JP6828655B2 - Own vehicle position estimation device - Google Patents

Description

The present invention relates to a vehicle position estimation device.

Conventionally, Japanese Patent Application Laid-Open No. 2015-194397 is known as a technical document relating to a vehicle position estimation device. This publication is a vehicle position detection device that detects the predicted position of the vehicle at the current time from the map information and the captured image around the vehicle, and the position information of a plurality of map line segments (white lines, etc.) included in the map information. Based on the position of a plurality of line segments detected from the captured image around the vehicle and subjected to bird's-eye view conversion, the corresponding set of the map line segment and the captured line segment is obtained, and the corresponding map line segment is obtained. A device that updates (detects) the predicted position of the vehicle so that the line segment and the line segment match is described.

JP 2015-194397

By the way, in the estimation of the position of the own vehicle using the image, there is a risk that the lane marking of the road, which is the standard for estimating the position of the own vehicle, is erroneously matched (matched) with the curbstone captured by the camera or the horizontal line of the body of another vehicle in the adjacent lane. Exists. In this case, there is a problem because the position of the own vehicle cannot be estimated appropriately.

Therefore, in the present technical field, it is desired to provide an own vehicle position estimation device capable of appropriately estimating the own vehicle position.

In order to solve the above problems, one aspect of the present invention is a self-vehicle position estimation device that estimates the self-vehicle position on a vehicle map, and stores map information including position information of road lane markings. Based on the map database and the captured image of the camera that captures the surroundings of the vehicle, the lane marking recognition unit that recognizes the lane markings around the vehicle, and the objects around the vehicle based on the detection results of the vehicle radar sensor. The own vehicle position estimation unit that estimates the vehicle's own vehicle position based on the recognized object recognition unit, the division line recognized by the division line recognition unit, and the position information of the division line included in the map information, and the object and division. A distance determination unit for determining whether or not the distance to the line is equal to or greater than the distance threshold is provided, and the lane marking unit recognizes the distance between the object and the lane line when the captured image includes an image of the object. when it is determined that the distance threshold or more, by excluding image information corresponding to the object have line recognition of a lane mark around the vehicle, the distance between the object and the lane mark by the distance determining section is less than the distance threshold value When it is determined that there is, the lane marking around the vehicle is recognized without excluding the image information corresponding to the object .

According to the own vehicle position estimation device according to one aspect of the present invention, the own vehicle position can be appropriately estimated.

It is a block diagram which shows the own vehicle position estimation apparatus which concerns on one Embodiment. (A) It is a figure which shows the image taken by the in-vehicle camera. (B) It is a figure for demonstrating the road surface image. (A) It is a figure which shows the case where the wall is detected around the vehicle. (B) It is a figure for demonstrating the exclusion of the image information corresponding to a wall. (A) It is a figure which shows the case where the other vehicle of the adjacent lane is detected. (B) It is a figure for demonstrating the exclusion of the image information corresponding to another vehicle of the adjacent lane. (A) It is a figure which shows the captured image when the preceding vehicle is included. (B) It is a figure for demonstrating the exclusion of the image information corresponding to the preceding vehicle. It is a flowchart which shows the own vehicle position estimation process.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

The own vehicle position estimation device 100 according to the embodiment shown in FIG. 1 is a device mounted on a vehicle such as a passenger car and estimates the own vehicle position which is a position on the map of the vehicle. The own vehicle position estimation device 100 recognizes the lane markings (roads) in which the vehicle travels from the captured image of the surroundings of the vehicle captured by the in-vehicle camera, and uses the lane markings included in the map information. And estimate the position of the own vehicle. The lane markings include roadway lane boundaries, lane boundaries, center lines, and the like.

The own vehicle position estimation device 100 recognizes an object such as a wall or a curb around the vehicle from the detection result of the vehicle-mounted radar sensor, excludes the image information corresponding to the object, and recognizes the lane marking, thereby recognizing the wall. Reduces the possibility of mistakenly recognizing or curbs as lane markings. Objects include stationary objects such as walls, guardrails and buildings, as well as moving objects such as pedestrians, bicycles and other vehicles.

[Configuration of own vehicle position estimation device]
As shown in FIG. 1, the own vehicle position estimation device 100 includes an ECU [Electronic Control Unit] 10 that collectively manages the device. The ECU 10 is an electronic control unit having a CPU [Central Processing Unit], a ROM [Read Only Memory], a RAM [Random Access Memory], a CAN [Controller Area Network] communication circuit, and the like. In the ECU 10, for example, various functions are realized by loading the program stored in the ROM into the RAM and executing the program loaded in the RAM in the CPU. The ECU 10 may be composed of a plurality of electronic units.

