In-vehicle device and data collection system
The in-vehicle device accurately detects visibility reduction of traffic safety facilities by identifying plant obstructions, allowing for efficient improvement through trend analysis and countermeasure prioritization.
Patent Information
- Application Number
- JP2022105046
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2022-06-29
- Publication Date
- 2026-01-07
- Estimated Expiration
- 2042-06-29
AI Technical Summary
Conventional technologies struggle to accurately determine the reduction in visibility of traffic safety facilities due to obstruction by surrounding vegetation such as trees and hedges.
An in-vehicle device equipped with a camera and GPS sensor detects the positions of traffic safety facilities and plants, determining if the plant positions obstruct visibility by overlapping or being adjacent to the facilities, and transmits data to a cloud-based data collection system for trend analysis and prioritization of countermeasures.
Accurately determines visibility reduction of traffic safety facilities, enabling efficient improvement by prioritizing pruning or other measures based on trend analysis.
Smart Images

Figure 0007795427000001 
Figure 0007795427000002 
Figure 0007795427000003
Abstract
Description
[Technical Field]
[0001] The present invention relates to an in-vehicle device and Data collection system Mu Regarding. [Background technology]
[0002] BACKGROUND ART Various techniques have been proposed in the past for identifying traffic safety facilities such as traffic lights and road signs by performing image processing on image data of the captured traffic safety facilities (see, for example, Patent Document 1). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2007-265292 Summary of the Invention [Problem to be solved by the invention]
[0004] However, the above-mentioned traffic safety facilities may be obscured by surrounding vegetation such as trees and hedges, reducing their visibility. However, the conventional technology has room for improvement in terms of accurately determining the reduction in visibility of traffic safety facilities.
[0005] The present invention has been made in view of the above, and provides an in-vehicle device capable of accurately determining a decrease in visibility of a traffic safety facility. and Data collection system M The purpose is to provide. [Means for solving the problem]
[0006] In order to solve the above problems and achieve the object, the present invention provides an in-vehicle device including a controller. The controller acquires image data of the surroundings of a vehicle, and detects the positions of traffic safety facilities and plants present around the traffic safety facilities based on the acquired image data. The controller also executes a determination process to determine whether the detected positions of the plants are obstacles that obstruct the visibility of the traffic safety facilities. [Effects of the Invention]
[0007] According to the present invention, it is possible to accurately determine the decrease in visibility of a traffic safety facility. [Brief explanation of the drawings]
[0008] [Figure 1] FIG. 1 is a diagram showing an overview of a data collection system according to an embodiment. [Figure 2] FIG. 2 is a block diagram illustrating an example of the configuration of a data collection system according to the embodiment. [Figure 3] FIG. 3 is a block diagram showing an example of the configuration of the in-vehicle device. [Figure 4] FIG. 4 is a diagram illustrating an example of the object information. [Figure 5] FIG. 5 is a diagram for explaining detection of the positions of traffic safety facilities and the like in image data. [Figure 6] FIG. 6 is a block diagram illustrating an example of the configuration of the data collecting device. [Figure 7] FIG. 7 is a diagram illustrating an example of collected information. [Figure 8] FIG. 8 is a diagram illustrating an example of the trend information. [Figure 9] FIG. 9 is a diagram showing the display of the manager terminal device to which the trend information has been notified. [Figure 10] FIG. 10 is a flowchart showing a processing procedure executed by the in-vehicle device according to the embodiment. [Figure 11] FIG. 11 is a flowchart showing a processing procedure executed by the data collection device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION
[0009] Hereinafter, embodiments of an on-vehicle device, a data collection device, a data collection system, and a data collection method disclosed in the present application will be described in detail with reference to the accompanying drawings. Note that the present invention is not limited to the embodiments described below.
[0010] <Data collection system overview> First, an overview of the data collection system according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an overview of the data collection system according to the embodiment.
[0011] 1, a data collection system 1 according to an embodiment includes on-vehicle devices 10-1, 10-2, etc., mounted on vehicles V-1, V-2, etc., respectively, and a data collection device 100. In the following, the term "vehicle V" will be used to refer to vehicles in general, and the term "on-vehicle device 10" will be used to refer to on-vehicle devices in general.
[0012] The in-vehicle device 10 is a device that includes various sensors such as a camera and a GPS (Global Positioning System) sensor, a storage device, a microcomputer, etc., and is connected to the data collection device 100 so as to be able to communicate with it.
[0013] The camera described above captures, for example, an image of the periphery of the vehicle V and outputs image data. The image data is video data, but is not limited to this and may be still image data, etc. The GPS sensor detects the position of the vehicle V. The in-vehicle device 10 may be, but is not limited to, a drive recorder.
[0014] The data collection device 100 is configured as a cloud server that provides cloud services via a network N (see FIG. 2) such as the Internet or a mobile phone network, and executes various processes. The data collection device 100 may be configured to perform distributed processing using multiple servers.
[0015] Meanwhile, traffic safety facilities are installed along the road on which the vehicle V travels. Examples of traffic safety facilities include traffic lights, road signs, traffic information boards, etc. In FIG. 1, a traffic light A is shown as an example of a traffic safety facility.
[0016] Furthermore, there may be plants B, such as trees or hedges, around traffic safety facilities such as traffic signal A. Such plants B may grow and cover the signal lights of traffic signal A, reducing the visibility of traffic signal A.
[0017] Therefore, the on-vehicle device 10 according to this embodiment is configured to be able to accurately determine the decrease in visibility of a traffic safety facility (here, traffic light A).
