Image generation system

Abstract

To provide an image generation system capable of reducing a communication amount when transmitting an image including a road feature object thereto.SOLUTION: An image generation system comprises: a server comprising an area information generation part that generates area information for determining an area where a road feature object is included inside an image, and a sever communication control part that transmits the area information via a server communication part, based on feature information of representing the road feature object acquired in the past; and an image generation device comprising a device communication control part that receives the area information via a device communication part, and an image generation part that determines a cut-out area cut out from the image acquired using an image acquisition part based on the area information, and generates a partial image by cutting out the cut-out area from the image. The device communication control part transmits the partial image generated by the image generation part to the server via the device communication part.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an image generation system. [Background technology]

[0002] High-precision maps that an autonomous driving system refers to in order to drive a vehicle autonomously are required to accurately represent information about roads. Road features around the road are represented on high-precision maps. Therefore, probe data representing road features around the road are collected from vehicles that have actually traveled in a specified area (see, for example, Patent Document 1).

[0003] A vehicle generates probe data while traveling on a road and transmits the probe data to a server, which receives the probe data from the vehicle and generates or updates a high-precision map based on the probe data.

[0004] The server compares the road feature information collected from the vehicle with the current map information, and if the comparison with the road feature indicates that the current map information has changed, the server requests the vehicle to send a new video (multiple images) containing the detected road feature in order to update the map information. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2020-187432 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, when video is transmitted from a vehicle to a server, the amount of information contained in the video is greater than the amount of information (eg, type and position) about road features, and so there is a demand for reducing the amount of communication.

[0007] An object of the present disclosure is to provide an image generation system capable of reducing communication traffic when transmitting an image including road features. [Means for solving the problem]

[0008] (1) According to one embodiment, an image generation system is provided, which includes a server having an area information generation unit that generates area information for determining an area in an image where a road feature is included based on feature information representing a road feature previously acquired, and a server communication control unit that transmits the area information via a server communication unit, an image generation device having an apparatus communication control unit that receives the area information via an apparatus communication unit, and an image generation unit that determines an excision area to be excised from an image acquired using an image acquisition unit based on the area information, and excises the excision area from the image to generate a partial image, and the apparatus communication control unit transmits the partial image generated by the image generation unit to the server via the apparatus communication unit.

[0009] (2) In the image generation system of (1), it is preferable that the area information generation unit generates area information based on feature information representing previously acquired road features so as to include the type of road feature about which a change has been detected, and the image generation unit determines an area within the image according to the type of road feature as the cut-out area.

[0010] (3) In the image generation system of (1), it is preferable that the area information generation unit generates the area information based on the feature information so as to include position information of the road feature in which a change has been detected, and the image generation unit determines, based on the position information of the road feature, an area in which the road feature is estimated to be represented in the image acquired using the image acquisition unit, as the cut-out area.

[0011] In the image generation system (4), it is preferable that the server has a change information generation unit that generates change information representing a type of change in road features based on the feature information, the server communication control unit transmits the change information to the image generation device via the server communication unit, the device communication control unit receives the change information via the device communication unit, and the image generation unit determines a cut-out area from the image acquired using the image acquisition unit based on the change information and the area information.

[0012] In the image generation system of (5), it is preferable that the server has a position information generation unit that generates position information representing the position of a road feature where a change has been detected based on the feature information, the server communication control unit transmits the position information to the image generation device via the server communication unit, the device communication control unit receives the position information and the change information via the device communication unit, and the image generation unit determines, based on the position information and the change information, a section from which an image is acquired using the image acquisition unit to generate a partial image. Effect of the Invention

[0013] The image generating system according to the present invention has an advantage that the amount of communication traffic can be reduced when transmitting an image including road features. [Brief description of the drawings]