The ECU 10 is connected to a GPS receiving unit 1, a camera 2, a radar sensor 3, an internal sensor 4, and a map database 5.

The GPS receiving unit 1 measures the position of the vehicle (for example, the latitude and longitude of the vehicle) by receiving signals from three or more GPS satellites. The GPS receiving unit 1 transmits the measured position information of the vehicle to the ECU 10.

The camera 2 is an imaging device that images the surroundings of the vehicle. As an example, the camera 2 is provided on the back side of the windshield of the vehicle and images the front of the vehicle. The camera 2 may be provided so as to image the rear of the vehicle as well as the front of the vehicle, or may be provided to image the side of the vehicle. The camera 2 transmits the captured image of the surroundings of the vehicle to the ECU 10. The camera 2 may be a monocular camera or a stereo camera.

The radar sensor 3 is a detection device that detects an object around a vehicle by using radio waves (for example, millimeter waves) or light. The radar sensor 3 includes, for example, a millimeter-wave radar or a lidar [LIDAR: Light Detection and Ranging]. The radar sensor transmits radio waves or light to the surroundings of the vehicle, and detects objects around the vehicle by receiving radio waves or light reflected by the object. The radar sensor 3 transmits the detection information of the object to the ECU 10.

The internal sensor 4 is a detection device that detects the traveling state of the vehicle. The internal sensor 4 includes a vehicle speed sensor, an acceleration sensor, and a yaw rate sensor. The vehicle speed sensor is a detector that detects the speed of the vehicle. As the vehicle speed sensor, for example, a wheel speed sensor provided on a wheel of a vehicle or a drive shaft that rotates integrally with the wheel or the like and detects the rotation speed of the wheel is used. The vehicle speed sensor transmits the detected vehicle speed information (wheel speed information) to the ECU 10.

An acceleration sensor is a detector that detects the acceleration of a vehicle. The acceleration sensor includes, for example, a front-rear acceleration sensor that detects the acceleration in the front-rear direction of the vehicle and a lateral acceleration sensor that detects the lateral acceleration of the vehicle. The acceleration sensor transmits, for example, vehicle acceleration information to the ECU 10. The yaw rate sensor is a detector that detects the yaw rate (rotational angular velocity) around the vertical axis of the center of gravity of the vehicle. As the yaw rate sensor, for example, a gyro sensor can be used. The yaw rate sensor transmits the detected yaw rate information of the vehicle to the ECU 10. The internal sensor 4 is not essential in the own vehicle position estimation device 100.

The map database 5 is a database that stores map information. The map database 5 is formed in, for example, an HDD [Hard Disk Drive] mounted on a vehicle. Map information includes road position information, road shape information (for example, curve, straight line type, curve curvature, etc.), lane marking position information, and position information of structures (stationary objects) such as walls and guardrails. Etc. are included. The map database 5 may be stored in a server capable of communicating with the vehicle.

Next, the functional configuration of the ECU 10 will be described. The ECU 10 has a measurement position acquisition unit 11, an object recognition unit 12, a distance determination unit 13, a lane marking recognition unit 14, and a vehicle position estimation unit 15. A part of the function of the ECU 10 may be executed in a server capable of communicating with the vehicle.

The measurement position acquisition unit 11 acquires the measurement position, which is the position on the map of the vehicle, based on the position information of the vehicle measured by the GPS reception unit 1. The measurement position acquisition unit 11 may acquire the measurement position of the vehicle from the vehicle speed history (or the wheel rotation speed history), the vehicle yaw rate history, and the like based on the detection result of the internal sensor 4. In other words, the measurement position acquisition unit 11 may acquire the measurement position of the vehicle by so-called odometry using a well-known method.

The object recognition unit 12 recognizes an object around the vehicle based on the detection result (object detection information) of the radar sensor 3. The object recognition unit 12 recognizes an object by grouping the detection points (reflection points) of the radar sensor 3 by a well-known method and collating it with an object model prepared in advance. Object models include vehicle (four-wheeled, two-wheeled) models, large vehicle models, pedestrian models, wall models, guardrail models, and the like.

