Data collection device, data collection method, computer program for data collection, and data collection system

Abstract

To provide a data acquisition device capable of collecting data representing a feature over a continuous section while suppressing an increase in communication volume.SOLUTION: A data acquisition device comprises: a detection unit 42 that detects a predetermined feature present around the vehicle 2 from an image representing the surroundings of the vehicle 2 generated by a camera 21 mounted on the vehicle 2 while the vehicle 2 is traveling, generates probe data based on the detected feature and stores the generated probe data in a storage unit 32; and a communication processing unit 43 that transmits probe data for an additional section through which the vehicle 2 has traveled just before the vehicle 2 enters an acquisition target region, or just after the vehicle 2 exits the acquisition target region, and for the acquisition target region itself when the vehicle 2 enters the acquisition target region, and the image generated in the acquisition target region to a server 4 via a communication unit 23 mounted on the vehicle 2.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present invention relates to a data collection device, a data collection method, a computer program for data collection, and a data collection system that collect data used for generating or updating a map.

Background Art

[0002] For a high-precision map referred to by a vehicle's automatic driving system to control the vehicle automatically, it is required to accurately represent information about roads. Therefore, data representing roads or features around roads within a predetermined area is collected from vehicles that have actually traveled in the predetermined area and obtained by sensors mounted on the vehicles. However, if data is transmitted from vehicles to a server that collects such data without limitation, the communication volume will become enormous. Therefore, a technique for suppressing the communication volume has been proposed in collecting data detected by vehicles (see Patent Document 1).

[0003] In the technique disclosed in Patent Document 1, an in-vehicle unit detects the difference between downloaded map data and feature data recognized by sensors or the like, and calculates the degree of difference and the margin. Even if there is a difference, when the in-vehicle unit can perform driving control, the in-vehicle unit reduces the communication volume by not transmitting the feature data with the difference to the center side as vehicle probe data.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] When the road section for which data representing features is to be collected is short, data for intermittent sections will be transmitted from the vehicle to the server. Therefore, there is a risk that the data collected on the server side will be insufficient. Also, if the collection target area is set wider than the area where data representing features is actually to be collected, data will be collected even from vehicles that only drive on road sections that do not require data representing features, resulting in a wasteful increase in communication traffic.

[0006] Therefore, an object of the present invention is to provide a data collection device capable of collecting data representing features over a continuous section while suppressing an increase in communication traffic.

Means for Solving the Problem

[0007] According to one embodiment, a data collection device is provided. This data collection device includes a storage unit that stores information representing a collection target area for probe data representing predetermined features on or around a road, and during the running of the vehicle, from an image representing the surroundings of the vehicle generated by a camera mounted on the vehicle, a detection unit that detects predetermined features existing around the vehicle, generates probe data based on the detected features, and stores the generated probe data in the storage unit, and when the vehicle enters the collection target area, the additional section where the vehicle was running immediately before the entry or immediately after the vehicle exited the collection target area and the probe data generated in each of the collection target areas, and an image generated while the vehicle was running in the collection target area, and a communication processing unit that transmits them to a server via a communication device mounted on the vehicle.

[0008] Further, it is preferable that this data collection device further includes an appropriateness determination data generation unit that generates appropriateness determination data indicating the appropriateness of collecting probe data for the vehicle or the environment around the vehicle, and stores the generated appropriateness determination data in the storage unit. In this case, when the vehicle enters the collection target area, the communication processing unit transmits the appropriateness determination data generated while the vehicle is traveling in the additional section and the appropriateness determination data generated while the vehicle is traveling in the collection target area to the server via the communication device mounted on the vehicle. And it is preferable that the communication processing unit transmits the probe data generated in each of the additional section and the collection target area and the image generated while the vehicle is traveling in the collection target area to the server via the communication device only when it receives a collection instruction from the server via the communication device.

[0009] Alternatively, when the additional section is a section in which the vehicle has traveled immediately before entering, the communication processing unit obtains the cumulative value of the number of predetermined ground features detected along the reverse direction of the route traveled by the vehicle in order from the entry position where the vehicle entered the collection target area, and preferably sets the route of the vehicle from the position where the cumulative value reaches the predetermined number to the entry position as the additional section.

[0010] Alternatively, it is preferable that the communication processing unit sets the length of the additional section to the length received from the server via the communication device.

[0011] Alternatively, the communication processing unit obtains the first number of ground features detected in the first section in which the vehicle traveled immediately before entering the collection target area and the second number detected in the second section in which the vehicle traveled immediately after exiting the collection target area, and preferably sets at least one of the first section and the second section as the additional section based on the first number and the second number.

[0012] Alternatively, the communication processing unit preferably sets the section designated from the server via the communication device among the first section in which the vehicle traveled immediately before entering the collection target area and the second section in which the vehicle traveled immediately after exiting the collection target area as the additional section.

[0013] According to another aspect of the present invention, a data collection method is provided. This data collection method includes, while the vehicle is running, detecting predetermined features on or around the road existing around the vehicle from an image representing the surroundings of the vehicle generated by a camera mounted on the vehicle, generating probe data representing the detected features, storing the generated probe data in a storage unit, and when the vehicle enters a collection target area of the probe data, transmitting, via a communication device mounted on the vehicle to a server, the probe data generated in each of an additional section in which the vehicle was running immediately before the entry or immediately after the vehicle exited the collection target area and the collection target area, and an image generated while the vehicle was running in the collection target area.

[0014] According to still another aspect of the present invention, a computer program for data collection is provided. This computer program for data collection includes instructions for causing a processor mounted on the vehicle to execute: while the vehicle is running, detecting predetermined features on or around the road existing around the vehicle from an image representing the surroundings of the vehicle generated by a camera mounted on the vehicle, generating probe data representing the detected features, storing the generated probe data in a storage unit, and when the vehicle enters a collection target area of the probe data, transmitting, via a communication device mounted on the vehicle to a server, the probe data generated in each of an additional section in which the vehicle was running immediately before the entry or immediately after the vehicle exited the collection target area and the collection target area, and an image generated while the vehicle was running in the collection target area.

[0015] According to still another aspect of the present invention, there is provided a data collection system including a data collection device mounted on a vehicle and a server communicably connected to the data collection device. In this data collection system, the data collection device includes a storage unit that stores information representing a collection target area for probe data representing predetermined features on or around a road, and a detection unit that, while the vehicle is traveling, detects predetermined features existing around the vehicle from an image representing the surroundings of the vehicle generated by a camera mounted on the vehicle, generates probe data based on the detected features, and stores the generated probe data in the storage unit. When the vehicle enters the collection target area, the data collection device further includes a communication processing unit that transmits, via a communication device mounted on the vehicle, to the server the probe data generated in each of an additional section in which the vehicle was traveling immediately before the entry or immediately after the vehicle exited the collection target area and the collection target area, and an image generated while the vehicle was traveling through the collection target area.

Advantages of the Invention

[0016] The data collection device according to the present disclosure can collect data representing features over a continuous section while suppressing an increase in communication volume.