[0014] [Figure 1] 1 is a schematic configuration diagram of a data collection system according to an embodiment of the present invention. [Diagram 2] FIG. 4 is a sequence diagram of an image generating process of the data collection system according to the present embodiment. [Diagram 3] 1 is a schematic configuration diagram of a vehicle in which a data collection device is installed. [Figure 4] 13 is an example of an operational flowchart of a section determination process of a data collection device. [Diagram 5] 13 is an example of an operational flowchart of an image generating process of the data collection device. [Figure 6] 13 is another example of an operational flowchart of the image generating process of the data collection device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] FIG. 1 is a schematic configuration diagram of a data collection system 1 in which a data collection device 11 of this embodiment is implemented. The data collection system 1 has at least one vehicle 10 and a server 30. The vehicle 10 is implemented with the data collection device 11. The data collection device 11 is connected to the server 30 via the macrocell base station 41 and the communication network 40 by, for example, accessing a wireless base station 41 (hereinafter also referred to as a macrocell base station 41) that provides a macrocell connected to the communication network 40 to which the server 30 is connected via a gateway (not shown) or the like. The data collection system 1 is an example of an image generation system. The data collection device 11 is an example of an image generation device.

[0016] 1, only one vehicle 10 is shown, but the data collection system 1 may include a plurality of vehicles 10. Similarly, a plurality of macrocell base stations 41 may be connected to the communication network 40.

[0017] A vehicle 10 is traveling on a road 50. The road 50 has two lanes 51 and 52. The vehicle 10 is traveling on the lane 51. The lane 51 is divided by a lane dividing line 53 and a lane dividing line 54. The lane 52 is divided by a lane dividing line 54 and a lane dividing line 55.

[0018] The server 30 acquires probe data or the like representing road features from the data collection device 11, and generates or updates a high-precision map. The high-precision map is referred to by an autonomous vehicle for autonomous driving.

[0019] The server 30 compares the obtained information representing the road features with the current high-precision map to detect changes in the road features, including the installation of new road features, changes in the positions of road features, and removal of road features.

[0020] When a change in a road feature is detected, the server 30 requests the vehicle 10 to collect a video showing the road feature. The data collection device 11 uses the camera 2 to acquire a camera image 100 showing the road feature in which a change has been detected. The data collection device 11 generates a partial image 110 by cutting out an area showing the road feature from the camera image. The data collection device 11 transmits the partial image 110 to the server 30. The server 30 updates the high-precision map based on the multiple images (videos) showing the road feature in which a change has been detected.

[0021] Fig. 2 is a sequence diagram of the image generation process of the data collection system 1. The operation of the data collection system 1 will be outlined below with reference to Fig. 2. Note that, although Fig. 1 shows only one vehicle 10, the server 30 can execute the same process for multiple vehicles.

[0022] First, the server 30 generates a collection target position representing the position of a road feature where a change is detected based on feature information representing a road feature previously acquired (step S101). The collection target position represents a position where an image is collected. The collection target position is an example of position information representing the position of a road feature where a change is detected.

[0023] The collection target location is represented such that the location can be determined by positioning information such as GNSS information. The collection target location may be associated with a road section in which a road feature in which a change is detected is located. The collection target location is represented, for example, in world coordinates. In the example shown in FIG. 1, the collection target location represents the location of the road feature 56 in which a change is detected.

[0024] The server 30 may also generate change information that indicates the type of change to the road feature. For example, the type of change includes that the position of the road feature has changed, that a new road feature has been installed, and that a road feature has been removed. Note that the change information does not necessarily have to be generated.

[0025] Next, the server 30 transmits the collection target position and the change information to the vehicle 10 via the communication network 40 and the macrocell base station 41 (step S102). The data collection device 11 receives the collection target position and the change information. Note that if the change information is not generated, only the collection target position is received.

[0026] The data collection device 11 determines an image acquisition section in which a camera image is acquired using the camera 2 to generate a partial image based on the collection target position and the change information (step S103). When the change information is not generated, the image acquisition section is determined based on the collection target position. The section determination process in which the data collection device 11 determines the image acquisition section will be described later with reference to FIG. 4.

[0027] When the vehicle 10 enters the image acquisition section, the data collection device 11 starts acquiring camera images showing the environment around the vehicle 10 using the camera 2 (step S104).

[0028] The data collection device 11 also starts generating judgment information (step S105). The judgment information includes, for example, the position of the vehicle 10 and the acquisition status of the camera image. The acquisition status of the camera image indicates whether the camera image is normally acquired or not. The data collection device 11 generates the judgment information for each predetermined image acquisition period. For example, the data collection device 11 generates the judgment information for each predetermined cycle (for example, 10 seconds to several minutes) or each time the vehicle 10 travels a predetermined distance (for example, 100 m to 1 km). The camera images are acquired at a predetermined cycle within the image acquisition period.

