JP2022067908A - Traveling lane determination device and traveling lane determination program - Google Patents

Abstract

To accurately determine a traveling lane for each travel on the basis of collected traveling data for each travel.SOLUTION: A driving data collection unit 20 collects traveling data. A target detection unit 26 generates a road surface image from a vehicle peripheral image and detects a target from the vehicle peripheral image or the road surface image for each of the traveling data within a target area, and generates traveling image data. A relative lane determination unit 32 calculates a relative location correction amount for each of the traveling image data pairs by mapping targets to each other and determines a relationship between traveling lanes for each of the traveling image data pairs on the basis of the relative location correction amount. A group determination unit 38 then generates a group consisting of traveling image data for the same traveling lane. A lane configuring determination unit 40 determines a lane relationship between the groups.SELECTED DRAWING: Figure 1

Description

The present invention relates to a traveling lane determination device and a traveling lane determination program.

When a moving body such as a vehicle travels on a road structured by a lane marking or the like, identifying the lane in which the moving body is traveling is useful information in a navigation system or the like.

In addition, a map that estimates the position of the vehicle on an existing map using the vehicle position, travel trajectory, and observation results around the vehicle (target detection results such as white lines) acquired using a positioning satellite or the like. A matching technique is known (Patent Document 1).

Further, there is known a technique of estimating the traveling lane of the own vehicle by collating the image acquired by another vehicle or the like placed around the position where the own vehicle is running with the image taken by the own vehicle (patented). Document 2). In this technique, the image used for collation needs to be an image capable of determining the lane configuration from a bird's-eye view of the entire track.

Japanese Unexamined Patent Publication No. 2015-68665 Japanese Unexamined Patent Publication No. 2018-189436

The map matching technique described in Patent Document 1 needs to already have a track map, and cannot be used for applications such as generating a new map.

Further, the technique described in Patent Document 2 does not require map information, but it is necessary to use a collation image that can determine the lane configuration, and information equivalent to the map information is required.

The present invention has been made in view of the above circumstances, and provides a traveling lane determination device and a traveling lane determination program capable of accurately determining the traveling lane of each traveling from the collected traveling data of each traveling. With the goal.

In order to achieve the above object, the traveling lane determination device of the present invention includes a traveling data collecting unit that collects traveling data that is a combination of the vehicle position and orientation and the vehicle peripheral image obtained in time series when the vehicle is traveling. For each of the traveling data in the lane determination target area, a road surface image is generated from the vehicle peripheral image, a target is detected from the vehicle peripheral image or the road surface image, and the road surface image and the detection result of the target are obtained. For each of the traveling image data generation unit that generates the traveling image data including the traveling image data and the pair of the traveling image data, the relative position correction amount is calculated by associating the targets with each other, and the relative position correction amount is calculated based on the relative position correction amount. For the pair, a group consisting of the traveling image data is generated for the same traveling lane based on the determination result by the traveling lane relationship determination unit for determining the relationship between the traveling lanes and the traveling lane relationship determination unit, and between the groups. It is configured to include a group determination unit for determining the lane relationship of the above.

The traveling lane determination program according to the present invention is a driving data collecting unit and a lane determination target area for collecting driving data obtained by combining a computer with a vehicle position / orientation and a vehicle peripheral image obtained in time series when the vehicle is traveling. For each of the traveling data in the vehicle, a road surface image is generated from the vehicle peripheral image, a target is detected from the vehicle peripheral image or the road surface image, and the traveling image data including the road surface image and the detection result of the target is obtained. For each of the traveling image data generation unit and the pair of traveling image data to be generated, the relative position correction amount is calculated by associating the targets with each other, and based on the relative position correction amount, the pair is of the traveling lane. Based on the determination result by the traveling lane relationship determination unit for determining the relationship and the determination result by the traveling lane relationship determination unit, a group consisting of the traveling image data is generated for the same traveling lane, and the lane relationship between the groups is determined. This is a program for functioning as a group judgment unit.