Brief Description of the Drawings

[0017]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying Out the Invention

[0018] Hereinafter, with reference to the drawings, a data collection device, a data collection method executed by the data collection device, a computer program for data collection, and a data collection system will be described. This data collection device is mounted on a vehicle. And this data collection device generates data representing predetermined features on or around a road (hereinafter referred to as probe data), which is used for generating or updating a map, based on an image representing the surroundings of the vehicle. Further, when a vehicle enters a collection target area of the probe data, the data collection device transmits, via a communication device, to a server, suitability determination data representing the degree of suitability of collection of the probe data generated in an additional section where the vehicle was traveling immediately before the entry, and suitability determination data generated while the vehicle is traveling in the collection target area. Furthermore, when the data collection device receives a collection instruction of the probe data from the server via the communication device, the data collection device transmits, via the communication device, to the server, the probe data generated while the vehicle is traveling in the additional section and the probe data generated while the vehicle is traveling in the collection target area. Moreover, the data collection device also transmits an image representing the surroundings of the vehicle generated while the vehicle is traveling in the collection target area to the server.

[0019] FIG. 1 is a schematic configuration diagram of a data collection system in which a data collection device is implemented. In the present embodiment, the data collection system 1 includes a data collection device 3 mounted on at least one vehicle 2 and a server 4. The data collection device 3 is connected to the server 4 via the wireless base station 6 and the communication network 5 by accessing, for example, a wireless base station 6 connected via a communication network 5 to which the server 4 is connected and a gateway (not shown). In FIG. 1, only one vehicle 2 is shown, but the data collection system 1 may include a plurality of vehicles 2 on which the data collection device 3 is mounted. Similarly, a plurality of wireless base stations 6 may be connected to the communication network 5.

[0020] First, the vehicle 2 and the data collection device 3 will be described. As described above, the data collection system 1 may include a plurality of vehicles 2 on which the data collection device 3 is mounted. However, since each vehicle 2 and each data collection device 3 may have the same configuration and execute the same processing with respect to the data collection process, hereinafter, one vehicle 2 and one data collection device 3 will be described.

[0021] FIG. 2 is a schematic configuration diagram of the vehicle 2. The vehicle 2 includes a camera 21 for photographing the surroundings of the vehicle 2, a GPS receiver 22, a wireless communication terminal 23, and a data collection device 3. The camera 21, the GPS receiver 22, the wireless communication terminal 23, and the data collection device 3 are communicably connected via an in-vehicle network compliant with a standard such as a controller area network. Further, the vehicle 2 may further include a distance measuring sensor (not shown), such as a LiDAR sensor, for measuring the distance to an object around the vehicle 2.

[0022] The camera 21 is an example of an imaging unit, and includes a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as a CCD or a C-MOS, and an imaging optical system that forms an image of a region to be photographed on the two-dimensional detector. Then, the camera 21 is attached, for example, inside the vehicle compartment of the vehicle 2 so as to face the front of the vehicle 2. And the camera 21 photographs the front region of the vehicle 2 at a predetermined photographing cycle (for example, 1 / 30 second to 1 / 10 second), and generates an image in which the front region is captured. The image obtained by the camera 21 may be a color image or a gray image. Note that a plurality of cameras 21 having different photographing directions or focal lengths may be provided in the vehicle 2.

[0023] Each time the camera 21 generates an image, it outputs the generated image to the data collection device 3 via the in-vehicle network.

[0024] The GPS receiver 22 receives GPS signals from GPS satellites at a predetermined cycle, and measures the self-position of the vehicle 2 based on the received GPS signals. Then, the GPS receiver 22 outputs, at a predetermined cycle, positioning information representing the measurement result of the self-position of the vehicle 2 based on the GPS signals to the data collection device 3 via the in-vehicle network. Note that the vehicle 2 may have a receiver compliant with a satellite positioning system other than the GPS receiver 22. In this case, the receiver may measure the self-position of the vehicle 2.

[0025] The wireless communication terminal 23 is an example of a communication device, which is a device that executes wireless communication processing compliant with a predetermined wireless communication standard. For example, by accessing the wireless base station 6, it is connected to the server 4 via the wireless base station 6 and the communication network 5. Then, the wireless communication terminal 23 receives a downlink wireless signal including a collection instruction signal or a signal representing a collection target area received from the server 4, and outputs the received signals to the data collection device 3. Further, the wireless communication terminal 23 generates an uplink wireless signal including the suitability determination data or the collection target data of a specified type (for example, probe data or an image) received from the data collection device 3. Then, the wireless communication terminal 23 transmits the uplink wireless signal to the wireless base station 6 to transmit the suitability determination data or the collection target data to the server 4.

[0026] Figure 3 is a hardware configuration diagram of the data collection device 3. The data collection device 3 temporarily stores the image received from the camera 21. Further, the data collection device 3 generates suitability determination data and probe data based on the image or the like, and temporarily stores the generated suitability determination data and probe data. Then, the data collection device 3 transmits the suitability determination data, the probe data, and the image to the server 4 via the wireless communication terminal 23. For this purpose, the data collection device 3 includes a communication interface 31, a memory 32, and a processor 33.

[0027] The communication interface 31 is an example of an in-vehicle communication unit and has an interface circuit for connecting the data collection device 3 to the in-vehicle network. That is, the communication interface 31 is connected to the camera 21, the GPS receiver 22, and the wireless communication terminal 23 via the in-vehicle network. And each time the communication interface 31 receives an image from the camera 21, it transfers the received image to the processor 33. Also, each time the communication interface 31 receives positioning information from the GPS receiver 22, it transfers the received positioning information to the processor 33. Furthermore, each time the communication interface 31 receives information from the server 4, such as a collection instruction signal, from the wireless communication terminal 23, it transfers that information to the processor 33. Additionally, the communication interface 31 outputs the suitability determination data, the collection target data, etc. received from the processor 33 to the wireless communication terminal 23 via the in-vehicle network.

[0028] The memory 32 is an example of a storage unit and has, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 32 may further have other storage devices such as a hard disk drive. And the memory 32 stores various data used in the processes related to data collection executed by the processor 33 of the data collection device 3. For example, the memory 32 stores the identification information of the vehicle 2, the parameters of the camera 21 such as the focal length, the shooting direction, and the installation position of the camera 21, the image received from the camera 21, various parameters for specifying an identifier for detecting ground objects from the image, and the positioning information received from the GPS receiver 22. Furthermore, the memory 32 stores the information representing the collection target area received from the server 4. Additionally, the memory 32 may store a computer program or the like for realizing each process executed by the processor 33.

[0029] The processor 33 has one or more CPUs (Central Processing Units) and its peripheral circuits. The processor 33 may further have other arithmetic circuits such as a logical arithmetic unit, a numerical arithmetic unit, or a graphic processing unit. Then, the processor 33 stores the image received from the camera 21, the positioning information received from the GPS receiver 22, etc. in the memory 32. At this time, each time the processor 33 receives an image from the camera 21, it associates the position of the vehicle 2 represented by the latest positioning information and the orientation of the vehicle 2 indicated by an orientation sensor (not shown) with the image. Further, the processor 33 may also associate the parameters of the camera 21 such as the focal length, the installation position, and the shooting direction of the camera 21 with the image. The information associated with these images is uploaded to the server 4 together with the images themselves when the images are uploaded to the server 4. Furthermore, while the vehicle 2 is running, the processor 33 executes data collection processing.

[0030] FIG. 4 is a functional block diagram of the processor 33 of the data collection device 3. The processor 33 has an appropriateness determination data generation unit 41, a detection unit 42, and a communication processing unit 43. Each of these units of the processor 33 is a functional module realized by, for example, a computer program operating on the processor 33. Alternatively, each of these units of the processor 33 may be a dedicated arithmetic circuit provided in the processor 33.