[0018] Specifically, the in-vehicle device 10 (more precisely, the in-vehicle device 10-1) uses a camera to capture an image of the periphery of the vehicle V and acquires image data of the image of the periphery of the vehicle V (step S1). Next, based on the acquired image data, the in-vehicle device 10 executes a determination process to determine whether the position of the plant B in the image data is an obstruction position that obstructs the visibility of the traffic light A (step S2).
[0019] Specifically, the in-vehicle device 10 detects the positions of traffic light A and plant B in the image data. Then, if the position of plant B in the image data overlaps with or is adjacent to the position of traffic light A, the in-vehicle device 10 determines that the position of plant B is an obstruction position. In other words, because the position of plant B is an obstruction position, the in-vehicle device 10 can determine that the visibility of the traffic safety facility (here, traffic light A) has decreased or is likely to decrease.
[0020] On the other hand, if the position of plant B in the image data does not overlap with the position of traffic light A and is separated by a predetermined distance or more, the in-vehicle device 10 determines that the position of plant B is not an obstruction position. In other words, since the position of plant B is not an obstruction position, the in-vehicle device 10 can determine that the visibility of the traffic safety facility (here, traffic light A) has not decreased or is not likely to decrease.
[0021] The predetermined distance is set to a value that indicates that the position of plant B and the position of traffic light A are not adjacent to each other, but is not limited to this. The determination of whether the position of plant B is an obstruction position will be described later with reference to Figures 3 and 5.
[0022] In this way, in the vehicle-mounted device 10 of this embodiment, the position of the traffic safety facility (traffic light A) and the position of the plant B are detected in the image data of the area around the vehicle V, and a determination process is performed to determine whether the position of the detected plant B is an obstacle position.
[0023] As a result, in this embodiment, the decrease in visibility of the traffic safety facility (here, traffic light A) can be accurately determined based on the determination result of the determination process.
[0024] Furthermore, if the visibility of traffic light A decreases, it is necessary to take measures such as pruning plant B to improve the visibility of traffic light A. Therefore, in this embodiment, the trend of the impact of plant B on the visibility of traffic light A is analyzed. Then, in this embodiment, the trend information that is the analysis result is notified to the manager of the traffic safety facility, so that measures such as pruning can be taken preferentially for plant B at points where visibility tends to decrease.
[0025] Specifically, when the position of plant B is determined to be an obstacle position in the determination process, the vehicle-mounted device 10 transmits the image data used in the determination process, imaging position information indicating the imaging position X where the image data was captured, and the like to the data collection device 100 (step S3). Note that the vehicle-mounted device 10 may also transmit imaging time zone information indicating the time zone where the image data was captured to the data collection device 100.
[0026] When the data collection device 100 collects image data and the like from the in-vehicle device 10, it sets collection conditions for collecting image data and the like from the target vehicle V. The collection conditions include, but are not limited to, information such as the imaging position X where the image data was captured, the imaging time period, and the collection time interval (for example, once a day).
[0027] The data collection device 100 then distributes the set collection conditions to the in-vehicle device 10 of the vehicle V that is the distribution target (step S4). The distribution target may be, for example, an in-vehicle device 10 such as a vehicle V that is registered in a prefecture that includes the image capture position X, a vehicle V that is estimated to pass through the image capture position X relatively frequently based on its driving history, or a vehicle V that is estimated to pass through the image capture position X based on route information from a navigation device, but these are merely examples and are not limited to these. Note that FIG. 1 shows an example in which the in-vehicle device 10-2 of vehicle V-2 is the distribution target.
[0028] Then, when the vehicle V-2 passes through the imaging position X of the collection condition described above, the in-vehicle device 10-2 captures images of the traffic light A and the plant B with the camera, and acquires progress image data including the traffic light A and the plant B (step S5).
[0029] The above-mentioned elapsed image data is image data captured when time has elapsed since the image data was captured by the camera of the in-vehicle device 10-1. Specifically, the elapsed image data is image data captured when time has elapsed since the vehicle V captured the image data in the past (here, the image data of step S1), and is image data that includes a traffic safety facility (here, traffic light A) and a plant B. Note that, while FIG. 1 shows an example in which the vehicle (vehicle V-1) that captured the image data in the past and the vehicle (vehicle V-2) that captured the elapsed image data are different vehicles, this is not limiting and they may be the same vehicle.
[0030] Next, the in-vehicle device 10-2 transmits the acquired progress image data to the data collection device 100 (step S6).
[0031] Next, the data collection device 100 generates trend information indicating the trend of the effect of plant B on the visibility of traffic light A based on the collected image data and progress image data (step S7).
[0032] For example, the data collection device 100 compares the image data with the time-lapse image data, and if the area where the position of plant B and the position of traffic light A overlap in the image data or the time-lapse image data increases over time, the data collection device 100 generates trend information indicating a tendency for the visibility of traffic light A to deteriorate. Specifically, the data collection device 100 generates trend information in which a high countermeasure priority is set, indicating the priority of taking countermeasures such as pruning work on the plant B.
[0033] Next, the data collection device 100 notifies the generated trend information to the administrator of the traffic safety facilities (step S8). Note that the data collection device 100 maps the locations of traffic safety facilities that have been determined to have reduced visibility based on the trend information, etc., along with the priority of countermeasures, and notifies the administrator of this, which will be described later with reference to FIG.
[0034] Then, based on the notified trend information, the manager can prioritize measures such as pruning for, for example, plants B near a traffic safety facility that have been determined to have reduced visibility and that have been set with a high priority. As a result, in this embodiment, even if there are multiple traffic safety facilities that have been determined to have reduced visibility, it is possible to efficiently improve the visibility of the traffic safety facilities.
[0035] <Overall configuration of the data collection system> Fig. 2 is a block diagram showing an example of the configuration of a data collection system 1 according to an embodiment. Note that in the block diagrams such as Fig. 2, only components necessary for explaining the features of the embodiment are shown, and descriptions of general components are omitted.
