sign information with the road on the map information specified by the specifying unit.

[0018] Figure 1 is a block diagram showing a configuration example of an information processing apparatus 100. As shown in Figure 1, the information processing apparatus 100 includes a communication unit 101, an input unit 102, an output unit 103, a storage unit 104, and a CPU 105.

[0019] The information processing apparatus 100 is a computer system implemented by a server apparatus, a PC, or the like, but is not limited thereto, and may be implemented by a mobile terminal such as a smartphone or a tablet terminal. As an example, the information processing apparatus 100 may generate map information used for route guidance (navigation), and identifies which road on the map information corresponds to a road sign included in a captured image, based on installation standards for installing road signs on roads. Road signs include guide signs, warning signs, regulatory signs, instruction signs, and the like. A guide sign is a sign on which information indicating directions of destinations and passing points, routes, and the current location is posted. A warning sign is a sign for notifying a driver of dangers on the road in advance and calling attention. Examples of warning signs include signs for intersections, curves, falling rock warnings, and the like. A regulatory sign is a sign that specifies contents such as prohibition, regulation, and restriction of a specific traffic method. Examples of regulatory signs include speed restrictions, entry prohibition for specific vehicles, overtaking prohibition, and the like. Further, an instruction sign is a sign that indicates matters that need to be observed when traveling, such as a specific traffic method. Examples of instruction signs include signs indicating pedestrian crossings, priority roads, safety zones, and the like.

[0020] The communication unit 101 has the function of sending and receiving information with other devices via wired or wireless communication. The communication unit 101 may, for example, receive captured images including road signs from an external device or a moving vehicle and transmit them to the CPU 105. The external device may, for example, be a server device that collects captured images including road signs, but is not limited to this. The communication unit 101 may also receive point cloud data corresponding to the captured images and transmit it to the CPU 105. Point cloud data is three-dimensional data having position information and color information measured by so-called LiDAR (Light Detection And Ranging). Point cloud data is obtained by measuring the distance from the radar emission position to an object using radar reflection, and it is information that shows the relative position of an object around the radar emission position and the shape of the object.

[0021] Here, the captured image is an image that includes at least a road sign and may include location information indicating where the image was taken. The information indicating where the image was taken may be latitude and longitude information determined by a positioning system such as GNSS or GPS, and may include the direction of the image. Furthermore, the captured image may be an image taken from a camera mounted on a moving vehicle, capturing the area outside the vehicle, and may be an image capturing the direction of travel of the vehicle.

[0022] The input unit 102 has the function of receiving input from the user of the information processing device 100 and transmitting it to the CPU 105. The input unit 102 can be implemented, for example, by hardware keys provided on the information processing device 100, or by soft keys such as a touch panel or touch keys. The input to the input unit 102 may also be voice input, in which case the input unit 102 is implemented by a microphone. The input unit 102 may also receive, for example, information indicating the location where the captured image was taken and transmit it to the CPU 105.

[0023] The output unit 103 has the function of outputting instructed data according to instructions from the CPU 105. For example, the output unit 103 may output information indicating road signs included in the captured image and roads on map information that are estimated to correspond to the road signs. The information output by the output unit 103 may be output as text or images to a monitor (display device) attached to or connected to the information processing device 100, or as sound output from a speaker attached to or connected to the information processing device 100, or as information output via communication to an external device via the communication unit 110.

[0024] The storage unit 104 is a recording medium that stores various programs and data necessary for the operation of the information processing device 100. The storage unit 104 can be implemented using, for example, an HDD (Hard Disk Drive), an SSD (Solid State Drive), or flash memory.

[0025] The storage unit 104 stores map information 141. Map information 141 is map information that includes at least road information. Map information 141 may include information on road signs. The storage unit 104 also stores road sign installation standard information 142, which indicates the criteria for installing road signs on roads. For example, the storage unit 104 stores a program that identifies which road on the map information 141 corresponds to a road sign included in an captured image, based on the inclination of the road sign relative to the road.