[0031] The appropriateness determination data generation unit 41 generates appropriateness determination data, for example, every predetermined period (for example, 10 seconds to several minutes), or each time the vehicle 2 travels a predetermined distance (for example, 100 m to 1 km).

[0032] The appropriateness determination data generation unit 41 generates appropriateness determination data representing the appropriateness of collecting the data to be collected for the vehicle 2 or the environment around the vehicle 2. The appropriateness determination data includes, for example, at least one of a sharpness index, a stillness index, a shielding index, and a position index.

[0033] The sharpness index is an index representing the sharpness of a road or a road feature represented in an image generated by a camera mounted on the vehicle 2. The sharpness index includes, for example, at least one of the current time, control information of the auto light of the vehicle 2, a sensor value of an illuminance sensor mounted on the vehicle 2, information regarding dirt on the camera mounted on the vehicle 2, and a value representing the sharpness of the image. Note that the value representing the sharpness of the image is, for example, the contrast or luminance distribution of the area where the road is represented, and is obtained as a result of analysis of the image generated by the camera mounted on the vehicle 2.

[0034] The stationary index is an index representing whether the vehicle 2 is stationary or not. The stationary index includes, for example, the shift position of the vehicle 2 or the vehicle speed of the vehicle 2.

[0035] The occlusion index is an index representing whether the features around the vehicle 2 in the image are occluded by other objects (for example, other vehicles around the vehicle 2). The occlusion index includes, for example, a set value of the inter-vehicle distance when auto-cruising is applied to the vehicle 2, or a measured value of the distance from the vehicle 2 to other objects existing around the vehicle 2 obtained by a distance measuring sensor mounted on the vehicle 2.

[0036] The position index is an index representing the relative positional relationship of the vehicle 2 with respect to the lane dividing line.

[0037] Furthermore, the suitability determination data includes position information indicating the position and traveling direction of the vehicle 2 when the suitability determination data was generated, and identification information of the vehicle 2. For this purpose, the suitability determination data generation unit 41 includes the position of the vehicle 2 represented by the latest positioning information received from the GPS receiver 22 in the suitability determination data as the position of the vehicle 2 when the suitability determination data was generated. Alternatively, the suitability determination data generation unit 41 may include, in the suitability determination data, as the position of the vehicle 2 when the suitability determination data was generated, a position obtained by correcting the position of the vehicle 2 represented by the latest positioning information with reference to the odometry information from the acquisition time of the latest positioning information to the current time. Furthermore, the suitability determination data generation unit 41 includes the latest traveling direction of the vehicle 2 indicated by an azimuth sensor (not shown) mounted on the vehicle 2 in the suitability determination data.

[0038] When the suitability determination data generation unit 41 includes the current time as a clarity index in the suitability determination data, information representing the current time may be obtained from a clock (not shown) mounted on the vehicle 2 or from time information received via the wireless communication terminal 23. Also, when the suitability determination data generation unit 41 includes the control information of the vehicle 2's auto light as a clarity index in the suitability determination data, the control information may be obtained from an electronic control device (not shown) that controls the headlight of the vehicle 2 via the in-vehicle network. Similarly, when the suitability determination data generation unit 41 includes the sensor value of an illuminance sensor (not shown) mounted on the vehicle 2 as a clarity index in the suitability determination data, the sensor value may be obtained from the illuminance sensor or from an electronic control device (not shown) that controls the wiper via the in-vehicle network.

[0039] Furthermore, when the suitability determination data generation unit 41 includes information regarding the dirt of the camera 21 as a sharpness index in the suitability determination data, for example, a value representing the degree of blurring caused by the dirt of the camera 21 may be obtained from the image generated by the camera 21. At this time, the suitability determination data generation unit 41 calculates, as a value representing the degree of blurring, a statistical representative value of the intensity of each edge detected by applying an edge detection filter to the image, for example. Alternatively, the suitability determination data generation unit 41 may obtain a value representing the degree of dirt of the camera 21 according to any of various methods for obtaining the degree of dirt of the camera from the image. Furthermore, when the suitability determination data generation unit 41 includes, as a sharpness index, a value representing the sharpness of the image generated by the camera 21 in the suitability determination data, the value representing the sharpness may be calculated from the image. For example, the suitability determination data generation unit 41 calculates the contrast within the region where the road is represented on the image (for example, the ratio of the difference between the maximum value and the minimum value of the luminance to the sum of the maximum value and the minimum value of the luminance of each pixel within the region) as a value representing the sharpness. Alternatively, the suitability determination data generation unit 41 may calculate, as a value representing the sharpness, the minimum value, the maximum value, the variance, etc. of the luminance of each pixel of the image. That is, when the minimum value of the luminance is a value close to the upper limit of the range in which the luminance value can be taken (for example, 0 to 255), it can be seen that the entire image is almost whitewashed and the sharpness of the image is low. Similarly, when the maximum value of the luminance is a value close to the lower limit of the range in which the luminance value can be taken, it can be seen that the entire image is almost blacked out and the sharpness of the image is low. Also, when the variance of the luminance value is low, since the entire image has almost uniform luminance, it can be seen that the sharpness of the image is low.

[0040] In addition, when the suitability determination data generation unit 41 includes the shift position of the vehicle 2 as a stationary index in the suitability determination data, it may acquire information representing the shift position from an electronic control device (not shown) that controls the running of the vehicle 2 via an in-vehicle network. Similarly, when the suitability determination data generation unit 41 includes the vehicle speed of the vehicle 2 as a stationary index in the suitability determination data, it may acquire the measured value of the vehicle speed from a vehicle speed sensor (not shown) that measures the vehicle speed of the vehicle 2 or from an electronic control device that controls the running of the vehicle 2 via an in-vehicle network.

[0041] Furthermore, when the suitability determination data generation unit 41 includes the set value of the inter-vehicle distance when auto-cruising is applied to the vehicle 2 as a shielding index in the suitability determination data, it may acquire the set value of the inter-vehicle distance from an electronic control device that controls the running of the vehicle 2 via an in-vehicle network. Similarly, when the suitability determination data generation unit 41 includes the measured value of the distance from the vehicle 2 to another object existing around the vehicle 2 as a shielding index in the suitability determination data, it may acquire the measured value of that distance from a distance measuring sensor or from an electronic control device that controls the running of the vehicle 2 via an in-vehicle network.

[0042] Furthermore, when the suitability determination data generation unit 41 includes, in the suitability determination data, information representing the relative positional relationship between the vehicle 2 and the lane dividing line as a position index, for example, the lane dividing line is detected from the image acquired by the camera 21. Then, the suitability determination data generation unit 41 may determine whether the vehicle 2 crosses the lane dividing line based on the position of the lane dividing line in the image, and use a flag representing the determination result as the position index. Note that, as will be described later with respect to the detection unit 42, the suitability determination data generation unit 41 can detect the lane dividing line by inputting the image to a discriminator that has been pre-trained to detect features such as the lane dividing line. Also, since the shooting direction of the camera 21 relative to the traveling direction of the vehicle 2 is known in advance, when the vehicle 2 crosses the lane dividing line, the range in which the lane dividing line is assumed to be represented in the image is also known. Therefore, such a range is stored in advance in the memory 32, and the suitability determination data generation unit 41 can determine whether the vehicle 2 crosses the lane dividing line by determining whether the detected lane dividing line is included in that range.

[0043] When the suitability determination data generation unit 41 generates the suitability determination data, it stores the generated suitability determination data in the memory 32.