[0036] In other words, each component shown in a block diagram such as Figure 2 is a functional concept and does not necessarily have to be physically configured as shown. For example, the specific form of distribution and integration of each block is not limited to that shown, and all or part of it can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.
[0037] In addition, in the explanation of FIG. 2 and subsequent figures, the explanation of components that have already been explained may be simplified or omitted.
[0038] 2, the data collection system 1 according to the embodiment includes the above-described in-vehicle device 10, a data collection device 100, and an administrator terminal device 200, and each device is communicably connected to each other via a communication network N. Note that, for the sake of simplicity, one in-vehicle device 10 is shown in FIG. 2, but multiple in-vehicle devices 10 may be used.
[0039] The administrator terminal device 200 is a device used by an administrator who manages traffic safety facilities. The administrator terminal device 200 may be, for example, a PC (Personal Computer), a smartphone, or a tablet terminal, but is not limited to these.
[0040] <In-vehicle equipment> Next, the configuration of the in-vehicle device 10 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing an example configuration of the in-vehicle device 10. As shown in Fig. 3, the in-vehicle device 10 includes a communication unit 11, a camera 12, a GPS sensor 13, an in-vehicle controller (control unit) 20, and a storage unit 30.
[0041] The communication unit 11 is a communication interface that is connected to the communication network N so as to enable two-way communication, and transmits and receives information to and from the data collection device 100, the administrator terminal device 200, and the like.
[0042] The camera 12 captures images of the surroundings of the vehicle V (for example, the front, rear, left and right directions, etc.) and outputs the captured image data to the in-vehicle controller 20. The GPS sensor 13 detects the position of the vehicle V and outputs position information indicating the detected position of the vehicle V to the in-vehicle controller 20.
[0043] The storage unit 30 is configured with a storage device such as a non-volatile memory, a data flash, a hard disk drive, etc. The storage unit 30 stores image data 31, a detection model 32, object information 33, collection condition information 34, progress image data 35, various programs, etc.
[0044] The image data 31 is image data of an image of the periphery of the vehicle V. The detection model 32 is a model for detecting the positions of traffic safety facilities, plants, etc. in the image data. In other words, the detection model 32 is a model for extracting and detecting areas in the image data where traffic safety facilities and plants are imaged.
[0045] The detection model 32 is obtained by learning using a machine learning algorithm such as a deep neural network (DNN). The detection model 32 may be obtained by supervised learning. The detection model 32 may be configured to use a machine learning algorithm such as a support vector machine (SVM) that uses a histogram of gradient (HOG) feature. The on-board device 10 may also be configured to detect the positions of traffic safety facilities and plants using, for example, template matching, without using a detection model that has undergone machine learning.
[0046] The object information 33 is information about the object to be analyzed, specifically, information about the object to be analyzed in the process of analyzing the tendency of the influence of plants on the visibility of traffic safety facilities. More specifically, the object information 33 includes information about traffic safety facilities whose visibility has been determined to be reduced or that may be reduced because the location of the plant is an obstruction position.
[0047] Here, the object information 33 will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the object information 33. As shown in Fig. 4, the object information 33 includes items such as "object information ID," "image data," "image capture location," "image capture time period," and "type of traffic safety facility," and the data for each item is associated (linked) with one another.
[0048] "Object information ID" is identification information that identifies the object information. "Image data" is image data used in the determination process in which the position of the plant was determined to be an obstruction position. In the example shown in Figure 4, for convenience, "image data" is written abstractly as "D1", but it is assumed that specific information is stored in "D1". Below, other information may also be written abstractly.
[0049] "Imaging location" is imaging location information indicating the imaging location where the corresponding image data was captured. "Imaging time period" is imaging time period information indicating the time period when the corresponding image data was captured. "Imaging time period" includes information such as 9:00 to 9:30. Note that "imaging time period" may also include imaging time information such as the time when the corresponding image data was captured (e.g. 9:00).
[0050] The "type of traffic safety facility" is information indicating the type of traffic safety facility detected in the corresponding image data. The "type of traffic safety facility" includes, for example, information indicating a traffic signal, a road sign, a traffic information board, etc.
[0051] In the example shown in Figure 4, the object information identified by the object information ID "C1" indicates that the image data is "D1", the imaging location is "E1", the imaging time period is "F1", and the type of traffic safety facility is "G1".
[0052] Returning to the explanation of Fig. 3, the collection condition information 34 is information indicating collection conditions for collecting image data (more specifically, progress image data) about traffic safety facilities that have been determined to have reduced visibility or that may have reduced visibility. As described above, the collection condition information 34 includes information such as the imaging position X (see Fig. 1) at which the image data used in the determination process that determined that the position of the plant was an obstacle position was captured, the imaging time period, and the collection time interval. Note that the imaging time period in the collection condition information 34 may include information about the time at which the image data used in the determination process was captured.
[0053] The progress image data 35 is progress image data including traffic safety facilities and plants, which is captured when the vehicle V passes the above-mentioned imaging position X (see FIG. 1). Specifically, the progress image data 35 is progress image data obtained after a certain time has elapsed since the vehicle V captured image data (image data used in the determination process) in the past, and is image data including traffic safety facilities and plants.
[0054] The in-vehicle controller 20 includes an acquisition unit 21, a detection unit 22, a determination unit 23, an upload unit 24, and a reception unit 25, and includes, for example, a computer having a CPU (Central Processing Unit), (Read Only Memory), RAM (Random Access Memory), a hard disk drive, an input / output port, and various other circuits. The CPU of the computer, for example, reads and executes a program stored in a ROM, thereby functioning as the acquisition unit 21, the detection unit 22, the determination unit 23, the upload unit 24, and the reception unit 25 of the in-vehicle controller 20. The in-vehicle controller 20 is an example of a controller.