According to the present invention, the traveling data collecting unit collects traveling data which is a combination of the position and posture of the vehicle and the vehicle peripheral image obtained in time series when the vehicle is traveling. The traveling image data generation unit generates a road surface image from the vehicle peripheral image for each of the traveling data in the lane determination target area, detects a target from the vehicle peripheral image or the road surface image, and detects the road surface image and the said. Generates running image data including the detection result of the target. The traveling lane relationship determination unit calculates a relative position correction amount for each of the traveling image data pairs by associating the targets with each other, and based on the relative position correction amount, the relationship between the traveling lanes and the pair. To judge. Then, the group determination unit generates a group consisting of the traveling image data for the same traveling lane based on the determination result by the traveling lane relationship determination unit, and determines the lane relationship between the groups.

In this way, for each pair of traveling image data, the relative position correction amount is calculated by associating the targets with each other, and based on the relative position correction amount, the relationship between the traveling lanes is determined for the pair. Based on the determination result, a group consisting of the traveling image data is generated for the same traveling lane, and the driving lane of each traveling is determined from the collected traveling data by determining the lane relationship between the groups. It can be judged accurately.

The storage medium for storing the program of the present invention is not particularly limited, and may be a hard disk or a ROM. Further, it may be a CD-ROM, a DVD disc, a magneto-optical disc, or an IC card. Furthermore, the program may be downloaded from a server or the like connected to a network.

As described above, according to the traveling lane determination device and the traveling lane determination program of the present invention, it is possible to obtain the effect that the traveling lane of each traveling can be accurately determined from the collected traveling data of each traveling. ..

It is a block diagram which shows the traveling lane determination apparatus which concerns on embodiment of this invention. It is a block diagram which shows the vehicle-mounted device which concerns on embodiment of this invention. It is a figure for demonstrating the target area. It is a figure for demonstrating the method of generating a road surface image. It is a figure which shows the example of the result of detecting a target from a road surface image. It is a figure for demonstrating the method of generating a traveling image data pair. It is a figure which shows the example of the traveling image data pair. It is a figure which shows the example of the correspondence of the target of the traveling image data pair. It is a figure which shows the example of the result of having performed the alignment with the traveling image data pair. It is a figure which shows the example of the traveling image data pair which determines the same lane. It is a figure which shows the example of the traveling image data pair which determines the adjacent lane. It is a figure which shows the example of the determination result about all combinations of running image data. It is a figure which shows the example of the traveling image data pair which determines the same lane. It is a figure which shows the example of the traveling image data pair which determines the adjacent lane. It is a figure which shows the example of the traveling image data pair which is determined to change a lane. It is a figure which shows the example of the lane group table. It is a figure which shows the example of the lane composition table. (A) is an image diagram showing an example of a determination result including an erroneous determination, and (B) is a diagram showing an example of a lane configuration result. It is a flowchart which shows the content of the traveling lane determination processing routine in the computer of the traveling lane determination apparatus which concerns on embodiment of this invention. Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

<System configuration>
As shown in FIG. 1, the traveling lane determination device 10 according to the embodiment of the present invention is based on the communication unit 12 for receiving the traveling data generated by the vehicle-mounted device described later and the received traveling data. It is equipped with a computer 14 that determines a traveling lane for each traveling and outputs the data to the output unit 16.

The communication unit 12 receives the travel data generated by the on-board unit of each vehicle. The travel data is generated by the on-board unit 50 shown in FIG.

The in-vehicle device 50 includes a GPS receiving unit 52 that receives radio waves from GPS satellites, a gyro sensor 53, an image pickup device 54 that images the front of the own vehicle, and a signal received from the GPS satellites received by the GPS receiving unit 52. , A computer 60 that generates driving data including a time series of positioning results and a time series of captured images based on the output of the gyro sensor 53 and the forward image captured by the imaging device 54, and a traveling lane determination device based on the driving data. It is provided with a communication unit 70 for transmitting to 10.

The GPS receiving unit 52 receives radio waves from a plurality of GPS satellites, and from the received signals from all the received GPS satellites, the GPS satellite number and the GPS satellite orbit information (Ephemeris) are used as GPS satellite information. , The time when the GPS satellite transmitted the radio wave, the strength of the received signal, the frequency, etc. are acquired and output to the computer 60.

The image pickup apparatus 54 repeatedly captures the front image and outputs it to the computer 60. For example, the image pickup range is around the lane in which the own vehicle is traveling.

