JP2021018661A - Traffic lane data generation device, position identification device, traffic lane data generation method, and position identification method - Google Patents

Abstract

To provide a traffic lane data generation device that appropriately generates traffic lane data containing position information for a plurality of traffic lanes.SOLUTION: A traffic lane data generation device 100 comprises: a border line determination unit 111 that determines whether a boarder line imaged by a camera 2 is an edge border line or an intermediate border line; a distance calculation unit 112 that calculates distances from a vehicle to left and right border lines on the basis of image information for the border line; an information acquisition unit 113 that acquires information on the number of traffic lanes on the basis of a position of the vehicle detected by a GPS unit 1; and a data generation unit 114 that generates position data for a plurality of traffic lanes on the basis of distance data which is calculated by the distance calculation unit 112 when it is determined by the border line determination unit 111 that one and the other of the left and right border lines are an edge border line and an intermediate border line, respectively, and the information on the number of traffic lanes acquired by the information acquisition unit.SELECTED DRAWING: Figure 2

Description

The present invention relates to a lane data generation device that generates lane data including lane position information, a position identification device that specifies the position of a moving body using the lane data, and a lane data generation method and a position identification method.

Conventionally, as this kind of device, the absolute position (latitude, longitude, altitude) of the left and right boundary lines that define the lane imaged by the in-vehicle camera based on the signals from the in-vehicle camera mounted on the vehicle and the GPS receiver. ) Is known (see, for example, Patent Document 1).

Patent Document 1: Japanese Unexamined Patent Publication No. 2018-55715

However, with the device described in Patent Document 1, sufficient lane data can be obtained when a vehicle is located on a road surface provided with a plurality of lanes and it is difficult for an in-vehicle camera to recognize all the boundary lines. Is difficult.

One aspect of the present invention is a lane data generation device that generates lane data of a plurality of lanes partitioned by a plurality of boundary lines extending laterally apart from each other on a road surface, wherein the plurality of boundary lines are , A pair of left and right end boundaries formed on the right side of the rightmost lane and a left side of the leftmost lane, and an intermediate boundary formed substantially parallel to the end boundary line inside the pair of left and right end boundaries. Includes lines and. The lane data generator includes a position detection unit that detects the position of the moving body, an imaging unit that images the boundary lines located on both the left and right sides of the moving body, and the boundary line imaged by the imaging unit at the end boundary line and the middle. A boundary line determination unit that determines which of the boundary lines is used, and a distance calculation unit that calculates the distance from the moving body to the left and right boundary lines based on the image information of the boundary line captured by the imaging unit. Based on the position of the moving body detected by the position detection unit, the information acquisition unit that acquires information on the number of lanes on the road surface on which the moving body is located, and the boundary line determination unit sets the boundary lines on both the left and right sides to the end boundary line and The distance data calculated by the distance calculation unit when it is determined to be the intermediate boundary line, the position data of the moving body detected by the position detection unit, and the information on the number of lanes acquired by the information acquisition unit are Based on this, it includes a data generation unit that generates position data of a plurality of lanes.

The position identification device according to another aspect of the present invention includes the above-mentioned lane data generation device, the position data of a plurality of lanes generated by the lane data generation device, and the position data of the moving body detected by the position detection unit. A lane identification unit that identifies the lane in which the moving body is located is provided based on.

Yet another aspect of the present invention is a lane data generation method for generating lane data of a plurality of lanes partitioned by a plurality of boundaries extending laterally apart from each other on a road surface, wherein the plurality of boundaries. The lines were formed on the right side of the rightmost lane and on the left side of the leftmost lane, and inside the pair of left and right end boundary lines, substantially parallel to the end boundary line. Includes intermediate boundaries. The lane data generation method includes a position detection step for detecting the position of the moving body, an imaging step for imaging the boundary lines located on both the left and right sides of the moving body, and the boundary line imaged in the imaging step at the end boundary line and the middle. A determination step for determining which of the boundary lines, a calculation step for calculating the distance from the moving body to the boundary lines on both the left and right sides based on the image information of the boundary line captured in the imaging step, and a position detection step. Based on the position of the moving body detected in, the acquisition step of acquiring the information on the number of lanes on the road surface on which the moving body is located and the determination step indicate that the boundary lines on both the left and right sides are the end boundary line and the intermediate boundary line. Positions of a plurality of lanes based on the distance data calculated in the calculation step at the time of determination, the position data of the moving body detected in the position detection step, and the information on the number of lanes acquired in the acquisition step. Includes a data generation step to generate data.

Yet another aspect of the present invention uses lane data of a plurality of lanes partitioned by a plurality of boundaries extending laterally apart from each other on the road surface to identify the lane in which the moving body is located. In the positioning method, a plurality of boundary lines are formed inside a pair of left and right end boundary lines formed on the right side of the right end lane and the left side of the left end lane, and inside a pair of left and right end boundary lines. Includes intermediate boundaries. The position identification method includes a position detection step for detecting the position of the moving object, an imaging step for imaging the boundary lines located on both the left and right sides of the moving object, and the boundary line imaged in the imaging step for the end boundary line and the intermediate boundary. In the determination step of determining which of the lines it is, the calculation step of calculating the distance from the moving body to the boundary lines on both the left and right sides based on the image information of the boundary line captured in the imaging step, and the position detection step. Based on the detected position of the moving body, the acquisition step of acquiring the information on the number of lanes on the road surface on which the moving body is located, the position data of the moving body detected in the position detection step, and the boundary between the left and right sides in the determination step. Position data of a plurality of lanes based on the distance data calculated in the calculation step when it is determined that the line is the end boundary line and the intermediate boundary line, and the information on the number of lanes acquired in the acquisition step. The lane in which the moving body is located is specified based on the data generation step for generating the data, the position data of a plurality of lanes generated in the data generation step, and the position data of the moving body detected in the position detection step. Including lane identification steps and.