[0055] In addition, at least some or all of the acquisition unit 21, detection unit 22, judgment unit 23, upload unit 24 and reception unit 25 of the vehicle controller 20 can be configured using hardware such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).
[0056] The acquisition unit 21 acquires image data of the periphery of the vehicle V from the camera 12, and stores the acquired data in the storage unit 30 as image data 31. At this time, the acquisition unit 21 detects the position of the vehicle V from the GPS sensor 13, and stores the detected position information as imaging position information of the image data 31 in association with the image data 31. The acquisition unit 21 also stores the time period when the image data was captured as imaging time period information in association with the image data 31.
[0057] Based on the acquired image data, the detection unit 22 detects the positions of traffic safety facilities in the image data and the positions of plants present around the traffic safety facilities. The detection of the positions of traffic safety facilities and plants in this image data will be described with reference to Fig. 5. Fig. 5 is a diagram for explaining the detection of the positions of traffic safety facilities and plants in image data. Note that Fig. 5 shows a portion of image data 31 in which the periphery of the vehicle V is captured.
[0058] As shown in Fig. 5, the detection unit 22 uses the above-described detection model 32 (see Fig. 3) to extract an area Ha in which a traffic safety facility (here, traffic light A) is captured and an area Hb in which a plant B is captured within the image data 31. Then, the detection unit 22 detects the area Ha as the position Ha of the traffic safety facility and the area Hb as the position Hb of the plant B. The detection unit 22 also detects the type of traffic safety facility (here, traffic light A).
[0059] The detection unit 22 outputs the detected position Ha of the traffic safety facility, the position Hb of the plant B, and information on the type of the traffic safety facility to the determination unit 23.
[0060] The determination unit 23 executes a determination process to determine whether the detected position Hb of the plant B is an obstacle position that obstructs the visibility of the traffic safety facility. Specifically, the determination unit 23 determines that the position of the plant B is an obstacle position when the position Hb of the plant B overlaps with or is adjacent to the position Ha of the traffic safety facility (traffic light A) in the image data 31. In the example of Fig. 5, the position Hb of the plant B partially overlaps with the position Ha of the traffic safety facility in the image data 31, so the determination unit 23 determines that the position of the plant B is an obstacle position.
[0061] Therefore, the determining unit 23 can determine that the visibility of the traffic safety facility (here, traffic light A) has decreased or is likely to decrease, since the position Hb of the plant B is an obstruction position.
[0062] In this way, the judgment unit 23 of this embodiment detects the position Ha of the traffic safety facility (traffic light A) and the position Hb of the plant B in the image data 31, and executes a judgment process to determine whether the detected position Hb of the plant B is an obstruction position or not, thereby making it possible to accurately judge the decrease in visibility of the traffic safety facility (here, traffic light A).
[0063] Continuing with the explanation of Fig. 3, the determination unit 23 sets traffic safety facilities that have been determined to have reduced visibility or that may have reduced visibility as the analysis target for processing to analyze the tendency of the impact on visibility of the traffic safety facilities. That is, the determination unit 23 generates object information 33 (see Fig. 4) for such traffic safety facilities. In detail, the determination unit 23 generates object information 33 including image data used in the determination processing, imaging position information of the image data, imaging time period information, information indicating the type of traffic safety facility, etc.
[0064] The upload unit 24 uploads the object information 33 to the data collection device 100. That is, when the determination unit 23 determines that the position of the plant is an obstruction position in the determination process, the upload unit 24 uploads (transmits) to the data collection device 100 the image data used in the determination process, imaging position information indicating the imaging position where the image data was captured, and the like.
[0065] This allows the data collection device 100 to efficiently perform analysis processing for analyzing trends in the influence of traffic safety facilities on visibility based on image data, image capture position information, and the like.
[0066] In addition, the upload unit 24 prevents the object information 33 from being uploaded to the data collection device 100 for traffic safety facilities for which analysis processing has already been performed in the data collection device 100; in other words, it prohibits the uploading (transmission) of the object information 33 to the data collection device 100.
[0067] Specifically, the location information of the traffic safety facility for which analysis processing is being performed in the data collection device 100 (in other words, the image capture location information of the image data of the traffic safety facility) is distributed from the data collection device 100 to the in-vehicle device 10 as the above-mentioned collection condition information.
[0068] Therefore, if the imaging position of the image data used in the current determination process is the imaging position included in the collection condition information (i.e., the position of a traffic safety facility for which analysis processing has already been performed), the upload unit 24 prohibits the uploading of the object information 33 to the data collection device 100. In other words, if the imaging position of the image data used in the current determination process is the same as the imaging position included in the imaging position information already transmitted to the data collection device 100, the upload unit 24 prohibits the uploading (transmission) of the image data used in the current determination process and the imaging position information of the image data to the data collection device 100.
[0069] As a result, in this embodiment, it is possible to prevent unnecessary information (such as information about traffic safety facilities that has already been analyzed in the data collection device 100) from being uploaded (sent) to the data collection device 100.
[0070] The reception unit 25 receives an instruction to collect data to be used for analysis processing from the data collection device 100. Then, the reception unit 25 acquires progress image data and the like in response to the collection instruction, and transmits (uploads) the acquired progress image data and the like to the data collection device 100.