[0029] Next, the data collection device 11 uses the communication device 3 to transmit the determination information to the server 30 via the macrocell base station 41 and the communication network 40 (step S106). The server 30 receives the determination information.

[0030] The server 30 generates a determination result and area information based on the determination information (step S107). For example, if the position of the vehicle 10 corresponds to the collection target position and the camera image is normally acquired, the server 30 generates a determination result that requests transmission of the image. On the other hand, if the position of the vehicle 10 does not correspond to the collection target position or the camera image is not normally acquired, the server 30 generates a determination result that does not request transmission of the image.

[0031] Furthermore, when generating a determination result requesting transmission of an image, the server 30 generates area information for determining an area in the image that includes a road feature. The area information is used by the data collection device 11 to determine an area in the camera image that includes the road feature. The area information includes, for example, the type of the road feature or location information that indicates the location of the road feature.

[0032] The server 30 transmits the determination result and the area information to the data collection device 11 via the communication network 40 and the macrocell base station 41 (step S108). The data collection device 11 receives the determination result and the area information.

[0033] When a judgment result requesting transmission of an image is received, the data collection device 11 determines a cut-out area to be cut out from the camera image acquired using the camera 2 based on the area information, and cuts out the cut-out area from the camera image to generate a partial image (step S109).

[0034] 1, the data collection device 11 generates a partial image 110 from a camera image 100. The capacity of the partial image 110 is smaller than that of the camera image 100. For example, the capacity of the partial image 110 is half or less that of the camera image 100. The image generation process in which the partial image is generated by the data collection device 11 will be described later with reference to FIGS. 5 and 6.

[0035] Next, the data collection device 11 uses the communication device 3 to transmit the partial images to the server 30 via the macrocell base station 41 and the communication network 40 (step S110). The data collection device 11 generates a partial image from each of the multiple camera images acquired during the image acquisition period, and transmits these multiple partial images to the server 30. The server 30 receives the multiple partial images.

[0036] Next, the server 30 updates the high precision map based on the multiple partial images (step S111), and ends the series of processes.

[0037] If the data collection device 11 receives a determination result that does not require transmission of images, the data collection device 11 does not generate partial images for the camera images acquired during the image acquisition period in which the determination information was generated. The data collection device 11 executes the processes from steps S104 to S111 described above while the vehicle 10 is located within the image acquisition section.

[0038] According to the data collection system 1 of the present embodiment described above, at a position where a change in a road feature is detected, a partial image including an area determined to include the road feature within a camera image captured by the vehicle 10 is transmitted to the server 30. This enables the data collection system 1 to reduce the amount of communication when transmitting an image including the road feature.

[0039] The data collection system 1 may include a plurality of vehicles 10. However, since each vehicle has the same configuration and executes the same processing with respect to parking information processing, the following description will be given of one vehicle 10.

[0040] Next, the vehicle 10 in which the data collection device 11 is installed will be described below with reference to Fig. 3. Fig. 3 is a schematic configuration diagram of the vehicle 10 in which the data collection device 11 is installed.

[0041] The vehicle 10 includes a camera 2, a communication device 3, a positioning information receiving device 4, a data collecting device 11, etc. The vehicle 10 may further include a distance measuring sensor (not shown) such as a LiDAR sensor for measuring distances to objects around the vehicle 10.

[0042] The camera 2, the communication device 3, the positioning information receiving device 4, and the data collecting device 11 are communicatively connected via an in-vehicle network 12 that complies with a standard such as a controller area network.

[0043] The camera 2 is attached to the vehicle 10 so as to face forward of the vehicle 10. The camera 2 acquires camera images showing the environment of a predetermined area ahead of the vehicle 10, for example at a predetermined period. The camera images are an example of information showing the environment around the vehicle. The camera images may show roads included in the predetermined area ahead of the vehicle 10 and road features around the roads. The camera 2 is an example of an image acquisition unit.

[0044] The camera 2 has a two-dimensional detector composed of 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 acquired on the two-dimensional detector.

[0045] Every time the camera 2 captures a camera image, the camera 2 outputs the camera image and the camera image capture time at which the camera image was captured to the data collection device 11 via the in-vehicle network 12.