According to the present invention, lane data of a plurality of lanes can be easily and satisfactorily obtained.

The plan view which shows an example of the road to which the lane data generation device which concerns on embodiment of this invention is applied. The block diagram which shows the main part structure of the lane data generation apparatus which concerns on embodiment of this invention. The figure for demonstrating an example of the process executed by the arithmetic unit of FIG. The figure which shows an example of the lane data obtained by the lane data generator of FIG. The flowchart which shows an example of the process executed by the arithmetic unit of FIG. The figure which shows the modification of FIG. The figure for demonstrating the processing of the position calculation part of FIG. The block diagram which shows the main part structure of the position identification apparatus which concerns on embodiment of this invention. The figure for demonstrating the processing of the lane identification part of FIG.

Hereinafter, embodiments of the present invention will be described with reference to FIGS. 1 to 9. The lane data generation device according to the embodiment of the present invention is mounted on, for example, a vehicle having an automatic driving function. In a vehicle of this type, while traveling on a wide road having a plurality of lanes, the traveling operation is controlled after identifying which lane the vehicle is traveling in. For this reason, it is necessary for the vehicle to accurately grasp the lane position data, but if it is attempted to acquire this from data included in a dynamic map (also called an HD map) via a communication means, for example, the data is acquired. Advanced communication means are required, which leads to an increase in cost. Therefore, the lane data generation device according to the present embodiment is configured to independently generate lane data instead of obtaining data from the dynamic map.

FIG. 1 is a plan view showing an example of a road having a plurality of lanes (for example, five lanes on each side). A lane is a traveling lane having a predetermined width that defines a traveling area of the vehicle 101. In the following, the front-rear direction and the left-right direction are defined as shown in the figure, and the configuration of each part will be described according to this definition. The front-rear direction is the direction in which the lane LN extends, and the left-right direction is the lane width direction orthogonal to the lane LN. When the vehicle 101 is traveling along the lane LN as shown in the drawing, the front-rear direction corresponds to the length direction of the vehicle 101, and the left-right direction corresponds to the vehicle width direction. The plurality of lanes LNs (LN1 to LN5) are referred to as a first lane LN1, a second lane LN2, a third lane LN3, a fourth lane LN4, and a fifth lane LN5 in order from the left side. In FIG. 1, a vehicle 101 having a lane data generation device 100 is traveling in the first lane LN1.

Each lane LN is defined by a plurality of boundary lines BL (BL1 to BL6) extending in parallel so as to be separated from each other in the left-right direction. That is, the first lane LN1 has a pair of left and right boundary lines BL1 and BL2, the second lane LN2 has a pair of left and right boundary lines BL2 and BL3, and the third lane LN3 has a pair of left and right boundary lines BL3 and BL4. The LN4 is defined by a pair of left and right boundary lines BL4 and BL5, and the fifth lane LN5 is defined by a pair of left and right boundary lines BL5 and BL6. Of the boundary lines BL1 to BL6, the boundary lines BL1 and BL6 at both left and right ends, that is, the boundary lines defining the road area are called end boundary lines, and the inner boundary lines BL2 to BL5 of the end boundary lines BL1 and BL6 are referred to. Called the intermediate boundary.

The end boundary lines BL1 and BL6 and the intermediate boundary lines BL2 and BL5 are represented in different forms from each other. For example, as shown in FIG. 1, the end boundary lines BL1 and BL6 are represented by solid lines, and the intermediate boundary lines BL2 to BL5 are represented by broken lines. The virtual line CL passing through the center of each lane LN shown by the alternate long and short dash line in FIG. 1 is referred to as a center line. The lane data of each lane LN includes the position data (latitude, longitude, etc.) of the pair of left and right boundary lines BL that define each lane LN, and the position data (latitude, longitude, etc.) of the center line CL of each lane LN. ..

FIG. 2 is a block diagram showing a main configuration of the lane data generation device 100 according to the present embodiment. As shown in FIG. 2, the lane data generation device 100 includes a GPS unit 1, a camera 2, a map database 3, a communication unit 4, and a controller 10. The GPS unit 1, the camera 2, the map database 3, and the communication unit 4 are connected to the controller 10 so as to be able to communicate with each other.

The GPS unit (GNSS unit) 1 has a GPS receiver (GPS sensor) that receives positioning signals from a plurality of GPS satellites, and an absolute position of a reference point of the vehicle 101 based on the positioning signal received by the GPS receiver. Measure (latitude, longitude, etc.). The reference point is set at a predetermined position in the center of the vehicle 101 in the vehicle width direction, for example, above the windshield.

The camera 2 is a monocular camera having an image sensor (image sensor) such as a CCD or CMOS. The camera 2 is attached to, for example, a reference point above the windshield, images the space in front of the vehicle 101, and acquires an image (camera image) of the object. The object includes a pair of left and right boundary lines BL diagonally forward of the vehicle. There is a predetermined correlation between the position of the object on the camera image and the actual position of the object (relative position with respect to the camera 2). This correlation is stored in the storage unit 12 in advance, and the actual position of the object (relative position from the camera 2) can be detected from the camera image by using this correlation. A stereo camera may be used as the camera 2 instead of the monocular camera, and the actual position of the object may be detected by the stereo camera.

