JP2015069287A - Own vehicle position recognition device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To calculate a relative lateral position of an own vehicle to a lane marker in a case that a branch lane or a confluent lane is included in a road where the own vehicle is traveling.SOLUTION: An own vehicle position recognition device 100 calculates a first relative lateral position of the own vehicle to a first lane marker which is detected when an evaluation value calculated by comparing a first evaluation value which is calculated by a lane marker detection function for detecting a first lane marker for dividing a first travel lane where the own vehicle is traveling, and a second lane marker adjacent to the first travel lane on the basis of an image of a camera 20 mounted on the own vehicle, and a first road parameter of the first lane marker, and a second evaluation value calculated by a second road parameter of a second lane marker. When the evaluation comparison value is equal to or more than a first predetermined threshold, the device calculates a second relative lateral position of the own vehicle to the second lane marker.

Description

  The present invention relates to a vehicle position recognition device that recognizes a lateral position with respect to a lane marker on which the vehicle travels.

  With regard to this type of device, when the vehicle travels on the main line and the road curvature or pitch angle calculated based on the lane marker of the road is larger than a predetermined value, the road for turning the road to the right or left ( An apparatus that recognizes a branched lane) is known (Patent Document 1).

JP 2005-346382 A

  However, in the conventional technique, when a branch lane with an increasing number of roads is detected, the position of the lane marker is estimated using past information instead of the current information. For example, the road curvature may differ between the past and the present. In such a situation, there is a problem that a shift occurs with respect to the current position of the lane marker.

  The problem to be solved by the present invention is to calculate the relative lateral position of the host vehicle with respect to the lane marker based on the current information.

  The present invention detects a pair of left and right first lane markers that separates a first traveling lane in which the host vehicle travels, and a pair of left and right second lane markers other than the first lane marker that separates a second traveling lane, A first evaluation value calculated from the first road parameter of the first lane determined from the relative position of the lane marker and a second value calculated from the second road parameter of the second lane determined from the relative position of the second lane marker. An evaluation comparison value is calculated by comparing with the evaluation value. If the evaluation comparison value is less than the first predetermined threshold value, the first relative lateral position of the host vehicle with respect to the detected first lane marker is calculated, and the evaluation comparison is performed. When the value is equal to or greater than the first predetermined threshold, the above problem is solved by calculating the second relative lateral position of the host vehicle with respect to the detected second lane marker.

  According to the present invention, either one of the first lane marker and the second lane marker is used as a reference for the relative lateral position of the own vehicle according to the calculated evaluation comparison value road, so that the number of lanes is increased or decreased. Even in a scene where there is, it is possible to calculate the current positional relationship of the host vehicle with respect to the lane marker based on real-time information.

It is a block block diagram of the driving assistance system 1 containing the own vehicle position recognition apparatus 100 which concerns on this embodiment. It is the 1st figure for explaining the example of installation of the camera of this embodiment, and a road parameter. It is the 2nd figure for explaining the example of installation of the camera of this embodiment, and a road parameter. It is a figure for demonstrating a lane marker model. It is a flowchart which shows the control procedure of the own vehicle position recognition process of this embodiment. It is a flowchart which shows the control procedure of the lane marker detection process of this embodiment. It is a figure for demonstrating the setting method of the detection area | region of a lane marker candidate point. It is a flowchart which shows the control procedure of the 1st method in the determination process of this embodiment. It is a flowchart which shows the control procedure of the 2nd method in the recognition process of this embodiment. It is a flowchart which shows the control procedure of the 3rd method in the determination process of this embodiment. It is a flowchart which shows the control procedure of the other 3rd method in the determination process of this embodiment. It is a flowchart which shows the control procedure of the travel control process of this embodiment. It is a figure which shows an example of the aspect of the branch lane of this embodiment. It is a figure which shows an example of the aspect of the merge lane of this embodiment. It is a figure for demonstrating the determination process in the branch lane of this embodiment. It is a figure for demonstrating the determination process in the branch lane of this embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the present embodiment, a case where the own vehicle position recognition device according to the present invention is applied to a driving support system for a vehicle will be described as an example.

  FIG. 1 is a diagram showing a block configuration of a vehicular driving support system 1 including a host vehicle position recognition device 100 according to the present embodiment. The own vehicle position recognition device 100 and the driving support system 1 for a vehicle including the same are mounted on the vehicle. The vehicle travel support system 1 performs part or all of the steering operation and acceleration / deceleration operation of the host vehicle, or outputs information necessary for traveling of the host vehicle to assist the travel of the host vehicle. The own vehicle position recognizing device 100 recognizes a relative lateral position where the own vehicle exists with respect to a lane in which the own vehicle travels. The relative lateral position is the position of the host vehicle in the width direction of the lane divided by the lane marker. In the present embodiment, the information on the recognized relative lateral position is used for driving support processing. Although the present embodiment will be described by taking a branch lane as an example, the vehicle position recognition device 100 and the travel control device 1 of the present embodiment also apply to a common lane in which the width of the travel lane changes. It can be applied to and has the same effect. Further, the branch lane of the present embodiment includes a mode in which the number of lanes increases, and the merge lane of the present embodiment includes a mode in which the number of lanes decreases.

