JP2022001975A - Map information collection device - Google Patents

Abstract

To provide a map information collection device capable of correctly estimating a road on which a vehicle is traveling even when there is another road vertically proximate to the road on which the vehicle is traveling.SOLUTION: This map information collection device comprises: an input unit 41; a storage unit 42 that stores a map in which probe information including information acquired by a vehicle 2 about a road on which the vehicle 2 is traveling is registered; and an estimation unit 52 that acquires the probe information, horizontal position information of the vehicle 2 when the probe information is acquired, and position estimation addition information including height position information of the vehicle 2 when the probe information is acquired through the input unit 41 from the vehicle 2, and estimates a road on which the vehicle 2 is traveling when the probe information is acquired from among a plurality of roads different in height around the vehicle 2 when the probe information is acquired, which are represented in the map 421 stored in the storage unit 42, on the basis of the horizontal position information and the position estimation addition information.SELECTED DRAWING: Figure 4

Description

The present invention relates to a map information collecting device.

High-precision road control maps that the vehicle's automated driving system refers to to automatically control the vehicle are required to accurately represent information about the road. It is desirable that the control map contains as many road features as possible on the road on which the vehicle can travel and road features around the road.

Therefore, it is proposed that the server appropriately collects information about the road from a plurality of vehicles and registers the collected information in the control map. The server registers the road feature received from the vehicle in the control map in association with the road on which the vehicle was traveling when the information on the road feature was acquired.

When the server receives information about the road from the vehicle, the server estimates the road on which the vehicle was traveling when the information on the road features was acquired, based on the longitude and latitude indicating the position of the vehicle.

Here, if there are other roads having different heights close to each other in the vertical direction of the road on which the vehicle is traveling, the server may erroneously estimate the road on which the vehicle is traveling.

For example, the self-position estimation device proposed in Patent Document 1 detects a sign around the vehicle, determines the current position of the vehicle, and is located around the road based on the relative position and the current position of the detected sign with respect to the vehicle. The altitude information of the detected sign is acquired from the map information in which the two-dimensional coordinate information and the altitude information of the existing sign are recorded. The self-position estimation device estimates the altitude of the vehicle based on the altitude information of the sign acquired from the map information.

International Publication No. 2020/031295

However, in the method proposed by Patent Document 1, if the number of road features registered in the control map is not sufficient, the sign existing around the road on which the vehicle is traveling is not registered in the control map. In addition, it may not be possible to estimate the altitude of the vehicle. In this case, the server may not be able to correctly estimate the road on which the vehicle is traveling.

Therefore, the present invention provides a map information collecting device capable of correctly estimating the road on which the vehicle is traveling even when there are other roads in the vertical direction of the road on which the vehicle is traveling. With the goal.

According to one embodiment, a map information collecting device is provided. This map information collecting device has an input unit, a storage unit that stores a map in which probe information including information about the road on which the vehicle is traveling acquired by the vehicle is registered, probe information, and probe information is acquired. The horizontal position information of the vehicle when the probe information is acquired and the additional position estimation information including the position information in the height direction of the vehicle when the probe information is acquired are acquired from the vehicle via the input unit, and the horizontal direction is obtained. Based on the position information and position estimation additional information of, the probe information is displayed from the multiple roads with different heights around the vehicle when the probe information is acquired, which is displayed on the map stored in the storage unit. Has an estimation unit that estimates the road on which the vehicle was traveling when the information was acquired.

The map information collecting device according to the present invention has an effect that the road on which the vehicle is traveling can be correctly estimated even when there are other roads close to each other in the vertical direction of the road on which the vehicle is traveling. ..

It is a schematic block diagram of a map information collection system in which a map information collection device is mounted. It is a schematic block diagram of a vehicle. It is a hardware configuration diagram of a server. It is an operation flowchart of a vehicle in a map information collection process. It is a figure explaining the data collection process. It is an operation flowchart of a server in a map information collection process. It is a figure explaining the operation of the estimation part of the processor of a server.

FIG. 1 is a schematic configuration diagram of a map information collection system in which a map information collection device is mounted. Hereinafter, the outline of the map information collection system 1 disclosed in the present specification will be described with reference to FIG.

In the present embodiment, the map information collection system 1 has a map information acquisition device 17 mounted on at least one vehicle 2 and a server 3. The map information acquisition device 17 may access the communication network 4 to which the server 3 is connected and the base station 5 connected via a gateway (not shown) or the like to the base station 5 via the base station 5 and the communication network 4. Is connected to the server 3. Although only one vehicle 2 is shown in FIG. 1, the map information collection system 1 may have a plurality of vehicles 2. Similarly, a plurality of base stations 5 may be connected to the communication network 4.

The map information acquisition device 17 acquires a camera image C showing the environment around the vehicle by using the camera 11 mounted on the vehicle 2 while the vehicle 2 is traveling on the road R1. In the example shown in FIG. 1, the map information acquisition device 17 acquires a camera image C including a road sign X indicating that the maximum speed is 50 km / h. The road sign X is an example of a road feature.

The map information acquisition device 17 detects the position and attribute information of the road sign X displayed in the camera image C. The position and attribute information of the road sign X is an example of probe information including information about the road R1 on which the vehicle 2 is traveling.

Further, the map information acquisition device 17 has the horizontal position information of the vehicle 2 when the probe information is acquired and the height direction of the vehicle 2 based on the GNSS information measured by the positioning information receiver 14. Get the location information of. The horizontal position information of the vehicle 2 represents a position in a direction parallel to the ground, and is represented by, for example, longitude and latitude. The position information in the height direction of the vehicle 2 represents a position in a direction perpendicular to the ground, and is represented by, for example, an elliptical body height.

