Data collection device and data collection system

Abstract

To provide a data collection device capable of collecting probe data by determining a position of a lane of a road on which a vehicle is traveling without using a highly accurate map.SOLUTION: A data collection device comprises: a detection section for generating probe data expressing a road feature object based on information expressing a peripheral environment of a vehicle; a generation section for generating lane information expressing a position of a lane of a road on which the vehicle is traveling when the road feature object expressed by the probe data is detected based on information expressing a lane division line in the periphery of the vehicle; a communication control section for transmitting the lane information via a communication section and receiving a determination result which is determined based on the lane information and includes presence / absence of a transmission request requesting the transmission of the probe data; and an information control section for transmitting the probe data via the communication section when the determination result including the transmission request is received.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a data collection device and a data collection system. [Background technology]

[0002] High-precision maps, which are referenced by autonomous driving systems for vehicles, are required to accurately represent road information. High-precision maps represent road features around the road. Therefore, probe data representing road features around the road are collected from vehicles that have actually traveled in a specified area.

[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] If a road has multiple lanes, the server collects probe data for each lane. To generate map information for each lane, a predetermined number of probe data items must be collected for each lane.

[0005] In the case of roads with left-hand traffic, it tends to be more difficult to collect probe data from the leftmost lane compared to other lanes due to parked vehicles and the like.

[0006] For example, Patent Document 1 proposes a traveling probe collection device that displays a driving request position where additional collection of traveling probe information for each lane is required, and prompts the user to drive the vehicle in accordance with the display, thereby efficiently collecting the required traveling probe information for each lane. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2020-140602 A Summary of the Invention [Problem to be solved by the invention]

[0008] However, vehicles that collect probe data are not necessarily equipped with high-precision maps. Vehicles that do not have high-precision maps cannot determine which lane the vehicle is traveling in on the road, and therefore cannot determine whether the vehicle is traveling in a lane for which probe data needs to be collected.

[0009] An object of the present disclosure is to provide a data collection device that can determine the position within a road of the lane in which a vehicle is traveling and collect probe data without using a high-precision map. [Means for solving the problem]

[0010] (1) According to one embodiment, there is provided a data collection device, which includes a detection unit that generates probe data representing road features based on information representing an environment around the vehicle, a generation unit that generates lane information representing the position of a lane in a road on which the vehicle was traveling when the road feature represented by the probe data was detected based on information representing lane markings around the vehicle, a communication control unit that transmits the lane information via a communication unit and receives a determination result including the presence or absence of a transmission request for transmitting the probe data, which is determined based on the lane information, and an information control unit that transmits the probe data via the communication unit when the determination result including the transmission request is received.

[0011] (2) In the data collection device of (1), it is preferable that the lane information includes information indicating whether the lane in which the vehicle is traveling is located on the leftmost side of the road, on the rightmost side of the road, or on a side other than the leftmost or rightmost side of the road.

[0012] (3) In the data collection device of (2), it is preferable that the lane information includes left side information representing road features that define the left edge of the travel lane relative to the vehicle's direction of travel, and right side information representing road features that define the right edge of the travel lane.

[0013] (4) In the data collection device of any of (1) to (4), it is preferable that the detection unit generates a probe data group including a plurality of probe data for each predetermined data collection period, the generation unit determines whether the vehicle has moved between lanes in a road during the data collection period based on information representing lane markings around the vehicle, and if the generation unit determines that the vehicle has moved between lanes in the road during the data collection period, the detection unit generates a first probe data group including a plurality of probe data representing road features detected in the lane before the movement between the lanes and a second probe data group including a plurality of probe data representing road features detected in the lane after the movement between the lanes, and the generation unit generates a first lane information group including a plurality of lane information representing positions of the lanes before the movement between the lanes corresponding to the first probe data group, and a second lane information group including a plurality of lane information representing positions of the lanes after the movement between the lanes corresponding to the second probe data group.