The object recognition unit 12 recognizes the position of the object with respect to the vehicle based on the detection result of the radar sensor 3. Further, the object recognition unit 12 recognizes the surface (or point) of the object closest to the vehicle based on the detection result of the radar sensor 3.

The distance determination unit 13 determines whether or not the distance between the object and the lane marking is equal to or greater than the distance threshold value. The distance threshold is a preset value. The distance determination unit 13 is based on, for example, the detection result of the radar sensor 3, or the map information around the current vehicle position predicted by the detection result of the internal sensor 4 from the vehicle position one step or more before the present. , Recognize the position of the lane marking with respect to the vehicle. White line recognition using the detection result of the radar sensor 3 is a well-known method. The distance determination unit 13 determines whether or not the distance between the object and the division line is equal to or greater than the distance threshold, based on the position of the object recognized by the object recognition unit 12 and the position of the division line. The distance between the object and the lane marking is the shortest distance.

The lane marking unit 14 recognizes (image recognition) the lane marking around the vehicle based on the image captured by the camera 2. The lane marking unit 14 converts the captured image of the camera 2 into a road surface image by a well-known projection conversion, and recognizes the lane marking around the vehicle from the road surface image.

Here, FIG. 2A is a diagram showing an image G captured by an in-vehicle camera. FIG. 2A shows the wall W, the lane marking L1 on the left side of the vehicle, the lane marking L2 on the right side of the vehicle, and the lane marking L3 on the adjacent lane. The lane marking L1 and the lane marking L2 form a traveling lane of the vehicle, and the lane marking L2 and the lane marking L3 form an adjacent lane adjacent to the traveling lane.

Further, FIG. 2B is a diagram for explaining a road surface image. FIG. 2B shows a vehicle (own vehicle) M and an image region A corresponding to the captured image of FIG. 2A among the road surface images. The image area A is an image area obtained by projecting and converting the captured image G of FIG. 2 (a). The road surface image is extended by superimposing the image area A on the road surface image generated immediately before according to the vehicle speed of the vehicle M (performing image matching). Here, the lane marking L3 is omitted for the sake of simplicity.

In image collation, for example, global alignment is performed by a phase-limited correlation method, and then line segments including lane markings and the like are collated by least squares matching to perform local alignment with high accuracy. In addition, in order to perform image matching with high accuracy, not only the immediately preceding road surface image but also the past road surface image may be used together. The conversion (generation) of the road surface image is not limited to the above-mentioned method, and a well-known method can be adopted.

The lane marking unit 14 recognizes the position of the lane marking based on the road surface image. The lane marking unit 14 recognizes the position of the lane marking with respect to the vehicle M by recognizing the lane marking from the road surface image by a well-known image recognition process such as pattern matching. The lane marking unit 14 may recognize the position of the lane marking by using not only the road surface image but also the position of the lane marking recognized by the distance determination unit 13 from the detection result of the radar sensor 3.

Further, when the image captured by the camera 2 includes an object, the lane marking recognition unit 14 displays the image information corresponding to the object in the recognition of the lane marking because the image information corresponding to the object becomes noise for recognizing the lane marking. Is excluded (masked).

First, the lane marking recognition unit 14 determines whether or not an object is included in the captured image based on the captured image of the camera 2. The lane marking unit 14 determines whether or not an object is included in the captured image by a well-known image recognition process such as pattern matching. The lane marking unit 14 may make the above determination by using the object recognition result by the object recognition unit 12.

When the lane marking unit 14 determines that an object is included in the captured image and the distance determination unit 13 determines that the distance between the object and the lane marking is equal to or greater than the distance threshold, the lane marking unit 14 corresponds to the object. The lane marking around the vehicle M is recognized by excluding the image information. As a result, the lane marking recognition unit 14 excludes image information of walls and other vehicles that cause noise in lane marking in advance, so that the pattern of the walls and walls, the horizontal lines and irregularities of the body of the other vehicle, etc. Can be avoided from being erroneously recognized as a lane marking, and unnecessary operations in recognizing the lane marking can be reduced.

On the other hand, when the lane marking unit 14 determines that the captured image contains an object and the distance determination unit 13 determines that the distance between the object and the lane marking is less than the distance threshold, the object The lane markings around the vehicle M are recognized without excluding the image information corresponding to. When the distance between the object and the division line is too close, the division line recognition unit 14 may exclude a part of the image information corresponding to the division line if the image information corresponding to the object is excluded from the captured image. Therefore, the lane marking is recognized without excluding the image information corresponding to the object.