When the computer 60 is represented by a functional block, as shown in FIG. 2, the GPS satellite information is acquired from the GPS receiving unit 52 for all the GPS satellites that have received the radio waves, and the GPS satellite information and the gyro sensor 53 are used. From the output, the positioning information acquisition unit 62 that acquires time-series values such as the position, orientation, and vehicle speed of the own vehicle at each time, and the front image captured at each time by the image pickup device 54 are acquired, and the acquired front image is obtained. , The image acquisition unit 64 that generates a plane image projected onto a plane so as to be a bird's-eye view, and the time-series values such as the position, orientation, and vehicle speed of the own vehicle at each time, and the running data including the plane image at each time are generated. It is provided with a traveling data generation unit 66.

The computer 14 shown in FIG. 1 is composed of a CPU, a ROM that stores a program for realizing a driving lane determination processing routine described later, a RAM that temporarily stores data, and a storage device such as an HDD. ..

When the computer 14 is represented by a functional block according to the driving lane determination processing routine described below, as shown in FIG. 1, a traveling data collecting unit 20, a traveling data storage unit 22, an area setting unit 24, and a target detection unit 26, travel data pair production unit 28, relative position correction unit 30, relative lane determination unit 32, positional relationship determination result correction unit 34, consistency determination result correction unit 36, group determination unit 38, and lane. It is provided with a configuration identification unit 40. The target detection unit 26 is an example of a traveling image data generation unit, the relative lane determination unit 32 is an example of a traveling lane relationship determination unit, and the group determination unit 38 and the lane configuration identification unit 40 are group determinations. This is an example of the department.

The travel data collection unit 20 collects travel data received from the vehicle-mounted device 50 of each vehicle and stores it in the travel data storage unit 22.

The travel data storage unit 22 stores a plurality of collected travel data.

The area setting unit 24 sets a target area, which is a small area for determining a traveling lane. For example, a small grid-shaped area of 100 m square is set as the target area (see FIG. 3).

The target detection unit 26 generates a road surface image for the travel data passing through the set target area among all the aggregated travel data, and at the same time detects the target (section line or the like). Specifically, the vehicle travel locus when the travel data is collected acquires the travel data passing through the target area from the travel data storage unit 22, and for each acquired travel data, the plane of each time of the travel data. A road surface image is generated by pasting the images along the vehicle traveling locus (see FIG. 4). The vehicle travel locus may be obtained from the vehicle position and direction at each time of the travel data, or may be obtained by connecting a predetermined imaging position to the plane image at each time.

The target detection unit 26 detects a target (for example, a lane marking, a sign, a signboard, a signal) from a vehicle peripheral image or a generated road surface image (see FIG. 5), and includes the generated road surface image and a target group. A unique driving ID is given to the driving image data. When passing through the target area a plurality of times, individual travel IDs are assigned to each.

The travel data pair generation unit 28 generates a one-to-one travel image data pair of travel image data having a unique travel ID generated for the set target area (see FIG. 6).

The relative position correction unit 30 calculates the relative position correction amount by associating the targets with each other for each of the traveling image data pairs, and using the relative position correction amount, the road surface of each traveling image data of the traveling image data pair. Overlay images. Specifically, the relative position correction unit 30 associates the target group of the travel image data A with the target group of the travel image data B with respect to the travel image data A and B constituting the travel image data pair. .. For example, as shown in FIG. 7, the end points of the lane markings are obtained from the traveling image data A and B, and as shown in FIG. 8, the endpoints of the lane markings are associated between the traveling image data A and B. Then, the coordinate conversion information that minimizes the positional deviation of the associated target group is calculated as the relative position correction amount. As the misalignment, for example, the average of the squares of the distances of the end points of the lane markings can be used as an index. Using the calculated relative position correction amount, for example, the alignment of the traveling image data A and the traveling image data B is performed (see FIG. 9).

The relative lane determination unit 32 determines the relative relationship between the traveling lanes based on the result of positioning each of the traveling image data pairs.

Specifically, the relative relationship between the traveling lanes is determined based on the traveling direction, the overlap ratio of the road surface images, the distance of the traveling locus, and the like with respect to the aligned traveling image data pair. It is determined whether the relative relationship between the traveling lanes is the same lane, an adjacent lane, or an oncoming lane. For example, as shown in FIG. 10, when the traveling directions are the same and the overlap ratio is equal to or more than the threshold value, it is determined that they are in the same lane. Further, as shown in FIG. 11, when the traveling directions are the same and the overlap ratio is larger than 0 and less than the threshold value, it is determined to be an adjacent lane. Further, when the traveling directions are opposite and the overlap ratio is larger than 0 and less than the threshold value, it is determined to be an oncoming lane. In other cases, it is determined that none of the above applies.