[0046] The communication device 3 has an interface circuit for connecting the data collection device 11 to the macrocell base station 41. The communication device 3 is configured to be able to communicate with the server 30 via the macrocell base station 41 and the communication network 40. The communication device 3 is an example of an apparatus communication unit.

[0047] The positioning information receiving device 4 outputs positioning information indicating the current position of the vehicle 10. For example, the positioning information receiving device 4 may be a GNSS receiver. Every time the positioning information receiving device 4 acquires GNSS information at a predetermined reception cycle, it outputs the positioning information and the positioning information acquisition time at which the GNSS information was acquired to the data collecting device 11 or the like. The positioning information includes, for example, the current position of the vehicle 10 expressed in world coordinates. The current position of the vehicle 10 includes, for example, latitude and longitude.

[0048] The data collection device 11 executes control processing and generation processing. To this end, the data collection device 11 has a communication interface (IF) 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 are connected via a signal line 24. The communication interface 21 has an interface circuit for connecting the data collection device 11 to the in-vehicle network 12.

[0049] The memory 22 is an example of a storage unit, and includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 22 may further include other storage devices such as a hard disk device. The memory 22 stores computer programs of applications used in the information processing executed by the processor 23 and various data.

[0050] All or part of the functions of the data collection device 11 are functional modules realized by, for example, a computer program running on the processor 23. The processor 23 has a control unit 231 and a generation unit 232. Alternatively, the functional modules of the processor 23 may be dedicated arithmetic circuits provided in the processor 23. The processor 23 has one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 23 may further have other arithmetic circuits such as a logic arithmetic unit, a numerical arithmetic unit, or a graphic processing unit. The data collection device 11 is, for example, an electronic control unit (ECU).

[0051] The control unit 231 executes a process of acquiring a camera image, a process of generating determination information, a process of transmitting the determination information, and a process of transmitting a partial image. The generation unit 232 executes a process of determining an image acquisition section, and a process of generating a partial image. The process of determining the image acquisition section and the process of generating a partial image by the generation unit 232 will be described later. The control unit 231 is an example of a device communication control unit. The generation unit 232 is an example of an image generation unit.

[0052] 1 shows a hardware configuration diagram of the server 30. The server 30 executes a control process, a determination process, and a generation process. To that end, the server 30 has a communication interface (IF) 31, a storage device 32, a memory 33, and a processor 34. The communication IF 31, the storage device 32, and the memory 33 are connected to the processor 34 via a signal line 35. The server 30 may further have input devices such as a keyboard and a mouse, and a display device such as a liquid crystal display.

[0053] The communication IF 31 has an interface circuit for connecting the server 30 to the communication network 40. The communication IF 31 is configured to be able to communicate with the vehicle 10 via the communication network 40 and the macrocell base station 41. The communication IF 31 is an example of a server communication unit.

[0054] The storage device 32 includes, for example, a hard disk device or an optical recording medium and an access device therefor. The storage device 32 stores the probe data and images transmitted from the vehicle 10, the high-precision map, the collection target positions, and the like. The storage device 32 may also store computer programs executed on the processor 34 for executing the processes of the server 30 related to the data collection process, and the processes of generating and updating the high-precision map. The storage device 32 is an example of a storage unit.

[0055] The memory 33 includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory, and stores various data and computer programs of applications used in the information processing executed by the processor 34. The memory 33 is an example of a storage unit.

[0056] All or part of the functions of the server 30 are functional modules realized by a computer program running on the processor 34, for example. The processor 34 has a control unit 341, a determination unit 342, and a generation unit 343. Alternatively, the functional modules of the processor 34 may be dedicated arithmetic circuits provided in the processor 34. The processor 34 has one or more central processing units (CPUs) and their peripheral circuits. The processor 34 may further have other arithmetic circuits such as a logic arithmetic unit, a numerical arithmetic unit, or a graphic processing unit. The control unit 341 is an example of a server communication control unit. The generation unit 343 is an example of a region information generation unit. The generation unit 343 is also an example of a change information generation unit. The generation unit 343 is also an example of a position information generation unit.

[0057] The control unit 341 executes a process of transmitting the collection target position, and a process of transmitting the determination result and area information. In the process of transmitting the collection target position, the control unit 341 transmits the collection target position to the data collection device 11 using the communication IF 31 at a position notification time having a predetermined period.