  As shown in FIG. 1, the vehicle travel support system 1 includes a host vehicle position recognition device 100 and an in-vehicle device 200. The in-vehicle device 200 includes a vehicle controller 50, a drive system 60, a steering device 70, a travel support device 80, and a navigation device 90. The own vehicle position recognition device 100 and each in-vehicle device 200 are connected by a CAN (Controller Area Network) or other in-vehicle LAN in order to exchange information with each other.

  The vehicle controller 50 is an ECU (Electronic Control Unit) that controls the operation of the entire vehicle. The vehicle controller 50 acquires detection signals from various sensors 51 mounted on the vehicle. The acquired signal is used for vehicle control, and is sent to the driving support device 80 and the vehicle position recognition device 100. The various sensors 51 detect the state of the vehicle, and specifically include a vehicle speed sensor, a steering angle sensor, and a current sensor for a steering actuator. A yaw rate sensor may also be included. The vehicle speed is detected by measuring the rotational speed of the output side of the transmission and the rotational speed of the wheels. The steering angle is detected as a steering angle detection signal by an angle detection mechanism such as a rotary encoder or a potentiometer after the rotational displacement of the steering shaft is amplified directly or by a gear mechanism or the like.

  The drive system 60 is a drive mechanism of the vehicle V, and drives the vehicle based on input signals by the driver's accelerator operation and brake operation, and control signals acquired from the vehicle controller 50 or the travel support device 80. The steering control device 70 includes a steering actuator. The steering actuator includes a motor and the like attached to the column shaft of the steering. The vehicle is moved based on an input signal obtained by the driver's steering operation and a control signal acquired from the vehicle controller 50 or the driving support device 80.

  The driving support device 80 uses the lane marker model that expresses the relative positional relationship between the driving lane and the host vehicle calculated by the host vehicle position recognition device 100 so that the host vehicle travels while maintaining the center position of the lane. Alternatively, the steering device 70 is controlled so that the host vehicle travels while maintaining the lateral position set with respect to the lane. The driving support device 80 calculates a steering control amount based on information on the vehicle speed, the steering angle, and the current of the steering actuator acquired from the various sensors 51 of the vehicle controller 50, and sends a current command to the steering actuator. Control is performed so that the vehicle travels in the target lateral position.

  The navigation device 90 includes a GPS (Global Positioning System) 91 that detects a current position, and map information that associates point information, road information, facility information, and the like with position information.

  Further, as shown in the figure, the own vehicle position recognition device 100 of the present embodiment includes a control device 10, a camera 20 that captures the front of the vehicle, including the side of the vehicle, and the relative lateral position of the own vehicle. And an output device 30 that outputs the recognition result.

  The camera 20 of the present embodiment is provided at a substantially central position in the vehicle width direction of the vehicle. In this embodiment, it attaches to the upper part of the front window in a vehicle interior. The camera 20 is a camera using an image sensor such as a CCD, and captures an image of the traveling direction of the vehicle V. The camera 20 is attached to the vehicle with a lower pitch angle along the direction of gravity. The pitch angle can be appropriately set according to the height of the vehicle and the performance of the camera 20. For this reason, the camera 20 of the present embodiment images a road surface several meters to several tens meters ahead of the vehicle. Further, in the present embodiment, not only the travel lane in which the host vehicle travels, but also the adjacent lane and the road in the adjacent lane can be imaged. In this case, it is preferable to use a wide-angle camera 20.

  The display 31 and the speaker 32 as the output device 30 of the present embodiment are installed around a dashboard that can be visually recognized by the driver of the vehicle, and correspond to information on the recognition result of the relative lateral position of the own vehicle and the relative lateral position of the own vehicle. Information on driving support is presented to the driver. Further, the output device 30 of the present embodiment has a wireless or wired communication function, and sends the calculation result to the driving support device 80 other than the vehicle position recognition device 100 and other in-vehicle devices 200 in accordance with instructions from the control device 10. . The calculation result includes the first relative lateral position and the second relative lateral position. Further, the calculation result may include a first evaluation value, a second evaluation value, an evaluation comparison value, and a road parameter.