Then, the determination result of the relative relationship of the traveling lane for each of the traveling image data pairs is stored in the relative relationship determination table (FIG. 12). In the example of FIG. 12, each row is a determination result for one traveling image data and has values such as "same lane", "adjacent lane", and "oncoming lane". In the case of adjacent lanes, there is a distinction between the case where the judgment target is the left lane and the case where the judgment target is the left lane with respect to the own lane. If the relative lane cannot be determined, it will be blank. That is, the value "0" is stored for the traveling image data pair determined to be in the same lane, and the value "-" is stored for the traveling image data pair determined to be the oncoming lane. Further, for the traveling image data pair determined to be in the adjacent lane, if the other traveling image data is the adjacent driving lane on the right side with respect to one traveling image data, the value "1" is stored and one traveling image data is stored. On the other hand, if the other traveling image data is the adjacent lane on the left side, the value "2" is stored.

For each of the traveling image data pairs, the positional relationship determination result correction unit 34 describes the traveling image data pair according to the positional relationship between the traveling locus and the target of each traveling image data for which the alignment of the traveling image data pair is performed. Correct the judgment result of.

Specifically, as shown in FIGS. 13 to 15, relative lane determination is performed based on the positional relationship between each vehicle traveling locus of the aligned traveling image data pair and the lane marking detected as a target. In FIGS. 13 and 14, a lane marking is searched in a direction orthogonal to the traveling direction of each vehicle traveling locus at each time, and if the traveling locus A and the traveling locus B exist on the same side with respect to a certain lane marking, the same lane is obtained. An example is shown in which the vehicle is corrected so that it is determined to be in the adjacent lane if it is on another side. FIG. 15 shows an example in which it is determined that there is a lane change if the same lane determination result and the determination result of the adjacent lane are mixed in the target area. The determination result may be invalidated instead of modifying the determination result.

The consistency determination result correction unit 36 corrects the determination result of the relative relationship of the traveling lanes in consideration of the consistency of the determination results for each of the traveling image data pairs.

The determination result by the relative lane determination unit 32 and the positional relationship determination result correction unit 34 may include an erroneous determination. For example, the traveling image data C is determined to be in the same lane with respect to the traveling image data A and B determined to be in the adjacent lane. By considering the consistency of the determination results of the relative lanes, erroneous determination is eliminated.

As a specific procedure, the following procedures 1 to 3 can be considered.

(Procedure 1) Initialize the lane group table shown in FIG. 16 and assume that there is no registration. In the lane group table, the ID of the driving image data determined to be the same lane is registered in the "same lane determination ID" for each group, and the driving image data determined to be the same lane is determined to be the adjacent lane on the right side. The ID of the driven image data is registered in the "right adjacent lane determination ID", and the ID of the driving image data determined to be the left adjacent lane with respect to the traveling image data determined to be the same lane is the "left adjacent lane". Register in "Judgment ID". In addition, a lane group table is prepared for each traveling direction.

(Procedure 2) For each traveling image data, the number of traveling image data determined to be in the same lane is calculated, the traveling image data is selected in descending order, and the procedure 3 described later is repeated. Here, the ID of the selected traveling image data is set to "I".

(Procedure 3) From the lane group table, the group whose ID "I" is registered in the "same lane determination ID" is searched.

(Procedure 3a) If the search result group does not exist, a new lane group is generated, the ID "I" is registered in the "same lane determination ID", and the right side with respect to the traveling image data of the ID "I". The ID of the driving image data determined to be the "adjacent lane" is registered in the "right adjacent lane determination ID" of the new lane group, and the "adjacent lane" on the left side of the driving image data of the ID "I" is displayed. The ID of the determined driving image data is registered in the "left adjacent lane determination ID" of the new lane group.

(Procedure 3b) There is only one group of search results, and the ID of the driving image data determined to be the "adjacent lane" on the right side of the driving image data of ID "I" is used as the "right adjacent lane" of the group. Registered in the "determination ID", the ID of the traveling image data determined to be the "adjacent lane" on the left side of the traveling image data of the ID "I" is registered in the "left adjacent lane determination ID" of the group.