[0044] During the running of the vehicle 2, the detection unit 42 detects a predetermined feature from the latest image generated by the camera 21 at every predetermined cycle or every time the vehicle 2 travels a predetermined distance. Note that the predetermined feature is a feature represented on the map to be generated or updated, and for example, various road markings, various road signs, curbs, guardrails, traffic lights, or poles for installing road signs, etc. Then, the detection unit 42 generates probe data representing the type of the feature detected in the image and the position of the feature.

[0045] For example, the detection unit 42 detects a predetermined ground object represented in the input image by inputting the image into an identifier. As such an identifier, the detection unit 42 can use a deep neural network (DNN) having a convolutional neural network (CNN) type architecture such as Single Shot MultiBox Detector or Faster R-CNN. Alternatively, the detection unit 42 may use a DNN having a self attention network (SAN) type architecture such as Vision Transformer as such an identifier. Or, the detection unit 42 may use an identifier based on another machine learning method such as an AdaBoost identifier as such an identifier. Such an identifier is pre-trained according to a predetermined learning method such as the error backpropagation method using a large number of teacher images in which the ground object is represented, so as to detect a predetermined ground object to be detected from the image. Then, the identifier outputs information representing an area (for example, a circumscribed rectangle of the ground object to be detected, hereinafter referred to as an object area) including the ground object to be detected on the input image, and information representing the type of the ground object represented in the object area.

[0046] The detection unit 42 estimates the position of the ground object represented in the object area based on parameters such as the azimuth from the camera 21, the position of the vehicle 2 at the time of image generation, the traveling direction and the shooting direction of the camera 21, the focal length and the installation position, corresponding to the center of gravity of the object area detected from the image. Then, the detection unit 42 generates probe data including information representing the type of the detected ground object and the estimated position. The detection unit 42 may further include information representing the position and the traveling direction of the vehicle 2 at the time of image generation in the probe data. The detection unit 42 may further include information representing the size and the position on the image of the object area in the probe data. Then, the detection unit 42 stores the generated probe data in the memory 32.

[0047] The communication processing unit 43 transmits the fitness determination data, the probe data, and the image stored in the memory 32 to the server 4 via the wireless communication terminal 23.

[0048] In this embodiment, the communication processing unit 43 refers to the information representing the collection target area stored in the memory 32 and the latest positioning information, and determines whether the vehicle 2 has entered the collection target area. The collection target area is specified, for example, for each continuous one or more road sections or for each area having a predetermined shape. When the collection target area is specified as a road section, the information representing the collection target area includes identification information for identifying the road section and information representing the positions of the ends where entry or exit to / from the road section is possible. Also, when the collection target area is an area having a predetermined shape, the information representing the collection target area includes information representing the positions of the outer edges of the area. And when the position of the vehicle 2 represented by the latest positioning information is included in the area or road section indicated by the information representing the collection target area, the communication processing unit 43 determines that the vehicle 2 has entered the collection target area.

[0049] When the vehicle 2 enters the collection target area, the communication processing unit 43 specifies the suitability determination data generated during the travel of the vehicle 2 in the additional section immediately before the vehicle 2 enters the collection target area among the suitability determination data stored in the memory 32. The additional section has a length of a predetermined distance (for example, several km) and is a section along the route traveled by the vehicle 2. Therefore, even when a plurality of vehicles 2 enter the collection target area from the same position, if the routes traveled by the vehicles 2 are different, the additional sections will also be different. The communication processing unit 43 may specify, as the suitability determination data generated in the additional section, the suitability determination data generated at a position within a predetermined distance from the position of the vehicle 2 when the vehicle 2 enters the collection target area by referring to the position information of the vehicle 2 included in the suitability determination data.

[0050] Furthermore, the communication processing unit 43 specifies the suitability determination data generated from when the vehicle 2 enters the collection target area until it exits the collection target area as the suitability determination data generated during the travel of the vehicle 2 in the collection target area. At that time, the communication processing unit 43 may determine that the vehicle 2 has exited the collection target area when the position of the vehicle 2 indicated by the latest positioning information deviates from the area or road section indicated by the information representing the collection target area.

[0051] The communication processing unit 43 outputs the suitability determination data generated while the vehicle 2 is traveling in the additional section and the suitability determination data generated while the vehicle 2 is traveling in the collection target area to the wireless communication terminal 23 via the communication interface 31. Thereby, the communication processing unit 43 transmits those suitability determination data to the server 4 via the wireless base station 6 and the communication network 5.

[0052] After the suitability determination data is sent from the data collection device 3 to the server 4, when the communication processing unit 43 receives a collection instruction signal from the server 4 via the wireless communication terminal 23, the communication processing unit 43 transmits the data specified by the collection instruction signal to the server 4 via the wireless communication terminal 23.

[0053] Specifically, if the probe data is specified as the data to be collected by the collection instruction signal, the communication processing unit 43 identifies the probe data generated while the vehicle 2 is traveling in the collection target area among the probe data stored in the memory 32. Further, the communication processing unit 43 identifies the probe data generated while the vehicle 2 is traveling in the above additional section. At that time, the communication processing unit 43 may identify those probe data by referring to the information representing the position of the vehicle 2 included in the probe data in the same manner as the identification of the above suitability determination data.

[0054] The communication processing unit 43 outputs the probe data generated while the vehicle 2 is traveling in the additional section and the probe data generated while the vehicle 2 is traveling in the collection target area to the wireless communication terminal 23 via the communication interface 31. Thereby, the probe data generated in the same section as the section in which the suitability determination data is transmitted to the server 4 is uploaded to the server 4.

[0055] Also, when the probe data and the image are designated as the data to be collected by the collection instruction signal, the communication processing unit 43 specifies, as described above, the probe data generated while the vehicle 2 is traveling in the additional section and the probe data generated while the vehicle 2 is traveling in the collection target area. Further, the communication processing unit 43 specifies an image generated by the camera 21 while the vehicle 2 is traveling in the collection target area among the images stored in the memory 32. At this time, the communication processing unit 43 may specify the image generated by the camera 21 while the vehicle 2 is traveling in the collection target area by referring to the information representing the position of the vehicle 2 associated with the image, in the same manner as the specification of the above-described appropriateness determination data.

[0056] The communication processing unit 43 outputs the probe data generated while the vehicle 2 is traveling in the additional section, and the probe data and the image generated while the vehicle 2 is traveling in the collection target area, to the wireless communication terminal 23 via the communication interface 31. As a result, for the probe data with a relatively small data amount, those generated for both the additional section and the collection target area are uploaded to the server 4. On the other hand, for the image with a relatively large data amount, only those generated for the collection target area are uploaded to the server 4. Therefore, the communication processing unit 43 can upload the data necessary for generating or updating the map to the server 4 while suppressing the communication volume.

[0057] Furthermore, the image specified by the collection instruction signal may be a partial image. In this case, the communication processing unit 43 generates a partial image by cutting out a range estimated to represent the road surface from each of the individual images generated in the collection target area. Then, the communication processing unit 43 may output the probe data generated while the vehicle 2 is traveling in the additional section, and the probe data and the partial image generated while the vehicle 2 is traveling in the collection target area, to the wireless communication terminal 23 via the communication interface 31.

[0058] FIG. 5 is a diagram showing an example of the relationship between the route traveled by the vehicle 2 and the data uploaded to the server 4. In FIG. 5, it is assumed that the vehicle 2 has traveled along the travel locus 500. Also, among the individual road sections shown in FIG. 5, it is assumed that the road section 501 and the road section 502 are each a collection target area.