Specifically, FIG. 3A is a diagram showing a case where a wall is detected around the vehicle. FIG. 3A shows the detection range B of the radar sensor 3 of the vehicle M, the wall portion Wa of the wall W detected by the radar sensor 3, and the distance Dw between the wall portion Wa and the lane marking L1.

In the situation shown in FIG. 3, the division line recognition unit 14 determines that the image captured by the camera 2 includes the wall W (object) because the image area A includes a part of the wall W. .. The distance determination unit 13 recognizes the distance Dw between the wall portion Wa and the lane marking L1 (that is, the distance Dw between the wall W and the lane marking L1 closest to the wall W) based on the detection result of the radar sensor 3.

When the distance determination unit 13 determines that the distance Dw between the wall portion Wa and the division line L1 is equal to or greater than the distance threshold value, the division line recognition unit 14 excludes the image information corresponding to the wall W from the road surface image. Recognize lane markings. FIG. 3B is a diagram for explaining the exclusion of the image information corresponding to the wall W. In FIG. 3B, the outer image region Ex1 including the wall W is shown as an exclusion target. The outer image area Ex1 is image information corresponding to the wall W in the road surface image. The lane marking unit 14 excludes the outer image area Ex1 as the image information corresponding to the wall W.

As shown in FIG. 3B, since it is considered that the lane marking unit 14 does not show the lane marking to be recognized in the region outside the object when viewed from the vehicle M in the road surface image, the vehicle Let M be the outer image area Ex1 that excludes all the areas outside the wall W (object) from the processing target of the recognition of the division line. The outer image region Ex1 is not limited as long as it is a region including the wall W.

Next, FIG. 4A is a diagram showing a case where another vehicle in an adjacent lane is detected. FIG. 4A shows the distance Dn between the other vehicle N1 and the other vehicle N1 traveling in the adjacent lane and the lane marking L2. The other vehicle N1 is included in the captured image of the camera 2 and is detected by the radar sensor 3.

In the situation shown in FIG. 4A, since the lane marking recognition unit 14 includes a part of the other vehicle N1 in the image area A, the image captured by the camera 2 includes the other vehicle N1 (object). Judge that The distance determination unit 13 recognizes the distance Dn between the other vehicle N1 and the lane marking L2 based on the detection result of the radar sensor 3.

When the distance determination unit 13 determines that the distance Dn between the other vehicle N1 and the lane marking L1 is equal to or greater than the distance threshold value, the lane marking unit 14 excludes the image information corresponding to the other vehicle N1 from the road surface image. , Recognize lane markings. FIG. 4B is a diagram for explaining exclusion of image information corresponding to the other vehicle N1. In FIG. 4B, the outer image region Ex2 including the other vehicle N1 is shown as an exclusion target. The outer image area Ex2 is image information corresponding to another vehicle N1 in the road surface image. The outer image region Ex2 includes the entire region outside the other vehicle N1 in the vehicle width direction of the vehicle M with reference to the vehicle M. The lane marking unit 14 excludes the outer image area Ex2 as the image information corresponding to the other vehicle N1. The outer image region Ex2 is not limited as long as it is a region including another vehicle N1.

The lane marking unit 14 may exclude the image information corresponding to the object from the image captured by the camera 2 before converting it into a road surface image. FIG. 5A is a diagram showing a captured image G when a preceding vehicle is included. FIG. 5A shows the preceding vehicle N2.

FIG. 5B is a diagram for explaining exclusion of image information corresponding to the preceding vehicle N2. As shown in FIG. 5B, the lane marking recognition unit 14 excludes (masks) the image region Ex3 corresponding to the preceding vehicle N2 in the captured image G of the camera 2. The lane marking unit 14 excludes the image area Ex3 as the image information corresponding to the preceding vehicle N2.

The lane marking unit 14 converts the captured image G excluding the image region Ex3 corresponding to the preceding vehicle N2 into a road surface image and recognizes the lane marking, thereby using the unevenness and pattern of the body of the preceding vehicle as noise. It is possible to avoid generating a road surface image including the road surface image and reduce unnecessary calculations in recognizing the lane markings.

