JP2022143591A - Road shape recognition device - Google Patents

Abstract

To provide a technique that can recognize a road shape.SOLUTION: A road shape recognition device 110, which is mounted on a vehicle 10 having a camera 122, comprises: a peripheral information recognition part 111; a point sequence setting part 112 which sets a point sequence that represents a shape of a road on which the vehicle travels on the basis of peripheral information; a first reliability setting part 113 which sets a first reliability of each point included in the point sequence; a road model calculation part 114 which calculates a new road model which represents the shape of the road, on which the vehicle travels, with a line on the basis of the point sequence, the first reliability and a road model which has been calculated in the past; a second reliability setting part which sets a second reliability of the road model; and an output part 117 which outputs the road model. The road model calculation part calculates on the basis of a point sequence which has been set in the past when the first reliability is lower the second reliability in the road model which has been calculated in the past, and calculates the model on the basis of the point sequence when the first reliability is higher than the second reliability in the road model which has been calculated in the past.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to a road shape recognition device.

2. Description of the Related Art A known road shape recognition device recognizes a road shape by calculating a road model representing the road shape with lines from edge points of road division lines recognized by a camera. Patent Literature 1 describes a technique for calculating a road model based on the previously recognized road model.

Japanese Patent No. 5559650

However, the road model calculated in the past does not necessarily conform to the actual road shape. If the road recognition model calculated in the past is incorrect, the road model cannot be calculated properly, and there is a possibility that the road shape cannot be recognized. Therefore, a technology capable of recognizing the shape of the road has been desired.

The present disclosure has been made to solve the above problems, and can be implemented as the following modes.

According to a first aspect of the present disclosure, there is provided a road shape recognition device (110) mounted on a vehicle (10) having a camera (122). The road shape recognition device is a surrounding information recognition unit (111) for recognizing surrounding information, and based on a surrounding image which is an image of the surroundings of the vehicle captured by the camera, each of one or more lane markings of the road is detected. A peripheral information recognition unit (111) capable of recognizing image information having a shape of . A point sequence setting unit (112) for setting a point sequence representing the shape of a road, and a first reliability setting unit (112) for setting a first reliability of each point included in the point sequence set by the point sequence setting unit ( 113), and a road model calculation unit (114) for calculating a road model representing a shape of the road on which the vehicle is traveling, wherein the point sequence set by the point sequence setting unit; A road model calculation unit that calculates a new road model based on the first reliability set by the reliability setting unit and the road model that the road model has calculated in the past, and the road model calculation unit a second reliability setting unit (115) for setting the second reliability of the road model within the range of the same size as the range of the magnitude of the first reliability set to the calculated points; an output unit (117) for outputting the model. The first reliability setting unit sets a first reliability of points included in a point sequence in a section in which the peripheral information includes a shape of a lane marking on either one of the left and right sides of the vehicle. is set lower than the first reliability of the points included in the point sequence of the section including the shapes of both the left and right lane markings. The second reliability setting unit sets the second reliability such that the second reliability of the road model increases as the first reliability of the point sequence in the section corresponding to the road model increases. do. The road model calculation unit determines a road model candidate based on the point sequence, and in a section of the road in front of the vehicle, the previously calculated road model and the road model candidate In a section separated by a threshold distance or more, if the first reliability of points included in the point sequence is lower than the second reliability of the road model calculated in the past, based on the previously set point sequence, the A road model is calculated, and if the first reliability of points included in the point sequence is higher than the second reliability of a previously calculated road model, the road model is calculated based on the point sequence.