(Procedure 3c) Other than the above, registration to the lane group table is not performed. That is, if there are two or more groups of search results, there is a possibility of erroneous determination, so registration in the lane group table is not performed.

The group determination unit 38 generates a lane group consisting of travel image data for the same traveling lane based on the determination result after the correction by the consistency determination result correction unit 36.

Specifically, the traveling image data determined to be in the same traveling lane are grouped as a lane group.

The lane configuration identification unit 40 determines the relative lane relationship between the lane groups. A pair of lane groups that are determined to be adjacent lanes are searched for between lane groups, a relative lane determination is performed between the lane groups, and a lane configuration is determined using the relative lane determination results between a plurality of lane groups.

Specifically, as shown in FIG. 17, between the lane groups, the same lane determination ID of one lane group and the right adjacent lane determination ID or the left adjacent lane determination ID of the other lane group are used for each traveling direction. To determine the relative lane relationship between lane groups.

In the example of FIG. 17, a plurality of lanes are collated between the same lane determination ID of one lane group and the right adjacent lane determination ID or the left adjacent lane determination ID of the other lane group. An example is shown in which lane IDs are assigned in the order in which the lanes are arranged in the lane group in which the lanes are arranged, and the driving ID of the traveling image data determined to be the same traveling lane as the relevant lane is registered in the lane configuration table.

The lane configuration identification unit 40 outputs the lane configuration determination result by the output unit 16. As shown in FIG. 18A, even if the determination result of the relative lane with respect to the traveling image data pair includes an erroneous determination, the erroneous determination is removed as shown in FIG. 18B. Above, the determination result of the relative lane relationship between the lane groups can be output as a lane configuration.

Next, the operation of this embodiment will be described.

First, in the on-board unit 50 of each vehicle, traveling data including a time series of positioning results and a time series of captured images is generated. When a large number of traveling data generated by the vehicle-mounted device 50 of each vehicle is transmitted to the traveling lane determination device 10, a large number of traveling data are stored in the traveling data storage unit 22.

Further, the traveling lane determination device 10 executes the traveling lane determination processing routine shown in FIG. 19 based on a large number of traveling data stored in the traveling data storage unit 22. The traveling lane determination processing routine is repeatedly executed for each target area, which is a small area for determining the traveling lane.

In step S100, the area setting unit 24 sets the target area.

In step S102, the target detection unit 26 acquires travel data that passes through the set target area among all the travel data stored in the travel data storage unit 22.

In step S104, the target detection unit 26 generates a road surface image for each of the travel data acquired in step S102, and at the same time detects the target, and travel image data including the generated road surface image and the target group. Is generated and a driving ID is given.

In step S106, the travel data pair generation unit 28 generates a one-to-one travel image data pair of travel image data generated for the set target area.

In step S108, the relative position correction unit 30 calculates the relative position correction amount by associating the targets with each other for each of the traveling image data pairs, and using the relative position correction amount, each traveling of the traveling image data pair. Overlay the road surface image of the image data.

In step S110, the relative lane determination unit 32 determines the relative relationship between the traveling lanes based on the result of positioning each of the traveling image data pairs.

In step S112, the positional relationship determination result correction unit 34 determines the travel of each of the travel image data pairs according to the positional relationship between the travel locus and the target of each travel image data for which the alignment of the travel image data pair is performed. Correct the judgment result for the image data pair.

In step S114, the consistency determination result correction unit 36 corrects the determination result of the relative relationship of the traveling lanes in consideration of the consistency of the determination results for each of the traveling image data pairs.

In step S116, the group determination unit 38 generates a lane group consisting of travel image data for the same traveling lane based on the determination result after the correction by the consistency determination result correction unit 36.

In step S118, the lane configuration identification unit 40 determines the relative lane relationship between the lane groups. The lane configuration identification unit 40 outputs the lane configuration determination result by the output unit 16.

As described above, according to the traveling lane determination device according to the embodiment of the present invention, for each of the traveling image data pairs, the relative position correction amount is calculated by associating the targets with each other, and the relative position correction amount is used as the relative position correction amount. Based on this, the relative relationship of the traveling lanes is determined for the traveling image data pair, and based on the determination result, a group consisting of traveling image data for the same traveling lane is generated, and the lane relationship between the groups is determined. Therefore, it is possible to accurately determine the traveling lane of each traveling from the collected traveling data of each traveling.