  Then, the control apparatus 10 of the own vehicle position recognition apparatus 100 of this embodiment is demonstrated. The own vehicle position recognition apparatus 100 recognizes the relative positional relationship between the own vehicle and the lane marker that divides each lane based on the captured image. The control device 10 according to the present embodiment includes a ROM (Read Only Memory) 12 in which a program for recognizing the position of the host vehicle is stored and a program stored in the ROM, thereby The computer includes a CPU (Central Processing Unit) 11 as an operation circuit that functions as a driving support system 1 for a vehicle, and a RAM (Random Access Memory) 13 that functions as an accessible storage device.

  The control device 10 of the vehicle position recognition device 100 according to the present embodiment has an image acquisition function, a lane marker detection function, an evaluation value calculation function, and a vehicle relative lateral position calculation function. The control device 10 of the present embodiment is a computer that executes each function by cooperation of software for realizing the above function and the above-described hardware.

  Hereinafter, each function of the vehicle position recognition device 100 according to the present embodiment will be described.

  First, the image acquisition function of the control apparatus 10 of this embodiment is demonstrated. The control device 10 acquires a captured image around the vehicle captured by the camera 20. The captured image includes an image of the road surface in front of and in front of the vehicle.

  The lane marker detection function of the control apparatus 10 of this embodiment is demonstrated. Based on the captured image, the control device 10 detects a pair (two) of first lane markers that divide the first travel lane in which the host vehicle travels. The detection method of the lane marker of a driving lane is not specifically limited, Techniques, such as the white line detection function known at the time of application, a driving assistance function, a key plane support function, can be used suitably. The control device 10 according to the present embodiment extracts an edge corresponding to a boundary between a road and a lane marker (white line) included in the captured image, and detects the lane marker by analyzing the extracted edge.

Moreover, the control apparatus 10 of this embodiment detects the 2nd lane marker which each divides the 2nd traveling lane adjacent to the 1st traveling lane where the own vehicle drive | works. When the first traveling lane and the second traveling lane are adjacent, the center lane marker is also the first lane marker and the second lane marker. Specifically, when there is a first travel lane in which the host vehicle that is divided by three lane markers travels and a second travel lane that is adjacent to the right side in parallel, the leftmost and center pair (two This lane marker is a first lane marker that divides the first lane, and a pair of (two) lane markers on the rightmost side and the center can be said to be a second lane marker that divides the second lane.
In order to clarify the attribute of the center lane marker, in the present embodiment, the second lane marker may be defined as not including the first lane marker. That is, the second lane marker is limited to lane markers other than the first lane marker. To explain using the above example, the leftmost and center lane markers among the three lane markers may be the first lane markers, and only the rightmost lane marker may be the second lane marker.
The second travel lane of this embodiment includes at least a lane adjacent to the first travel lane. Further, the second travel lane includes not only the lane having the same travel direction as the first travel lane, but also an opposite lane having the travel direction opposite to the first travel lane. The second lane includes an adjacent lane that exists next to the lane in which the host vehicle travels, and an adjacent lane that is adjacent to the adjacent lane (the lane adjacent to the own vehicle lane). The control device 10 detects a plurality of lane markers belonging to the road on which the host vehicle travels, such as the traveling lane of the host vehicle, the adjacent lane adjacent to the host vehicle, and the next adjacent lane. The control device 10 acquires the position of the detected lane marker.

  The evaluation value calculation function of the control apparatus 10 of this embodiment is demonstrated. The control device 10 of the present embodiment calculates the road curvature of the first traveling lane divided by the first lane marker, the relative pitch angle with respect to the host vehicle, or the host vehicle calculated based on the relative position of the first lane marker in the captured image. A first evaluation value is calculated using a first road parameter including any one or more of relative yaw angles with respect to. Further, the control device 10 of the present embodiment calculates the road curvature of the second traveling lane divided by the second lane marker calculated based on the relative position of the second lane marker in the captured image, the relative pitch angle with respect to the host vehicle, Alternatively, the second evaluation value is calculated using the second road parameter including any one or more of the relative yaw angles with respect to the host vehicle. The first evaluation value and the second evaluation value are values obtained through a predetermined calculation process from the road curvature of the traveling lane defined as the road parameter, the relative pitch angle with respect to the host vehicle, or the relative yaw angle with respect to the host vehicle. An evaluation value (including the first evaluation value and the second evaluation value, the same applies hereinafter) is calculated using any one of the road curvature of the traveling lane, the relative pitch angle with respect to the own vehicle, or the relative yaw angle with respect to the own vehicle. Alternatively, the evaluation value may be calculated by combining two or more values. Different arithmetic processing may be defined for each type of road parameter.

  The control device 10 according to the present embodiment calculates an evaluation value for determining whether a road includes a branch lane or a merge lane by any one of the following methods.