According to a second aspect of the present disclosure, there is provided a road shape recognition device mounted on a vehicle having a peripheral object sensor capable of measuring the distance between a camera and an object. The road shape recognition device obtains peripheral information including image information representing the shape of each of one or more lane markings on the road, based on a peripheral image, which is an image of the periphery of the vehicle captured by the camera, and the peripheral object sensor. a peripheral information recognition unit capable of recognizing peripheral information including sensor information, which is one or more of the shape of a roadside object and the movement trajectory of another vehicle, based on the output of the peripheral information recognition unit; a sequence of points setting unit for setting a sequence of points representing the shape of the road on which the vehicle is traveling based on the peripheral information; A first reliability level setting unit that sets a reliability level; and a road model calculation unit that calculates a road model that represents the shape of the road on which the vehicle is traveling by lines, the points set by the point sequence setting unit. a road model calculation unit that calculates a new road model based on the column, the first reliability set by the first reliability setting unit, and the road model previously calculated by the road model; Second reliability setting for setting the second reliability of the road model with a numerical value within the same magnitude range as the magnitude range of the first reliability set for the points calculated by the road model calculation unit. and an output unit that outputs the road model. The first reliability setting unit converts the reliability of the points included in the point sequence of the section recognized based on the image information, which is the shape of only one of the left and right marking lines of the vehicle, to the sensor information. Set the reliability to be lower than the reliability of the points included in the point sequence of the section recognized based on the The second reliability level setting unit sets a reliability level in a section where the reliability level of the point sequence is low to be lower than a reliability level in a section where the reliability level of the point sequence is high. The road model calculation unit determines a road model candidate based on the point sequence, and in a section of the road in front of the vehicle, the previously calculated road model and the road model candidate When the reliability of points included in the point sequence is lower than the reliability of the road model calculated in the past in a section separated by a threshold distance or more, the road model is calculated based on the point sequence set in the past. If the reliability of the points included in the point sequence is higher than the reliability of the previously calculated road model, the road model is calculated based on the point sequence.

According to the road shape recognition device of these forms, the road model calculation unit, in the section where the road model calculated in the past and the road model candidate are separated by a threshold distance or more in the width direction of the road, according to the reliability, Either the point sequence set in the past or the point sequence set this time is determined as the reference point sequence for calculation of the road model. That is, in a section where the road model calculated in the past and the road model candidate diverge, the road model calculation unit calculates the road model based on the highly reliable point sequence. Therefore, the road shape can be recognized according to the actual road shape.

BRIEF DESCRIPTION OF THE DRAWINGS It is a schematic diagram which shows the structure of an automatic operation control system. It is a flow chart showing road shape recognition processing. It is a figure which shows an example of peripheral information, a point sequence, and a road model candidate. It is a figure which shows an example of the road model calculated in the past. It is explanatory drawing which shows an example of calculation of a road model. It is explanatory drawing which shows an example of a road model. It is a schematic diagram which shows the structure of the automatic operation control system in 2nd Embodiment. It is a figure which shows an example of sensor information.

A. First embodiment:
As shown in FIG. 1 , the vehicle 10 has an automatic driving control system 100 . In this embodiment, the automatic driving control system 100 executes automatic driving of the vehicle 10 . In this embodiment, the automatic driving control system 100 includes a road shape recognition device 110, a camera 122, a driving control unit 210, a driving force control ECU (Electronic Control Unit) 220, a braking force control ECU 230, and a steering control ECU 240. And prepare. Road shape recognition device 110 , driving control unit 210 , driving force control ECU 220 , braking force control ECU 230 and steering control ECU 240 are connected via in-vehicle network 250 . The vehicle 10 may be driven not only by automatic driving but also by manual driving performed manually by the driver.

The camera 122 acquires an image by imaging the surroundings of the own vehicle 10 .

The road shape recognition device 110 includes a surrounding information recognition unit 111, a first reliability setting unit 113, a point sequence setting unit 112, a road model calculation unit 114, a second reliability setting unit 115, and a storage unit 116. , and an output unit 117 . The road shape recognition device 110 is composed of a central processing unit (CPU), a microcomputer configured with a RAM and a ROM, etc. The microcomputer executes pre-installed programs to realize the functions of these units. . However, some or all of the functions of these units may be realized by hardware circuits.

The peripheral information recognition unit 111 can recognize image information as at least part of the peripheral information based on the peripheral image that is the image captured by the camera 122 . "Image information" is the shape of each of one or more lane markings on the road. "Peripheral information" is information about the periphery of the vehicle 10, including image information and sensor information described in the second embodiment. In the present embodiment, the peripheral information recognition unit 111 recognizes the presence of left and right division lines on the road on which the vehicle is traveling, their positions, and the like from the image captured by the camera 122 . Note that the surrounding information recognition unit 111 recognizes the shape of the lane marking and the like from these pieces of information using, for example, the Kalman filter or the method of least squares.