The map information acquisition device 17 includes probe information including the position and attribute information of the road feature X, the longitude and latitude of the vehicle 2 when the probe information is acquired, and an ellipse of the vehicle 2 when the probe information is acquired. The position estimation additional information including the body height is transmitted to the server 3 via the base station 5 and the communication network 4.

The server 3 is an example of a map information collecting device. The server 3 has a control map 421 in which probe information is registered, an estimation unit 52 that estimates the road on which the vehicle 2 is traveling when the probe information is acquired, and information for registering the probe information in the control map 421. It has a registration unit 54 and the like. The control map 421 is a high-precision road map referred to by the autonomous driving system for automatically controlling the autonomous driving vehicle. The control map 421 has horizontal position information and height position information of the road.

The estimation unit 52 estimates the road around the vehicle 2 when the probe information is acquired, based on the longitude and latitude of the vehicle 2 when the probe information is acquired, with reference to the control map 421. .. When it is determined that there are a plurality of roads around the vehicle 2 when the probe information is acquired, the estimation unit 52 acquires the probe information represented on the control map based on the position estimation additional information. From a plurality of roads having different heights around the vehicle 2, the road on which the vehicle 2 was traveling is estimated when the probe information is acquired.

As shown in FIG. 1, the estimation unit 52 is around the horizontal position P of the vehicle 2 when the probe information is acquired, based on the longitude and latitude of the vehicle 2 when the probe information is acquired. Select a plurality of roads R1 and R2. Map D in FIG. 1 is an excerpt of a part of the control map 421, and represents a region including the horizontal position P of the vehicle 2 when the probe information is acquired. The map D shows that there are two roads R1 and R2 around the vehicle 2 when the probe information is acquired. Road R2 is an elevated highway, and road R1 is a general road below road R2.

The estimation unit 52 refers to the control map 421 and acquires the heights of the two roads R1 and R2, respectively. The estimation unit 52 selects the road R1 having the height closest to the elliptical height of the vehicle 2 included in the position estimation additional information from the two selected roads R1 and R2 when the probe information is acquired. It is estimated as the road on which 2 was traveling.

The information registration unit 54 associates the position and attribute information of the road feature X around the vehicle 2 included in the probe information with the road R1 presumed that the vehicle 2 was traveling when the probe information was acquired. Register in the control map 421. As a result, the server 3 correctly estimates the road on which the vehicle 2 is traveling and registers it in the control map 421 even if there is another road in the vertical direction of the road on which the vehicle 2 is traveling. You can collect the map information to be created.

In the map information collection system 1, a plurality of vehicles 2 may be included, but since each vehicle 2 may have the same configuration and execute the same processing for the map information collection processing, one vehicle 2 is described below. Will be explained.

FIG. 2 is a schematic configuration diagram of the vehicle 2. The vehicle 2 includes a camera 11 for photographing the environment in front of the vehicle 2, a wireless communication terminal 12, a barometer 13, a positioning information receiver 14, a navigation device 15, a vehicle speed sensor 16, and a map information acquisition device 17. And so on. Further, the vehicle 2 may have a sensor for acquiring probe information such as a distance measuring sensor (not shown) for measuring the distance to an object around the vehicle 2, such as a LiDAR sensor.

The camera 11, the wireless communication terminal 12, the barometer 13, the positioning information receiver 14, the navigation device 15, the vehicle speed sensor 16, and the map information acquisition device 17 are in-vehicle networks conforming to standards such as a controller area network. It is connected so as to be communicable via 18.

The camera 11 is an example of a sensor that acquires probe information. The camera 11 is mounted, for example, in the vehicle interior of the vehicle 2 so as to face the front of the vehicle 2. The camera 11 acquires a camera image C showing the environment of a predetermined area in front of the vehicle 2 at a predetermined cycle. The camera image C may represent a road feature such as a lane marking line on the road surface included in a predetermined area in front of the vehicle 2. The image generated by the camera 11 may be a color image or a gray image. The camera 11 is an example of a sensor arranged in the vehicle 2, and is a two-dimensional detector composed of an array of photoelectric conversion elements having sensitivity to visible light such as a CCD or C-MOS, and a two-dimensional detector thereof. It has an imaging optical system that forms an image of an area to be imaged.

The wireless communication terminal 12 is an example of a communication unit, and is a device that executes wireless communication processing conforming to a predetermined wireless communication standard. For example, by accessing the base station 5, the base station 5 and the communication network 4 can be connected. It is connected to the server 3 via.

The barometer 13 measures the atmospheric pressure (atmospheric pressure) at the position of the vehicle 2. For example, as the barometer 13, a capacitance type or vibration type barometric pressure measuring device can be used. The barometer 13 outputs the measured barometric pressure to the map information acquisition device 17. The atmospheric pressure changes according to the altitude at which the vehicle 2 is located.

The positioning information receiver 14 outputs positioning information representing the current location of the vehicle 2. For example, the positioning information receiver 14 can be a GNSS receiver. Each time the positioning information receiver 14 acquires the positioning information in a predetermined reception cycle, the positioning information and the positioning information acquisition time at which the positioning information is acquired are output to the navigation device 15 and the map information acquisition device 17.

The navigation device 15 generates a travel route from the current location of the vehicle 2 to the destination based on the navigation map, the destination of the vehicle 2, and the current location of the vehicle 2. The navigation device 15 uses the positioning information output by the positioning information receiver 14 as the current location of the vehicle 2. The navigation map has the position information of the road link representing the road section and the position information of the node connected by the road link. The road layout of a travel route is represented by a road link representing a road section and a node connected by the road link. Each time the navigation device 15 generates a travel route, the navigation device 15 outputs the travel route to the map information acquisition device 17 via the in-vehicle network 18.