  As a first method, the control device 10 according to the present embodiment has a difference between the first evaluation value calculated from the first road parameter and the second evaluation value calculated from the road curvature of the traveling lane of the second road parameter. When it is more than the 1st predetermined threshold set according to the kind of each road parameter and the combination of each road parameter, it judges with a 1st run lane including a branch lane or a merge lane. On the other hand, when the difference between the first evaluation value and the second evaluation value is less than the predetermined threshold value, it is determined that the first lane does not include a branch lane or a merge lane. In this process, a branch lane or a merge lane may be included in the second travel lane, but there is no problem even if it is adopted as a method for predicting the presence of a branch lane or a merge lane.

  Incidentally, the first predetermined threshold in the present embodiment is a value set to achieve the purpose of discriminating between a straight road where the width of the lane marker is constant and a branch lane or a merged lane where the width of the lane marker increases or decreases. is there. The first predetermined threshold is set to a different value for each of the road curvature of the traveling lane, the relative pitch angle with respect to the host vehicle, and the relative yaw angle with respect to the host vehicle.

  As a second method, the control device 10 according to the present embodiment determines whether the road includes a branch lane or a merge lane using the first road parameter and the second road parameter at different timings. Specifically, the control device 10 calculates the road curvature of the first traveling lane divided by the first lane marker, the relative pitch angle with respect to the own vehicle, or the own vehicle calculated based on the relative position of the first lane marker at the first timing. A first road parameter including any one or more of relative yaw angles with respect to the vehicle is calculated. Then, at a second timing after the first timing, the control device 10 calculates the first road parameter calculated based on the relative position of the first lane marker. The control device 10 calculates the first evaluation value based on the first difference between the first road parameter at the first timing and the first road parameter at the second timing. As a result, a first evaluation value is acquired in consideration of different timings, for example, current and past road parameters.

  Similarly, the same processing is performed for the second travel lane other than the first travel lane in which the host vehicle travels. That is, the control device 10 calculates the second road parameter of the second lane marker at the first timing and the second road parameter of the second lane marker at the subsequent second timing. The control device 10 calculates the second evaluation value based on the second difference between the second road parameter at the first timing and the second road parameter at the second timing. Thereby, the second evaluation value in consideration of different timing, for example, current and past road parameters is acquired. Road parameters and evaluation values that are sequentially stored in association with the processing time may be read in this processing.

  When the difference between the first difference and the second difference is equal to or greater than a second predetermined threshold, the control device 10 of the present embodiment includes a branch lane or a merge lane on the first traveling lane or a road including the first lane. judge. Although the branch lane or the merge lane may be included in the second travel lane, there is no problem even if it is adopted as a method for predicting the presence of the branch lane or the merge lane.

  Incidentally, the second predetermined threshold in the present embodiment is a value set to achieve the purpose of discriminating between a straight road in which the width of the lane marker is constant and a branch lane or a merged lane in which the width of the lane marker increases or decreases. is there. The second predetermined threshold is set to a different value for each of the road curvature of the traveling lane, the relative pitch angle with respect to the host vehicle, and the relative yaw angle with respect to the host vehicle. The second predetermined threshold may be the same value as the first predetermined threshold, or may be a different value.

  This method can be performed independently of the first method described above and the third method described later. That is, the control device 10 of the present embodiment uses the lane marker detection function, the evaluation value calculation function that calculates the first evaluation value and the second evaluation value using the second method, and the second method. It can be configured to execute an own vehicle relative lateral position calculation function for calculating an evaluation comparison value and calculating a relative lateral position of the own vehicle.

  The third method is a method suitable when there are a plurality of second traveling lanes. The control device 10 of the present embodiment calculates the first evaluation value based on the first road parameter of the first lane marker for the host vehicle. The control device 10 calculates the second evaluation value based on the second road parameters of the plurality of second lane markers for the host vehicle.

  The control apparatus 10 according to the present embodiment uses the first evaluation value and the second evaluation value as a population, and calculates a deviation of the first evaluation value (or the second evaluation value) with respect to this population. If the deviation of the first evaluation value (or the second evaluation value) is greater than or equal to a third predetermined threshold, a branch lane or a merge lane is in the first first lane (or second lane) on which the host vehicle is traveling. It is determined that it is included.

  The deviation in the present embodiment is the degree of bias of each parameter with respect to the population including the first road parameter and the second road parameter. Although not particularly limited, the deviation in the present embodiment may be a difference between the first road parameter and the second road parameter from the average of the population including the first road parameter and the second road parameter. It may be a standard deviation of each first road parameter for a population including road parameters.

  Incidentally, the third predetermined threshold in the present embodiment is a value set to achieve the purpose of discriminating between a straight road where the width of the lane marker is constant and a branch lane or a merged lane where the width of the lane marker increases or decreases. is there. Different values are set for the third predetermined threshold value for the road curvature of the traveling lane, the relative pitch angle with respect to the host vehicle, and the relative yaw angle with respect to the host vehicle. The third predetermined threshold may be the same value as the first predetermined threshold or the second predetermined threshold, or may be a different value.