[0014] (5) According to another embodiment, a data collection system is provided, comprising: a data collection device having a detection unit that generates probe data representing road features based on information representing an environment around the vehicle, a generation unit that generates lane information representing the position of a lane in a road on which the vehicle was traveling when the road feature represented by the probe data was detected based on information representing lane markings around the vehicle, a communication control unit that transmits the lane information via a device communication unit and receives a determination result including the presence or absence of a transmission request for transmitting the probe data, determined based on the lane information, and an information control unit that transmits the probe data via the device communication unit when the determination result including the transmission request is received, and a server having a server communication unit, a determination unit that generates a determination result based on the lane information received via the server communication unit and collection lane information representing lanes for which probe data is requested to be collected, and a transmission control unit that transmits the determination result to the data collection device via the server communication unit. Effect of the Invention

[0015] The parking information processing device according to the present invention has an effect of being able to determine the position within the road of the lane in which the vehicle is traveling and collect probe data without using a high-precision map. [Brief description of the drawings]

[0016] [Figure 1] 1 is a schematic configuration diagram of a data collection system in which a data collection device according to an embodiment of the present invention is implemented. [Diagram 2] FIG. 2 is a sequence diagram of a data collection 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 data collection process of a data collection device. [Diagram 5] (A) to (C) are diagrams explaining the generation of lane information, where (A) is a diagram showing a vehicle traveling in the leftmost lane, (B) is a diagram showing a vehicle traveling in a lane other than the leftmost or rightmost lane, and (C) is a diagram showing a vehicle traveling in the rightmost lane. [Figure 6] 13 is an example of an operational flowchart of a lane change determination process of the data collection device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] 1 is a schematic configuration diagram of a data collection system 1 in which a data collection device 11 of the present embodiment is implemented. The data collection system 1 has at least one vehicle 10 and a server 30. The data collection device 11 is implemented in the vehicle 10. The vehicle 10 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 that is connected to a communication network 40 to which the server 30 is connected via a gateway (not shown) or the like.

[0018] 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.

[0019] Vehicle 10 is traveling on road 50. Road 50 has three lanes 51, 52, and 53. Lane 51 is the lane located on the leftmost side of road 50. Lane 53 is the lane located on the rightmost side of road 50. Lane 52 is a lane located other than the leftmost or rightmost side of road 50. Vehicle 10 is traveling on lane 51.

[0020] Lane 51 is divided by lane markings 54 and 55. Lane 52 is divided by lane markings 55 and 56. Lane 53 is divided by lane markings 56 and 57. Lane markings 54 and 57 are represented by solid lines. Lane markings 55 and 56 are represented by dashed lines.

[0021] The vehicle 10 generates probe data representing road features and transmits the probe data to the server 30. The server 30 receives the probe data from the vehicle 10 and generates or updates a high-precision map. The high-precision map is referred to for the autonomous vehicle to drive autonomously.

[0022] In a high definition map, a road is represented as a series of road segments, and a lane is represented as a series of lane segments, each of which is associated with a road segment.

[0023] When a road has multiple lanes, the server 30 collects probe data for each lane. In order to generate or update a high-precision map for each lane, it is necessary to collect a predetermined number of probe data for each lane. In the case of a road with left-hand traffic, it tends to be more difficult to collect probe data from the leftmost lane compared to the other lanes due to parked vehicles, etc.

[0024] In the data collection system 1, when the vehicle 10 is traveling in a lane for which probe data needs to be collected, the vehicle 10 transmits the probe data to the server 30. On the other hand, when the vehicle 10 is traveling in a lane for which probe data does not need to be collected, the vehicle 10 does not transmit the probe data to the server 30.

[0025] Fig. 2 is a sequence diagram of the data collection 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.

[0026] First, the server 30 transmits a collection target area in which probe data is to be collected to the vehicle 10 via the communication network 40 and the macrocell base station 41 (step S101). The collection target area is specified, for example, for one or more continuous road sections. The information representing the collection target area includes information that allows the road section to be determined by positioning information such as GNSS information. In addition, the server 30 sets a target number of probe data to be collected for each lane section associated with the road section in the collection target area.