[0071] In more detail, the reception unit 25 receives the collection conditions transmitted from the data collection device 100 and stores them in the storage unit 30 as collection condition information 34. The reception unit 25 acquires progress image data and the like when the collection conditions are satisfied. Specifically, when the current time is included in the imaging time period of the collection conditions and corresponds to the collection time interval, and when the vehicle V passes through the imaging position of the collection conditions, the reception unit 25 images the traffic safety facilities and plants with the camera 12 and acquires progress image data including the traffic safety facilities and plants. The reception unit 25 also stores the acquired data in the storage unit 30 as progress image data 35.
[0072] Then, the reception unit 25 uploads (transmits) the progress image data and the like to the data collection device 100. Note that this uploading process may be performed by the upload unit 24.
[0073] This allows the data collection device 100 to efficiently collect progress image data including traffic safety facilities and plants that are the subject of analysis processing.
[0074] Note that the reception unit 25 may be configured to upload progress image data and the like to the data collection device 100 when receiving an upload instruction from the data collection device 100. This enables the data collection device 100 to more efficiently collect progress image data including traffic safety facilities and plants that are the targets of analysis processing.
[0075] More specifically, as described above, the data collection device 100 distributes the collection conditions to the in-vehicle device 10 of the target vehicle V, and therefore the collection conditions may be distributed to a plurality of in-vehicle devices 10. In such a case, the progress image data may be acquired by both the in-vehicle device 10 and another in-vehicle device (not shown) mounted on another vehicle.
[0076] In this case, for example, if one piece of progress image data is required for analysis processing in the data collection device 100, the data collection device 100 may collect the progress image data from either the in-vehicle device 10 or the other in-vehicle device.
[0077] Therefore, the in-vehicle device 10 according to this embodiment is configured to upload the acquired progress image data to the data collection device 100 when the acquired progress image data satisfies the collection conditions set by the data collection device 100.
[0078] More specifically, when the reception unit 25 of the in-vehicle device 10 acquires the progress image data, it first uploads the image capture time information and image capture position information of the acquired progress image data to the data collection device 100. Similarly, the other in-vehicle devices also upload the image capture time information and image capture position information of the progress image data that they have acquired to the data collection device 100.
[0079] Then, in the data collection device 100, when the collection conditions include image capture time information (for example, 9:00), the data collection device 100 selects the progress image data whose image capture time is closest to the image capture time information in the collection conditions as data that satisfies the collection conditions, in other words, the data that best satisfies the collection conditions among the multiple progress image data. The data collection device 100 transmits an instruction to upload the progress image data to the in-vehicle device 10 (or another in-vehicle device) that has the selected progress image data.
[0080] When the reception unit 25 of the in-vehicle device 10 receives an upload instruction from the data collection device 100, in other words, when the progress image data acquired by itself satisfies the collection conditions set by the data collection device 100, the reception unit 25 uploads the progress image data to the data collection device 100.
[0081] If the reception unit 25 does not receive an upload instruction, it does not upload the progress image data to the data collection device 100. In other words, the other in-vehicle device receives the upload instruction and uploads the progress image data acquired by the other in-vehicle device to the data collection device 100.
[0082] This allows the data collection device 100 to more efficiently collect necessary progress image data from the progress image data including traffic safety facilities and plants that are the subject of analysis processing.
[0083] Furthermore, in this embodiment, it is possible to prevent information unnecessary for the analysis process (here, progress image data for which no upload instruction has been given) from being uploaded to the data collection device 100, thereby reducing the communication load.
[0084] <Data collection device> Next, the configuration of the data collection device 100 will be described with reference to Fig. 6. Fig. 6 is a block diagram showing an example configuration of the data collection device 100. As shown in Fig. 6, the data collection device 100 includes a communication unit 101, a controller (control unit) 110, and a storage unit 120.
[0085] The communication unit 101 is a communication interface that is connected to the communication network N so as to enable two-way communication, and transmits and receives information to and from the in-vehicle device 10, the administrator terminal device 200, and the like.
[0086] The storage unit 120 is configured with a storage device such as a non-volatile memory, a data flash, a hard disk drive, etc. The storage unit 120 stores map information 121, collected information 122, vehicle management information 123, trend information 124, various programs, etc.
[0087] The map information 121 is information that indicates a map of the roads on which the vehicle V travels. The map information 121 may also include facility location information that indicates the locations of traffic safety facilities.
[0088] The collected information 122 is information collected from the in-vehicle device 10, other in-vehicle devices (not shown), etc. by the collection unit 111, which will be described later. The collected information 122 will now be described with reference to FIG.
[0089] Fig. 7 is a diagram showing an example of the collected information 122. As shown in Fig. 7, the collected information 122 includes items such as "collected information ID," "image data," "imaging location," "imaging time period," "type of traffic safety facility," and "progressive image data," and the data in each item is associated (linked) with one another.
[0090] The "collected information ID" is identification information for identifying the collected information. The "image data" is image data collected from the vehicle-mounted device 10, and more specifically, is image data used in the determination process in which the vehicle-mounted device 10 determined that the position of the plant was an obstacle position.
[0091] The "imaging position", "imaging time period", and "type of traffic safety facility" are the same as those in the object information 33 (see FIG. 4), and therefore will not be described here.
[0092] The "progress image data" is the progress image data collected from the in-vehicle device 10 or other in-vehicle devices. The "progress image data" includes one or more progress image data that satisfy the collection conditions.
[0093] In the example shown in Figure 7, the collected information identified by the collected information ID "J1" indicates that the image data is "D1", the imaging location is "E1", the imaging time period is "F1", the type of traffic safety facility is "G1", and the progress image data is "K1".
[0094] Returning to the explanation of Fig. 6, the vehicle management information 123 is information relating to the management of the vehicle V. The vehicle management information 123 includes, for example, current location information of the vehicle V, driving status information such as when the vehicle is driving or parked, vehicle registration information such as the prefecture in which the vehicle is registered, driving history information, route information of a navigation device, etc. Note that the vehicle management information 123 may include part of the above-mentioned current location information, etc., or may include other information relating to the management of the vehicle V in addition to or instead of the current location information, etc.