The sequence of points setting unit 112 sets a sequence of points representing the shape of the road on which the vehicle 10 is traveling, based on the peripheral information recognized by the peripheral information recognition unit 111 . In this embodiment, the sequence of points setting unit estimates the coordinate position of the sequence of points based on the shape of the road marking recognized by the peripheral information recognition unit 111 .

The first reliability setting unit 113 sets a first reliability for each point included in the point sequence set by the point sequence setting unit. "First reliability" indicates the degree of certainty of the shape of the road indicated by each point. The higher the first reliability, the higher the possibility that the shape can be trusted. The first reliability setting unit 113 can set the first reliability according to the peripheral information used for setting the sequence of points. In this embodiment, the first reliability setting unit 113 sets the first reliability of the points included in the point sequence in the section in which the peripheral information includes only one of the left and right lane markings of the vehicle. It is set lower than the first reliability of points included in the point sequence of the section including the shapes of both the left and right lane markings of the vehicle.

The road model calculation unit 114 calculates a road model that represents the shape of the road on which the vehicle is running by lines. The road model calculation unit 114 calculates a road model based on the point sequence set by the point sequence setting unit, the first reliability set by the first reliability setting unit, and the road model calculated in the past by the road model. Calculate Details of calculation of the road model will be described later.

The second reliability level setting unit 115 sets the second reliability level of the road model with a numerical value within the same range as the first reliability level range set by the first reliability level setting unit. "Second reliability" indicates the degree of certainty of the shape of the road indicated by the road model. The higher the second reliability, the higher the possibility that the shape can be trusted. The second reliability level setting unit 115 sets the second reliability level such that the second reliability level of the road model increases as the first reliability level of the point sequence in the section corresponding to the road model increases.

The storage unit 116 stores the set point sequence, the calculated road model, and the second reliability of the road model.

The output unit 117 outputs the road model calculated by the road model calculation unit 114 to the driving control unit 210 and the like through the in-vehicle network 250 .

The operation control unit 210 is composed of a central processing unit (CPU), a microcomputer composed of a RAM and a ROM, and the like, and realizes an automatic operation function by having the microcomputer execute pre-installed programs. The driving control unit 210 controls the driving force control ECU 220, the braking force control ECU 230, and the steering control ECU 240 using, for example, the point sequence representing the road shape set by the point sequence setting unit 112.

The driving force control ECU 220 is an electronic control unit that controls actuators such as the engine that generate the driving force of the vehicle. When the driver manually drives the vehicle, the driving force control ECU 220 controls the power source such as the engine or the electric motor according to the amount of operation of the accelerator pedal. On the other hand, when performing automatic operation, the driving force control ECU 220 controls the power source according to the required driving force calculated by the operation control section 210 .

The braking force control ECU 230 is an electronic control unit that controls the brake actuator that generates the braking force of the vehicle. When the driver manually drives the vehicle, the braking force control ECU 230 controls the brake actuator according to the amount of operation of the brake pedal. On the other hand, when performing automatic operation, the braking force control ECU 230 controls the brake actuators according to the required braking force calculated by the operation control section 210 .

The steering control ECU 240 is an electronic control unit that controls a motor that generates steering torque for the vehicle. When the driver manually drives the vehicle, the steering control ECU 240 controls the motor according to the operation of the steering wheel to generate an assist torque for the steering operation. As a result, the driver can operate the steering wheel with a small amount of force, thereby achieving steering of the vehicle. On the other hand, when performing automatic driving, the steering control ECU 240 performs steering by controlling the motor according to the required steering angle calculated by the driving control section 210 .

The road shape recognition process shown in FIG. 2 is a series of processes in which the road model calculation unit 114 recognizes the road shape of the route on which the vehicle 10 is traveling. This process is a process repeatedly executed by the road shape recognition device 110 while the vehicle 10 is running, for example, a process repeatedly executed every 100 ms.