[0026] The CPU 105 is a processor that uses various programs and data stored in the memory unit 104 to execute the processing that the information processing device 100 should perform.

[0027] The CPU 105 executes a program stored in the memory unit 104 to identify the area covered by the regulation of the road sign with a restricted area and registers it in the map information 141. The CPU 105 functions as an acquisition unit, extraction unit, calculation unit, identification unit, and registration unit.

[0028] The acquisition unit acquires an image of the road sign from the communication unit 101 or the storage unit 104. The acquisition unit also acquires point cloud data that overlaps with the acquired image and at least the positioning range. The point cloud data includes information that has been positioned at least around the road sign. The acquisition unit transmits the acquired image and point cloud data to the calculation unit. The acquisition unit also transmits the acquired image to the extraction unit.

[0029] The extraction unit extracts road signs from the transmitted captured image. For example, the extraction unit uses generally known image recognition techniques on the captured image to extract one or more road signs from the captured image. The extraction unit may then identify which road sign each extracted road sign is by pattern matching. The storage unit 140 of the information processing device 100, although not shown, may hold image information representing each road sign, and when the extraction unit extracts road signs from the captured image, it compares this image information with the road signs to extract the road signs from the captured image and identify which road sign each extracted road sign is. The extraction unit transmits the information of the extracted road signs to the calculation unit and the identification unit.

[0030] The calculation unit identifies the installation angle of the road sign in the captured image relative to the road candidate, based on the captured image and point cloud data transmitted from the acquisition unit and the road sign information transmitted from the extraction unit. Here, a road candidate is a road on the map information 141 that could be the target of the installation of the road sign. A road candidate may be a road captured in the captured image, a road within a predetermined range from the imaging position where the captured image was taken, or a road identified from the imaging position and imaging angle where the captured image was taken. The installation angle is the angle of the road (direction of vehicle travel) when the road sign is viewed from above (plan view). For each road sign transmitted from the extraction unit, the calculation unit identifies one or more corresponding road candidates and calculates the installation angle of the road sign for each identified road candidate. The calculation unit may calculate the installation angle of the road sign relative to the road candidate from the inclination of the road sign in the point cloud data relative to the road candidate. Alternatively, the calculation unit may calculate the installation angle of the road sign relative to the road candidate from the inclination of the road sign in the captured image and the inclination of the road candidate.

[0031] The identification unit identifies the road on the map information 141 that the road sign corresponds to, based on the angle of the road sign relative to the road candidate calculated by the calculation unit, and the angle at which the road sign should be installed relative to the road, that is, the installation angle identified from the information of which road sign the extracted road sign is and the road sign installation standard information 142. In other words, it identifies the road candidate that has the closest angle between the installation angle at which the road sign extracted by the extraction unit should be installed relative to the road identified from the road sign installation standard information 142, and the angle formed by the road sign and the road candidate. The identification unit may transmit the identified road corresponding to the road sign to the registration unit. The identification unit may also have the information of the identified road corresponding to the road sign output to the output unit 103.

[0032] Here, using Figures 3 to 5, we will explain, with specific examples, how to identify the roads that road signs correspond to.

[0033] First, using Figure 3, we will explain how to determine whether a road sign corresponds to the road on which a vehicle is traveling. Figure 3(a) is an example of an image captured, an image of the direction of travel outside the vehicle as it moves. Figure 3(c) is a top view of the area around the image captured in Figure 3(a), and may be an excerpt from map information 141. In Figure 3(a), the vehicle is traveling on road 320, and as shown in area 330, there are three road signs 310, 311, and 312. In addition to road 320, the area around the vehicle includes roads 321, 322, 323, 324, 325, and 326. Based on their installation locations, road signs 310, 311, and 312 may be candidates for roads 320 and 321 that are targeted for installation.