The vehicle speed sensor 16 detects the vehicle speed based on the rotation speed of the tire of the vehicle 2 and the outer peripheral length of the tire. The vehicle speed sensor 16 outputs the vehicle speed to the map information acquisition device 17 via the in-vehicle network 18.

The map information acquisition device 17 executes a detection process for detecting the position and attribute information of the road feature displayed in the camera image C. The location and attribute information of road features is an example of information about roads. Further, the map information acquisition device 17 includes additional position estimation information including the horizontal position information of the vehicle 2 when the probe information is acquired and the position information in the height direction of the vehicle 2 when the probe information is acquired. Executes the position information generation process to generate and. Further, the map information acquisition device 17 includes probe information including the position and attribute information of road features, horizontal position information of the vehicle 2 when the probe information is acquired, and additional position estimation information. The first data generation process of generating the acquired data and transmitting the first acquired data to the server 3 is executed. Further, the map information acquisition device 17 generates a second acquisition data including the information of the camera image C in response to a transmission request from the server 3, and a second data generation process of transmitting the second acquisition data to the server 3. To execute. Therefore, the map information acquisition device 17 has a communication interface 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 are connected via a signal line 24.

The communication interface (IF) 21 is an example of an in-vehicle communication unit, and has an interface circuit for connecting the map information acquisition device 17 to the in-vehicle network 18. That is, the communication IF 21 is connected to the camera 11, the wireless communication terminal 12, the barometer 13, the positioning information receiver 14, the navigation device 15, the vehicle speed sensor 16, and the like via the in-vehicle network 18. Each time the first acquisition data or the second acquisition data is input from the processor 23, the communication interface 21 outputs the input first acquisition data or the second acquisition data to the wireless communication terminal 12.

The memory 22 is an example of a storage unit, and has, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 22 stores a computer program of an application used in information processing executed by the processor 23 of the map information acquisition device 17, various data, a vehicle ID that identifies the vehicle 2, and the like. The vehicle ID can be used to identify each vehicle 2, for example, when the server 3 communicates with a plurality of vehicles 2.

The processor 23 has one or a plurality of CPUs (Central Processing Units) and peripheral circuits thereof. The processor 23 may further include other arithmetic circuits such as a logical operation unit, a numerical operation unit, or a graphic processing unit. When the processor 23 has a plurality of CPUs, each CPU may have a memory. The processor 23 executes a detection process, a position information generation process, and a data generation process.

The processor 23 has a detection unit 31 that executes detection processing, a position information generation unit 32 that executes position information generation processing, and a data generation unit 33 that generates and transmits first acquisition data or second acquisition data. .. Each of these parts of the processor 23 is, for example, a functional module realized by a computer program running on the processor 23. Alternatively, each of these parts of the processor 23 may be a dedicated arithmetic circuit provided in the processor 23.

FIG. 3 is a hardware configuration diagram of the server 3. The server 3 has a communication interface (IF) 41, a storage device 42, a memory 43, a processor 44, and the like. The communication IF 41, the storage device 42, the memory 43, and the processor 44 are connected via a signal line 45. The server 3 may further include an input device such as a keyboard and a mouse, and a display device such as a liquid crystal display.

The communication IF 41 is an example of an input unit, and has an interface circuit for connecting the server 3 to the communication network 4. The communication IF 41 is configured to be able to communicate with the vehicle 2 via the communication network 4 and the base station 5.

The storage device 42 is an example of a storage unit, and includes, for example, a hard disk device or an optical recording medium and an access device thereof. Then, the storage device 42 stores the control map 421 in which the probe information is registered, the navigation map 422, and the like. The storage device 42 may further store the vehicle ID of the vehicle 2. Further, the storage device 42 may store a computer program for executing the processing of the server 3 related to the map information collection processing, which is executed on the processor 44.

The control map 421 is a high-precision road map referred to by the autonomous driving system for automatically controlling the autonomous driving vehicle. The autonomous driving system acquires information on the surroundings of the autonomous driving vehicle by using a sensor such as a camera mounted on the autonomous driving vehicle, and obtains the acquired information and information on the road included in the control map 421. Estimate the current location of self-driving vehicles by comparison. The vehicle 2 may be an autonomous driving vehicle or may not be an autonomous driving vehicle. The control map 421 includes the positions of road features (for example, lane markings, stop lines, road markings such as speed indications, road signs or traffic lights, etc.) that define the driving conditions of the individual roads represented on the map. Attribute information is registered in association with the road. The horizontal position information and the height position information of the road are registered in the control map 421. In the control map 421, one road is divided into a plurality of road sections, and each of the plurality of road sections is identified by a road section ID. The information about the road is registered in the control map 421 in association with the road section ID.

Similar to the navigation map mounted on the vehicle 2, the navigation map 422 has the position information of the road link representing the road section and the position information of the node connected by the road link. The navigation map 422 may be the same map as the navigation map mounted on the vehicle 2. The road layout of a travel route is represented by a road link representing a road section and a node connected by the road link. The road link is associated with the road section ID of the control map 421. The navigation map 422 includes information on road types of general roads and highways, and road information on road signs indicating the maximum speed or the direction of travel.

The memory 43 is another example of the storage unit, and has, for example, a non-volatile semiconductor memory and a volatile semiconductor memory. The memory 43 contains various data generated during execution of the process related to the server 3 in the map information collection process, probe information received from the vehicle 2, horizontal position information of the vehicle, and height direction. Various data and the like acquired by communication with the vehicle 2 such as the position information of the vehicle 2 are temporarily stored.

The processor 44 has one or a plurality of CPUs (Central Processing Units) and peripheral circuits thereof. The processor 44 may further include other arithmetic circuits such as a logical operation unit or a numerical operation unit. Then, the processor 44 executes the process related to the server 3 in the map information collection process.