[0027] When the vehicle 10 enters the collection target area, the vehicle 10 starts generating probe data representing road features based on information representing the environment around the vehicle 10 (step S102). The vehicle 10 generates a probe data group including a plurality of probe data for each predetermined data collection period. For example, the vehicle 10 generates a probe data group at each predetermined cycle (e.g., 10 seconds to several minutes) or each time the vehicle 10 travels a predetermined distance (e.g., 100 m to 1 km).

[0028] Next, the vehicle 10 generates determination information including lane information based on information representing lane markings around the vehicle 10 (step S103). The lane information represents the position of the lane on the road on which the vehicle 10 was traveling when the road feature represented by the probe data was detected. The determination information includes, in addition to the lane information, position information of the vehicle 10 when the road feature represented by the probe data was detected.

[0029] For example, the lane information includes information indicating whether the lane on which the vehicle 10 is traveling is located on the leftmost side of the road, on the rightmost side of the road, or on a side other than the leftmost or rightmost side of the road.

[0030] In the example shown in FIG. 1, the lane information indicates that the lane 51 on which the vehicle 10 is traveling is located on the leftmost side of the road 50.

[0031] Next, the vehicle 10 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 S104).

[0032] The server 30 generates a determination result based on the collected lane information and the determination information. The collected lane information indicates lanes for which probe data is required to be collected. The server 30 transmits the determination result to the vehicle 10 via the communication network 40 and the macrocell base station 41 (step S105).

[0033] 1, the lane 51 on which the vehicle 10 is traveling is a lane for which probe data is requested to be collected. The determination result includes a transmission request for transmitting the probe data.

[0034] Next, the vehicle 10 uses the communication device 3 to transmit the probe data to the server 30 via the macrocell base station 41 and the communication network 40 (step S106).

[0035] Next, the server 30 stores the probe data (step S107) and ends the series of processes. When a target number of pieces of probe data have been collected for one lane section, the server 30 uses the probe data to generate or update a high-precision map.

[0036] According to the data collection system 1 of the present embodiment described above, it is possible to determine the position within the road of the lane in which the vehicle is traveling and collect probe data without using a high-precision map. As a result, the data collection system 1 allows the vehicle 10 to transmit probe data to the server 30 when the vehicle 10 is traveling in a lane for which probe data collection is required. On the other hand, when the vehicle 10 is traveling in a lane for which probe data collection is not required, the vehicle 10 does not transmit probe data to the server 30.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] The data collection device 11 executes a control process, a detection process, and a generation process. 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.

[0047] 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.

[0048] All or part of the functions of the data collection device 11 are functional modules realized by a computer program running on the processor 23, for example. The processor 23 has a control unit 231, a detection unit 232, and a generation unit 233. 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 central processing units (CPUs) 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). Details of the operation of the data collection device 11 will be described later.

[0049] 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.

[0050] 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.

[0051] 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 area, and collection lane information indicating lanes for which probe data is required to be collected. 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.

[0052] 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.

[0053] All or part of the functions of the server 30 are functional modules realized by, for example, a computer program running on the processor 34. 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.

[0054] The control unit 341 determines a collection target area in which probe data is to be collected, based on a predetermined area for generating or updating a high-precision map. The collection target area is specified, for example, for one or more continuous road sections. The information representing the collection target area includes, for example, information that allows the road section to be determined by positioning information based on GNSS information. The control unit 341 also sets a target number of probe data to be collected for each lane section associated with the road section in the collection target area.

[0055] The control unit 341 transmits the collection target area to the vehicle 10 using the communication IF 31 at an area notification time having a predetermined period. In addition, the control unit 341 updates the number of acquired probe data for each lane section every time it receives probe data from the vehicle 10. The target number and the acquired number of probe data for each lane section are an example of collection lane information.

[0056] Each time the determination unit 342 receives determination information, the determination unit 342 generates a determination result based on the lane information included in the determination information and the collected lane information.