[0059] When the vehicle 2 enters the road section 501 which is one of the collection target areas, the suitability determination data generated in each of the section 501a where the vehicle 2 has traveled in the road section 501 and the section 511 before its entry is transmitted to the server 4. And in this example, it is assumed that for the road section 501, the server 4 is instructed to collect probe data and images. Therefore, the probe data generated in each of the sections 511 and 501a and the image generated in the section 501a are uploaded to the server 4.

[0060] Also, when the vehicle 2 enters the road section 502 which is the other one of the collection target areas, the suitability determination data generated in each of the section 502a where the vehicle 2 has traveled in the road section 502 and the section 512 before its entry is transmitted to the server 4. And in this example, it is assumed that for the road section 502, the server 4 is instructed to collect only probe data. Therefore, the probe data generated in each of the sections 512 and 502a are uploaded to the server 4.

[0061] FIG. 6 is an operation flowchart of the data collection process. The processor 33 executes the data collection process according to the following operation flowchart.

[0062] The suitability determination data generation unit 41 of the processor 33 generates suitability determination data at a predetermined cycle or each time the vehicle 2 travels a predetermined distance (step S101). Also, the detection unit 42 of the processor 33 detects a predetermined ground object from the latest image at a predetermined cycle or each time the vehicle 2 travels a predetermined distance, and generates probe data representing the detected ground object (step S102).

[0063] The communication processing unit 43 of the processor 33 determines whether the vehicle 2 has entered the collection target area (step S103). If the vehicle 2 has not entered the collection target area (step S103 - No), the processor 33 repeats the processing after step S101.

[0064] On the other hand, when the vehicle 2 enters the collection target area (step S103 - Yes), the communication processing unit 43 transmits the suitability determination data generated in each of the additional section before the entry and the collection target area to the server 4 via the wireless communication terminal 23 (step S104).

[0065] Thereafter, the communication processing unit 43 determines whether the data collection device 3 has received a collection instruction signal from the server 4 via the wireless communication terminal 23 (step S105). If the data collection device 3 has not received the collection instruction signal (step S105 - No), the processor 33 repeats the processing of step S105.

[0066] On the other hand, when the data collection device 3 receives the collection instruction signal (step S105 - Yes), the communication processing unit 43 determines whether the collection target data specified by the collection instruction signal includes an image in addition to the probe data (step S106). If an image is not specified as the collection target data (step S106 - No), only the probe data is specified as the collection target data. Therefore, in this case, the communication processing unit 43 transmits the probe data generated in each of the additional section and the collection target area to the server 4 via the wireless communication terminal 23 (step S107).

[0067] On the other hand, when an image is specified as the data to be collected (step S106 - Yes), the communication processing unit 43 transmits the probe data generated in each of the additional section and the collection target area and the image generated in the collection target area to the server 4 via the wireless communication terminal 23 (step S108). After step S107 or step S108, the processor 33 ends the data collection process. Also, if the collection instruction signal is not received even after a certain period has elapsed after the transmission of the suitability determination data, the processor 33 may end the data collection process without transmitting the probe data and the image to the server 4. In this case, when the storage area of the memory 32 is full, the processor 33 may overwrite the storage area with the newly generated probe data and image, thereby deleting the suitability determination data and probe data generated in each of the additional section and the collection target area from the memory 32.

[0068] Next, the server 4 will be described. The server 4 stores the probe data or images transmitted from the data collection devices 3 mounted on the individual vehicles 2. Then, based on those probe data or images, the server 4 generates or updates a map of the collection target area. Further, the server 4 notifies each individual vehicle 2 of the collection target area. Furthermore, based on the received suitability determination data, the server 4 designates the type of data to be collected for the collection target area and transmits a collection instruction signal representing the designated type of data as the data to be collected to the vehicle 2 that transmitted the suitability determination data.

[0069] FIG. 7 is a hardware configuration diagram of the server 4. The server 4 includes a communication interface 51, a storage device 52, a memory 53, and a processor 54. The communication interface 51, the storage device 52, and the memory 53 are connected to the processor 54 via signal lines. The server 4 may further include an input device such as a keyboard and a mouse, and a display device such as a liquid crystal display.

[0070] The communication interface 51 is an example of a communication unit and has an interface circuit for connecting the server 4 to the communication network 5. The communication interface 51 is configured to be communicable with the data collection devices 3 mounted on the individual vehicles 2 via the communication network 5 and the radio base station 6. That is, the communication interface 51 delivers to the processor 54 the suitability determination data, the data to be collected, etc. received from the data collection devices 3 of the individual vehicles 2 via the radio base station 6 and the communication network 5. Further, the communication interface 51 transmits the collection instruction signal, etc. received from the processor 54 to the data collection devices 3 of the individual vehicles 2 via the communication network 5 and the radio base station 6.

[0071] The storage device 52 is an example of a storage unit and has, for example, a hard disk device or an optical recording medium and its access device. The storage device 52 stores the type designation information and, for each of the plurality of road sections, the data to be collected, etc. collected for that road section. The storage device 52 may further store the identification information of the individual vehicles 2. Further, the storage device 52 may store a computer program for executing the data collection process on the server 4 side, which is executed on the processor 54. Furthermore, the storage device 52 may store a map generated or updated based on the data to be collected.

[0072] The memory 53 is another example of a storage unit and has, for example, a non-volatile semiconductor memory and a volatile semiconductor memory. The memory 53 temporarily stores various data generated during the execution of the data collection process and various data obtained by communication with the individual vehicles 2 such as the suitability determination data.

[0073] The processor 54 is an example of a control unit and has one or more CPUs (Central Processing Units) and its peripheral circuits. The processor 54 may further have other arithmetic circuits such as a logical arithmetic unit or a numerical arithmetic unit. The processor 54 executes the data collection process on the server 4 side.

[0074] FIG. 8 is a functional block diagram of a processor 54 related to data collection processing on the server 4 side. The processor 54 includes a determination unit 61 and an instruction unit 62. Each of these units included in the processor 54 is a functional module realized by, for example, a computer program operating on the processor 54. Alternatively, each of these units included in the processor 54 may be a dedicated arithmetic circuit provided in the processor 54.

[0075] Each time the server 4 receives suitability determination data from the data collection device 3 of any one of the vehicles 2, the determination unit 61 determines whether the current situation of the vehicle 2 is suitable for collecting the data to be collected based on the suitability determination data. In the present embodiment, the determination unit 61 determines whether the current situation of the vehicle 2 is suitable for collecting the data to be collected for each of the suitability determination data generated in the collection target area and the suitability determination data generated for the additional section. Since the determination unit 61 may execute the same process for each suitability determination data, hereinafter, the process for one suitability determination data will be described.

[0076] For example, when the suitability determination data includes a sharpness index, the determination unit 61 determines that the current situation of the vehicle 2 is suitable for collecting the data to be collected only when the sharpness index indicates that the road or the road features are sharp in the image generated by the camera mounted on the vehicle 2. Thereby, it is possible to prevent the data to be collected, for which it is difficult to recognize the features to be represented on the map, from being transmitted from the vehicle 2 to the server 4.