The processor 44 transmits the probe information, the horizontal position information of the vehicle 2 when the probe information is acquired, and the additional position estimation information including the position information in the height direction of the vehicle 2 from the vehicle 2 to the communication IF 41. It has an information acquisition unit 51 to be acquired through the system. Further, the processor 44 is around the vehicle 2 when the probe information represented on the control map 421 stored in the storage device 42 is acquired based on the horizontal position information and the position estimation additional information. It has an estimation unit 52 that estimates the road on which the vehicle 2 was traveling when the probe information was acquired from a plurality of roads having different heights. Further, the processor 44 has a determination unit 53 for determining whether or not the road estimated by the estimation unit 52 on which the vehicle 2 is traveling is correct. Further, the processor 44 has an information registration unit 54 that registers the probe information in the control map 421 in association with the road estimated that the vehicle 2 was traveling. Each of these parts of the processor 44 is, for example, a functional module realized by a computer program running on the processor 44. Alternatively, each of these parts of the processor 44 may be a dedicated arithmetic circuit provided in the processor 44.

FIG. 4 is an operation flowchart of the vehicle 2 in the map information collection process. In the map information collection system 1, the map information acquisition device 17 of the vehicle 2 repeatedly executes the map information acquisition process according to the operation flowchart shown in FIG. 4 while the vehicle 2 is traveling.

The detection unit 31 of the processor 23 in the map information acquisition device 17 of the vehicle 2 determines whether or not the road on which the vehicle 2 is traveling is a data collection road that is required to collect information about the road. (Step S101). If the road link ID representing the road link on which the vehicle 2 is traveling matches one of the road link IDs received from the server in advance, the detection unit 31 determines that the road is a data collection road (). Step S101-Yes). On the other hand, if the road link ID representing the road on which the vehicle 2 is traveling is not included in the road link ID received from the server, the detection unit 31 determines that the road is not a data collection road (step S101). −No), the process of the map information acquisition device 17 returns to before step S101.

FIG. 5 is a diagram illustrating a data collection process. The information acquisition unit 51 of the processor 44 of the server 3 divides the control map 421 into a plurality of sections 4211, and determines the data acquisition road in the section 4211 for each of the plurality of sections 4211. For example, the information acquisition unit 51 determines a road having a number of registered road features or images including roads less than a predetermined number as a data collection road. The information acquisition unit 51 acquires a road link ID corresponding to the road section included in the data collection road with reference to the control map 421 and the navigation map 422, and the vehicle via the communication network 4 and the base station 5. Send to 2.

When it is determined that the road is a data collection road, the camera 11 arranged in the vehicle 2 is controlled by the detection unit 31 to acquire a camera image C showing the environment around the vehicle 2 (step S102). The camera 11 outputs the camera image C and the camera image acquisition time when the camera image C is acquired to the map information acquisition device 17 via the in-vehicle network 18.

The detection unit 31 of the processor 23 in the map information acquisition device 17 detects the road feature represented in the camera image C and estimates the position of the road feature (step S103). The detection unit 31 detects the road feature represented by the camera image C input from the camera 11, and also detects the attribute information of the road feature detected in the camera image C, and the road feature. Estimate the position of. The attribute information of the road feature represents, for example, a road marking such as a lane marking line, a stop line or a speed display, or a type of a structure such as a road sign such as a speed display or a traffic light.

For example, the detection unit 31 inputs the camera image C to the classifier to detect the road feature represented by the input camera image C. As such a discriminator, the detection unit 31 uses, for example, a deep neural network (DNN) pre-learned to detect a road feature represented by the camera image C from the input camera image C. be able to. As such a DNN, the detection unit 31 can use a DNN having a convolutional neural network type architecture such as a Single Shot MultiBox Detector (SSD) or a Faster R-CNN. In this case, when the detection unit 31 inputs the camera image C to the classifier, the classifier inputs the type of road feature to be detected (for example, lane) in various regions on the input camera image C. For each lane marking, pedestrian crossing, pause line, etc.), calculate the certainty of the certainty that the road feature is represented in the area. The classifier determines that the road feature of any type is represented in a region where the certainty of the road feature of any type is equal to or higher than a predetermined detection threshold. Then, the classifier has information representing an area including the road feature to be detected on the input camera image C (for example, an extrinsic rectangle of the road feature to be detected, hereinafter referred to as an object area), and information. , Outputs attribute information indicating the type of road feature represented in the object area.

Alternatively, the detection unit 31 may use a classifier other than the DNN. For example, the detection unit 31 inputs the feature amount calculated from the window set on the image (for example, Histograms of Oriented Gradients, HOG) as the classifier, and the road feature to be detected is displayed in the window. A support vector machine (SVM) trained in advance to output the certainty to be performed may be used. The detection unit 31 calculates a feature amount from the window while variously changing the position, size, and aspect ratio of the window set on the camera image C, and inputs the calculated feature amount to the SVM to input the calculated feature amount to the window. Ask for confidence about. When the certainty level is equal to or higher than a predetermined detection threshold value, the detection unit 31 sets the window as an object area representing a road feature to be detected.

The detection unit 31 is based on internal parameters such as the orientation from the camera 11, the position of the vehicle 2, the traveling direction, and the shooting direction and angle of view of the camera 11 corresponding to the center of gravity of the object region detected from the camera image C. Estimate the position of road features represented in the object area. Then, the detection unit 31 notifies the data generation unit 33 of the attribute information and the estimated position of the detected road feature.