The map database 3 is a device that stores general map information used in a navigation device (not shown), and is composed of, for example, a hard disk or a semiconductor element. Map information includes road position information, road shape (curvature, etc.) information, and intersection and branch point position information. The map information stored in the map database 3 may be stored in the storage unit 12 of the controller 10.

The communication unit 4 communicates with various servers (not shown) via a network including a wireless communication network such as an Internet line, and acquires map information, traffic information, and the like from the server periodically or at an arbitrary timing. The acquired map information is output to the map database 3 and the storage unit 12, and the map information is updated.

The controller 10 is composed of an electronic control unit (ECU). More specifically, the controller 10 includes a computer having a calculation unit 11 such as a CPU, a storage unit 12 such as a ROM and a RAM, and other peripheral circuits (not shown) such as an I / O interface. ..

Road information is stored in the storage unit 12. Road information includes information indicating the type of road such as highways, toll roads, and national roads, the number of lanes, the width of each lane, the slope of the road, the three-dimensional coordinate position of the road, the curvature of the curve of the lane, and the lane. Information such as the positions of merging points and branching points, road signs, etc. is included. The lane data generated by the lane data generation device 100, that is, the position data of the lane LN (position data of the boundary line BL, position data of the center line CL, etc.) is also stored in the storage unit 12 as a part of the road information. Information such as various control programs and threshold values used in the programs is also stored in the storage unit 12.

The calculation unit 11 has a boundary line determination unit 111, a distance calculation unit 112, an information acquisition unit 113, and a data generation unit 114 as a functional configuration for generating lane data.

FIG. 3 is a diagram for explaining an example of processing executed by the calculation unit 11. In addition, FIG. 3 shows a state in which the vehicle 101 is indicated by a schematic circular mark on the plan view of the road and the vehicle 101 has moved from the fifth lane LN5 at the right end to the fourth lane LN4 adjacent to the left. Is done. The orientation of the vehicle 101 is indicated by the orientation of the protruding mark in the circular mark, and the vehicle 101 is oriented in the extending direction of the lane LN. The tip P of the protruding mark is the position of the vehicle 101 detected by the GPS unit 1, that is, the reference point. The hatched area extending from the circular mark in the vehicle traveling direction represents the imaging range AR by the camera 2 provided at the reference point P. The imaging range AR is limited. For example, when the vehicle 101 is located in the fifth lane LN5, the boundary lines BL5 and BL6 on both the left and right sides of the lane LN5 are included in the imaging range, but all the boundary lines BL1 to BL6 are imaged. It cannot be expected to be included in the range AR.

The boundary line determination unit 111 recognizes the image of the boundary line BL included in the image captured by the camera 2 by performing edge detection and pattern matching processing. Further, the boundary line determination unit 111 extracts feature points of the image of the recognized boundary line BL, and based on the extracted feature points, the recognized boundary line BL is the end boundary lines BL1 and BL6 (solid lines). And which of the intermediate boundary lines BL2 to BL5 (broken line) is determined.

The distance calculation unit 112 is based on the image information of the boundary lines BL on both the left and right sides captured by the camera 2, and the boundary lines BL on both the left and right sides (for example, a boundary line having a predetermined width) from the reference point P at the center in the left-right direction of the vehicle 101 The distances D1 and D2 to the center of the BL or the inner edge of the boundary line BL in the left-right direction are calculated. More specifically, by using the correlation between the position on the image and the actual position stored in the storage unit 12 in advance, from the camera 2 located at the reference point P to the boundary line BL recognized by the boundary line determination unit 111. The distance in the left-right direction of, that is, the distance in the direction perpendicular to the boundary line BL and the center line CL is calculated. For example, as shown in FIG. 3, when the vehicle 101 is located in the fifth lane LN5, the distance D1 on the left side from the reference point P to the intermediate boundary line BL5 and the distance D2 on the right side to the end boundary line BL6 are calculated. ..

The information acquisition unit 113 identifies the road point where the vehicle 101 is located based on the signal transmitted from the GPS unit 1, and from the road information stored in the storage unit 12, information on the number of lanes corresponding to the road point. To get. In the example of FIG. 3, the information of the number of lanes = 5 is acquired.

The data generation unit 114 of the distances D1 and D2 calculated by the distance calculation unit 112 when one of the left and right boundary lines BL is determined by the boundary line determination unit 111 to be the end boundary line BL1 or BL6. Based on the data (distance data), the position data of the vehicle 101 (reference point P) detected by the GPS unit 1, and the information on the number of lanes acquired by the information acquisition unit 113, the plurality of lanes LN1 to LN5 Generate position data.

More specifically, when the image of the boundary line BL recognized by the camera 2 is recognized as the image of the end boundary line BL6 as shown in FIG. 3, the data generation unit 114 sets the reference point P. Position data (lane data) of the lane LN5 where the vehicle 101 is located, that is, position data of the boundary lines BL5, BL6 and the center line CL, using the data of the distances D1 and D2 from the boundary lines BL5 and BL6 on both the left and right sides thereof. To generate. Further, the lane width ΔW is calculated from the position data of the boundary lines BL5 and BL6 included in the lane data, and the number of lanes on the road acquired by the information acquisition unit 113 corresponding to the own vehicle position detected by the GPS unit 1. By offsetting the position data of the boundary lines BL5 and BL6 to the left by the length of the lane width ΔW, the position data of the remaining lanes LN1 to LN4 (position data of the boundary lines BL1 to BL4, etc.) can be obtained. Generate.