[0095] The trend information 124 is information that indicates the trend of the influence of plants on the visibility of traffic safety facilities. Specifically, the trend information 124 is information that includes the results of a process that analyzes the trend of the influence of plants on the visibility of traffic safety facilities.
[0096] Here, the trend information 124 will be described with reference to Fig. 8. Fig. 8 is a diagram showing an example of the trend information 124. As shown in Fig. 8, the trend information 124 includes items such as "trend information ID," "location of traffic safety facility," "type of traffic safety facility," "trend," and "countermeasure priority," and the data for each item is associated (linked) with one another.
[0097] The "trend information ID" is identification information that identifies the trend information. The "location of traffic safety facility" is information that indicates the location of the traffic safety facility that is the subject of the process for analyzing the trend of the impact on visibility. In other words, the "location of traffic safety facility" is information that indicates the location of the traffic safety facility that has been determined to have reduced visibility. Therefore, the "location of traffic safety facility" is also information that indicates the imaging location where the image data used in the determination process that determined the location of the plant to be an obstacle location was captured.
[0098] "Type of traffic safety facility" is information indicating the type of the corresponding traffic safety facility (for example, traffic lights, road signs, etc.).
[0099] The "trend" is information indicating the tendency of the influence that plants have on the visibility of traffic safety facilities. For example, when the analysis unit 113, which will be described later, compares image data with time-lapse image data and finds that the area P (the shaded area in FIG. 5) where the position Hb of the plant B (see FIG. 5) and the position Ha of the traffic safety facility (traffic light A) overlap in the image data or the time-lapse image data increases over time, the "trend" becomes information indicating that the visibility of the traffic safety facility is tending to worsen.
[0100] The "trend" is information indicating "no change" when there is no change in the overlapping area P, and "improvement" when the overlapping area P decreases.
[0101] "Countermeasure priority" is information indicating the priority of taking countermeasures such as pruning work on plants. The "countermeasure priority" is set by the analysis unit 113 (described later) in stages, such as "high," "medium," and "low."
[0102] In the example shown in Figure 8, the trend information identified by the trend information ID "M1" indicates that the location of the traffic safety facility is "E1", the type of traffic safety facility is "G1", the trend is "deteriorating", and the countermeasure priority is "high".
[0103] 6, the controller 110 includes a collection unit 111, an instruction unit 112, an analysis unit 113, and a notification unit 114, and includes, for example, a computer having a CPU, RAM, a hard disk drive, input / output ports, etc., and various circuits. The CPU of the computer functions as the collection unit 111, instruction unit 112, analysis unit 113, and notification unit 114 of the controller 110, for example, by reading and executing a program stored in a ROM.
[0104] Furthermore, at least some or all of the collection unit 111, instruction unit 112, analysis unit 113, and notification unit 114 of the controller 110 can be configured using hardware such as ASIC or FPGA.
[0105] The collection unit 111 collects various types of information from the in-vehicle device 10, other in-vehicle devices (not shown), etc. For example, the collection unit 111 collects image data of the periphery of the vehicle V from the in-vehicle device 10. As described above, the in-vehicle device 10 collects such image data when it is determined that the position of a plant included in the image data is an obstacle position that obstructs the visibility of a traffic safety facility.
[0106] The collection unit 111 also collects image data imaging position information, imaging time period information, information indicating the type of traffic safety facility, and the like from the in-vehicle device 10. The collection unit 111 then stores the collected information in the storage unit 120 as collected information 122.
[0107] The collection unit 111 also collects, from the in-vehicle device 10, progress image data that satisfies the collection conditions distributed by the instruction unit 112, which will be described later. The collection unit 111 then stores the collected progress image data in the storage unit 120 as collection information 122.
[0108] When the collection unit 111 collects image data and the like from the in-vehicle device 10, the instruction unit 112 sets collection conditions for collecting progress image data and the like. The collection conditions include information such as the imaging position where the image data was captured, the imaging time period, and the time interval for collection.
[0109] Then, the instruction unit 112 distributes the set collection conditions to the in-vehicle device 10 of the vehicle V that is the distribution target. The in-vehicle device 10 that is the distribution target is set based on the vehicle management information 123, etc. As described above, the distribution target is the in-vehicle device 10 of the vehicle V that is registered in the prefecture that includes the imaging location where the image data was captured, but is not limited to this.
[0110] Furthermore, as described above, when multiple pieces of imaging time information and imaging position information for progress image data are collected from the in-vehicle device 10, the instructing unit 112 selects the progress image data that best satisfies the collection conditions from among the multiple pieces of progress image data. Then, the instructing unit 112 transmits an instruction to upload the progress image data to the in-vehicle device 10 that has the selected progress image data, thereby collecting the progress image data.
[0111] Based on the collected image data and progress image data, the analysis unit 113 generates trend information 124 (see FIG. 8) that indicates the trend of the impact that plants have on the visibility of traffic safety facilities. For example, the analysis unit 113 analyzes the image data and progress image data, and calculates an area P where the position Hb of plant B (see FIG. 5) and the position Ha of the traffic safety facility (traffic light A) overlap in the image data and progress image data. The area P can also be said to be the area where visibility is lacking in the traffic safety facility.
[0112] Then, the analysis unit 113 generates trend information based on the calculated area P, etc. As an example, if the area P is increasing over time, the analysis unit 113 sets the "trend" of the trend information 124 to "deterioration," which indicates that the visibility of the traffic safety facility is tending to deteriorate.