The position information generation unit 32 of the processor 23 in the map information acquisition device 17 obtains the horizontal position information of the vehicle 2 and the vehicle 2 when the position and attribute information of the road feature which is an example of the probe information is acquired. The position information in the height direction is generated (step S104). That is, the position information generation unit 32 has the horizontal position information and the height position of the vehicle 2 at the camera image acquisition time when the camera image C is acquired based on the positioning information input from the positioning information receiver 14. Generate information. For example, the position information generation unit 32 represents the horizontal position information of the vehicle 2 in longitude and latitude, and the position information in the height direction in elliptical height. The position information in the height direction of the vehicle 2 represents the altitude of the road on which the vehicle 2 was traveling when the probe information was acquired. Then, the position information generation unit 32 notifies the data generation unit 33 of the longitude and latitude of the vehicle 2 when the probe information is acquired and the elliptical body height of the vehicle 2.

The data generation unit 33 of the processor 23 in the map information acquisition device 17 includes the position and attribute information of the detected road feature, the longitude and latitude of the vehicle 2 when the probe information is acquired, and the elliptical height of the vehicle 2. The first acquisition data having the estimation additional information and the vehicle speed at the time when the probe information is acquired is generated. The data generation unit 33 outputs the first acquired data together with the first acquired data ID that identifies the first acquired data to the wireless communication terminal 12 via the communication interface 21. The wireless communication terminal 12 transmits the first acquired data and the first acquired data ID to the server 3 via the base station 5 and the communication network 4 (step S105).

The data generation unit 33 determines whether or not a second acquisition data transmission request requesting transmission of the second acquisition data from the server 3 has been received (step S106). The details will be described later, but if the server 3 that has received the first acquired data can estimate the road on which the vehicle 2 was traveling when the probe information was acquired, the server 2 will transmit the second acquired data. Request for.

When the second acquisition data transmission request is received (step S106-Yes), the data generation unit 33 generates the second acquisition data. The second acquired data is around the vehicle 2 acquired by the vehicle 2 when the probe information included in the first acquired data identified by the first acquired data ID included in the second acquired data transmission request is acquired. Includes images taken. For example, the second acquired data includes a partial image of a region presumed to represent the road on which the vehicle 2 is traveling, which is cut out from the camera image C. Further, when the position of the vehicle 2 at the time when the probe information is acquired is in front of the intersection, the data generation unit 33 includes the entire camera image C in the second acquisition data so that the intersection is represented in the image. May be good. The data generation unit 33 outputs the second acquired data to the wireless communication terminal 12 via the communication IF 1 together with the first acquired data ID that identifies the first acquired data represented by the second acquired data transmission request. The wireless communication terminal 12 transmits the second acquired data to the server 3 via the base station 5 and the communication network 4 (step S107).

The detection unit 31 of the processor 23 in the map information acquisition device 17 determines whether or not the vehicle 2 has arrived at the destination (step S108). When the vehicle 2 arrives at the destination (step S108-Yes), the processing of the map information acquisition device 17 ends. On the other hand, when the vehicle 2 has not arrived at the destination (step S108-No), the process of the map information acquisition device 17 returns to the front of step S101. Similarly, when the second acquisition data transmission request has not been received (step S106-No), the processing of the map information acquisition device 17 returns to the front of step S101.

FIG. 6 is an operation flowchart of the server 3 in the map information collection process. The communication IF 41 of the server 3 receives the first acquired data and the first acquired data ID from the vehicle 2 (step S201). The communication IF 41 outputs the first acquired data and the first acquired data ID received from the vehicle 2 via the base station 5 and the communication network 4 to the processor 44. The information acquisition unit 51 of the processor 44 inputs the first acquisition data and the first acquisition data ID, and notifies the estimation unit 52 of the first acquisition data.

The estimation unit 52 of the processor 44 of the server 3 has probe information represented on the control map 421 stored in the storage device 42 based on the longitude and latitude of the vehicle 2 and the vehicle speed included in the first acquisition data. The road around the vehicle 2 at the time of acquisition is selected (step S202). First, the estimation unit 52 sets the position represented by the longitude and latitude of the vehicle 2 when the probe information is acquired as the first position in the horizontal direction of the vehicle 2. Further, the estimation unit 52 calculates the second horizontal position of the vehicle 2 based on the previously estimated horizontal position of the vehicle 2 and the vehicle speed. As the traveling direction of the vehicle 2 when determining the second position, the estimation unit 52 may use the extending direction of the road on which the vehicle 2 was traveling when the position was estimated last time. The estimation unit 52 estimates the horizontal position of the vehicle when the probe information is acquired, based on the first position and the second position. For example, the estimation unit 52 inputs the first position and the second position to the Kalman filter, and estimates the horizontal position of the vehicle when the probe information is acquired. Then, the estimation unit 52 refers to the control map 421 and selects a road within a predetermined range centered on the horizontal position of the vehicle 2. As a predetermined range, the accuracy of the horizontal position based on the positioning information can be used. When first estimating the horizontal position of the vehicle 2, the estimation unit 52 may use only the first position.

FIG. 7 is a diagram illustrating the operation of the estimation unit 52 of the processor 44 of the server 3. The estimation unit 52 estimates the horizontal position P of the vehicle 2 when the probe information is acquired, based on the longitude and latitude of the vehicle 2 when the probe information is acquired and the vehicle speed. The estimation unit 52 selects two roads R1 and R2 within a predetermined range Q centered on the horizontal position P of the vehicle 2 with reference to the control map 421. Road R2 is an elevated highway, and road R1 is a general road below road R2.

The estimation unit 52 determines whether or not there are a plurality of selected roads (step S203). When there are a plurality of selected roads (step S203-Yes), the estimation unit 52 is represented by the control map 421 stored in the storage device 42 based on the position estimation additional information included in the first acquisition data. The road on which the vehicle 2 was traveling when the probe information was acquired is estimated from a plurality of roads having different heights around the vehicle 2 when the probe information is acquired (step S204). ..