The position data of the lane LN5 obtained by calculating the distances D1 and D2 from the reference point P is the measured lane data, and the position data of the remaining lanes LN1 to LN4 obtained by using the measured lane data is estimated lane data. Called. From the above, lane data of a plurality of lanes LN1 to LN5 can be obtained. When the image of the boundary line BL recognized by the camera 2 is recognized as the image of the end boundary line BL1, the data generation unit 114 uses the position data of the first lane LN1 in which the vehicle 101 is located as the number of lanes. Estimated lane data of lanes LN2 to LN5 is generated by offsetting to the right by the number. The position data generated by the data generation unit 114 is stored in the storage unit 12 as lane data (measured lane data, estimated lane data).

The data generation unit 114 generates lane data at predetermined time intervals, for example, and updates the lane data stored in the storage unit 12. As shown in FIG. 3, when the vehicle 101 changes lanes from the fifth lane LN5 to the fourth lane LN4, the data generation unit 114 calculates the distances D1 and D2 from the vehicle 101 to the left and right boundary lines BL4 and BL5. Then, the lane data (measured lane data) of the fourth lane LN4 is generated using the calculated data of the distances D1 and D2. Then, the estimated lane data of the fourth lane LN4 stored in the storage unit 12 is replaced with the actually measured lane data and updated, and the first lane data is updated (for example, the position data of the boundary line BL4 is changed). Correct (update) the estimated lane data for lanes LN1 to 3rd lane LN3.

Similarly, when the vehicle 101 moves to the first lane LN1 to the third lane LN3, the measured lane data of each lane LN1 to LN3 is generated, the estimated lane data is replaced with the measured lane data, and the lane data is updated. .. By updating the lane data using the data of the distances D1 and D2 actually measured in this way, the lane data can accurately represent the position of the actual lane LN, and the lane data generation accuracy is improved.

The lane data generated as described above is the position data (with the first lane data) of a plurality of lane LNs existing within a predetermined distance (imaging range of the camera 2) in the extending direction of the lane LN from the vehicle 101. Call). The data generation unit 114 is based on the first lane data and the map information (road information) obtained by the map database 3, and the position data (first) of a plurality of lane LNs existing over a predetermined distance from the vehicle 101. (Called 2 lane data) is further generated.

Specifically, the vehicle position on the map is recognized based on the vehicle position detected by the GPS unit 1 and the map information. Then, when the data generation unit 114 determines that the road becomes a curved road having a predetermined curvature as shown in FIG. 4, for example, the lane data is changed along the curved road (for example, as shown by the arrow in FIG. 4). The lane data of each lane LN1 to LN5 exceeding a predetermined distance from the vehicle 101 is generated (so that the position of the center line CL changes), and the lane data is stored in the storage unit 12. By generating the second lane data according to the road shape in this way, it is possible to accurately generate lane data of a plurality of lanes LNs at positions away from the vehicle 101. Further, lane data when there is a lane LN that exists within a predetermined distance from the vehicle 101 but cannot be recognized by the camera 2 can be satisfactorily generated by using the road shape data. That is, not only the second lane data but also the first lane data can be generated by using the road shape data.

FIG. 5 is a flowchart showing an example of processing executed by the calculation unit 11 according to a program stored in the storage unit 12 in advance, particularly an example of processing related to the generation of the first lane data. The process shown in this flowchart is started, for example, by turning on the vehicle power, and is repeated at a predetermined cycle. In the description of the flowchart below, the lanes LN1 to LN5 of FIG. 1 are used for convenience.

First, in step S1, the position data of the vehicle 101 (reference point P) detected by the GPS unit 1 is read. Next, in step S2, the camera image acquired by the camera 2 is read. Next, in step S3, road information corresponding to the position data of the vehicle 101 in step S1 is acquired from the storage unit 12. That is, the information on the number of lanes and the information on the road shape in the traveling direction of the vehicle 101 are acquired. Next, in step S4, edge detection and pattern matching are performed to determine whether or not the camera image read in step S2 includes the image of the boundary line BL. If affirmed in step S4, the process proceeds to step S5, and if denied, the process ends.

In step S5, it is determined whether or not the image of the boundary line BL determined in step S4 is the image of the end boundary line BL1 or BL6. If affirmed in step S5, the process proceeds to step S6, and the distances D1 and D2 from the vehicle 101 (reference point P) to the left and right boundary lines BL1, BL2 or BL5 and BL6 based on the camera image read in step S2. Is calculated. Next, in step S7, the position data (measured lane data) of the lane LN1 or LN5 in which the vehicle 101 is located is generated, and the lane data is rotated in the left-right direction (as many as the number of lanes included in the road information acquired in step S3). The position data (estimated lane data) of the remaining lanes LN2 to LN5 or LN1 to LN4 is generated by offsetting in the lane width direction). Then, these generated lane data are stored in the storage unit 12.