[0034] The information processing device 100 uses point cloud data to determine the installation angle of each road sign relative to each candidate road. This will be explained with reference to a partially enlarged view of Figure 3(b). Figure 3(b) is a partially enlarged view of the region 330 in Figure 3(a). The information processing device 100 extracts road signs 310, 311, and 312 from the captured image 300. Then, it identifies which road each of the road signs 310, 311, and 312 is installed on.

[0035] The information processing device 100 uses point cloud data of the left and right endpoints of the road sign to determine the installation angle of the road sign. Specifically, the information processing device 100 identifies the left and right endpoints that are at the same height when viewed from the front for each road sign. In the case of Figure 3(b), as an example, for road sign 310, point cloud data corresponding to the right endpoint 310r and the left endpoint 310l is acquired. As described above, since the point cloud data includes position information, the direction (azimuth) that the surface formed by road sign 310 is facing when viewed from above can be determined from the position information of the right endpoint 310r and the position information of the left endpoint 310l. Then, the angle that the identified direction makes with respect to road candidates 320 and 321 is determined.

[0036] The information processing device 100 identifies the type of road sign 310 by analyzing the image and determines the installation angle by referring to the road sign installation standards information 142. For example, suppose the direction of the surface of road sign 311 is determined from the point cloud data of the rightmost point 311r and the leftmost point 311l of road sign 311, and as a result, the installation angle is approximately 0° with respect to road candidate 321 and approximately 90° with respect to road candidate 320. Here, as shown in the figure, road sign 311 is a speed limit sign of 50 km / h, and it can be understood from the road sign installation standards information 142 that it should be installed perpendicular or diagonally to the road. Therefore, in this case, the information processing device 100 identifies road sign 311 as a sign installed with respect to road 320.

[0037] Similarly, for road signs 310 and 312, the direction of the road sign is determined from the point cloud data of their respective right endpoints 310r and 312r, and left endpoints 310l and 312l. As a result, the information processing device 100 can determine that road signs 310 and 312 are installed on road 320. By using the point cloud data, which is indeed accurately positioned data, to determine the direction of the road sign, and then utilizing the installation angle relative to the corresponding candidate road and the road sign installation standard information 142, the road to which the road sign corresponds can be determined more accurately than by using only the captured image.

[0038] Figure 4 illustrates a method for improving the accuracy of identifying the roads that road signs correspond to. Figure 4(a) is an example of an image captured differently from Figure 3(a). The image captured 401 shown in Figure 4(a) includes road signs 410, 411, 412, and 413, as shown in the figure. Similar to the explanation using Figure 3, it is possible to identify which road each road sign corresponds to from the image captured in Figure 4(a) alone. However, let's consider the case where we also have the image captured in Figure 4(b). Figure 4(b) is an image captured from the same location as Figure 4(a), but from a different angle, and includes road signs 410, 411, 412, and 413. Having an image captured from a different angle and point cloud data means that calculations (road identification) can be performed using different data, thus improving the accuracy of identifying the roads that road signs correspond to.

[0039] The information processing device 100 can identify the corresponding roads from the captured image 401 based on the point cloud data acquired from the imaging position, as explained using Figure 3, by determining the direction of each of the faces of the road signs 410, 411, 412, and 413 and their angles to the candidate roads. Similarly, the information processing device 100 uses the captured image 402 to identify the roads corresponding to each of the road signs 410, 411, 412, and 413. The device can then verify whether the identified roads are correct by checking whether the roads identified using the captured image 401 and the roads identified using the captured image 402 match. If they match, the accuracy of the identified roads is relatively high; if they do not match, the accuracy of the identified roads is relatively low, and it is possible that the roads identified using either the captured image 401 or the captured image 402 are incorrect, or that both are incorrect. Furthermore, if there are images taken from three or more different angles, and the roads identified from each image and the point cloud data are different, the road that is identified most frequently may be identified as the road corresponding to the road sign. As a result, the accuracy of the identified roads can be improved.