  This method can be performed independently of the first method and the second method described above. That is, the control device 10 of the present embodiment uses the lane marker detection function, the evaluation value calculation function that calculates the first evaluation value and the second evaluation value using the third method, and the third method. It can be configured to execute an own vehicle relative lateral position calculation function for calculating an evaluation comparison value and calculating a relative lateral position of the own vehicle.

  The control device 10 includes a vehicle relative lateral position calculation function for calculating the vehicle's relative lateral position with respect to the lane marker. The control device 10 compares the first evaluation value acquired from the evaluation value calculation function with the second evaluation value to calculate an evaluation comparison value. When the evaluation comparison value is less than the first predetermined threshold value, the control device 10 calculates the first relative lateral position of the host vehicle with respect to the detected first lane marker, and the evaluation comparison value is the first predetermined threshold value. In the case above, the second relative lateral position of the host vehicle with respect to the detected second lane marker is calculated. The evaluation comparison value may be a difference between the first evaluation value and the second evaluation value, or the second evaluation value of the first evaluation value (or a population including the first evaluation value and the second evaluation value). It may be a deviation value.

  The control device 10 may include a lane recognition function that recognizes the relative position between the vehicle and the lane marker based on the detection result of the lane marker. The control device 10 detects a lane marker on the road by processing an image captured by the camera 20, and then uses a plurality of parameters (hereinafter also referred to as "road parameters") representing the road shape and vehicle behavior to determine the road lane. By updating the road parameters with time so that the lane marker model that mathematically represents the shape matches the detection result of the lane marker, the relative position of the host vehicle with respect to the lane or the relative position of the lane with respect to the host vehicle is obtained. recognize. And the control apparatus 10 estimates the road shape and vehicle behavior of the recognized lane. The control device 10 performs an evaluation value calculation process using the road parameters obtained in this process.

Here, the road parameters of the present embodiment including the first road parameter and the second road parameter will be described. 2A and 2B are diagrams for explaining a plurality of parameters expressing the road shape and the vehicle behavior. As shown in FIGS. 2A and 2B, the road parameters include the lateral displacement y _r of the center of gravity of the vehicle relative to the reference lane marker, the yaw angle φ _{r of} the vehicle relative to the lane, the pitch angle η of the vehicle, and the height from the road surface of the camera. H, road curvature (reciprocal of curvature radius) ρ, travel lane width W, and the like.

  Then, on the screen coordinate system x, y as shown in FIG. 3, the lane marker model is expressed by the equation (1) using the road parameters. The expression method of the lane marker model is not particularly limited, and a model known at the time of filing can be used.

In the formula (1), a to e are road parameters. When the height h of the camera 1 from the road surface is constant, each road parameter represents the following road and white line shape or vehicle behavior. That, a is the vehicle lateral displacement y _r in the lane, b is the ρ curvature of the road, c is the yaw angle phi _r with respect to the road of the vehicle (the optical axis of the camera 1), d is the vehicle ( The pitch angle η with respect to the road of the optical axis of the camera 1 and e corresponds to the lane width W of the road. Here, the reference lane marker is set on the left side of the vehicle lane, but other lane markers can also be set as a reference, and in this case, the {} portion in equation (1) changes. . By using {a + 2e}, {a + 3e} or {a-2e}, {a-3e}, it is possible to express lane markers for multiple lanes such as the next lane as well as the next lane it can. Lateral displacement y _r indicates the position lateral displacement of the lane marker as a reference for the vehicle. For example, when the center of the lane is the target travel position, y _r = −W / 2 may be set as the target. Hereinafter, the above equation (1) will be described.

  When an arbitrary point on the real coordinate system x (vehicle left-right direction), y (vehicle vertical direction), z (vehicle front-back direction) fixed to the vehicle is projected onto the screen coordinate system x, y, the following formula ( 2).

  However, f is a lens parameter and is a coefficient corresponding to the focal length of the lens. Assuming that the road curvature ρ is not so large and the road surface is a plane, the coordinates of the road white line with respect to the vehicle center line (camera center line) ahead of Z [m] are given by the following equation (3). However, this assumption is an assumption set for the simplification of the model. By increasing the order of the model, the general condition can be established.

  The following formula (4) is obtained by erasing X, Y, and Z from the above formulas (2) to (3).

  The above equation (1) is obtained by normalizing each parameter using the equation (5) with the camera height h having the smallest fluctuation among the variables being constant.

  In the initial state, since the shapes of the road and lane markers and the vehicle behavior are unknown, for example, a value corresponding to the median value is set as an initial value for each road parameter. For example, the lane center is set as the lateral displacement amount correspondence parameter a of the host vehicle in the lane, the straight line is set as the road curvature correspondence parameter b, the yaw angle correspondence parameter c for the lane is zero degrees, and the pitch angle correspondence to the lane is set. The parameter d is set to η degrees in a stopped state, and the lane width corresponding parameter e is set to a general road lane width.