[0057] First, the determination unit 342 acquires the position and traveling direction of the vehicle 10 during the data collection period when the probe data was generated, based on the position information included in the determination information. Then, the determination unit 342 identifies a road section within the collection target area, based on the position and traveling direction of the vehicle 10 at the time when the probe data was generated. The determination unit 342 compares the target number of probe data with the acquired number for the lanes represented by the lane information among the lane sections associated with this road section. Here, the lane information indicates the position of the lane in the road on which the vehicle 10 was traveling when the road feature represented by the probe data was detected.

[0058] When the number of acquired probe data is less than the target number, the determination unit 342 generates a determination result including a transmission request for transmitting the probe data. On the other hand, when the number of acquired probe data is equal to the target number, the determination unit 342 generates a determination result not including a transmission request.

[0059] The lane information indicates whether the lane on which the vehicle 10 is traveling is located on the leftmost side of the road, on the rightmost side of the road, or on a side other than the leftmost or rightmost side of the road.

[0060] Examples of lanes for which it is difficult to reach the target number of probe data acquisitions include the leftmost lane and the rightmost lane on the road. On the other hand, road features are often located on the leftmost or rightmost lane on the road.

[0061] The determination unit 342 generates a determination result including a transmission request to transmit probe data for the lane located on the leftmost side, the lane located on the rightmost side, and lanes other than the leftmost and rightmost lanes, until the number of acquired probe data reaches a target number.

[0062] If the road has three lanes, the number of lanes other than the leftmost and rightmost lanes is one. In this case, the target number is set for this one lane. On the other hand, if the road has four lanes, the number of lanes other than the leftmost and rightmost lanes is two. In this case, the target number may be set to twice the number of lanes set for one lane. Since the number of vehicles traveling on lanes other than the leftmost and rightmost lanes is relatively large, statistically, approximately the same number of probe data can be collected for one lane.

[0063] The determination unit 342 may generate a determination result that requests transmission of an image showing the environment around the vehicle 10 together with the probe data. For example, for a lane section in which a change in a road feature has been detected, it is preferable to obtain an image of the lane section to confirm the change in the road feature. In this case, the determination unit 342 generates a determination result that includes a request to transmit the image together with the probe data.

[0064] The generating unit 343 generates a high-precision map using the collected probe data and images. The generating unit 343 also updates the high-precision map using the collected probe data. For example, the generating unit 343 compares a newly collected road feature with a previously collected road feature for the lane section to be updated. If there is no previously collected road feature corresponding to the newly collected road feature, the generating unit 343 determines that a new road feature has been installed in the lane section. If there is no newly collected road feature corresponding to a previously collected road feature, the generating unit 343 determines that the road feature has been removed from the lane section. The generating unit 343 adds or deletes a road feature in association with the lane section to update the high-precision map information. The high-precision map is stored in the storage device 32. The generating unit 343 distributes the high-precision map to the autonomous vehicle via the communication IF 31.

[0065] Fig. 4 is an example of an operation flowchart of the data collection process of the data collection device 11. Hereinafter, the data collection process of the data collection device 11 will be described with reference to Fig. 4. The data collection device 11 executes the data collection process shown in Fig. 4 at each data collection process time having a predetermined period.

[0066] First, the control unit 231 determines whether or not the current position of the vehicle 10 represented by the positioning information is included in the collection target area (step S201).

[0067] If the current position of the vehicle 10 is included in the collection target area (step S201-Yes), the detection unit 232 generates probe data representing road features based on the camera image (step S202). The detection unit 232 may generate a probe data group including a plurality of probe data for each data collection period. For example, the data collection period may be a predetermined cycle (e.g., 10 seconds to several minutes) or a predetermined travel distance (e.g., 100 m to 1 km) of the vehicle 10.

[0068] The detection unit 232 detects predetermined road features from the camera image. The predetermined road features are road features that are shown on the high-precision map to be generated or updated. For example, the predetermined road features are various road markings, various road signs, road edges, guard rails, traffic lights, or poles for installing road signs, etc. The detection unit 232 then generates probe data that indicates the types of road features detected on the camera image and the positions of the road features.

[0069] For example, the detection unit 232 has a classifier that has been machine-learned to detect road features shown in an input image. As the classifier, for example, a deep neural network (DNN) that has been trained in advance to detect the area and type of road features shown in an input image can be used.