[0040] As shown in Figure 4, the identification unit may identify the road to which a road sign corresponds from captured images and point cloud data obtained by capturing the same road sign from multiple angles. That is, the identification unit identifies the road that is most likely to correspond to the road sign from the first captured image and calculates the installation angle. The accuracy of the probability that the road sign corresponds can be improved from the second and subsequent captured images. Furthermore, if the road identified from the second and subsequent captured images does not match the road identified from the previous captured image (the first captured image), the information processing device 100 may output information indicating this to the output unit 103.

[0041] Figure 5 illustrates an example of determining the installation angle of a road sign relative to a candidate road based on the inclination of the road sign in the captured image relative to the captured image and the inclination of the candidate road in the captured image relative to the captured image.

[0042] Figure 5 shows an example of an image captured that differs from Figures 3 and 4. The image captured in Figure 5, 501, shows an example that includes road signs 510, 511, and 512. Figure 5(b) will be used to explain which roads road signs 510, 511, and 512 correspond to in such an image captured in 501. As shown in Figure 5(b), the image captured in 501 includes roads 520 and 521 that intersect with each other.

[0043] Here, the information processing device 100 identifies the outlines of road 520 and road 521 in the captured image. That is, it analyzes the captured image 501 to identify boundary lines 530 and 531, which are the endpoints of each road. Boundary line 530 shows the boundary shape of road 520. Boundary line 531 shows the boundary shape of road 521.

[0044] The information processing device 100 forms a line segment from the intersection point 540 of boundary line 530 and boundary line 531 to the point of contact between the support post to which the road sign is attached and the road, and identifies the road to which the road sign corresponds based on the smaller angle between the line segment and each boundary line. For example, as shown in Figure 5, the line segment 541 from the intersection point 540 to the support post to which road signs 511 and 512 are attached has an angle with boundary line 531 that is smaller than the angle with boundary line 530, so the information processing device 100 may identify that road signs 511 and 512 are installed on road 521. Similarly, the information processing device 100 may identify that road sign 510 is installed on road 520.

[0045] In this example, the road to which a road sign corresponds is identified by the angle between the road boundary line and the line segment formed by the intersection of the boundary lines and the support post to which the road sign is attached. However, it is also possible to simply identify the road to which the road sign corresponds by having the closest boundary line among the boundary shapes of each road in the captured image, from the base of the support post to which the road sign is attached. In this way, the information processing device 100 can also identify a road sign and the road to which it corresponds from the captured image.

[0046] The registration unit may register the roads identified by the identification unit and the road signs in the map information 141. Furthermore, before performing the association, the registration unit may output a screen to the output unit 103 asking the user whether they wish to proceed with the association.

[0047] The above is an example of the configuration of the information processing device 100.

[0048] <Data> Here, we will explain Road Sign Installation Standard Information 142. Road Sign Installation Standard Information 142 is information that specifies how each road sign should be installed on the target road, and more specifically, it specifies the installation angle of the road sign relative to the road.

[0049] As shown in Figure 2, the road sign installation standard information 142 is information that associates the sign type 201 with the mounting angle 202. For explanatory purposes, this figure also shows an installation example 203 illustrating the mounting angle.

[0050] Sign type 201 is information indicating the type of road sign.

[0051] The mounting angle 202 is information indicating the angle at which the road sign, indicated by the corresponding sign type 201, should be installed relative to the road.

[0052] As shown in Figure 2, in the case of guide signs and warning signs, they should be installed so that they are approximately perpendicular to the road, that is, the angle that the surface of the road sign 210a makes with respect to the direction of vehicle travel is 80° to 90°.

[0053] Furthermore, in the case of one-way signs, which are a type of regulatory sign, they should be installed so that the angle between the faces of road signs 210b and 210c and the road is 0° or 45° with respect to the direction of vehicle travel, either parallel or diagonally to the road.