The own vehicle position estimation unit 15 of the vehicle M is based on the measurement position of the vehicle M acquired by the measurement position acquisition unit 11, the recognition result of the lane marking by the lane marking unit 14, and the map information of the map database 5. Estimate the position of the own vehicle, which is the position on the map. Specifically, the own vehicle position estimation unit 15 extracts a lane marking to be collated in the map information based on the measurement position of the vehicle M acquired by the measurement position acquisition unit 11 (area to be collated on the map). Narrow down). The own vehicle position estimation unit 15 determines the own vehicle position of the vehicle M based on the position of the lane marking with respect to the vehicle M recognized by the lane marking unit 14 and the position information on the map of the lane marking extracted from the map information. presume.

The method of estimating the position of the own vehicle using the lane marking is not limited to the above-mentioned method, and a well-known method can be adopted. The own vehicle position estimation unit 15 may extract a lane marking to be collated in the map information by using the own vehicle position estimated immediately before, and may use the lane marking extracted immediately before to extract the current self from the map information. The lane marking used for vehicle position estimation may be extracted.

[Own vehicle position estimation process of own vehicle position estimation device]
Hereinafter, the own vehicle position estimation process of the own vehicle position estimation device 100 will be described with reference to FIG. FIG. 6 is a flowchart showing the own vehicle position estimation process. The flowchart shown in FIG. 6 is executed, for example, while the vehicle M is traveling. It is assumed that the measurement position acquisition unit 11 acquires the measurement position of the vehicle M at any time.

As shown in FIG. 6, the ECU 10 of the own vehicle position estimation device 100 acquires the captured image of the camera 2 and the detection result of the radar sensor 3 as S10.

In S12, the ECU 10 recognizes an object around the vehicle M by the object recognition unit 12. The object recognition unit 12 recognizes an object by grouping the detection points (reflection points) of the radar sensor 3 by a well-known method and collating it with an object model prepared in advance. The object recognition unit 12 recognizes the position of the object with respect to the vehicle M based on the detection result of the radar sensor 3.

In S14, the ECU 10 determines whether or not an object is included in the captured image of the camera 2 by the lane marking recognition unit 14. The lane marking unit 14 determines whether or not an object is included in the captured image by performing a well-known image recognition process on the captured image of the camera 2. When it is not determined that the captured image of the camera 2 contains an object (S12: NO), the ECU 10 shifts to S16. On the other hand, when it is determined that the captured image of the camera 2 contains an object (S12: YES), the ECU 10 shifts to S20.

In S16, the ECU 10 projects and converts the captured image of the camera 2 into a road surface image by the lane marking recognition unit 14. The lane marking unit 14 projects and transforms the captured image to generate a road surface image by the phase-limited correlation method or the least squares matching of the line segments in the image.

In S18, the ECU 10 recognizes the lane markings around the vehicle M from the road surface image by the lane marking recognition unit 14. The lane marking unit 14 recognizes the position of the lane marking with respect to the vehicle M by recognizing the lane marking from the road surface image by pattern matching or other well-known method. After that, the ECU 10 shifts to S26.

In S20, the ECU 10 projects and converts the captured image of the camera 2 into a road surface image by the lane marking recognition unit 14. The processing content is the same as in S16.

In S22, the ECU 10 determines whether or not the distance between the object and the lane marking is equal to or greater than the distance threshold value by the distance determination unit 13. The distance determination unit 13 makes the above determination by recognizing, for example, the position of the object and the position of the lane marking with respect to the vehicle M based on the detection result of the radar sensor 3. When it is determined that the distance between the object and the lane marking is less than the distance threshold value (S22: NO), the ECU 10 does not exclude the image information corresponding to the object, so the process proceeds to S18 described above. On the other hand, when it is determined that the distance between the object and the lane marking is equal to or greater than the distance threshold value (S22: YES), the ECU 10 shifts to S24.

In S24, the ECU 10 recognizes the lane markings around the vehicle M by excluding the image information corresponding to the object by the lane marking recognition unit 14. The lane marking unit 14 excludes the image information corresponding to the object from the road surface image, and recognizes the lane marking for the remaining area. The lane marking unit 14 recognizes the position of the lane marking with respect to the vehicle M.

In S26, the ECU 10 estimates the position of the own vehicle by the own vehicle position estimation unit 15. The own vehicle position estimation unit 15 of the vehicle M is based on the measurement position of the vehicle M acquired by the measurement position acquisition unit 11, the recognition result of the lane marking by the lane marking unit 14, and the map information of the map database 5. Estimate the position of the own vehicle, which is the position on the map. The own vehicle position estimation unit 15 is based on the position of the lane marking with respect to the vehicle M recognized by the lane marking unit 14 and the position information on the map of the lane marking extracted from the map information using the measurement position. Estimate the position of your vehicle.