[0113] Furthermore, the analysis unit 113 sets the "countermeasure priority" of the trend information 124 based on the area P. As an example, when the area P is equal to or greater than a threshold, the visibility of the traffic safety facility is relatively poor, and therefore the analysis unit 113 sets the "countermeasure priority" of the trend information 124 to "high," which indicates a high priority for taking countermeasures such as pruning work. Note that the above-mentioned threshold is set to a value at which it is estimated that the visibility of the traffic safety facility is relatively poor and that countermeasures such as pruning work are necessary, but is not limited to this and can be set to any value.
[0114] On the other hand, if the area P is less than the threshold value, the visibility of the traffic safety facilities is relatively ensured, and therefore the analysis unit 113 sets the "countermeasure priority" of the trend information 124 to "low," which indicates that the priority of taking countermeasures such as pruning work is low.
[0115] Furthermore, the analysis unit 113 may generate the trend information 124 based on the current season information in addition to the image data and the time-lapse image data described above. This allows the trend information 124 to be generated with high accuracy in this embodiment.
[0116] That is, depending on the plant, the growth speed may change depending on the season. Specifically, the growth speed of the plant increases in summer, whereas the growth speed of the plant decreases in winter.
[0117] Therefore, for example, when the current seasonal information indicates that the season is summer, the analysis unit 113 sets the "countermeasure priority" in the trend information 124 to "high" even if the area P is less than the threshold value, taking into account the increasing growth speed of plants. Also, for example, when the current seasonal information indicates that the season is winter and the area P is less than the threshold value, the analysis unit 113 leaves the "countermeasure priority" in the trend information 124 at "low" taking into account the decreasing growth speed of plants. Note that when the current seasonal information indicates that the season is in between spring or autumn, the analysis unit 113 sets the "countermeasure priority" in the trend information 124 to "medium."
[0118] In this way, in this embodiment, the trend information 124 can be generated with high accuracy by using the current seasonal information.
[0119] The notification unit 114 notifies the administrator who manages the traffic safety facilities of the above-mentioned trend information. Specifically, the notification unit 114 notifies the administrator by transmitting the trend information to the administrator terminal device 200 for use by the administrator.
[0120] For example, the notification unit 114 maps the locations of traffic safety facilities whose visibility has been determined to be reduced, along with the priority of countermeasures, based on the trend information, and notifies the administrator. Notification of trend information will now be described with reference to Fig. 9. Fig. 9 is a diagram showing the display 210 of the administrator terminal device 200 to which trend information has been notified.
[0121] As shown in Fig. 9, the notification unit 114 notifies the user by displaying on a map the locations of traffic safety facilities whose visibility has been determined to be reduced based on trend information, etc. In the example of Fig. 9, the notification unit 114 notifies the user by attaching a mark 221 to the locations of traffic safety facilities whose visibility has been determined to be reduced. In addition, the notification unit 114 notifies the user by displaying information such as the type of traffic safety facility and the priority of countermeasures in a display field 222.
[0122] The manager who has been notified of the trend information, etc., can prioritize measures such as pruning for plants that are located near a traffic safety facility that has been determined to have reduced visibility and that have been set to a high priority, based on the trend information, etc. As a result, in this embodiment, even if there are multiple traffic safety facilities that have been determined to have reduced visibility, it is possible to efficiently improve the visibility of the traffic safety facilities.
[0123] <Control processing of in-vehicle devices> Next, a processing procedure executed by the in-vehicle device 10 according to the embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart showing the processing procedure executed by the in-vehicle device 10 according to the embodiment.
[0124] 10, the on-vehicle controller 20 of the on-vehicle device 10 acquires image data of the periphery of the vehicle V (step S100). Next, based on the acquired image data, the on-vehicle controller 20 determines whether or not the position of a plant in the image data is an obstruction position that obstructs the visibility of a traffic safety facility (step S101), that is, whether or not the visibility of the traffic safety facility is reduced by the plant.
[0125] If the position of the plant in the image data is determined to be an obstacle position (step S101, Yes), the on-board controller 20 determines whether the imaging position at which the image data was captured is the same as the imaging position included in the collection conditions (step S102). That is, the on-board controller 20 determines whether the imaging position of the image data used in the current determination process is the imaging position included in the collection condition information (i.e., the position of a traffic safety facility for which analysis processing has already been performed).
[0126] If the vehicle controller 20 determines that the imaging location where the image data was captured is not the same as the imaging location included in the collection conditions (step S102, No), it uploads the image data, imaging time zone information, etc. to the data collection device 100 (step S103).
[0127] On the other hand, if the in-vehicle controller 20 determines that the imaging position of the image data is the same as the imaging position included in the collection conditions (step S102, Yes), it skips the process of step S103, i.e., it does not upload the image data, etc. Also, if the in-vehicle controller 20 determines that the position of the plant in the image data is not an obstacle position (step S101, No), it skips the processes of steps S102 and S103.
[0128] Next, the in-vehicle controller 20 determines whether the collection conditions for the progress image data are satisfied (step S104). That is, the in-vehicle controller 20 determines whether the traveling state of the vehicle V satisfies the collection conditions, such as whether the vehicle V passes through the imaging position during the imaging time period included in the collection conditions.
[0129] If the in-vehicle controller 20 determines that the collection conditions for the progress image data are not met (step S104, No), it ends the process. On the other hand, if the in-vehicle controller 20 determines that the collection conditions for the progress image data are met (step S104, Yes), it captures images of the traffic safety facilities and plants with the camera 12 and acquires progress image data including the traffic safety facilities and plants (step S105).