In step S100, the peripheral information recognition unit 111 recognizes peripheral information. In this embodiment, the peripheral information recognition unit 111 recognizes image information as at least part of the peripheral information based on the peripheral image that is the image captured by the camera 122 .

In step S110, the sequence of points setting unit 112 sets a sequence of points representing the shape of the road based on the peripheral information recognized in step S100.

In step S120, the first reliability setting unit 113 sets the first reliability of each point included in the point sequence set in step S110 based on the peripheral information recognized in step S100.

In step S130, the road model calculation unit 114 determines road model candidates based on the point sequence set in step S110. A “road model candidate” is a line candidate representing a road shape.

In step S140, the road model calculator 114 calculates a road model. In this embodiment, the road model calculation unit 114 determines that the road model calculated in the past and the road model candidate determined in step S130 in the section of the road ahead of the vehicle are separated by a threshold distance or more in the width direction of the road. In the section, a new road model is calculated according to the relationship between the first reliability of the points included in the point sequence set in step S120 in the section and the second reliability of the previously calculated road model in the section. . If the first reliability of the points included in the point sequence is lower than the second reliability of the previously calculated road model, the road model calculation unit 114 creates a new road model based on the previously set point sequence. Calculate On the other hand, if the first reliability of the points included in the point sequence is higher than the second reliability of the previously calculated road model, the road model calculation unit 114 calculates a new point based on the point sequence set in step S110. Calculate the road model.

In step S150, the second reliability setting unit 115 sets the second reliability to the road model calculated in step S140. Note that this process may be performed before step S140. In this case, the road model calculation unit 114 sets the second reliability of the new road model calculated in step S140 in the previous road shape recognition process.

As shown in FIG. 3, the peripheral information recognized in step S100 (see FIG. 2) in the road shape recognition process includes the shape of the right lane marking LnR and the left lane marking LnL of the lane Ln1 in which the vehicle 10 is traveling. Shape. The shape of the partition line LnR is indicated by a point sequence of points Pr1 to Pr7. The shape of the partition line LnL is indicated by a point sequence of points Pl1 to Pl4. The peripheral information recognition unit 111 converts the captured image into a bird's-eye view and recognizes image information. Therefore, the image information recognized by the surrounding information recognition unit 111 tends to deviate from the actual shape of the lane marking as the distance from the vehicle 10 increases due to road gradients and pitching of the vehicle 10 .

In FIG. 3, the points P1 to P7 included in the point sequence set by the point sequence setting unit 112 based on the peripheral information in step S110 (see FIG. 2) are represented by crosses. For example, for a section in which the peripheral information includes the shapes of the left and right lane markings of the lane Ln1, the sequence of points setting unit 112 indicates a sequence of points Pr1 to Pr4 indicating the shape of the lane marking LnR and the shape of the lane LnL. A point sequence is set at the center in the width direction of the lane Ln1 of the points at positions corresponding to the points Pl1 to Pl4. Also, for a section in which the peripheral information includes the shape of the lane marking on either the left or right side of the lane Ln1, a point sequence is set based on the points Pr5 to Pr7 indicating the shape of the lane LnR. Therefore, as shown in FIG. 3, the sequence of points set by the sequence of points setting unit 112 is curved toward the demarcation line LnR.

In FIG. 3, the road model candidate MC1 determined by the road model calculation unit 114 in step S130 (see FIG. 2) is indicated by a dashed line. The road model calculation unit determines road model candidates based on the point sequence. Therefore, the road model candidate MC1 curves toward the lane marking LnR.

The peripheral information recognized in step S100 (see FIG. 2) in the previous road shape recognition process shown in FIG. is. As shown in FIG. 4, the shape of the demarcation line LnR is indicated by a point sequence of points Pr1 to Pr7. The shape of the partition line LnL is indicated by a point sequence of points Pl1 to Pl7.

In FIG. 4, points P01 to P07 included in the point sequence set by the point sequence setting unit 112 based on the surrounding information in step S110 (see FIG. 2) in the previous road shape recognition process are indicated by Δ marks. In FIG. 4, the road model M0 calculated by the road model calculation unit 114 in step S140 (see FIG. 2) in the previous road shape recognition process is represented by a dashed line.