[0077] Specifically, when the clarity index is the current time, if the current time corresponds to a time during the day, the determination unit 61 determines that the road or roadside objects in the image are clear. On the other hand, if the current time corresponds to a time at night, the determination unit 61 determines that the road or roadside objects in the image are not clear. Alternatively, the determination unit 61 may determine that the road or roadside objects in the image are clear when the current time corresponds to sunrise or sunset and the traveling direction of the vehicle 2 is towards the sun. Also, when the clarity index is the control information of the auto light of the vehicle 2, if the control information indicates that the headlight of the vehicle 2 is turned off, the determination unit 61 determines that the road or roadside objects in the image are clear. On the other hand, if the control information indicates that the headlight of the vehicle 2 is turned on, the determination unit 61 determines that the road or roadside objects in the image are not clear. Further, when the clarity index is the sensor value of the illuminance sensor mounted on the vehicle 2, if the sensor value is higher than a predetermined illuminance threshold, the determination unit 61 determines that the road or roadside objects in the image are clear. On the other hand, if the sensor value is equal to or lower than the predetermined illuminance threshold, the determination unit 61 determines that the road or roadside objects in the image are not clear. Additionally, when the clarity index is information regarding the dirt of the camera mounted on the vehicle 2, if the information indicates that there is no influence on the clarity of the image due to dirt, the determination unit 61 determines that the road or roadside objects in the image are clear. For example, when the degree of blur caused by dirt, which is an example of the clarity index, is equal to or lower than a predetermined threshold, the determination unit 61 determines that the road or roadside objects in the image are clear. On the other hand, if the information indicates that there is an influence on the clarity of the image due to dirt, the determination unit 61 determines that the road or roadside objects in the image are not clear. Furthermore, when the clarity index is a value representing the clarity of the image, if the value satisfies the clarity condition for the image to be clear, the determination unit 61 determines that the road or roadside objects in the image are clear. On the other hand, if the value does not satisfy the clarity condition, the determination unit 61 determines that the road or roadside objects in the image are not clear.In addition, when the value representing the sharpness of the image is the maximum value of contrast, variance, or luminance, the sharpness condition is determined to be satisfied when the value is equal to or greater than a predetermined threshold. Further, when the value representing the sharpness of the image is the minimum value of luminance, the sharpness condition is determined to be satisfied when the value is equal to or less than a predetermined threshold.

[0078] Also, when the suitability determination data includes a stationary index, the determination unit 61 determines that the current situation of the vehicle 2 is suitable for collecting the collection target data only when the stationary index indicates that the vehicle 2 is moving. This prevents the collection target data representing the same ground object from being transmitted from the vehicle 2 to the server 4. Specifically, when the stationary index is the shift position of the vehicle 2, the determination unit 61 determines that the vehicle 2 is moving when the shift position is neither parking nor neutral, while determining that the vehicle 2 is stationary when the shift position is parking or neutral. Also, when the stationary index is the vehicle speed of the vehicle 2, the determination unit 61 determines that the vehicle 2 is moving when the vehicle speed is higher than a predetermined speed threshold (for example, 5 to 10 km / h), while determining that the vehicle 2 is stationary when the vehicle speed is equal to or lower than the predetermined speed threshold.

[0079] Furthermore, when the suitability determination data includes a shielding index, the determination unit 61 determines that the current situation of the vehicle 2 is suitable for collecting the collection target data only when the shielding index indicates that the ground objects (for example, road markings, road signs, or traffic signals) around the vehicle 2 are not shielded in the image. This prevents the collection target data that does not represent the ground objects to be shown on the map from being transmitted from the vehicle 2 to the server 4.

[0080] Specifically, when the shielding index is the set value of the inter-vehicle distance when auto-cruising is applied to vehicle 2, if the set value of the inter-vehicle distance is longer than a predetermined distance threshold (for example, 50 m to 100 m), the determination unit 61 determines that the ground objects around vehicle 2 are not shielded. On the other hand, if the set value of the inter-vehicle distance is equal to or less than the predetermined distance threshold, the determination unit 61 determines that the ground objects around vehicle 2 are shielded. Further, when the shielding index is the measured value of the distance from vehicle 2 to other objects existing around vehicle 2 obtained by the ranging sensor mounted on vehicle 2, if the measured value of the distance is longer than the predetermined distance threshold, the determination unit 61 determines that the ground objects around vehicle 2 are not shielded. On the other hand, if the inter-vehicle distance is equal to or less than the predetermined distance threshold, the determination unit 61 determines that the ground objects around vehicle 2 are shielded.

[0081] Furthermore, when the suitability determination data includes a position index, the determination unit 61 determines that the current situation of vehicle 2 is suitable for collecting the data to be collected only when the position index indicates that the position of vehicle 2 is suitable for collecting the data to be collected. Specifically, when the position index is information representing the relative positional relationship of vehicle 2 with respect to the lane dividing line, for example, if the information indicates that vehicle 2 is not crossing the lane dividing line, the determination unit 61 determines that the current situation of vehicle 2 is suitable for collecting the data to be collected. This prevents the data to be collected, in which the ground objects are represented in a different view from the normal time (for example, when vehicle 2 is traveling along the lane), from being transmitted from vehicle 2 to server 4.

[0082] Note that the suitability determination data may include a plurality of clarity indicators. In this case, the determination unit 61 may determine that the current situation of the vehicle 2 is suitable for collecting the data to be collected, as long as each clarity indicator indicates that the road or the road features in the image are clear. Similarly, the suitability determination data may include a plurality of stillness indicators. In this case, the determination unit 61 may determine that the current situation of the vehicle 2 is suitable for collecting the data to be collected, as long as each stillness indicator indicates that the vehicle 2 is moving. Further, the suitability determination data may include a plurality of occlusion indicators. In this case, the determination unit 61 may determine that the current situation of the vehicle 2 is suitable for collecting the data to be collected, as long as each occlusion indicator indicates that the features around the vehicle 2 in the image are not occluded. Furthermore, the suitability determination data may include two or more of the clarity indicator, the stillness indicator, the occlusion indicator, and the position indicator. In this case, the determination unit 61 may determine that the current situation of the vehicle 2 is suitable for collecting the data to be collected, as long as it is determined that the current situation of the vehicle 2 is suitable for collecting the data to be collected for each of the two or more indicators. On the other hand, if any one of the two or more indicators indicates that the current situation of the vehicle 2 is not suitable for collecting the data to be collected, the determination unit 61 may determine that the current situation of the vehicle 2 is not suitable for collecting the data to be collected.

[0083] Note that a plurality of suitability determination data may be generated in the collection target area. In this case, when the determination unit 61 determines that the current situation of the vehicle 2 is suitable for collecting the data to be collected for a predetermined ratio (for example, 50% to 80%) or more of the plurality of suitability determination data, it may be determined that the current situation of the vehicle 2 is suitable for collecting the data to be collected for the collection target area. Similarly, when a plurality of suitability determination data are generated for the additional section, when the determination unit 61 determines that the current situation of the vehicle 2 is suitable for collecting the data to be collected for a predetermined ratio or more of the plurality of suitability determination data, it may be determined that the current situation of the vehicle 2 is suitable for collecting the data to be collected for the additional section.

[0084] The determination unit 61 notifies the instruction unit 62 of the determination result as to whether the current state of the vehicle 2 is suitable for collecting the data to be collected, with respect to the suitability determination data generated in each of the collection target area and the additional section.

[0085] When the determination unit 61 determines that the current state of the vehicle 2 is suitable for collecting the data to be collected for both the collection target area and the additional section, the instruction unit 62 generates a collection instruction signal for instructing the vehicle 2 to collect the data to be collected.