[0070] The detection unit 232 may use a classifier other than the DNN. For example, the detection unit 232 may use a support vector machine (SVM) as a classifier that is trained in advance to receive a feature (e.g., Histograms of Oriented Gradients, HOG) calculated from a window set on an image as input and output a confidence level that the road feature to be detected is represented in the window. Alternatively, the detection unit 232 may detect the road feature by performing template matching between a template representing the road feature to be detected and the image.

[0071] The detection unit 232 estimates the position of the road feature depicted in the object area detected from the camera image based on parameters such as the direction from the camera 2, the position of the vehicle 10 at the time of image generation, the direction of travel of the vehicle 10 and the imaging direction of the camera 2, the focal length and the installation position, which correspond to the center of gravity of the object area detected from the camera image.

[0072] The detection unit 232 may also track a road feature detected from the camera images and obtain the area of ​​the road feature depicted in each of the two camera images. The detection unit 232 may estimate the position of the road feature using a triangulation method based on the area of ​​the road feature depicted in the two camera images and the position and traveling direction of the vehicle 10 at the time when each camera image was captured.

[0073] The detection unit 232 generates probe data including information indicating the type and estimated position of the detected road feature. The detection unit 232 associates the probe data with position information indicating the position of the vehicle 10 at the camera image acquisition time when the camera image was acquired, and stores the probe data in the memory 22. The memory 22 stores a probe data group including the position information of the vehicle 10 arranged in chronological order and the probe data associated with the position information.

[0074] Furthermore, the detection unit 232 may store the camera image at the time when the probe data is detected in the memory 22 in association with position information indicating the position of the vehicle 10 at the camera image acquisition time when the camera image was acquired. The memory 22 stores a group of camera images including the position information of the vehicle 10 arranged in chronological order and the camera images associated with the position information.

[0075] Next, the generating unit 233 generates determination information including lane information based on the camera image (step S203). The camera image is an example of information representing lane markings around the vehicle 10. The generating unit 233 generates a plurality of pieces of lane information within a data collection period during which the probe data is generated.

[0076] Specifically, the generation unit 233 generates lane information indicating whether the lane in which the vehicle 10 is traveling is located on the leftmost side of the road, on the rightmost side of the road, or on a side other than the leftmost or rightmost side of the road.

[0077] For example, the generating unit 233 has a classifier that has been machine-learned to detect lane markings shown in an input image. As the classifier, for example, a deep neural network (DNN) that has been trained in advance to detect the area and type of lane markings shown in an input image from the image can be used. The classifier may also detect road edges.

[0078] The generating unit 233 may use a classifier other than a DNN. For example, the generating unit 233 may use, as a classifier, a support vector machine (SVM) that is trained in advance to receive a feature amount (e.g., Histograms of Oriented Gradients, HOG) calculated from a window set on an image as input and output a confidence level that the lane marking to be detected is represented in the window. Alternatively, the generating unit 233 may detect the lane marking by performing template matching between a template representing the lane marking to be detected and the image.

[0079] The generating unit 233 detects the lane markings located on the left side of the vehicle 10 and the lane markings located on the right side of the vehicle 10 based on the area of ​​the lane markings in the camera image. Since the imaging direction of the camera 2 relative to the traveling direction of the vehicle 10 is known, the expected range in which the lane markings are expected to be represented on the camera image is also known. This expected range includes the left side area and the right side area with respect to the traveling direction of the vehicle 10. The generating unit 233 determines whether the lane markings are detected in the expected range. In addition, solid lines and dashed lines are detected as the types of lane markings. Then, the generating unit 233 generates lane information based on the types of lane markings located on the left and right sides of the vehicle 10. If the classifier can detect road edges, the generating unit 233 may generate lane information based on the positions of the road edges.

[0080] Fig. 5(A) to Fig. 5(C) are diagrams for explaining generation of lane information. Fig. 5(A) is a diagram showing the vehicle 10 traveling in the lane located at the leftmost position. Fig. 5(B) is a diagram showing the vehicle 10 traveling in a lane other than the leftmost or rightmost position. Fig. 5(C) is a diagram showing the vehicle 10 traveling in the lane located at the rightmost position.