On the other hand, if it is denied in step S5, the process proceeds to step 8, and it is determined whether or not the position data (lane data) of the lanes LN1 to LN5 corresponding to the position data of the vehicle 101 is already stored in the storage unit 12. This lane data includes estimated lane data obtained by offsetting the position data of the lane LN in the lane width direction in step S7. If affirmed in step S8, the process proceeds to step S9, and if denied, the process ends. In step S9, the distances D1 and D2 from the vehicle 101 to the boundary lines BL on both the left and right sides are calculated based on the camera image read in step S2. Next, in step S10, the position data (measured lane data) of the lane LN in which the vehicle 101 is located is generated using the data of the distances D1 and D2 calculated in step S9, and further, the lane generated in step S7. The position data (estimated lane data) of the LN is updated by this measured lane data.

When the lane data is generated in step S7, the lane data (second lane data) in the traveling direction of the vehicle 101 is simultaneously generated by using the road shape information included in the road information acquired in step S3. It may be. Further, the presence / absence of the second lane data may be determined in step S8, and the second lane data may be updated in step S10.

The operation of the lane data generation device 100 according to the present embodiment can be summarized as follows. When the vehicle 101 travels in, for example, the fifth lane LN5 at the right end of the plurality of lanes LN1 to LN5, the image of the right boundary line BL6 captured by the camera 2 is recognized as the end boundary line image. As a result, the distances D1 and D2 from the vehicle 101 to the left and right boundary lines BL5 and BL6 are calculated based on the camera image (step S6). Further, position data (lane data) of all lanes LN1 to LN5 are generated by using this distance data and information on the number of lanes on the road corresponding to the position of the own vehicle (step S7). As a result, lane data can be easily generated even when the camera 2 cannot recognize all lane LNs.

After that, when the vehicle 101 changes lanes to the fourth lane LN4, the distances D1 and D2 from the own vehicle position (reference point P) to the boundary lines BL4 and BL5 recognized by the camera 2 are calculated (step S9). Then, the lane data of the fourth lane LN4 is updated using this distance data (step S10). As a result, the estimated lane data is replaced with the actually measured lane data, and the accuracy of lane data generation is improved.

FIG. 6 is a block diagram showing a schematic configuration of a lane data generation device 100A as a modification of FIG. 2. In FIG. 6, the calculation unit 11 of the controller 10 has a position calculation unit 115 in addition to the boundary line determination unit 111, the distance calculation unit 112, the information acquisition unit 113, and the data generation unit 114 as a functional configuration.

The position calculation unit 115 is based on the lane data generated by the data generation unit 114 and the distances D1 and D2 calculated by the distance calculation unit 112, and the position of the vehicle 101 (reference point P), more specifically, the lane. Calculate the position in the width direction. That is, the position data of the reference point P is calculated by subtracting the distance D2 from the position data of the boundary line BL on the left and right sides (for example, the right side) of the vehicle 101 included in the lane data. P1 in FIG. 7 is an example of a reference point calculated by the position calculation unit 115, and the reference point P1 is calculated by a camera image from the position data of the boundary line BL5 (dashed-dotted line) stored in the storage unit 12. It is obtained by subtracting the distance D2. P2 in FIG. 7 is an example of the reference point detected by the GPS unit 1 after the reference point P1 is calculated. That is, the reference point P1 is obtained at the first time point, and the reference point P2 is obtained at the second time point after the first time point.

The data generation unit 114 calculates the position deviation of these reference points P1 and P2 (for example, the distance between the reference points P1 and P2 in the lane width direction). Then, when the deviation is equal to or greater than a predetermined value, the lane data is regenerated using the position data of the reference point P2. That is, the distance calculation unit 112 calculates the distances D1 and D2 from the reference point P2 to the boundary line (boundary lines BL4 and BL5 in the example of FIG. 4), and the distance data, the position data of the reference point P2, and the number of lanes. Lane data is generated based on the information, and the lane data at the first time point is updated with the lane data at the second time point. The positions of the boundary lines BL4 and BL5 based on the updated lane data are shown by broken lines, and the positions of the boundary lines BL6 are shown by solid lines.

By generating lane data based on the latest position data of the vehicle 101 in this way, for example, when the shape of the lane LN around the vehicle changes as the vehicle 101 travels, good lane data corresponding to the change is obtained. Can be updated to. That is, the lane data generation device 100 of the present embodiment not only generates lane data at a location where lane data is not generated, but also updates lane data at a location where lane data has already been generated. Even if the position of the boundary line BL changes after road construction or the like, it can be appropriately dealt with.

According to this embodiment, the following effects can be obtained.
(1) The lane data generation device 100 is provided in the vehicle 101 and generates lane data of a plurality of lane LNs defined by a plurality of boundary lines BL extending laterally apart from each other on the road surface. The plurality of boundary lines BL are formed inside the pair of left and right end boundary lines BL1 and BL6 formed on the right side of the rightmost lane LN5 and the left side of the leftmost lane LN1 and the pair of left and right end boundary lines BL1 and BL6. The intermediate boundary lines BL2 to BL5 formed substantially parallel to the end boundary lines BL1 and BL6 are included (FIG. 1). The lane data generation device 100 has a GPS unit 1 that detects the position of the vehicle 101, a camera 2 that captures the boundary lines BL located on both the left and right sides of the vehicle 101, and a boundary line BL imaged by the camera 2 at the ends. Vehicle 101 (reference point P) based on the image information of the boundary line BL captured by the camera 2 and the boundary line determination unit 111 for determining which of the boundary lines BL1 and BL6 and the intermediate boundary lines BL2 and BL5. Based on the distance calculation unit 112 that calculates the distances D1 and D2 from to the boundary lines BL on both the left and right sides and the position of the vehicle 101 detected by the GPS unit 1, information on the number of lanes on the road surface on which the vehicle 101 is located is acquired. Distance calculation when it is determined by the information acquisition unit 113 and the boundary line determination unit 111 that the boundary lines BL on both the left and right sides are either the end boundary lines BL1 and BL6 and the intermediate boundary lines BL2 to BL5. Based on the distance data calculated by the unit 112, the position data of the vehicle 101 detected by the GPS unit 1, the information on the number of lanes acquired by the information acquisition unit 113, and the position data of a plurality of lane LNs. It includes a data generation unit 114 to be generated (FIG. 2).