  When entering a fork or lane, the width of the lane marker for the lane that connects to the fork or lane changes, while the lane marker for a lane that belongs to the same road as the lane and does not connect to the fork or lane. The width does not change. In this embodiment, paying attention to this point, based on the difference in the positional relationship between the lane marker of the first traveling lane on which the host vehicle travels and the host vehicle, and the positional relationship between the lane marker of another second traveling lane and the host vehicle, It is determined whether the road includes a branch lane or a merge lane.

  According to the own vehicle position recognition device 100 of the present embodiment, on a road where a plurality of main lanes exist, branch lanes, merge lanes (roads with increasing lanes) based on changes in the positional relationship between each lane and the own vehicle. And the relative lateral position of the host vehicle with respect to the lane marker that divides the lane in which no branch lane and no merge lane exist can be calculated. The calculated relative lateral position of the host vehicle is used for driving support of the host vehicle.

  Next, the procedure of the vehicle position recognition process and the driving support process according to the present embodiment will be described with reference to FIGS.

  As shown in FIG. 4, the vehicle position recognition device 100 of the driving support system 1 according to the present embodiment includes an edge extraction process S1, a lane marker detection process S2, a road parameter calculation process S3, a branch lane, and the vehicle position recognition process. A merge lane determination process S4 and a vehicle relative lateral position output process S5 are performed. Following this, the driving support device 80 performs a driving support process S6.

  In the edge extraction process S1, an edge of an image corresponding to a lane marker is extracted from a captured image including a road image. In general, since the lane marker is provided with a color that can be distinguished from a road, an edge can be extracted based on the contrast of the color.

  In the lane marker detection process S2, the continuity of the edges extracted in the edge extraction process S1 is examined, and the presence and position of the lane marker are detected based on edge information constituting the lane marker. Edge extraction is performed in a range including the image of the traveling lane of the host vehicle and the adjacent traveling lane. If necessary, it is performed in a range including images of the traveling lane of the host vehicle, the adjacent traveling lane, and the adjacent traveling lane adjacent to the traveling lane of the host vehicle.

  FIG. 5 shows a subroutine of the lane marker detection process S2. In step S101, since the shapes of the road and lane markers and the vehicle behavior are unknown in the initial state, for example, a value corresponding to the median value is set as an initial value for each road parameter. For example, the lane center is set as the lateral displacement amount correspondence parameter a of the host vehicle in the lane, the straight line is set as the road curvature correspondence parameter b, the yaw angle correspondence parameter c for the lane is zero degrees, and the pitch angle correspondence to the lane is set. The parameter d is set to η degrees in a stopped state, and the lane width corresponding parameter e is set to a general road lane width. The lane width may be read from the road information of the road to which the position information detected by the GPS 91 belongs by referring to the map information 92 including the road width and other road information stored in the navigation device 90.

  In step S102, as shown in FIG. 6, the initial setting of the region LM for detecting lane marker candidate points is performed. The region LM for detecting the lane marker candidate point is first performed for the first traveling lane in which the host vehicle travels, and sequentially for the second traveling lane adjacent to the first traveling lane. If necessary, it is also performed on the second traveling lane adjacent to the first traveling lane. In the initial state, it is expected that there is a large gap between the white line model in which the initial value is set as the road parameter and the road white line on the actual screen. Therefore, it is desirable to set a region as large as possible.

  In step S103, edge point information is input. In step S104, in the initial state, the detection area set in S102 is used. If the lane marker has already been detected by the previous processing, the detection area of the lane marker candidate point is set so that the previous detection position is at the center of the area. Furthermore, when the road parameter is calculated in the previous process, the lane marker candidate point detection area may be set at a position offset in the vehicle change direction from the lane marker model obtained in the previous process.

  In subsequent step S105, an edge point existing in the lane marker candidate point detection area is detected as a lane marker candidate point. In step S106, it is confirmed whether or not the number of lane marker candidate points is equal to or greater than a predetermined value. If the number is less than the predetermined value, it is determined that no lane marker is included in the lane marker candidate point detection area. If it is larger than the predetermined value, the process proceeds to step S107, and the lane marker candidate point information included in the detected lane marker is output. The lane marker candidate point information is used in the next road parameter calculation process. Similar processing is performed not only on the first lane marker of the first travel lane in which the host vehicle travels but also on other travel lanes, and the second lane marker of the second travel lane is also detected. In step S104, the lane marker candidate point detection area is set at a position offset by the road width W with respect to the previously detected lane marker based on the road parameter calculated in the previous process, so that the lane marker of the adjacent lane is An area that can exist can be set as a candidate point detection area.