[0081] 5(A), the generation unit 233 detects that a solid lane marking 54 is located on the left side of the vehicle 10, and detects that a dashed lane marking 55 is located on the right side of the vehicle 10. The generation unit 233 generates lane information indicating that the lane 51 on which the vehicle 10 is traveling is located on the leftmost side of the road 50, based on the camera image.

[0082] 5(B), the generation unit 233 detects that a dashed lane marking 55 is located on the left side of the vehicle 10, and detects that a dashed lane marking 56 is located on the right side of the vehicle 10. The generation unit 233 generates lane information indicating that the lane 52 on which the vehicle 10 is traveling is located other than the leftmost or rightmost side of the road 50, based on the camera image.

[0083] 5(C), the generation unit 233 detects that a dashed lane marking 56 is located on the left side of the vehicle 10, and detects that a solid lane marking 57 is located on the right side of the vehicle 10. The generation unit 233 generates lane information indicating that the lane 53 on which the vehicle 10 is traveling is located on the leftmost side of the road 50, based on the camera image.

[0084] The generation unit 233 associates the lane information detected from each camera image with position information indicating the position of the vehicle 10 at the camera image acquisition time when the camera image was acquired, and stores the information in the memory 22.

[0085] Furthermore, the generation unit 233 determines whether the vehicle 10 is moving between lanes on the road based on the camera image. If no lane markings are detected in an expected range where lane markings are expected to be represented on the camera image, the generation unit 233 determines that the vehicle 10 is moving between lanes on the road. If it is determined that the vehicle 10 is moving between lanes on the road, the generation unit 233 stores in the memory 22 a movement flag indicating that the vehicle 10 is moving between lanes in association with position information indicating the position of the vehicle 10 at the camera image acquisition time when the camera image was acquired.

[0086] The generating unit 233 generates determination information including lane information, a movement flag, and position information in association with the data collection period, and stores the information in the memory 22. The determination information includes the position information arranged in chronological order, and the lane information or the movement flag associated with the position information. Note that, when the vehicle 10 is not moving between lanes on the road, the determination information does not include the movement flag.

[0087] Next, the data collecting device 11 executes a lane change determination process (step S204). This lane change determination process will be described below with reference to FIG.

[0088] 6 is an example of an operation flowchart of lane change determination processing of the data collection device 11. First, the generation unit 233 determines whether or not the vehicle 10 has moved between lanes on a road during a data collection period based on a movement flag generated using a camera image (step S301). Since the camera image is an example of information representing lane markings around the vehicle 10, the movement flag is also generated based on the camera image. Determining whether or not the vehicle 10 has moved between lanes on a road based on the movement flag is an example of determining whether or not the vehicle 10 has moved between lanes on a road based on information representing lane markings around the vehicle 10.

[0089] When the determination information includes a movement flag, the generation unit 233 determines that the vehicle 10 has moved between lanes on the road. On the other hand, when the determination information does not include a movement flag, the generation unit 233 determines that the vehicle 10 has not moved between lanes on the road.

[0090] When the vehicle 10 moves between lanes on the road (step S301-Yes), the detection unit 232 generates a first probe data group including a plurality of probe data representing road features detected in the lane before the movement between the lanes, and a second probe data group including a plurality of probe data representing road features detected in the lane after the movement between the lanes (step S302).

[0091] The detection unit 232 generates, as a first probe data group, a plurality of probe data associated with a position before the position of the vehicle 10 associated with the movement flag included in the determination information. The detection unit 232 also generates, as a second probe data group, a plurality of probe data associated with a position after the position of the vehicle 10 associated with the movement flag included in the determination information. The first probe data group and the second probe data group are generated based on the probe data group for the data collection period. The first probe data group and the second probe data group are stored in the memory 22.