With this configuration, when the vehicle 101 is located on a road having a plurality of lane LNs, the lane LNs are independently based on the image of the in-vehicle camera 2 without obtaining lane data from a dynamic map or the like via a communication means. Position data can be generated. As a result, for example, a vehicle having an automatic driving function can recognize the traveling lane of the own vehicle, and the traveling operation of the automatic driving vehicle can be satisfactorily controlled.

(2) When the data generation unit 114 determines by the boundary line determination unit 111 that the boundary lines BL on both the left and right sides are either the end boundary lines BL1 and BL6 and the intermediate boundary lines BL2 to BL5. Based on the distance data calculated by the distance calculation unit 112 and the position data detected by the GPS unit 1, the position data of the boundary lines BL on both the left and right sides captured by the camera 2 is calculated, and based on this position data. , Generates position data for the leftmost lane LN1 or the rightmost lane LN5. Further, by offsetting the position data of the lanes LN1 and LN5 in the left-right direction by the number of lanes acquired by the information acquisition unit 113, the position data of the other lanes LN2 to LN5 or L1 to LN4 is generated. As a result, lane data for all lanes LN1 to LN5 can be easily and satisfactorily generated.

(3) The position data of the plurality of lanes LN1 to LN5 generated by the data generation unit 114 as described above includes the plurality of lanes LN1 to located within a predetermined distance in the direction in which the plurality of lanes LNs extend from the vehicle 101. It is the first lane data which is the position data of LN5. The information acquisition unit 113 further acquires road shape information, and the data generation unit 114 generates the first lane data, and then the first lane data and the road shape information acquired by the information acquisition unit 113. Second lane data, which is position data of a plurality of lanes LN1 to LN5 located beyond a predetermined distance from the vehicle 101, is generated based on the above (FIG. 4). This makes it possible to accurately generate lane data for a plurality of lanes LN1 to LN5 at positions away from the vehicle 101. Further, lane data when there is a lane LN that exists within a predetermined distance from the vehicle 101 but cannot be recognized by the camera 2 can be satisfactorily generated by using the road shape data.

(4) The lane data generation device 100A of the modified example determines the position of the vehicle 101 based on the position data of the plurality of lane LNs generated by the data generation unit 114 and the distance data calculated by the distance calculation unit 112. A position calculation unit 115 for calculation is further provided (FIG. 6). The GPS unit 1 detects the positions of the vehicle 101 at the first time point and the second time point after the first time point, respectively, and the data generation unit 114 of the vehicle 101 calculated by the position calculation unit 115 at the first time point. When the deviation between the position P1 and the position P2 of the vehicle 101 detected by the GPS unit 1 at the second time point is equal to or greater than a predetermined value, based on the position data of the vehicle 101 detected by the GPS unit 1 at the second time point. , Regenerate the position data of a plurality of lane LNs (Fig. 7). By generating lane data based on the latest position data of the vehicle 101, when the shape of the lane LN around the vehicle changes as the vehicle 101 travels, it is updated to good lane data corresponding to the change. Can be done.

By using the lane data generated by the above lane data generation devices 100 and 100A, the lane LN in which the vehicle 101 is located can be specified. Hereinafter, the position specifying device according to the embodiment of the present invention will be described.

FIG. 8 is a block diagram showing a schematic configuration of the position specifying device 200 according to the present embodiment. The position identification device 200 is configured based on, for example, the lane data generation device 100 of FIG. That is, the position specifying device 200 is configured by adding the lane specifying unit 116 as a functional configuration to the calculation unit 11 of FIG. The lane identification unit 116 may be added to the calculation unit 11 of FIG.

FIG. 9 is a plan view of a road for explaining the processing of the lane identification unit 116. The solid line and broken line boundaries BL1 to BL6 in FIG. 9 are boundary lines previously generated by the lane data generation device 100 and stored in the storage unit 12. The lane identification unit 116 identifies the lane LN in which the vehicle 101 is located based on the position data of the plurality of lane LNs generated by the lane data generation device 100 and the position data of the vehicle 101 detected by the GPS unit 1. To do.

More specifically, the lane identification unit 116 is a boundary imaged by the camera 2 based on the position data of the vehicle 101 detected by the GPS unit 1 and the data of the distances D1 and D2 calculated by the distance calculation unit 112. Calculate the position of the line BL. For example, when the vehicle 101 is located in the third lane LN3 as shown in FIG. 9, the position of the boundary line BL on the right side of the vehicle 101 is calculated using the distance D2 from the vehicle 101. The calculated position of the boundary line BL is shown by a dotted line in FIG. Then, the deviations between the positions of the boundary lines BL and the positions of the plurality of boundary lines BL1 to BL6 stored in the storage unit 12 in advance are calculated, and the boundary line BL having the smallest deviation is extracted. In the example of FIG. 9, the boundary line BL4 is extracted from the plurality of boundary lines BL1 to BL6 as the boundary line having the smallest deviation. As a result, the third lane LN3 having the boundary line BL4 on the right side is specified as the lane LN in which the vehicle 101 is located.