[0086] The instruction unit 62 specifies the collection target area including the position of the vehicle 2 represented in the suitability determination data, and refers to the type designation information corresponding to the specified collection target area. Then, the instruction unit 62 specifies the type of the data to be collected specified for the collection target area based on the type designation information. The types of the data to be collected include an image representing the environment around the vehicle 2 generated by the camera 21 mounted on the vehicle 2, a partial image representing the road surface cut out from the image, or probe data representing a ground object detected from the image. Therefore, the type designation information indicates, for each collection target area, any one of an image, a partial image, and probe data as the type of the data to be collected.

[0087] The instruction unit 62 includes information for designating the specified type of the data to be collected in the collection instruction signal. When probe data is indicated in the type designation information, the instruction unit 62 designates only the probe data as the data to be collected. When an image is indicated in the type designation information, the instruction unit 62 designates the probe data and the image as the data to be collected. Further, when a partial image is indicated in the type designation information, the instruction unit 62 designates the probe data and the partial image as the data to be collected.

[0088] The instruction unit 62 transmits the generated collection instruction signal to the vehicle 2 specified by the identification information received together with the suitability determination data via the communication interface 51, the communication network 5, and the radio base station 6.

[0089] Note that the processor 54 may set a collection target area based on the number of probe data collected for each road section stored in the storage device 52. For example, a road section where the number of probe data collected in the most recent predetermined period (e.g., several weeks to several months) is less than a predetermined collection threshold is set as the collection target area. Alternatively, the processor 54 may set, as the collection target area, a road section for which the elapsed time since the previous update is equal to or longer than a predetermined elapsed time threshold among the individual road sections represented in the map to be updated. Then, the processor 54 may notify the data collection device 3 of each vehicle 2 of the set collection target area via the communication interface 51.

[0090] Furthermore, the processor 54 may generate or update a map using the collected probe data and images. In this case, the processor 54 aligns the features represented by the respective probe data collected for continuous sections from one vehicle 2 with the corresponding features represented by other probe data collected in the past or represented in the map to be updated. Then, the processor 54 identifies, as newly installed features, those among the features represented by the respective probe data collected for continuous sections for which there are no corresponding features in other probe data or in the map to be updated. Then, the processor 54 adds information (position and type) regarding the identified features to the map to be generated or updated. Also, the processor 54 may identify, as removed, a feature that has no corresponding feature among the features represented by the respective probe data collected for continuous sections among the features represented in the map to be updated. Then, the processor 54 may delete information regarding the feature identified as removed from the map to be updated.

[0091] As described above, this data collection device transmits, via a communication device, probe data generated while the vehicle is traveling in each of the collection target area and an additional section where the vehicle was traveling immediately before the collection target area to a server. Further, this data collection device also transmits, via the communication device, an image representing the surroundings of the vehicle, which is generated while the vehicle is traveling in the collection target area, to the server. In this way, this data collection device can collect and transmit probe data for a certain continuous section even if the collection target area is narrow. Therefore, the server can accurately align the position of a ground feature represented in the collected probe data with the corresponding ground feature represented in the map to be updated or separately collected probe data. Since the server can accurately align the position of the ground feature represented in the collected probe data, it can accurately estimate the position of the ground feature detected by the server from the image generated in the collection target area. Therefore, even if the road section where it is actually required to collect information about the ground feature is short, it is not necessary to set a wide collection target area. Accordingly, it is suppressed that probe data and an image are transmitted from a vehicle that has traveled only on road sections where it is not actually required to collect information about the ground feature to the server. As a result, this data collection device can suppress an increase in communication traffic.

[0092] According to a modification, the length of the route from the position when the ignition switch of vehicle 2 is turned on to when vehicle 2 enters the collection target area may be less than the length of the additional section. In such a case, the communication processing unit 43 may transmit, via the wireless communication terminal 23, the suitability determination data and the probe data generated on the route from the position when the ignition switch of vehicle 2 is turned on to when vehicle 2 enters the collection target area to the server 4. That is, the route from the position when the ignition switch of vehicle 2 is turned on to when vehicle 2 enters the collection target area is set as the additional section.

[0093] Further, the length of the additional section may be specified by the server 4. In this case, when the server 4 notifies the data collection device 3 of each vehicle 2 of the collection target area, the server 4 may also notify the length of the additional section. For example, the shorter the distance traveled by the vehicle 2 in the collection target area, the longer the server 4 may set the additional section.

[0094] Also, the alignment of features on the server 4 side improves in accuracy as the number of detected features increases. Therefore, the communication processing unit 43 refers to the probe data, obtains the cumulative value of the number of features detected along the reverse direction of the route of the vehicle 2 in order from the entry position where the vehicle 2 entered the collection target area, and may set an additional section based on the cumulative value. In this case, the communication processing unit 43 may set the route of the vehicle 2 from the position when the cumulative value of the number of features reaches a predetermined number to the above-described entry position as the additional section. According to this modification, since the communication processing unit 43 sets the additional section based on the number of detected features, the data collection device 3 can set an additional section of an appropriate length so as to suppress the communication amount while ensuring the accuracy of the alignment of features by the server 4.

[0095] Note that the usage method in alignment may be different between linear features such as lane dividing lines and point-like features such as poles or traffic signals. Therefore, the communication processing unit 43 may calculate the cumulative value for each type of feature or for each group of types of features according to the use in alignment. Further, a predetermined number may be set for each type of feature or for each group. Then, the communication processing unit 43 may set the route of the vehicle 2 from the position when the cumulative value for each type or for each group reaches the corresponding predetermined number to the entry position as the additional section.

[0096] Also, according to the above modification, the communication processing unit 43 may add the number of features detected while the vehicle 2 is traveling in the collection target area to the above-described cumulative value. Also in this case, the data collection device 3 can obtain the same effects as those of the above modification.

[0097] According to another modification example, the additional section may be a section having a length of a predetermined distance traveled by the vehicle 2 after the vehicle 2 exits the collection target area. In this case, the communication processing unit 43 may transmit the suitability determination data to the server 4 via the wireless communication terminal 23 after the vehicle 2 finishes traveling in the additional section. Also in this modification example, the data collection device 3 can obtain the same effects as those in the above-described embodiment.

[0098] Furthermore, even when the additional section is set as a section after exiting the collection target area, the server 4 may notify the data collection device 3 of each vehicle 2 of the length of the additional section. Alternatively, the communication processing unit 43 may obtain the cumulative value of the number of ground features detected along the route of the vehicle 2 from the point where the vehicle 2 exits the collection target area. Further, the communication processing unit 43 may also add the number of ground features detected while the vehicle 2 is traveling in the collection target area to the above cumulative value. Then, the communication processing unit 43 may set the route up to the position when the cumulative value reaches a predetermined number as the additional section. Also in this case, the communication processing unit 43 may obtain the cumulative value for each type or group of ground features and set the additional section.