  In the road parameter calculation process S3, any one of the road curvature of the traveling lane corresponding to each lane marker calculated based on the relative position of the own vehicle with respect to each lane marker, the relative pitch angle with respect to the own vehicle, or the relative yaw angle with respect to the own vehicle. Calculate road parameters including at least two. The control device 10 includes a first evaluation value based on the first road parameter for the first traveling lane on which the host vehicle travels, and a second evaluation value based on the second road parameter for the second traveling lane other than the first traveling lane. Are calculated respectively. The first (second) evaluation value is a numerical value having a predetermined correlation with the first (second) road parameter. By expressing various first (second) road parameters as first (second) evaluation values, one evaluation value based on different types of road parameters can be obtained.

  Specifically, two lane markers that distinguish the lane in which the host vehicle travels in the center of the image are selected, and the first road parameter based on the first travel lane in which the host vehicle travels is calculated. This calculation method can be calculated by, for example, a method of fitting a plurality of detected lane marker candidate points to the lane marker model equation (1) by the least square method. Furthermore, it converts into an actual physical quantity using Formula (5). Similarly, the second road parameter is calculated based on the lane markers on both sides of the second lane marker in the second lane other than the first lane. Based on the first and second road parameters of the lane marker model detected from the captured image of the camera 20 in this way, the relative positional relationship between the host vehicle and each traveling lane is recognized.

In the determination process S4 of the branch lane and the merge lane, the first evaluation value calculated from the first road parameter is compared with the second evaluation value calculated from the second road parameter, and the difference is calculated as an evaluation comparison value. . When the evaluation comparison value is equal to or greater than the first predetermined threshold, it is determined that the road on which the host vehicle travels includes a branch lane or a merge lane. In this example, the control device 10 relates to a first predetermined threshold value ρ ₀₁ related to the road curvature of the traveling lane corresponding to each lane marker, a first predetermined threshold value η ₀₁ related to the relative pitch angle relative to the host vehicle, and a relative yaw angle relative to the host vehicle. The first predetermined threshold φ _r01 is stored in advance.

  FIG. 7A to FIG. 7D show a branching / merging lane determination process, a calculation of the vehicle's relative lateral position, and an output process subroutine. 7A shows a control procedure according to the first method, FIG. 7B shows a control procedure according to the second method, and FIGS. 7C and 7D show the third procedure among the methods for determining the presence of the branch lane or the merge lane. The control procedure which concerns on a method is shown. Processing other than step S203 in each flowchart is substantially common.

  Based on FIG. 7A, a first method for determining the presence of a branch lane or a merge lane and determining the vehicle's relative lateral position according to the determination result will be described.

First, in step S201, road parameters of the host vehicle lane (first travel lane) within a predetermined time are stored, and average values ρ _p , φ _rp , η _p , y _rp , W _p are calculated. A first evaluation value is calculated from this road parameter. In step S202, it is determined whether or not road parameters are calculated not only for the first travel lane but also for other second travel lanes. When the first evaluation value based on the first road parameter of the first traveling lane and the second evaluation value based on the second road parameter of the second traveling lane are calculated, the process proceeds to step S203A. .

  In step S202, when the 2nd evaluation value by the 2nd road parameter of 2nd driving lanes other than the own vehicle driving lane is not calculated, it returns to step S201 and repeats steps S201 and S202. Although not shown, when the second evaluation value based on the second road parameter of the second traveling lane other than the own vehicle traveling lane is not calculated, only the first evaluation value of the road parameter of the own vehicle traveling lane is used. It may be determined whether a branch lane or a merge lane exists in the first travel lane in which the vehicle travels. In this case, the first evaluation value based on the first road parameter obtained this time is compared with the first evaluation value based on the past first road parameter, and the first evaluation value based on any one of the first road parameters is compared. When the change in the value (difference between the current and previous first road parameters) is equal to or greater than the predetermined value, it is determined that a branch lane or a merge lane exists in the first travel lane. When the change in the first evaluation value of the first road parameter is less than the set predetermined value, there is no branch lane or merge lane in the first traveling lane, and the position of the host vehicle can be recognized normally. It is determined that there is, and the process proceeds to step S206.

In step S203A in the first method, the control device 10 uses the first road parameter ρ ₁ , φ _r1 , η _{1 of} the first traveling lane on which the host vehicle travels, or the first evaluation value calculated based on the first evaluation value and the own evaluation value. The difference (change) from the road parameter ρ ₂ , φ _r2 , η ₂ of the second traveling lane other than the vehicle traveling lane or the second evaluation value calculated based on the road parameter ρ ₂ , φ _r2 , η ₂ is calculated. The control device 10 determines that the difference between the first road parameters ρ ₁ , φ _r1 , η ₁ and the road parameters ρ ₂ , φ _r2 , η _{2 of} the second lane is a first predetermined threshold ρ ₀₁ , η ₀₁ , φ _r01. If it is less than that, it is determined that there is no branching lane or merging lane on the road on which the host vehicle is traveling, and that the host vehicle traveling lane (first traveling lane) can be recognized normally, and the process proceeds to step S206. To do. In step S <b> 206, the control device 10 calculates the first relative lateral position of the host vehicle with respect to the detected first lane marker, and outputs this to the travel control device 80.