[0092] Furthermore, the generating unit 233 generates, as a first camera image group, a plurality of camera images associated with a position before the position of the vehicle 10 associated with the movement flag included in the determination information. The generating unit 233 generates, as a second camera image group, a plurality of camera images associated with a position after the position of the vehicle 10 associated with the movement flag included in the determination information. The first camera image group and the second camera image group are generated based on the camera image group during the data collection period. The first camera image group and the second camera image group are stored in the memory 22.

[0093] Next, the generating unit 233 generates first determination information including a first lane information group corresponding to the first probe data group and second determination information including a second lane information group corresponding to the second probe data group (step S303), and ends the series of processes. The first lane information group includes a plurality of lane information representing the position of the lane before moving between lanes. The second lane information group includes a plurality of lane information representing the position of the lane after moving between lanes.

[0094] The generating unit 233 generates, as a first lane information group, a plurality of pieces of lane information associated with positions prior to the position of the vehicle 10 associated with the movement flag included in the determination information. The first determination information includes position information arranged in chronological order before the vehicle 10 moves between lanes, and a first lane information group associated with the position information.

[0095] Furthermore, the detection unit 232 generates, as a second lane information group, a plurality of pieces of lane information associated with positions subsequent to the position of the vehicle 10 associated with the movement flag included in the determination information. The second determination information includes position information arranged in chronological order after the vehicle 10 moves between lanes, and a second lane information group associated with the position information. The first determination information and the second determination information are generated based on the determination information for the data collection period. The first determination information and the second determination information are stored in the memory 22.

[0096] On the other hand, if the vehicle 10 is not moving between lanes on the road (step S301-No), the series of processes ends. This concludes the description of the lane change determination process.

[0097] Next, the control unit 231 transmits the determination information to the server 30 via the communication device 3 (step S205). If the vehicle 10 has moved between lanes during the data collection period, the control unit 231 transmits the first determination information and the second determination information to the server 30. On the other hand, if the vehicle 10 has not moved between lanes during the data collection period, the control unit 231 transmits one piece of determination information to the server 30. The control unit 231 is an example of a communication control unit.

[0098] Next, the control unit 231 receives the determination result from the server 30 via the communication device 3 (step S206). If the vehicle 10 has moved between lanes during the data collection period, the determination result includes the presence or absence of a transmission request before and after the vehicle 10 has moved between lanes. There are cases where a request is made to transmit probe data only before the vehicle 10 has moved between lanes, only after the vehicle 10 has moved between lanes, or both before and after the vehicle 10 has moved between lanes.

[0099] Next, the control unit 231 judges whether the judgment result includes a transmission request (step S207). If the judgment result includes a transmission request (step S207-Yes), the control unit 231 transmits the probe data group to the server 30 via the communication device 3 (step S208), and ends the series of processes. The control unit 231 is an example of an information control unit.

[0100] If the vehicle 10 moves between lanes during the data collection period in which the probe data is generated, the probe data according to the determination result is transmitted to the server 30. The control unit 231 transmits the first probe data group and / or the second probe data group to the server 30 via the communication device 3.

[0101] On the other hand, if the vehicle 10 does not move between lanes during the data collection period, the control unit 231 transmits one probe data group to the server 30.

[0102] Furthermore, when the determination result includes a request to transmit images together with the probe data, the control unit 231 transmits the camera images together with the probe data to the server 30 via the communication device 3.

[0103] In this case, if the vehicle 10 moves between lanes during the data collection period, the control unit 231 transmits the first camera image group and / or the second camera image group to the server 30 via the communication device 3. On the other hand, if the vehicle 10 does not move between lanes during the data collection period, the control unit 231 transmits one camera image group to the server 30.

[0104] On the other hand, if the determination result indicates that the transmission request is not included (step S207-No), the series of processes ends.

[0105] The data collection system of this embodiment described above in detail can determine the position within the road of the lane in which the vehicle is traveling and collect probe data without using a high-precision map. As a result, in the data collection system, when the vehicle is traveling in a lane for which probe data collection is required, the vehicle transmits probe data to the server. On the other hand, when the vehicle is traveling in a lane for which probe data collection is not required, the vehicle does not transmit probe data to the server 30.