[0058] The determination unit 342 executes a process for generating a determination result based on the determination information. When the position of the vehicle 10 corresponds to the collection target position and the camera image has been normally acquired, the determination unit 342 generates a determination result that requests transmission of the image. On the other hand, when the position of the vehicle 10 does not correspond to the collection target position or the camera image has not been normally acquired, the server 30 generates a determination result that does not request transmission of the image. The determination process may be performed based on other information included in the determination information.

[0059] The determination unit 342 acquires the position and traveling direction of the vehicle 10 during the image acquisition period based on the position of the vehicle 10 included in the determination information. Then, the determination unit 342 identifies the road section in which the vehicle 10 is located based on the position and traveling direction of the vehicle 10 when the camera image was acquired. If the identified road section matches the road section associated with the collection target position, the determination unit 342 may determine that the position of the vehicle 10 corresponds to the collection target position.

[0060] The generating unit 343 generates a collection target position representing the position of the road feature where a change has been detected, based on feature information representing the road feature acquired in the past. The feature information representing the road feature acquired in the past includes, for example, the position or type of the road feature represented in the probe data. The collection target position is represented, for example, as a two-dimensional position or a three-dimensional position in a world coordinate system. The generating unit 343 associates the road section where the road feature where a change has been detected is located with the collection target position.

[0061] For example, when information representing a predetermined number of road features is collected, the server 30 compares it with the current high-precision map and determines whether a change in the road features has been detected.

[0062] The generating unit 343 may generate change information representing a type of change in a road feature object based on feature information representing a road feature object previously acquired. The generating unit 343 determines that the position of a road feature object has changed when the variance of the position of the road feature object exceeds a reference variance value. The generating unit 343 also determines that a new road feature object has been installed when a new road feature object is detected at a rate equal to or greater than a predetermined first criterion. Furthermore, the generating unit 343 determines that a road feature object has been removed when a rate at which the road feature object is detected is equal to or less than a predetermined second criterion. The generating unit 343 generates change information representing a type of change in a road feature object. The types of change include that the position of a road feature object has changed, that a new road feature object has been installed, and that a road feature object has been removed.

[0063] The generating unit 343 also executes a process of generating area information. The generating unit 343 generates area information for determining an area in the camera image that includes a road feature, based on feature information representing a road feature previously acquired. The area information is used by the data collecting device 11 to determine an area in the camera image that includes the road feature.

[0064] For example, the generating unit 343 generates area information based on previously acquired feature information representing road features, so as to include the type of road feature in which a change has been detected. The area information represents the type of road feature in which a change has been detected. Examples of the type of road feature include road signs and road markings (indications on the road surface).

[0065] Furthermore, the generating unit 343 may generate area information based on previously acquired feature information representing road features, so as to include position information of the road feature in which a change has been detected. The area information has position information representing the position of the road feature in which a change has been detected. The position information may be a three-dimensional position representing the position of the road feature. Alternatively, the position information may be a two-dimensional position representing the position of the road feature and the type of the road feature. The position of the road feature is expressed, for example, in world coordinates.

[0066] Furthermore, the generation unit 343 generates a high-precision map using the collected probe data and images. Also, the generation unit 343 updates the high-precision map using the collected probe data. For example, the generation unit 343 compares newly collected road features with previously collected road features for the lane section to be updated, and detects road features for which changes have been detected.

[0067] Based on the multiple images transmitted from the data collection device 11, it is determined whether the position of a road feature has changed, a new road feature has been installed, or a road feature has been removed. The generation unit 343 updates the high-precision map information based on this determination result. The high-precision map is stored in the storage device 32. The control unit 341 distributes the high-precision map to the autonomous vehicle via the communication IF 31.

[0068] Fig. 4 is an example of an operation flowchart of the interval determination process of the data collection device 11. Hereinafter, the interval determination process of the data collection device 11 will be described with reference to Fig. 4. The data collection device 11 executes the interval determination process shown in Fig. 4 every time it receives the collection target position and change information.

[0069] First, the generating unit 232 of the data collecting device 11 determines whether the type of change included in the change information is that a new road feature has been installed (step S201).