As shown in FIG. 5, among the sections of the road in front of the vehicle, the road model in the section S2 where the distance d between the previously calculated road model M0 and the road model candidate MC1 is greater than or equal to the threshold distance in the width direction of the road. Calculation of is explained. A point included in the point sequence in the section S2 is a point included in the point sequence in the section in which the surrounding information includes the shape of the marking line on either the left or right side of the vehicle. The road model calculated in the past in section S2 is calculated based on points P05 to P07 (see FIG. 4) included in the point sequence of the section in which the peripheral information includes the shape of both the left and right lane markings of the vehicle. Therefore, the first reliability of the points P05 to P07 included in the point sequence is lower than the second reliability of the previously calculated road model M0. Therefore, the road model calculation unit 114 calculates a road model based on the point sequence set in the past in the section S2.

Of the sections of the road ahead of the vehicle, the road model calculation unit 114 calculates the current road in the section S1 in which the previously calculated road model M0 and the road model candidate MC1 are not separated by a threshold distance or more in the width direction of the road. A road model is calculated based on the point sequence set in step S110 of the recognition process. That is, in step S140 (see FIG. 2), the road model calculation unit adopts the road model candidate MC1 determined in step S130 as the road model.

As indicated by the solid line in FIG. 6, the road model calculator 114 calculates the road model M1.

According to the road shape recognition device 110 of the present embodiment described above, the road model calculation unit 114 calculates a section in which the previously calculated road model M0 and the road model candidate MC1 are separated by a threshold distance or more in the width direction of the road. In S2, either the previously set point sequence or the currently set point sequence is determined as the reference point sequence for calculating the road model M1 according to the degree of reliability. For example, when the road model M0 calculated in the past is calculated based on the shape of both the left and right lane markings, and the road model candidate MC1 determined this time is determined based on the shape of the left and right lane markings only, the road The model calculation unit 114 calculates the road model M1 based on the point sequence set in the past in the section S2. Further, when the road model M0 calculated in the past is calculated based on the shape of the lane markings on only one of the left and right sides, and the road model candidate MC1 determined this time is determined based on the shape of the lane markings on both the left and right sides, the road The model calculation unit 114 calculates the road model M1 based on the point sequence set this time in the section S2. That is, in the section S2 where the previously calculated road model M0 and the road model candidate MC1 diverge, the road model calculation unit 114 calculates the road model M1 based on the highly reliable point sequence. Therefore, the road shape can be recognized according to the actual road shape.

B. Second embodiment:
The configuration of an automatic driving control system 100B of the second embodiment shown in FIG. 7 is different from that of the first embodiment in that a peripheral object sensor 124 is provided, and other configurations are the same.

The peripheral object sensor 124 measures the distance to objects around the vehicle 10 . Examples of the peripheral object sensor 124 include object sensors using reflected waves, such as laser radar, millimeter wave radar, Lidar (Light Detection and Ranging), and ultrasonic sensors.

In the present embodiment, the peripheral information recognition unit 111 recognizes sensor information, which is one or more of the shape of a roadside object and the movement trajectory of another vehicle, based on the output of the peripheral object sensor 124 . recognize as part of

The peripheral information shown in FIG. 8 is sensor information indicating the locus of movement of another vehicle 20 traveling in front of the vehicle 10 . In FIG. 8, the road model M2 is represented by a one-dot chain line.

In this embodiment, the first reliability level setting unit 113 sets the first reliability level of the points included in the point sequence of the section recognized based on the image information that is the shape of the lane marking on either the left or right side of the vehicle. is set lower than the first reliability of the sequence of points in the section recognized based on the sensor information.

For example, road model calculation will be described using a case where the road model calculated in the past is the road model M2 (see FIG. 8) and the road model candidate determined this time is the road model candidate MC1 (see FIG. 5). The road model M2 (see FIG. 8) calculated in the past is calculated based on the shape of the roadside object detected by Lidar and the movement trajectory of the other vehicle. If determined based on the shape of the lane marking, the road model calculation unit 114 calculates the road model M2 based on the point sequence set in the past in the section.