Further, by considering the consistency of the relative relationship of the traveling lanes based on the alignment of the one-to-one traveling image data pair of the collected traveling image data, it is possible to determine the traveling lane and the lane configuration with few errors. Further, even if the traveling data group cannot have a bird's-eye view of the entire lane only around the own lane and has an error in the absolute position, the traveling lane and the lane configuration of each traveling can be determined.

The present invention is not limited to the above-described embodiment, and various modifications and applications are possible without departing from the gist of the present invention.

For example, the positional relationship determination result correction unit 34 may be omitted and only the correction by the consistency determination result correction unit 36 may be omitted, or the consistency determination result correction unit 36 may be omitted and the correction by the positional relationship determination result correction unit 34. May be only. Further, the positional relationship determination result correction unit 34 and the consistency determination result correction unit 36 may be omitted to generate a lane group and determine the lane configuration without correcting the determination result.

10 Driving lane determination device 12 Communication unit 14 Computer 16 Output unit 20 Driving data collection unit 22 Driving data storage unit 24 Area setting unit 26 Target detection unit 28 Driving data pair production unit 30 Relative position correction unit 32 Relative lane determination unit 34 Position Relationship judgment result correction unit 36 Consistency judgment result correction unit 38 Group judgment unit 40 Lane configuration identification unit 50 On-board unit 52 GPS receiver 53 Gyro sensor 54 Imaging device 60 Computer

Claims (5)

A driving data collection unit that collects driving data that is a combination of the vehicle's position and orientation and the vehicle's peripheral image, which is obtained in chronological order when the vehicle is running.
For each of the traveling data in the lane determination target area, a road surface image is generated from the vehicle peripheral image, a target is detected from the vehicle peripheral image or the road surface image, and the road surface image and the detection result of the target are included. A driving image data generator that generates driving image data,
For each of the pairs of traveling image data, the relative position correction amount is calculated by associating the targets with each other, and based on the relative position correction amount, the traveling lane relationship determination for determining the relationship between the traveling lanes is determined. Department and
Based on the determination result by the traveling lane relationship determination unit, a group consisting of the traveling image data for the same traveling lane is generated, and a group determination unit for determining the lane relationship between the groups, and a group determination unit.
Driving lane determination device including. In consideration of the consistency of the determination result for each of the pairs by the traveling lane relationship determination unit, the consistency determination result correction unit for correcting the determination result for each of the pairs is further included.
The traveling lane determination device according to claim 1, wherein the group determination unit generates the group based on the determination result corrected by the consistency determination result correction unit, and determines the lane relationship between the groups. For each of the pairs, a positional relationship determination result correction unit that corrects the determination result for the pair according to the positional relationship between the vehicle travel locus and the target when the travel data is collected is further included.
The traveling lane determination device according to claim 1, wherein the group determination unit generates the group based on the determination result corrected by the positional relationship determination result correction unit, and determines the lane relationship between the groups. For each of the pairs, a positional relationship determination result correction unit that corrects the determination result for the pair according to the positional relationship between the travel locus when the travel data is collected and the target.
In consideration of the consistency of the determination result after the correction by the positional relationship determination result correction unit for each of the pairs, the consistency determination result correction unit for correcting the determination result for each of the pairs is further included.
The traveling lane determination device according to claim 1, wherein the group determination unit generates the group based on the determination result corrected by the consistency determination result correction unit, and determines the lane relationship between the groups. Computer,
A driving data collection unit that collects driving data that is a combination of the vehicle's position and posture and the vehicle's peripheral image, which is obtained in chronological order when the vehicle is running.
For each of the traveling data in the lane determination target area, a road surface image is generated from the vehicle peripheral image, a target is detected from the vehicle peripheral image or the road surface image, and the road surface image and the detection result of the target are included. Driving image data generation unit that generates driving image data,
For each of the pairs of traveling image data, the relative position correction amount is calculated by associating the targets with each other, and based on the relative position correction amount, the traveling lane relationship determination for determining the relationship between the traveling lanes is determined. To generate a group consisting of the traveling image data for the same traveling lane based on the determination result by the unit and the traveling lane relationship determination unit, and to function as a group determination unit for determining the lane relationship between the groups. Driving lane judgment program.

Images