[0070] If the type of change is that a new road feature has been installed (step S201-Yes), the generation unit 232 sets the reference section as the image acquisition section (step S202) and ends the series of processes. The reference section is a predetermined range before and after the collection target position. For example, the reference section is a range of several hundred meters before and after the collection target position. When a new road feature has been installed, the position of the road feature is clear, so the reference section is set as the image acquisition section. The reference section may be a road section associated with the road feature.

[0071] On the other hand, if the type of change is not the installation of a new road feature (step S201-No), the generation unit 232 sets the section obtained by expanding the reference section as the image acquisition section (step S202) and ends the series of processes. The type of change not being the installation of a new road feature includes the type of change being a change in the position of a road feature or the type of change being the removal of a road feature.

[0072] If the position of the road feature changes or is removed, the position of the road feature is unclear, so the image acquisition section is expanded from the reference section. For example, the image acquisition section is expanded from 1.5 to 2.0 times the reference section. This concludes the description of the section determination process.

[0073] Fig. 5 is an example of an operation flowchart of the image generation process of the data collection device. Hereinafter, the image generation process of the data collection device 11 will be described with reference to Fig. 5. The data collection device 11 executes the image generation process shown in Fig. 5 every time it receives a determination result requesting transmission of an image and area information indicating the type of road feature in which a change has been detected.

[0074] First, the generating unit 232 determines an area in the camera image according to the type of road feature as a cut-out area to be cut out from the camera image (step S301). The same cut-out area is set for camera images acquired in one image acquisition period. When the type of road feature is a road sign, the road sign is located at the edge of the road, so the generating unit 232 determines a vertically long cut-out area at the right or left edge of the camera image, as shown in FIG. 1. When vehicles drive on the left side of the road, the cut-out area is determined to be on the left side of the camera image. On the other hand, when vehicles drive on the right side of the road, the cut-out area is determined to be on the right side of the camera image. The position and dimensions of the cut-out area may be determined by default. It is preferable that the size of the cut-out area is half or less of the camera image.

[0075] Furthermore, when the type of the road feature is a road marking, since the road marking is displayed on the road surface, the generating unit 232 determines a landscape cropping region so as to include the center of the camera image. The position and dimensions of the cropping region may be determined by default.

[0076] Here, the generation unit 232 may determine the cut-out area based on the area information and the change information. If the change information includes that the position of a road feature has changed or that a road feature has been removed, the cut-out area may be enlarged from the default dimensions. This is because when the position of a road feature has changed or when a road feature has been removed, the position of the road feature is unclear. On the other hand, if the change information includes that a new road feature has been installed, the cut-out area is set to the default dimensions. This is because when a new road feature has been installed, the position of the road feature is clear.

[0077] When the types of road features include road signs and road markings, the generation unit 232 may determine a vertically elongated cut-out region and a horizontally elongated cut-out region for the camera image.

[0078] Next, the generation unit 232 cuts out a cutout region from the camera image to generate a partial image (step S302), and ends the series of processes.

[0079] Since the partial images are a part of the original camera image, the image capacity can be reduced. In addition, since the same cropping area is set for the camera images captured in one image capture period, the multiple partial images form a video including the position of the road feature where a change has been detected. This makes it possible to clearly detect the change in the road feature by viewing the video. This has been an explanation of one example of the image generation process.

[0080] Fig. 6 is another example of an operation flowchart of the image generation process of the data collection device. Hereinafter, another image generation process of the data collection device 11 will be described with reference to Fig. 6. The data collection device 11 executes the image generation process shown in Fig. 6 every time it receives a determination result requesting transmission of an image and area information including position information indicating the position of a road feature in which a change has been detected.

[0081] First, the generating unit 232 determines, based on the position information of the road feature, an area in the camera image in which it is estimated that the road feature is represented, as a clipping area (step S401).

[0082] When the area information includes a three-dimensional position indicating the position of the road feature, the generation unit 232 estimates the position of the road feature shown in the camera image based on the three-dimensional position of the road feature, the position of the vehicle 10 at the time of image acquisition, and parameters such as the traveling direction of the vehicle 10 and the imaging direction, focal length, and installation position of the camera 2. The generation unit 232 determines the cut-out area so as to include the position of the road feature shown in the camera image. The dimensions of the cut-out area are set, for example, by default. It is preferable that the size of the cut-out area is half or less of the camera image.