Specifically, the estimation unit 52 refers to the control map 421, and for each of the selected roads, the road at a point corresponding to the horizontal position of the vehicle 2 when the probe information is acquired. Get the height of. The estimation unit 52 is traveling on the road whose road height is closest to the height represented by the elliptical height of the vehicle 2 when the probe information is acquired, when the vehicle 2 is acquired. Estimated as a road. The height of the road at the point corresponding to the horizontal position of the vehicle 2 when the probe information is acquired is the altitude of the portion of the road within a predetermined range Q centered on the horizontal position P of the vehicle 2. It may be the average value of.

The determination unit 53 of the processor 44 of the server 3 determines whether or not the road estimated by the estimation unit 52 is correct based on the attribute information of the road features around the vehicle 2 included in the probe information (step S205). ).

For example, the determination unit 53 indicates that the attribute information of the road feature around the vehicle 2 included in the probe information is the road feature arranged on the general road, and the vehicle 2 travels by the estimation unit 52. When the road presumed to have been used is a general road, it is determined that the road presumed to have been driven by the vehicle 2 is correct. On the other hand, the determination unit 53 indicates that the attribute information of the road feature around the vehicle 2 included in the probe information is the road feature arranged on the general road, and the vehicle 2 travels by the estimation unit 52. When the road presumed to have been driven is a highway, it is determined that the road presumed to have been driven by the vehicle 2 is not correct. Examples of road features arranged on general roads include traffic lights, pedestrian crossings, stop lines, and the like.

Further, the determination unit 53 indicates that the attribute information of the road features around the vehicle 2 included in the probe information indicates the road features arranged on the highway, and the estimation unit 52 states that the vehicle 2 was traveling. When the estimated road is a highway, it is determined that the road on which the vehicle 2 is traveling is correct. On the other hand, the determination unit 53 states that the attribute information of the road features around the vehicle 2 included in the probe information indicates the road features arranged on the expressway, and that the vehicle 2 was traveling by the estimation unit 52. When the estimated road is a general road, it is determined that the road on which the vehicle 2 is traveling is not correct. Examples of the road feature arranged on the expressway include a road sign indicating the direction and distance of travel, a road sign indicating a service area or a parking area, and the like.

Further, when the attribute information of the road features around the vehicle 2 included in the probe information matches the road information included in the navigation map 422 stored in the storage device 42, the determination unit 53 causes the vehicle 2 to travel. The road that was presumed to have been used is judged to be correct. On the other hand, if this is not the case, the determination unit 53 determines that the road on which the vehicle 2 is presumed to be traveling is incorrect. For example, the determination unit 53 is a road marking in which the attribute information of the road feature indicates the traveling direction, and the traveling direction is the horizontal direction of the vehicle 2 when the probe information is acquired, which is included in the navigation map 422. If it matches the road information at the position, it is determined that the road on which the vehicle 2 is presumed to be traveling is correct. Further, the determination unit 53 is a road marking in which the attribute information of the road feature indicates the maximum speed, and the maximum speed is included in the navigation map, and the position in the horizontal direction of the vehicle 2 when the probe information is acquired. If it matches the road information in, it is determined that the road on which the vehicle 2 is presumed to be traveling is correct.

When it is determined that the road on which the vehicle 2 is presumed to be traveling is not correct (step S205-No), the estimation unit 52 of the processor 44 is selected from among a plurality of roads having different heights selected in step S202. One of the unselected roads is estimated as the road on which the vehicle 2 was traveling when the probe information was acquired (step S206). Here, when the probe information is acquired, the estimation unit 52 obtains the road whose road height is the second closest to the height represented by the elliptical height of the vehicle 2 when the probe information is acquired. It is estimated as the road on which the vehicle 2 was traveling. Then, the processing of the processor 44 proceeds to step S207. The newly estimated road may also be determined in step S205.

When the number of selected roads is not plural (step S203-No), the estimation unit 52 estimates the road selected in step S202 as the road on which the vehicle 2 was traveling when the probe information was acquired. (Step S207). Then, the processing of the processor 44 proceeds to step S208. Further, even when it is determined that the road on which the vehicle 2 is presumed to be traveling is correct (step S205-Yes), the processing of the processor 44 proceeds to step S208.

When the probe information included in the first acquired data identified by the first acquired data ID is acquired, the information acquisition unit 51 of the processor 44 of the server 3 photographs the surroundings of the vehicle 2 acquired by the vehicle 2. Generates a second acquisition data transmission request requesting transmission of the second acquisition data including the image. The information acquisition unit 51 includes the first acquisition data ID in the second acquisition data transmission request. The information acquisition unit 51 outputs the second acquisition data transmission request to the communication IF 41, so that the second acquisition data transmission request is transmitted to the vehicle 2 via the communication network 4 and the base station 5 (step S208). The image included in the second acquired data has a large amount of communication and a large amount of processing in the server 3. Therefore, the server 3 first receives the first acquired data having a relatively small amount of communication, and estimates the road on which the vehicle 2 was traveling when the probe information was acquired. Then, the server 3 requests the vehicle 2 to transmit the second acquisition data after it is determined that the road on which the vehicle 2 is traveling is correctly estimated when the probe information is acquired, and the server 3 relates to the road. Receive an image that represents the information. As a result, the server 3 can collect accurate road information and prevent unnecessary communication and processing.

When the second acquired data is input via the communication IF 41, the information registration unit 54 of the processor 44 includes the position and attribute information of the road features around the vehicle 2 included in the first acquired data, and the second. The image taken around the vehicle 2 included in the acquired data is registered in the control map 421 in association with the road estimated that the vehicle 2 was traveling (step S209).