[0054] Furthermore, in the case of a pedestrian crossing prohibition sign, which is a type of regulatory sign, it should be installed parallel to the road, that is, so that the angle between the surface of the road sign 210d and the direction of vehicle travel is 0°.

[0055] Furthermore, in the case of signs prohibiting travel in directions other than specified, safety zones, road closure signs, bicycle-only signs, bicycle and pedestrian-only signs, pedestrian-only signs, and signs installed using the overhang or overhead type, they shall be installed perpendicular to the road, that is, the angle between the faces of road signs 210e and 210f and the direction of vehicle travel shall be 90°.

[0056] Furthermore, general signs, namely one-way signs, pedestrian crossing prohibition signs, signs prohibiting traffic in directions other than specified, safety zone signs, road closure signs, bicycle-only signs, bicycle and pedestrian-only signs, pedestrian-only signs, and regulatory and directional signs other than those installed by overhang or overhead installation, shall be installed perpendicular or oblique to the road, that is, the angle that the face of road sign 210a makes with respect to the direction of vehicle travel shall be between 45° and 90°.

[0057] <Operation of the Information Processing Device> An example of the operation of the information processing device 100 will be explained using Figure 6. Figure 6 is a flowchart showing an example of the operation when identifying which road on the map information 141 a road sign included in an captured image is installed on.

[0058] As shown in Figure 6, the acquisition unit of the CPU 105 of the information processing device 100 acquires an image containing road signs and point cloud data corresponding to the image (step S601). The acquisition unit transmits the acquired image and point cloud data to the calculation unit. The acquisition unit also transmits the acquired image to the extraction unit.

[0059] When the extraction unit receives the captured image, it extracts the road signs from the captured image (step S602). Then, it transmits the extracted road sign information to the calculation unit.

[0060] The calculation unit calculates the installation angle of the road sign extracted by the extraction unit and the road candidate that the road sign may correspond to (step S603). The calculation unit may identify the road candidate that the road sign extracted by the extraction unit may correspond to, for example, based on the location information of where the captured image was taken. Alternatively, the calculation unit may identify the road candidate that the extracted road sign may correspond to from the captured image and identify the road on the map information. Then, it determines the installation angle of the road sign for the identified road candidate. As described above, the calculation unit may determine the installation angle of the road sign based on point cloud data, or it may determine the installation angle from the inclination between the road sign and the road candidate (boundary of the road candidate) in the captured image, or it may determine the installation angle from multiple captured images of the same road sign taken from different angles, or it may determine the installation angle by combining these methods. The calculation unit transmits the determined installation angle of the road sign for the road candidate to the identification unit.

[0061] The extraction unit identifies which road sign the extracted road sign is. The extraction unit identifies the road sign, for example, by analyzing the image of the extracted road sign and using pattern matching technology. The extraction unit identifies the installation reference angle at which the identified road sign should be installed relative to the road by referring to the road sign installation reference information 142 (step S604). The extraction unit transmits the identified installation reference angle to the identification unit.

[0062] The identification unit identifies the road on the map information 141 to which the road sign corresponds, based on the installation reference angle identified by the extraction unit and the installation angle for each road candidate calculated by the calculation unit (step S605). That is, the identification unit identifies the road candidate with the installation angle closest to the identified installation reference angle as the road to which the road sign corresponds. The identification unit may output the information of the identified road to the output unit 103 or transmit it to the registration unit. Here, the identification unit transmits the information of the identified road to the registration unit.

[0063] The registration unit registers the applicable area of ​​the road sign transmitted from the determination unit into the map information 141 (step S606), and terminates the process. Note that the process in step S606 is not mandatory; the process may be stopped at identifying the road to which the road sign corresponds, and the association between the road sign and the road may be performed by the user of the information processing device 100.