In this way, in the position identification device 200, the lane identification unit 116 is imaged by the camera 2 based on the position data of the vehicle 101 detected by the GPS unit 1 and the distance data calculated by the distance calculation unit 112. The position of the boundary line BL is calculated, and the position data of the boundary line BL is compared with the position data of a plurality of lanes (boundary lines BL1 to BL6) generated by the lane data generation device 100, and based on the comparison result. The lane LN in which the vehicle 101 is located is specified. As a result, it is possible to always grasp the traveling lane in which the own vehicle 101 is located among the plurality of lane LNs.

The lane LN in which the vehicle 101 is located can also be grasped by counting the number of times the vehicle 101 crosses the boundary line BL, but for that purpose, it is necessary to accurately count this number of times. Therefore, in a situation where accurate counting is difficult, the position of the lane LN may be erroneously recognized. In this respect, in the present embodiment, since it is not necessary to count the number of times the vehicle crosses the boundary line BL, the lane LN in which the vehicle 101 is located can be accurately recognized.

In the above embodiment, an example in which the lane data generation devices 100 and 100A and the position identification device 200 are provided in the automatic driving vehicle 101 has been described, but these can also be provided in various vehicles other than the automatic driving vehicle. It is also possible to provide a lane data device and a position identification device on other moving bodies other than the above. In the above embodiment, the position of the vehicle 101 is detected by the GPS unit 1, but the configuration of the position detection unit that detects the position of the moving body is not limited to this. In the above embodiment, the left and right boundary lines BL are imaged by the camera 2 provided at the reference point P of the vehicle 101, but the configuration of the imaging unit is not limited to this.

The lane data generation devices 100 and 100A of the present embodiment can also be configured as a lane data generation method. In this case, the position detection step for detecting the position of the moving body (vehicle 101), the imaging step for imaging the boundary lines BL located on the left and right sides of the moving body, and the boundary line BL imaged in the imaging step are the ends. The distance from the moving body to the boundary lines BL on both the left and right sides based on the determination step of determining which of the partial boundary lines BL1 and BL6 and the intermediate boundary lines BL2 to BL5 and the image information of the captured boundary line BL. A calculation step for calculating D1 and D2, an acquisition step for acquiring information on the number of lanes on the road surface on which the moving body is located based on the position of the moving body detected in the position detection step, and a boundary between the left and right sides in the determination step. Acquisition of distance data calculated in the calculation step when it is determined that the line BL is the end boundary lines BL1 and BL6 and the intermediate boundary lines BL2 and BL5, and the position data of the moving body detected in the position detection step. The lane data generation method can be configured to include a data generation step for generating position data of a plurality of lanes LN1 to LN5 based on the information on the number of lanes acquired in the step (FIG. 5). ..

Further, the position identification device 200 of the present embodiment can be configured as a position identification method. In this case, the position detection step for detecting the position of the moving body (vehicle 101), the imaging step for imaging the boundary lines BL located on both the left and right sides of the moving body, and the boundary line BL imaged in the imaging step are ends. The distance from the moving body to the left and right boundary lines BL based on the determination step of determining which of the partial boundary lines BL1 and BL6 and the intermediate boundary lines BL2 and BL5 and the image information of the captured boundary line BL. It was detected in the calculation step for calculating D1 and D2, the acquisition step for acquiring information on the number of lanes on the road surface on which the moving body is located, and the position detection step based on the position of the moving body detected in the position detection step. Acquisition of position data of the moving body and distance data calculated in the calculation step when it is determined in the determination step that the left and right boundary lines BL are the end boundary lines BL1 and BL6 and the intermediate boundary lines BL2 and BL5. A data generation step that generates position data of a plurality of lanes LN1 to LN5 based on the information on the number of lanes acquired in the step, and position data of a plurality of lanes LN1 to LN5 generated in the data generation step. The position identification method can be configured to include the position data of the moving body detected in the position detection step and the lane identification step for specifying the lane LN in which the moving body is located.

The above description is merely an example, and the present invention is not limited to the above-described embodiments and modifications as long as the features of the present invention are not impaired. It is also possible to arbitrarily combine one or a plurality of the above-described embodiments and the modified examples, and it is also possible to combine the modified examples.

1 GPS unit, 2 cameras, 12 storage units, 100, 100A lane data generator, 101 vehicle, 111 boundary line determination unit, 112 distance calculation unit, 113 information acquisition unit, 114 data generation unit, 115 position calculation unit, 116 lanes Specific part, 200 position identification device, BL1, BL6 end boundary line, BL2 to BL5 intermediate boundary line

Claims (8)