As described above, this map information collecting device has probe information, horizontal position information of the vehicle when the probe information is acquired, and height direction of the vehicle when the probe information is acquired. The probe information, which is acquired from the vehicle via the input unit and is displayed on the map stored in the storage unit based on the horizontal position information and the position estimation additional information, includes the position estimation additional information including the position information. The road on which the vehicle was traveling when the probe information was acquired is estimated from a plurality of roads having different heights around the vehicle at the time of acquisition. As a result, the map information collecting device correctly estimates the road on which the vehicle is traveling and registers it on the map even if there are other roads in the vertical direction of the road on which the vehicle is traveling. Information can be collected.

Next, a modified example of the map information collection system described above will be described below. In the map information collection system of the modified example 1, the position information generation unit 32 of the processor 23 in the map information acquisition unit device 17 of the vehicle 2 adds position estimation including other information together with the position information in the height direction of the vehicle 2. Generate information. Then, the estimation unit 52 of the processor 44 in the server 3 obtains probe information based on the position information in the height direction of the vehicle 2 and the position estimation additional information including the position information in the height direction of the vehicle 2 and other information. It is estimated as the road on which the vehicle 2 was traveling when it was acquired. For example, the position information generation unit 32 may use other position estimation additional information such as information indicating an altitude change in the position of the vehicle 2, information indicating whether or not there is a structure above the vehicle 2, and lanes around the vehicle 2. At least one of the information indicating the lane marking and the information indicating the reception state of the positioning radio wave from the positioning satellite in the vehicle 2 is generated. The data generation unit 33 of the processor 23 generates the position estimation additional information including the position information in the height direction of the vehicle 2.

The position information generation unit 32 has acquired probe information from the time when the vehicle 2 starts traveling based on the positioning information input from the positioning information receiver 14 and the atmospheric pressure input from the barometer 13. The atmospheric pressure change information showing the relationship between the horizontal position information of the vehicle 2 up to the time point and the atmospheric pressure measured in the vehicle 2 is generated. The atmospheric pressure change information represents the change in atmospheric pressure from the point where the vehicle 2 starts traveling to the point where the probe information is acquired, and this change in atmospheric pressure corresponds to the altitude change of the vehicle 2.

Further, the position information generation unit 32 inputs the camera image C to the classifier, determines whether or not there is a structure above the vehicle 2 in the input camera image C, and acquires probe information. When this is done, the upper structure information indicating whether or not there is a structure above the vehicle 2 is generated. Examples of the structure above the vehicle 2 include an elevated road such as a highway, a tunnel ceiling, and the like. When there is a structure above the vehicle 2, it is presumed that the vehicle 2 is traveling on the road located on the lower side of the roads located above and below. For example, since the camera image C shown in FIG. 1 includes an elevated road, the position information generation unit 32 determines that the camera image C has a structure above the vehicle 2.

Further, the position information generation unit 32 is notified of the detection result of the detection unit 31, detects the number of lane marking lines around the vehicle 2, and generates the lane marking number information when the probe information is acquired. do. The lane marking number information is presumed to represent the number of lane markings on the road on which the vehicle 2 was traveling when the probe information was acquired. Since the number of lane marking lines may differ depending on the road, it is information for estimating the road on which the vehicle 2 is traveling.

Further, the position information generation unit 32 is the number of positioning satellites for which positioning radio waves are received at a predetermined reception intensity or higher when probe information is acquired based on the positioning information input from the positioning information receiver 14. Generates positioning radio wave reception status information that represents. When the upper part is not covered with a structure, the predetermined number of positioning satellites for which positioning radio waves are received at a predetermined reception intensity or higher can be estimated for each point. Therefore, when the number of positioning satellites represented by the positioning radio wave reception status information is less than a predetermined number, it is estimated that there is a structure above the vehicle 2. The position estimation additional information may include at least the position information in the height direction of the vehicle 2, and may not include other position estimation additional information.

When the position estimation additional information includes the above-mentioned other information together with the position information in the height direction of the vehicle 2, the estimation unit 52 of the processor 44 in the server 3 uses the position information in the height direction of the vehicle 2 and the pressure change information. , Upper structure information, lane division line number information, and positioning radio wave reception status information are used to calculate evaluation values for each of a plurality of roads having different heights. Then, the estimation unit 52 estimates the road on which the vehicle 2 was traveling when the probe information was acquired, based on the evaluation value.

With reference to the control map 421, the estimation unit 52 acquires the height of the road at the point corresponding to the horizontal position of the vehicle 2 when the probe information is acquired for each of the selected roads. do. The estimation unit 52 has a plurality of different heights so that the closer the height of the road is to the height represented by the position information in the height direction of the vehicle 2 when the probe information is acquired, the higher the evaluation point is. A first evaluation point is given to each of the roads. The height of the road at the point corresponding to the horizontal position of the vehicle 2 when the probe information is acquired is the altitude of the portion of the road within a predetermined range centered on the horizontal position of the vehicle 2. It may be an average value.

The estimation unit 52 refers to the control map 421 and acquires the height at the point where the vehicle starts traveling. Further, the estimation unit 52 converts the atmospheric pressure included in the atmospheric pressure change information to an altitude by using a method of a public land, and the altitude change from the height of the point where the vehicle starts traveling to the time when the probe information is acquired. Ask for information. The estimation unit 52 refers to this altitude change information and obtains the height of the vehicle 2 when the probe information is acquired. The estimation unit 52 makes a second evaluation for each of the plurality of roads having different heights so that the evaluation point becomes higher as the height of the road is closer to the height of the vehicle 2 at the time when the probe information is acquired. Give points.

When the upper structure information indicates that the structure is above the vehicle 2, the estimation unit 52 indicates that the evaluation point is higher as the height of the road is lower, so that the evaluation point is higher for each of the plurality of roads having different heights. A third evaluation point is given. On the other hand, when the upper structure information indicates that there is no structure above the vehicle 2, the estimation unit 52 sets each of the plurality of roads having different heights so that the higher the road height, the higher the evaluation point. A third evaluation point is given to.