[Effect of own vehicle position estimation device]
According to the own vehicle position estimation device 100 according to the above-described embodiment, when an object such as a wall or another vehicle is included in the captured image, the image information corresponding to the object is excluded to recognize the lane marking. Therefore, it is possible to avoid erroneously recognizing the horizontal line of the body of another vehicle as a lane marking line, and to appropriately estimate the position of the own vehicle.

Although the preferred embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment. The present invention can be carried out in various forms having various modifications and improvements based on the knowledge of those skilled in the art, including the above-described embodiment.

When the camera 2 is a stereo camera, the distance determination unit 13 recognizes the position of the object with respect to the vehicle and the position of the lane marking with respect to the vehicle based on the image pickup information (including the distance information in the depth direction) of the camera 2. May be good. The distance determination unit 13 may recognize the distance between the object and the division line based on the map information. In the situation shown in FIG. 3A, when the object recognition unit 12 recognizes that the object is the wall W, the distance determination unit 13 has the position information of the wall W on the map included in the map information and the position information on the map. The distance between the object and the lane marking can be determined based on the position information of the lane marking L1. The object in this case needs to be a stationary object such as a wall, a guardrail, or a utility pole whose map information includes position information.

The own vehicle position estimation device 100 does not necessarily have to include the distance determination unit 13. In this case, when the image captured by the camera 2 includes an object, the lane marking unit 14 recognizes the lane marking by excluding the image information corresponding to the object regardless of the distance between the object and the lane marking.

The lane marking unit 14 corresponds to the exclusion of the image information corresponding to the wall W described in FIGS. 3A and 3B, and the other vehicle N1 described in FIGS. 4A and 4B. It is not necessary to exclude all of the image information to be used and the image information corresponding to the preceding vehicle N2 described in FIGS. 5 (a) and 5 (b). The lane marking unit 14 may be in a mode of excluding any one of the image information.

The lane marking unit 14 may predict the range in which the lane marking exists in the current (current) image information based on the recognition result of the lane marking in the past. In this case, the lane marking unit 14 can recognize the lane marking around the vehicle by excluding the image information other than the range in which the lane marking is predicted to exist from the image information. This aspect is useful when the position of the lane marking in the traveling lane of the vehicle is less volatile, such as when the vehicle is traveling in a straight section that continues for a certain distance or more from the position of the vehicle.

For example, when the lane marking unit 14 recognizes the lane marking at the time one step before, the lane marking information obtained from the object recognition unit 12, and the position information of the lane marking included in the map information match, the lane marking unit 14 starts from the above time. It is possible to exclude other than the image information corresponding to the position of the lane marking at the current vehicle position predicted based on the vehicle movement information based on the detection result of the internal sensor 4 up to the current time.

1 ... GPS receiver, 2 ... camera, 3 ... radar sensor, 4 ... internal sensor, 5 ... map database, 10 ... ECU, 11 ... measurement position acquisition unit, 12 ... object recognition unit, 13 ... distance determination unit, 14 ... Section line recognition unit, 15 ... own vehicle position estimation unit, 100 ... own vehicle position estimation device.

Claims (1)

It is a vehicle position estimation device that estimates the vehicle position on the map of the vehicle.
A map database that stores map information including the location information of road lane markings,
A lane marking recognition unit that recognizes a lane marking around the vehicle based on an image captured by a camera that captures the surroundings of the vehicle.
An object recognition unit that recognizes objects around the vehicle based on the detection results of the vehicle radar sensor,
The own vehicle position estimation unit that estimates the own vehicle position of the vehicle based on the division line recognized by the division line recognition unit and the position information of the division line included in the map information.
A distance determination unit that determines whether or not the distance between the object and the division line is equal to or greater than the distance threshold value.
With
The division line recognition unit, in the case where the image of the object is included in the captured image, when the distance between the object and the lane mark by the distance determination unit is determined to be equal to or greater than the distance threshold value, the object wherein the object when a distance between the partition lines and the object is determined to be smaller than the distance threshold by a row have, the distance determining section recognizes demarcation line around the vehicle by excluding the image information corresponding to the A vehicle position estimation device that recognizes a lane marking around the vehicle without excluding the image information corresponding to the above .

Images