It is a lane data generation device that generates lane data of a plurality of lanes partitioned by a plurality of boundary lines extending laterally apart from each other on the road surface.
The plurality of boundary lines are formed on the right side of the rightmost lane and on the left side of the leftmost lane, and inside the pair of left and right end boundary lines, with respect to the end boundary line. Includes intermediate boundaries formed approximately parallel
A position detector that detects the position of a moving object,
An imaging unit that images the boundary lines located on the left and right sides of the moving body, and
A boundary line determination unit that determines whether the boundary line imaged by the imaging unit is the end boundary line or the intermediate boundary line, and
A distance calculation unit that calculates the distance from the moving body to the boundary lines on both the left and right sides based on the image information of the boundary line captured by the imaging unit.
An information acquisition unit that acquires information on the number of lanes on the road surface on which the moving body is located based on the position of the moving body detected by the position detecting unit.
The distance data calculated by the distance calculation unit when the boundary line determination unit determines that the left and right boundary lines are the end boundary line and the intermediate boundary line, and the position detection unit detects the distance data. It is characterized by including a data generation unit that generates position data of the plurality of lanes based on the position data of the moving body and the information on the number of lanes acquired by the information acquisition unit. Lane data generator. In the lane data generator according to claim 1,
The data generation unit is the distance data and the position calculated by the distance calculation unit when the boundary line determination unit determines that the left and right boundary lines are the end boundary line and the intermediate boundary line. Based on the position data detected by the detection unit, the position data of the boundary lines on both the left and right sides captured by the imaging unit is calculated, and the position data of the leftmost or rightmost lane is generated based on this position data. Further, a lane data generation device characterized in that position data of another lane is generated by offsetting the position data of this lane in the left-right direction by the number of lanes acquired by the information acquisition unit. In the lane data generator according to claim 1 or 2.
A position calculation unit for calculating the position of the moving body based on the position data of the plurality of lanes generated by the data generation unit and the distance data calculated by the distance calculation unit is further provided.
The position detection unit detects the positions of the moving body at the first time point and the second time point after the first time point, respectively.
In the data generation unit, the deviation between the position of the moving body calculated by the position calculation unit at the first time point and the position of the moving body detected by the position detection unit at the second time point is a predetermined value. In the above case, the lane data generation device is characterized in that the position data of the plurality of lanes is regenerated based on the position data of the moving body detected by the position detection unit at the second time point. In the lane data generation device according to any one of claims 1 to 3.
The position data of the plurality of lanes generated by the data generation unit is first lane data which is position data of a plurality of lanes located within a predetermined distance in a direction in which the plurality of lanes extend from the moving body. And
The information acquisition unit further acquires road shape information and obtains information on the road shape.
After generating the first lane data, the data generation unit exceeds the predetermined distance from the moving body based on the first lane data and the road shape information acquired by the information acquisition unit. A lane data generation device characterized in that it generates second lane data which is position data of a plurality of lanes located in a row. The lane data generator according to any one of claims 1 to 4,
A lane identification unit that identifies the lane in which the moving body is located based on the position data of a plurality of lanes generated by the lane data generation device and the position data of the moving body detected by the position detecting unit. A positioning device characterized by being provided with. In the position identifying device according to claim 5,
The lane identification unit is based on the position data of the moving body detected by the position detection unit and the distance data calculated by the distance calculation unit, and the position of the boundary line imaged by the image pickup unit. Is calculated, and the position data of the boundary line is compared with the position data of a plurality of lanes generated by the lane data generation device, and the lane in which the moving body is located is specified based on the comparison result. Positioning device. It is a lane data generation method that generates lane data of a plurality of lanes partitioned by a plurality of boundary lines extending laterally apart from each other on the road surface.
The plurality of boundary lines are formed on the right side of the rightmost lane and on the left side of the leftmost lane, and inside the pair of left and right end boundary lines, with respect to the end boundary line. Includes intermediate boundaries formed approximately parallel
A position detection step that detects the position of a moving object, and
An imaging step for imaging the boundary lines located on the left and right sides of the moving body, and
A determination step for determining whether the boundary line imaged in the imaging step is the edge boundary line or the intermediate boundary line, and
A calculation step of calculating the distance from the moving body to the boundary lines on both the left and right sides based on the image information of the boundary line captured in the imaging step.
An acquisition step of acquiring information on the number of lanes on the road surface on which the moving body is located based on the position of the moving body detected in the position detection step, and
The distance data calculated in the calculation step when it is determined in the determination step that the boundary lines on both the left and right sides are the end boundary line and the intermediate boundary line, and the movement detected in the position detection step. A lane data generation method including a data generation step for generating position data of a plurality of lanes based on body position data and information on the number of lanes acquired in the acquisition step. .. It is a position identification method for identifying the lane in which the moving body is located by using the lane data of a plurality of lanes partitioned by a plurality of boundary lines extending horizontally apart from each other on the road surface.
The plurality of boundary lines include a pair of left and right end boundary lines formed on the right side of the rightmost lane and a left side of the leftmost lane, and an intermediate boundary line formed inside the pair of left and right end boundary lines. Including
A position detection step for detecting the position of the moving body and
An imaging step for imaging the boundary lines located on the left and right sides of the moving body, and
A determination step for determining whether the boundary line imaged in the imaging step is the edge boundary line or the intermediate boundary line, and
A calculation step of calculating the distance from the moving body to the boundary lines on both the left and right sides based on the image information of the boundary line captured in the imaging step.
An acquisition step of acquiring information on the number of lanes on the road surface on which the moving body is located based on the position of the moving body detected in the position detection step, and
Calculated in the position data of the moving body detected in the position detection step and in the calculation step when it is determined in the determination step that the boundary lines on both the left and right sides are the end boundary line and the intermediate boundary line. A data generation step that generates position data of the plurality of lanes based on the obtained distance data and the information on the number of lanes acquired in the acquisition step.
A lane identification step for identifying the lane in which the moving body is located based on the position data of the plurality of lanes generated in the data generation step and the position data of the moving body detected in the position detection step. And, a positioning method characterized by including.

Images