The estimation unit 52 refers to the control map 421, and for each of the plurality of selected roads, the number of lane division lines of the road at the point corresponding to the horizontal position of the vehicle 2 when the probe information is acquired. To get. The estimation unit 52 is the first for each of a plurality of roads having different heights so that the evaluation point becomes higher as the number of lane division lines of the road is closer to the number of lane division lines represented by the lane division number information. 4 Evaluation points are given.

When the number of positioning satellites represented by the positioning radio wave reception status information is less than a predetermined number, it is estimated that there is a structure above the vehicle 2. In this case, the estimation unit 52 assigns a fifth evaluation point to each of the plurality of roads having different heights so that the lower the height of the road, the higher the evaluation point. On the other hand, when the number of positioning satellites represented by the positioning radio wave reception status information is a predetermined number or more, it is estimated that there is no structure above the vehicle 2. In this case, the estimation unit 52 assigns a fifth evaluation point to each of the plurality of roads having different heights so that the higher the height of the road, the higher the evaluation point.

The estimation unit 52 obtains the sum of products of the first evaluation points to the fifth evaluation points and the first weights to the fifth weights, which are the respective weights, and obtains the evaluation values of the plurality of roads having different heights. .. The estimation unit 52 estimates the road showing the highest evaluation value as the road on which the vehicle 2 was traveling when the probe information was acquired. When the position estimation additional information does not include all the above-mentioned information, the estimation unit 52 may obtain an evaluation point of the information possessed by the position estimation additional information. Further, the position estimation additional information may include other information as long as it is information related to the position of the vehicle 2 in the height direction.

Then, when it is determined that the road on which the vehicle 2 is presumed to be traveling is not correct (step S205-No), the estimation unit 52 has acquired probe information on the road having the second highest evaluation value. It is estimated as the road on which the vehicle 2 was traveling.

In the map information collection system of the modified example 2, the vehicle 2 passes through one data collection section and then transmits a plurality of collected first acquired data to the server 3. The server 3 estimates the road on which the vehicle was traveling when the probe information was acquired for each of the plurality of first acquired data received.

In the map information collection system of the variant example 3, when the server 3 is estimated that the vehicle 2 is traveling on the same road based on the plurality of first acquired data, the first acquired data is the first for each of the plurality of first acquired data. 2 Request the transmission of acquired data collectively. As a result, it is possible to reliably collect a plurality of information about this road after it is confirmed that the vehicle 2 is traveling on the same road.

In the present invention, the map information collecting device of the above-described embodiment can be appropriately modified as long as it does not deviate from the gist of the present invention. Further, the technical scope of the present invention is not limited to those embodiments, but extends to the inventions described in the claims and their equivalents.

For example, the present invention may be applied not only to distinguish roads in the height direction but also to distinguish a plurality of roads adjacent to each other on the left and right. For example, if the vehicle is traveling on a side road beside the freeway, the map information collector determines whether the vehicle is traveling on the side road or on the freeway. It can also be used for things. That is, the estimation unit is in a plurality of roads around the vehicle when the probe information is acquired, which is displayed on the map stored in the storage unit based on the horizontal position information and the position estimation additional information. Therefore, the road on which the vehicle was traveling may be estimated when the probe information is acquired.

Further, in the above-described embodiment, the server has the function of the map information collecting device, but the map information collecting device may be arranged in the vehicle. Further, in the above-described embodiment, the horizontal position is represented by longitude and latitude, and the height position is represented by elliptical height, but the method of representing the vehicle position is not limited to this. .. For example, the position of the vehicle may be represented by the earth center / earth fixed Cartesian coordinate system.

Further, in the above-described embodiment, the determination unit determines whether or not the road estimated by the estimation unit is correct, but the map information collecting device may not have the determination unit. In this case, the information acquisition unit transmits the second acquisition data transmission request to the vehicle after the road on which the vehicle was traveling is estimated when the probe information is acquired by the estimation unit.

Further, in the above-described embodiment, the information acquisition unit requests the vehicle for the second acquisition data, but the map information collecting device does not have to request the second acquisition data to the vehicle. In this case, the information registration unit estimates the road on which the vehicle was traveling when the probe information was acquired by the estimation unit, and then acquires the probe information included in the first acquisition data. Register in the control map in relation to the road on which the vehicle was traveling.

1 Map information collection system 2 Vehicle 11 Camera 12 Wireless communication terminal 13 Pressure gauge 14 Positioning information receiver 15 Navigation device 16 Vehicle speed sensor 17 Map information acquisition device 18 In-vehicle network 21 Communication interface 22 Memory 23 Processor 24 Signal line 31 Detection unit 32 Position Information generation unit 33 Data generation unit 3 Server 41 Communication interface 42 Storage device 421 Control map 422 Navigation map 43 Memory 44 Processor 45 Signal line 51 Information acquisition unit 52 Estimating unit 53 Judgment unit 54 Information registration unit 4 Network 5 Base station

Claims (1)

Input section and
A storage unit that stores a map in which probe information including information about the road on which the vehicle is traveling acquired by the vehicle is registered, and a storage unit.
The probe information, the horizontal position information of the vehicle when the probe information is acquired, and the additional position estimation information including the position information in the height direction of the vehicle when the probe information is acquired. , The probe information represented on the map stored in the storage unit based on the horizontal position information and the position estimation additional information acquired from the vehicle via the input unit was acquired. An estimation unit that estimates the road on which the vehicle was traveling when the probe information was acquired from a plurality of roads having different heights around the vehicle.
Map information collection device with.

Images