[0106] Furthermore, in the data collection system of this embodiment, probe data is transmitted to the server only when the vehicle is traveling in a lane for which probe data collection is required, making it possible to efficiently collect probe data for each lane on a road having multiple lanes.

[0107] In the present invention, the data collection device and data collection system of the above-mentioned embodiments can be modified as appropriate 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.

[0108] For example, in the above embodiment, a plurality of pieces of lane information are transmitted to the server for each data collection period, but lane information may be transmitted to the server each time probe data is generated. Then, when a determination result including a transmission request is received, the probe data is transmitted to the server.

[0109] In the above-described embodiment, the lane information generated by the data collection device includes information indicating that the lane on the road on which the vehicle is traveling is located at the leftmost side, the rightmost side, or a position other than the leftmost side or the rightmost side. The lane information is not particularly limited as long as it represents the position of the lane on the road on which the vehicle is traveling when the road feature represented by the probe data is detected. For example, the lane information may include left side information representing a road feature that defines the left edge of the traveling lane and right side information representing a road feature that defines the right edge of the traveling lane with respect to the traveling direction of the vehicle.

[0110] Specifically, the left side information may be a solid or dashed lane marking, or a road edge. The right side information may be a solid or dashed lane marking, or a road edge. In this case, the server can determine, based on the left side information and the right side information, whether the lane position on the road on which the vehicle is traveling is the leftmost lane, the rightmost lane, or a lane position other than the leftmost or rightmost lane. [Explanation of symbols]

[0111] 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 Detection unit 233 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 detection unit for generating probe data representative of road features based on information representative of the environment around the vehicle; a generating unit that generates lane information representing a position of a lane on a road on which a vehicle is traveling when a road feature represented by the probe data is detected, based on information representing lane markings around the vehicle; a communication control unit that transmits the lane information via a communication unit and receives a determination result including the presence or absence of a transmission request for transmitting the probe data, the determination result being determined based on the lane information; an information control unit that transmits the probe data via the communication unit when the determination result including the transmission request is received; A data collection device comprising:

2. The data collection device of claim 1 , wherein the lane information includes information indicating whether the lane on which the vehicle is traveling is located on the leftmost side of the road, on the rightmost side of the road, or other than the leftmost or rightmost side of the road.

3. 2. The data collection device according to claim 1, wherein the lane information includes left side information representing road features that define the left edge of the driving lane relative to the vehicle's traveling direction, and right side information representing road features that define the right edge of the driving lane.

4. the detection unit generates a probe data group including a plurality of the probe data for each predetermined data collection period, The generating unit determines whether the vehicle moves between lanes in a road during the data collection period based on the information representing lane markings around the vehicle; and 4. The data collection device according to claim 1, wherein when the generation unit determines that the vehicle has moved between lanes in a road during the data collection period, the detection unit generates a first probe data group including the plurality of probe data representing road features detected in the lane before the movement between lanes and a second probe data group including the plurality of probe data representing road features detected in the lane after the movement between lanes, and the generation unit generates a first lane information group including the plurality of lane information representing positions of the lane before the movement between lanes corresponding to the first probe data group, and a second lane information group including the plurality of lane information representing positions of the lane after the movement between lanes corresponding to the second probe data group.

5. a detection unit for generating probe data representative of road features based on information representative of the environment around the vehicle; a generating unit that generates lane information representing a position of a lane on a road on which a vehicle is traveling when a road feature represented by the probe data is detected, based on information representing lane markings around the vehicle; a communication control unit that transmits the lane information via a device communication unit and receives a determination result including the presence or absence of a transmission request for transmitting the probe data, the determination result being determined based on the lane information; an information control unit that transmits the probe data via the device communication unit when the determination result including the transmission request is received; A data collection device having A server communication unit; a determination unit that generates the determination result based on the lane information received via the server communication unit and collection lane information that indicates lanes for which the probe data is required to be collected; a transmission control unit that transmits the determination result to the data collection device via the server communication unit; A server having A data collection system comprising:

Images