[0083] Furthermore, when the region information includes a two-dimensional position representing the position of the road feature and the type of the road feature, the generation unit 232 estimates the height of the road feature based on the type of the road feature to obtain a three-dimensional position representing the position of the road feature. As described above, the generation unit 232 determines the cutout region so as to include the position of the road feature shown in the camera image.

[0084] Furthermore, the generating unit 232 may divide the camera image vertically into M pieces (M is a positive integer) and horizontally into N pieces (N is a positive integer). The generating unit 232 may determine the cropping area by selecting one or more of the divided areas so as to include the positions of road features shown in the camera image.

[0085] The generating unit 232 may also determine the cutout region based on the region information and the change information. If the change information includes that the position of a road feature has changed or that a road feature has been removed, the cutout region may be enlarged from the default dimensions. On the other hand, if the change information includes that a new road feature has been installed, the cutout region is set to the default dimensions.

[0086] Next, the generation unit 232 cuts out a cutout region from the camera image to generate a partial image (step S402), and ends a series of processes. This completes the description of another example of the image generation process.

[0087] The data collection system of the present embodiment described above in detail transmits to the server a partial image including an area determined to include the road feature within a camera image captured by a vehicle at a position where a change in the road feature is detected, thereby enabling the data collection system to reduce communication traffic when transmitting an image including the road feature.

[0088] In the present invention, the image generating system of the above-mentioned embodiment can be appropriately modified without departing from the spirit of the present invention. Furthermore, the technical scope of the present invention is not limited to those embodiments, but extends to the inventions described in the claims and their equivalents.

[0089] For example, in the above-described embodiment, the image acquisition section is determined based on the acquisition target position and the change information. On the other hand, when the change information is not generated, the image acquisition section is determined based on the acquisition target position. For example, the image acquisition section may be a reference section.

[0090] In the above embodiment, the area information is transmitted to the data collection device together with the determination result, but the area information may be transmitted to the data collection device together with the collection target position. When the data collection device receives a determination result requesting transmission of an image, the data collection device generates a partial image based on the area information received in advance. [Explanation of symbols]

[0091] 1. Data collection system 2 Camera 3. Communications equipment 4 Positioning information receiving device 10 Vehicles 11 Data collection equipment 21 Communication Interface 22 Memory 23 Processors 231 Control Unit 232 Generation part 24 Signal Line 12 In-vehicle network 30 Servers 31 Communication Interface 32 Storage Device 33 Memory 34 processors 341 Control Unit 342 Judgment section 343 Generation part 35 Signal Line 40 Communication Network 41 Macrocell base station

Claims

1. a region information generating unit that generates region information for determining a region in an image including road features based on previously acquired feature information representing the road features; a server communication control unit that transmits the area information via a server communication unit; a server having a device communication control unit that receives the area information via a device communication unit; an image generating unit that determines a cutout region to be cut out from an image acquired by the image acquiring unit based on the region information, and cuts out the cutout region from the image to generate a partial image; an image generating device having Including, The image generating system according to claim 1, wherein the device communication control unit transmits the partial image generated by the image generating unit to the server via the device communication unit.

2. the area information generating unit generates the area information based on the feature information representing previously acquired road features, so as to include a type of the road feature in which a change has been detected; The image generating system according to claim 1 , wherein the image generating unit determines an area in the image according to a type of a road feature as the clipping area.

3. the region information generating unit generates the region information based on the feature information so as to include position information of a road feature object in which a change has been detected; 2. The image generation system according to claim 1, wherein the image generation unit determines, as the cut-out area, an area in which the road feature is estimated to be represented in the image acquired using the image acquisition unit, based on the position information of the road feature.

4. the server has a change information generating unit that generates change information representing a type of change in a road feature based on the feature information; the server communication control unit transmits the change information to the image generating device via the server communication unit; The device communication control unit receives the change information via the device communication unit, The image generating system according to claim 1 , wherein the image generating unit determines the cut-out region from the image acquired using the image acquiring unit, based on the change information and the region information.

5. The server has a position information generating unit that generates position information representing a position of a road feature object where a change has been detected based on the feature information, the server communication control unit transmits the location information to the image generating device via the server communication unit; the device communication control unit receives the position information and the change information via the device communication unit; The image generating system according to claim 4 , wherein the image generating unit determines a section in which images are acquired using the image acquiring unit to generate the partial image, based on the position information and the change information.

Images