[0130] Next, the in-vehicle controller 20 uploads the imaging position information and imaging time information of the acquired progress image data to the data collection device 100 (step S106). Next, the in-vehicle controller 20 determines whether or not there is an upload instruction from the data collection device 100 (step S107). In other words, the process of step S107 is a process of determining whether or not the progress image data acquired by the in-vehicle controller 20 has been selected by the data collection device 100 as the data that best satisfies the collection conditions among the multiple progress image data.
[0131] If it is determined that an upload instruction has been issued (step S107, Yes), the in-vehicle controller 20 uploads the progress image data acquired in step S105 to the data collection device 100 (step S108). On the other hand, if it is determined that an upload instruction has not been issued (step S107, No), the in-vehicle controller 20 ends the process.
[0132] <Data collection device control processing> Next, a processing procedure executed by the data collection device 100 according to the embodiment will be described with reference to Fig. 11. Fig. 11 is a flowchart showing a processing procedure executed by the data collection device 100 according to the embodiment.
[0133] 11, the controller 110 of the data collection device 100 acquires image data from the in-vehicle device 10 (step S200). That is, the controller 110 acquires image data used in the determination process in which the in-vehicle device 10 determined that the position of the plant was an obstacle position.
[0134] Next, the controller 110 distributes the collection conditions for collecting the progress image data to the in-vehicle device 10 of the vehicle V to be distributed (step S201). Next, the controller 110 collects the imaging position information and imaging time information of the progress image data from the in-vehicle device 10 to which the collection conditions have been distributed (step S202).
[0135] The controller 110 determines whether a plurality of pieces of progress image data have been acquired by the in-vehicle device 10 (step S203). In other words, the process of step S203 is a process of determining whether a plurality of pieces of imaging position information, etc. of progress image data have been collected from the in-vehicle device 10.
[0136] If the controller 110 determines that there are multiple sets of progress image data (step S203, Yes), it selects the data from the multiple sets of progress image data that best meets the collection conditions, and sends an instruction to upload the progress image data to the in-vehicle device 10 that has the selected progress image data (step S204).
[0137] Then, the controller 110 collects the progress image data from the in-vehicle device 10 (step S205). On the other hand, if the controller 110 determines that there is not a plurality of progress image data (step S203, No), the controller 110 proceeds to the process of step S205.
[0138] Next, the controller 110 generates trend information indicating the trend of the influence of plants on the visibility of the traffic safety facility based on the collected image data, progress image data, etc. (Step S206) Next, the controller 110 notifies the generated trend information to the manager of the traffic safety facility (Step S207).
[0139] As described above, the in-vehicle device 10 according to the embodiment includes an in-vehicle controller (an example of a controller) 20. The in-vehicle controller 20 acquires image data of the periphery of the vehicle V, and detects the positions of traffic safety facilities in the image data and the positions of plants present around the traffic safety facilities based on the acquired image data. The in-vehicle controller 20 also executes a determination process to determine whether the detected positions of plants are obstruction positions that obstruct the visibility of the traffic safety facilities. This allows for accurate determination of a decrease in visibility of the traffic safety facilities.
[0140] Further advantages and modifications will readily occur to those skilled in the art. Therefore, the invention in its broader aspects is not limited to the specific details and representative embodiments shown and described above. Accordingly, various modifications may be made without departing from the spirit or scope of the general inventive concept as defined by the appended claims and their equivalents. [Explanation of symbols]
[0141] 1. Data Collection System 10 Onboard equipment 20 In-vehicle controller 100 Data Collection Device 110 Controller
Claims
1. An in-vehicle device including a controller, The controller Acquiring image data from a camera installed in a vehicle, the image data being captured by the camera and capturing an image of the surroundings of the vehicle; extracting an area in which traffic safety facilities are imaged and an area in which plants are imaged from the acquired image data; executes a process of determining whether an area in which the traffic safety equipment is covered by the plants is equal to or greater than a threshold; If the value is equal to or greater than the threshold, the determination image data used in the determination process and image capture position information at which the determination image data was captured are transmitted to a server. In-vehicle device.
2. The traffic safety equipment is a traffic light, a road sign, or a traffic information monitor. The in-vehicle device according to claim 1 .
3. The controller receiving data collection conditions including an imaging time period and a designated imaging position from the server; When the image capturing time period includes a time when the vehicle is traveling and the vehicle passes through the designated image capturing position, the image data is acquired using the camera. The in-vehicle device according to claim 1 .
4. the data collection conditions further include a transmission prohibition position; The controller If the imaging position of the image data corresponds to the transmission prohibited position, the determination image data and the imaging position information are not transmitted to the server. The in-vehicle device according to claim 3 .
5. A data collection system including an in-vehicle device and a server, The in-vehicle device Acquiring image data from a camera installed in a vehicle, the image data being captured by the camera and capturing an image of the surroundings of the vehicle; extracting an area in which traffic safety facilities are imaged and an area in which plants are imaged from the acquired image data; executes a process of determining whether an area in which the traffic safety equipment is covered by the plants is equal to or greater than a threshold; If the value is equal to or greater than the threshold, the determination image data used in the determination process and image capture position information at which the determination image data was captured are transmitted to the server; The server recording a change over time in an area of the traffic safety equipment covered by the plants based on a plurality of determination image data after the determination process at the same location transmitted from the in-vehicle device; Mapping the same point on a map; and displaying the map with a priority set according to the degree of the change over time. Data collection system.
Citation Information
Patent Citations
Control system of road, surrounding facility, and the like
JP2002357557A
Road sign database construction device
JP2007265292A
Road monitoring device, road monitoring system, method, and program
JP2016151887A
Data collection device, road status evaluation support device, and program
JP2018120409A
Assessing visibility of a target object with autonomous vehicle fleet
US20210358167A1