[0064] <Summary> As described above, the information processing device 100 can identify which road on the map information a road sign is installed on based on the type of road sign included in the captured image and the installation angle at which the road sign should be installed relative to the road. Then, by registering the identified road in association with the road sign in the map information 141, it can be used for driving guidance. For example, in situations where multiple road signs are installed and the driver cannot make a decision at a glance, the navigation device using the map information 141 can provide accurate guidance to the driver.

[0065] <Supplement> The information processing device according to the above embodiment is not limited to the above embodiment and may be implemented by other methods. Various modifications will be described below.

[0066] (1) In the above embodiment, the information processing device 100 was shown to function as a map information creation device by identifying the road on the map information 141 that corresponds to the road sign and registering it in the map information 141. However, the information processing device 100 may also function as a navigation device. That is, as shown in the above embodiment, the information processing device 100 may extract road signs from an image captured in the direction of travel of the vehicle, and identify whether the road sign is for the road the vehicle is traveling on based on the type of road sign and the angle at which it is installed relative to the road the vehicle is traveling on. When the information processing device 100 identifies that the road sign is for the road the vehicle is traveling on, it may provide guidance related to that road sign. For example, if the road sign is a regulatory sign, the regulatory content may be output as audio or as an image from the output unit 103.

[0067] Furthermore, if the navigation is performed using map information 141 that has been registered with information linking road signs to specific roads, the system may be configured to provide guidance when a corresponding road sign is found based on the vehicle's current location and the map information 141. In this way, the information processing device 100 may be a device that identifies whether a road sign is installed on the road the vehicle is traveling on based on the installation angle of the road sign relative to the road, and then provides guidance for the road sign. This allows the information processing device 100 to provide the driver of the vehicle with guidance for the correct applicable road sign.

[0068] (2) In the above embodiment, the information processing device 100 may acquire vehicle driving information that indicates the driving history of a vehicle, such as CAN (Control Area Network) information and probe information, and verify the road sign associated with the road. That is, if the road sign is related to the driving of a vehicle, the information processing device 100 may use the vehicle driving information of a vehicle that has driven on the road to which the road sign is associated to verify whether it is complying with the content of the road sign. For example, if the road sign is a speed limit of 40 km / h, the CAN information of the vehicle driving information of each of the multiple vehicles driving on that road may be used to determine whether the driving speed of each vehicle is 40 km / h or less, and verify whether the road sign associated with the road is correct. With this configuration, the user can determine whether the road sign associated with the road is correct without having to go to the site to check. If the result of this determination is that it is incorrect, the information processing device 100 may output information indicating the road in question and the road sign to the output unit 103. As a result, the user of the information processing device 100 can recognize that the road and road sign are incorrectly associated.

[0069] (3) In the above embodiment, the method for identifying which road on the map information a road sign in the information processing device is installed on and registering it in the map information is performed by the processor of the information processing device executing a predetermined program, etc. However, this may be realized by logic circuits (hardware) or dedicated circuits formed on an integrated circuit (IC (Integrated Circuit) chip, LSI (Large Scale Integration)) etc. in the device. Furthermore, these circuits may be realized by one or more integrated circuits, and the functions of the multiple functional units shown in the above embodiment may be realized by a single integrated circuit. Depending on the degree of integration, LSIs may be called VLSI, super LSI, ultra LSI, etc. That is, as shown in Figure 7, the information processing device 100 may consist of a communication circuit 101a, an input circuit 102a, an output circuit 103a, a storage circuit 104a, and a control circuit 105a, which correspond to the communication unit 101, input unit 102, output unit 103, storage unit 104, and CPU 105, respectively.

[0070] Furthermore, the above program may be recorded on a recording medium readable by the processor, and the recording medium can be a "non-temporary tangible medium," such as tape, disk, card, semiconductor memory, or programmable logic circuit. The above program may also be supplied to the processor via any transmission medium capable of transmitting the program (such as a communication network or broadcast wave). In other words, for example, the program may be downloaded and executed from a network using an information processing device such as a smartphone. The present invention can also be realized in the form of a data signal embedded in a carrier wave, in which the above program is embodied by electronic transmission.