Calculation of the road model will be described by taking as an example a case where the road model calculated in the past is the road model candidate MC1 (see FIG. 5) and the road model candidate determined this time is the road model M2 (see FIG. 8). A road model candidate MC1 (see FIG. 5), which is a road model calculated in the past, is calculated based on the shape of lane markings on only one of the left and right sides. , the road model calculation unit 114 calculates the road model M2 based on the point sequence set this time in the section.

According to the first reliability setting unit 113 of the present embodiment described above, the first reliability setting unit 113 recognizes based on the image information that is the shape of the marking line on either the left or right side of the vehicle 10. The first reliability of the points included in the point sequence of the detected section is set lower than the first reliability of the point sequence of the section recognized based on the sensor information. A road model calculated based on the shape of a roadside object detected by Lidar and the movement trajectory of another vehicle 20 is more suitable than a road model calculated based on a point sequence set based on the shape of lane markings on only one of the left and right sides. is more in line with the actual road shape. Therefore, according to this embodiment, the road shape can be recognized in accordance with the actual road shape.

C. Other embodiments:
(C1) In the above-described embodiment, the road model calculation unit 114 performs the current road recognition process in the section S1 in which the previously calculated road model M0 and the road model candidate MC1 are not separated by a threshold distance or more in the width direction of the road. The road model M1 is calculated based on the point sequence set in . Not limited to this, the road model calculation unit 114 may calculate the road model M1 based on the point sequence newly set by the point sequence setting unit 112 in the current road shape recognition process and the point sequence set in the past. good. The road model calculation unit 114 calculates the road model M1 based on the newly set point sequence and the previously set point sequence. is weighted according to the time when the sequence of points is set by the sequence of points setting unit 112, and the road model M1 can be calculated. For example, the road model calculation unit 114 can perform weighting so that the value closer to the current time at which the point sequence is set is heavier. As a result, the road model can be calculated based on the newly set point sequence rather than the previously set point sequence.

(C2) In the second embodiment, the first reliability setting unit 113 sets the first reliability of points included in the point sequence of the section S2 recognized based on the image information representing the shape of the lane markings on both the left and right sides of the vehicle 10. The reliability may be set higher than the first reliability of the point sequence of the section S2 recognized based on the sensor information.

The present disclosure is not limited to the embodiments described above, and can be implemented in various configurations without departing from the scope of the present disclosure. For example, the technical features in the embodiments corresponding to the technical features in each form described in the outline of the invention are In addition, it is possible to perform replacement and combination as appropriate. Moreover, if the technical feature is not described as essential in this specification, it can be deleted as appropriate.

DESCRIPTION OF SYMBOLS 10... Vehicle 20... Other vehicle 100, 100B... Automatic driving control system 110... Road shape recognition apparatus 111... Surrounding information recognition part 112... Point sequence setting part 113... First reliability setting part 114... Road model calculation unit 115 Second reliability setting unit 116 Storage unit 117 Output unit 122 Camera 124 Peripheral object sensor 210 Operation control unit 220 Driving force control ECU 230 Control Power control ECU 240 Steering control ECU 250 In-vehicle network

Claims (4)