[0099] According to still another modification example, the communication processing unit 43 may set the additional section to either, or both, of the section traveled immediately before the vehicle 2 enters the collection target area or the section traveled immediately after the vehicle 2 exits the collection target area, in accordance with an instruction from the server 4. In this case, the data collection device 3 includes, in the suitability determination data, the number of ground objects detected by the detection unit 42 in the first section of a predetermined distance traveled immediately before the vehicle 2 enters the collection target area (hereinafter sometimes referred to as the first number). Similarly, the data collection device 3 includes, in the suitability determination data, the number of ground objects detected by the detection unit 42 in the second section of a predetermined distance traveled immediately after the vehicle 2 exits the collection target area (hereinafter sometimes referred to as the second number). Alternatively, the data collection device 3 may receive, from the electronic control device for driving support or automatic driving control of the vehicle 2, the first number and the second number of ground objects detected by the electronic control device from the image obtained by the camera 21, and include them in the suitability determination data. Then, the communication processing unit 43 transmits the suitability determination data generated in each of the first section and the second section to the server 4 via the wireless communication terminal 23. The instruction unit 62 of the server 4 sets the additional section based on the first number of ground objects detected in the first section and the second number of ground objects detected in the second section, which are included in the suitability determination data generated in each of the first section and the second section. For example, the instruction unit 62 sets the section with the larger number of detected ground objects among the first section and the second section as the additional section. Alternatively, when the sum of the first number and the second number is less than a predetermined number, the instruction unit 62 may set both the first section and the second section as the additional section. Then, the instruction unit 62 may include, in the collection instruction signal transmitted to the vehicle 2 that transmitted the suitability determination data, information indicating which of the first section and the second section is set as the additional section. According to this modification example, the data collection device 3 can set more appropriately the additional section for collecting probe data before and after the collection target area.

[0100] Further, the instruction unit 62 of the server 4 may determine which of the first section and the second section is to be set as the additional section based on the suitability determination data generated in the first section and the suitability determination data generated in the second section. For example, if the suitability determination data generated in the first section indicates that the current situation of the vehicle 2 is suitable for collecting the data to be collected, while the suitability determination data generated in the second section indicates that the current situation of the vehicle 2 is not suitable for collecting the data to be collected, the instruction unit 62 may set the first section as the additional section. Conversely, if the suitability determination data generated in the first section indicates that the current situation of the vehicle 2 is not suitable for collecting the data to be collected, while the suitability determination data generated in the second section indicates that the current situation of the vehicle 2 is suitable for collecting the data to be collected, the instruction unit 62 may set the second section as the additional section.

[0101] In the above embodiment or modification, when the server 4 notifies the data collection device 3 of each vehicle 2 of the collection target area, the server 4 may also notify the type of data to be collected in the collection target area. Further, the processor 33 of the data collection device 3 may execute the processes of the determination unit 61 and the instruction unit 62 of the processor 54 of the server 4. Then, the communication processing unit 43 may set an additional section based on the determination result, or may determine whether to transmit the probe data and the image to the server 4. That is, for each of the additional section and the collection target area, only when it is determined that the current situation of the vehicle 2 is suitable for collecting the data to be collected, the communication processing unit 43 may transmit the specified type of data to be collected to the server 4 via the wireless communication terminal 23. According to this modification, it is not necessary to transmit the suitability determination data to the server 4 in advance, so that the data collection device 3 can further suppress the communication volume in data collection.

[0102] As described above, those skilled in the art can make various changes according to the implemented forms within the scope of the present invention.

Explanation of reference numerals

[0103] 1 Data collection system 2 Vehicle 21 Camera 22 GPS receiver 23 Wireless communication terminal 3 Data collection device 31 Communication interface 32 Memory 33 Processor 41 Fitness determination data generation unit 42 Detection unit 43 Communication processing unit 4 Server 51 Communication interface 52 Storage device 53 Memory 54 Processor 61 Judgment unit 62 Instruction unit 5 Communication network 6 Wireless base station

Claims

1. A storage unit that stores information representing a collection target area for probe data representing predetermined features on or around a road; During the travel of the vehicle, a predetermined feature existing around the vehicle is detected from an image representing the surroundings of the vehicle generated by a camera mounted on the vehicle, probe data is generated based on the detected feature, and the generated probe data is stored in the storage unit; a detection unit; When the vehicle enters the collection target area, the additional section in which the vehicle travels immediately before the entry or immediately after the vehicle exits the collection target area and the probe data generated in each of the collection target areas, and the image generated while the vehicle travels through the collection target area are transmitted to a server via a communication device mounted on the vehicle; a communication processing unit; A data collection device having the above.

2. Further comprising an appropriateness determination data generation unit that generates appropriateness determination data representing the appropriateness of collection of the probe data for the vehicle or the environment around the vehicle, and stores the generated appropriateness determination data in the storage unit; When the vehicle enters the collection target area, the communication processing unit transmits the appropriateness determination data generated while the vehicle travels through the additional section and the appropriateness determination data generated while the vehicle travels through the collection target area to the server via the communication device; The data collection device according to claim 1, wherein the probe data generated in each of the additional section and the collection target area and the image generated while the vehicle travels through the collection target area are transmitted to the server via the communication device only when a collection instruction is received from the server via the communication device.

3. When the additional section is the section where the vehicle traveled immediately before the entry, the communication processing unit obtains a cumulative value of the number of the predetermined features detected along the reverse direction of the route traveled by the vehicle in order from the entry position where the vehicle entered the collection target area, and sets the route from the position where the cumulative value reaches a predetermined number to the entry position as the additional section. The data collection device according to claim 1 or 2.

4. The communication processing unit sets the length of the additional section to the length received from the server via the communication device. The data collection device according to claim 1 or 2.

5. The communication processing unit obtains a first number of features detected in a first section traveled by the vehicle immediately before entering the collection target area and a second number of features detected in a second section traveled by the vehicle immediately after exiting the collection target area, and based on the first number and the second number, sets at least one of the first section and the second section as the additional section. The data collection device according to claim 1 or 2.

6. The communication processing unit sets the section designated from the server via the communication device as the additional section among the first section traveled by the vehicle immediately before entering the collection target area and the second section traveled by the vehicle immediately after exiting the collection target area. The data collection device according to claim 1 or 2.

7. During the travel of the vehicle, predetermined features on or around the road existing around the vehicle are detected from an image representing the surroundings of the vehicle generated by a camera mounted on the vehicle, probe data representing the detected features is generated, the generated probe data is stored in the storage unit, When the vehicle enters the collection target area of the probe data, the additional section in which the vehicle is traveling immediately before the entry or immediately after the vehicle exits the collection target area and the probe data generated in each of the collection target areas, and the image generated while the vehicle is traveling in the collection target area are transmitted to a server via a communication device mounted on the vehicle. A data collection method including this.

8. During the running of the vehicle, from an image representing the surroundings of the vehicle generated by a camera mounted on the vehicle, predetermined ground objects on or around the road existing around the vehicle are detected. Probe data representing the detected ground objects is generated. The generated probe data is stored in a storage unit. When the vehicle enters the collection target area of the probe data, the additional section in which the vehicle is traveling immediately before the entry or immediately after the vehicle exits the collection target area and the probe data generated in each of the collection target areas, and the image generated while the vehicle is traveling in the collection target area are transmitted to a server via a communication device mounted on the vehicle. A computer program for data collection that causes a processor mounted on the vehicle to execute this.

9. A data collection system having a data collection device mounted on a vehicle and a server communicably connected to the data collection device, The data collection device includes a storage unit that stores information representing a collection target area of probe data representing predetermined ground objects on or around the road, a detection unit that, during the running of the vehicle, detects the predetermined ground objects existing around the vehicle from an image representing the surroundings of the vehicle generated by a camera mounted on the vehicle, generates the probe data based on the detected ground objects, and stores the generated probe data in the storage unit. When the vehicle enters the collection target area, the probe data generated in each of the additional section where the vehicle travels immediately before the entry or immediately after the vehicle exits the collection target area and the collection target area, and the image generated while the vehicle travels through the collection target area are transmitted to the server via a communication device mounted on the vehicle by a communication processing unit. A data collection system having the above.

Images