[0071] The above program can be implemented using scripting languages ​​such as ActionScript and JavaScript®, or object-oriented programming languages ​​such as Objective-C, Java®, C++, Python, and R, but these languages ​​are just examples.

[0072] (4) The various embodiments shown in the above embodiment may be combined as appropriate. Also, the execution order of each operation shown in the flowchart may be changed or executed in parallel, as long as there is no inconsistency in the result. For example, the execution timing of the process in step S603 and the process in step S604 shown in Figure 6 may be in reverse order, that is, the process in step S604 may be executed before the process in S603, or they may be executed in parallel. [Explanation of Symbols]

[0073] 100 Information Processing Devices 101 Communications Department 102 Input section 103 Output section 104 Storage section 105 CPU (Acquisition unit, Extraction unit, Calculation unit, Identification unit, Registration unit)

Claims

1. A memory unit that stores map information including road information, An acquisition unit that acquires an image containing at least road signs, An extraction unit for extracting road signs from the captured image, A calculation unit that calculates the inclination of the extracted road sign with respect to a candidate road that the road sign may correspond to, Based on the slope calculated by the calculation unit, an identification unit identifies which road on the map information the road sign regulations apply to, Equipped with, The aforementioned storage unit stores road sign installation standard information that associates angle information to be used for installation relative to the road for each type of road sign. The extraction unit identifies the type of road sign, The identification unit identifies the road on the map information to which the road sign regulations apply, based on the inclination calculated by the calculation unit and the road sign installation standard information. Information processing device.

2. The acquisition unit acquires images of the area outside the vehicle while the vehicle is in motion as the captured image. The information processing apparatus according to feature 1.

3. The identification unit identifies road areas in the captured image, determines which of the identified road areas the road sign corresponds to based on the boundary shape of the identified road area, and determines which road on the map information the regulations of the road sign apply to. The information processing apparatus according to feature 2.

4. The acquisition unit acquires multiple captured images of the road sign taken from different directions. The calculation unit calculates the inclination of the road sign included in the plurality of captured images, The identification unit identifies the road on the map information to which the road sign regulations apply, based on the multiple inclines calculated by the calculation unit. The information processing apparatus according to feature 1.

5. The system includes a registration unit that associates information on road signs with roads on the map information identified by the identification unit. The information processing apparatus according to feature 1.

6. A computer that can access a storage unit that stores map information including road information and road sign installation standard information that associates the angle information that should be used for installation relative to the road for each type of road sign, An acquisition step to acquire an image containing at least road signs, Extraction step of extracting road signs from the captured image, A calculation step of calculating the inclination of the extracted road sign with respect to a candidate road that the road sign may correspond to, Based on the slope calculated in the calculation step, the identification step identifies which roads on the map information the regulations of the road sign apply to, Execute, The extraction step identifies the type of road sign, The aforementioned identification step identifies the road on the map information to which the road sign regulations apply, based on the slope calculated in the calculation step and the road sign installation standard information. Road identification method.

7. A computer that can access a storage unit that stores map information including road information and road sign installation standard information that associates the angle information that should be used for installation relative to the road for each type of road sign, An acquisition function that acquires captured images including at least road signs, An extraction function for extracting road signs from the aforementioned captured image, A calculation function that calculates the inclination of the extracted road signs with respect to potential road candidates to which the road signs may correspond, Based on the slope calculated by the calculation function, an identification function identifies which road on the map information the regulations of the road sign apply to, To make it happen, The extraction function identifies the type of road sign, The aforementioned identification function identifies the road on the map information to which the road sign regulations apply, based on the slope calculated by the calculation function and the road sign installation standard information. Road Identification Program.

Images