A road shape recognition device (110) mounted on a vehicle (10) having a camera (122),
A peripheral information recognizing unit (111) for recognizing peripheral information, wherein image information is the shape of each of one or more lane markings of a road based on a peripheral image, which is an image of the periphery of the vehicle captured by the camera. a peripheral information recognition unit (111) capable of recognizing as at least part of the peripheral information;
a point sequence setting unit (112) for setting a point sequence representing the shape of the road on which the vehicle is traveling, based on the peripheral information recognized by the peripheral information recognition unit;
a first reliability setting unit (113) for setting a first reliability of each point included in the point sequence set by the point sequence setting unit;
A road model calculation unit (114) for calculating a road model representing the shape of the road on which the vehicle is traveling by lines, wherein the sequence of points set by the sequence of points setting unit and the first reliability setting unit a road model calculation unit that calculates a new road model based on the first reliability set by and the road model calculated by the road model in the past;
A second reliability setting unit ( 115) and
An output unit (117) that outputs the road model,
The first reliability setting unit sets a first reliability of points included in a point sequence in a section in which the peripheral information includes a shape of a lane marking on either one of the left and right sides of the vehicle. set lower than the first reliability of the points included in the point sequence of the section containing the shapes of both the left and right lane markings,
The second reliability setting unit sets the second reliability such that the second reliability of the road model increases as the first reliability of the point sequence in the section corresponding to the road model increases. death,
The road model calculation unit
determine road model candidates based on the sequence of points;
In a section of the road in front of the vehicle, in which the previously calculated road model and the road model candidate are separated by a threshold distance or more in the width direction of the road,
calculating the road model based on the point sequence set in the past when the first reliability of the points included in the point sequence is lower than the second reliability of the previously calculated road model;
A road shape recognition apparatus for calculating the road model based on the point sequence when the first reliability of points included in the point sequence is higher than the second reliability of a road model calculated in the past. The road shape recognition device according to claim 1,
the vehicle has a peripheral object sensor (124) capable of measuring distances to objects in the vicinity of the vehicle;
The peripheral information recognition unit recognizes sensor information, which is one or more of a shape of a roadside object and a movement trajectory of another vehicle, as a part of the peripheral information based on an output of the peripheral object sensor. can
The first reliability setting unit determines the reliability of the points included in the point sequence of the section recognized based on the image information, which is the shape of only one of the left and right marking lines of the vehicle, based on the sensor information. A road shape recognition device that is set lower than the reliability of the point sequence of the section recognized based on. The road shape recognition device according to claim 1 or claim 2,
The road model calculation unit calculates the point sequence newly set by the point sequence setting unit in a section in which the previously calculated road model and the road model candidate are not separated by the threshold distance or more in the width direction of the road. Calculate the road model based on the point sequence set in
The calculation of the road model based on the newly set point sequence and the previously set point sequence is performed by the point sequence setting unit using the point sequence newly set by the point sequence setting unit and the point sequence set in the past. is weighted according to the time when the point sequence is set. A road shape recognition device mounted on a vehicle having a peripheral object sensor capable of measuring the distance between a camera and an object,
Based on a peripheral image, which is an image captured by the camera around the vehicle, peripheral information including image information representing the shape of each of one or more lane markings on the road, and based on the output of the peripheral object sensor, a peripheral information recognition unit capable of recognizing peripheral information including sensor information that is one or more of the shape of a roadside object and the movement trajectory of another vehicle;
a point sequence setting unit that sets a point sequence representing a shape of a road on which the vehicle is traveling based on the peripheral information recognized by the peripheral information recognition unit;
a first reliability setting unit for setting a first reliability of each point included in the point sequence set by the point sequence setting unit;
A road model calculation unit for calculating a road model representing a shape of a road on which the vehicle is traveling, wherein the sequence of points set by the sequence of points setting unit and the sequence of points set by the first reliability setting unit a road model calculation unit that calculates a new road model based on the first reliability and a road model previously calculated by the road model;
Second reliability setting for setting the second reliability of the road model with a numerical value within the same size range as the first reliability magnitude range set for the points set by the point sequence setting unit. Department and
an output unit that outputs the road model,
The first reliability setting unit converts the reliability of the points included in the point sequence of the section recognized based on the image information, which is the shape of only one of the left and right marking lines of the vehicle, to the sensor information. set lower than the reliability of the points included in the point sequence of the section recognized based on
The second reliability setting unit sets the reliability in the section where the reliability of the point sequence is low to be lower than the reliability in the section where the reliability of the point sequence is high,
The road model calculation unit
determine road model candidates based on the sequence of points;
In a section of the road in front of the vehicle, in which the previously calculated road model and the road model candidate are separated by a threshold distance or more in the width direction of the road,
calculating the road model based on the previously set point sequence when the reliability of the points included in the point sequence is lower than the reliability of the previously calculated road model;
A road shape recognition apparatus for calculating the road model based on the point sequence when the reliability of the points included in the point sequence is higher than the reliability of a previously calculated road model.

Images