On the other hand, in step S203A, the control device 10 performs the second evaluation based on the first evaluation value based on the first road parameters ρ ₁ , φ _r1 , η ₁ and the road parameters ρ ₂ , φ _r2 , η _{2 of} the second lane. If the evaluation comparison value obtained by comparing the evaluation value (for example, the difference between the first evaluation value and the second evaluation value) is _{equal to} or greater than the first predetermined threshold ρ ₀₁ , η ₀₁ , φ _r01 , the step The process proceeds to S205. In step S205, the control device 10 determines that a branch lane or a merge lane exists on the road including the first travel lane on which the host vehicle travels. In step S207, the second relative lateral position of the host vehicle with respect to the detected second lane marker is calculated and output to the driving support device 80. With the processing in step S207, the control device 10 may stop outputting the first road parameter. Moreover, the control apparatus 10 may output the past 1st road parameter calculated | required in the scene where it was judged that a branch lane or a merge lane does not exist. Furthermore, instead of the process of step S207, the control device 10 determines that the lane marker is not used when the first road parameter obtained in a scene where it is determined that there is no branch lane or merge lane on the road cannot be acquired for a predetermined time or more. The result of detection may be output, and the output of the first road parameter may be stopped.

  Next, based on FIG. 7B, a second method for determining the presence of a branch lane or a merged lane and determining the vehicle's relative lateral position according to the determination result will be described. Here, the description based on FIG. 7A is cited, and step S203B, which is a different process, will be described.

In step S203B in the second method, the control device 10 determines the first road of the first travel lane currently calculated with respect to the first road parameters ρ _p , φ _rp , η _{p of} the first travel lane calculated in the past. A first evaluation value is obtained from the first difference (change) of the parameters ρ ₁ , φ _r1 , η ₁ . The first difference may be the first evaluation value. In addition, the control device 10 determines the second road of the second travel lane currently calculated with respect to the second road parameters ρ _p , φ _rp , η _p of the second travel lane other than the first travel lane calculated in the past. A second difference (change) of the parameters ρ ₂ , φ _r2 , and η ₂ is obtained from the second evaluation value. The second difference may be the second evaluation value. When the difference between the first difference and the second difference is less than the second predetermined threshold value ρ ₀₂ , η ₀₂ , φ _{r 02} , the control device 10 determines that the branch lane or the merge lane is on the road on which the _host vehicle is traveling. It is determined that the vehicle is in a state where the vehicle lane and the position of the vehicle can be recognized normally, and the process proceeds to step S206. In step S206, the first relative lateral position of the host vehicle with respect to the first lane marker that divides the first travel lane in which the host vehicle travels is calculated, and this is output to the travel control device 80.

On the other hand, in step S203B, the control device 10 determines the first difference (first evaluation) between the first road parameters ρ _p , φ _rp , η _p calculated in advance and the first road parameters ρ ₁ , φ _r1 , η _1. Value) and a second difference (second evaluation value) between the second road parameter ρ _p , φ _rp , η _p calculated in advance and the road parameter ρ ₂ , φ _r2 , η _{2 of} the second lane. If the difference is _{equal to} or greater than the second predetermined threshold _values ρ ₀₂ , η ₀₂ , φ _{r 02} , the _process proceeds to step S205. Step S205 determines that a branch lane or a merge lane exists on the road including the first travel lane in which the host vehicle travels. The processing in step 207 is common to the first method.

  Next, based on FIG. 7C and FIG. 7D, a third method for determining the presence of a branch lane or a merged lane and obtaining the vehicle's relative lateral position according to the determination result will be described. Here, description based on FIG. 7A and FIG. 7B is used, and steps S203C and S203D which are different processes will be described.

In step S203C in the third method, the control device 10 determines the first road parameters ρ ₁ , φ _r1 , η ₁ of the first traveling lane and the second road parameters (ρ ₂ , φ _r2 , _{η 2), (ρ 3,} φ r2, η 3), (ρ 4, φ r4, η 4) ... (ρ n, φ rn, seek eta _n) and. The control device 10 uses the first evaluation value calculated from the first road parameters and the second evaluation value calculated from the plurality of second road parameters as a population, the road curvature of the first lane, and the relative pitch angle with respect to the host vehicle. Or the deviation of the first evaluation value for any one of the relative yaw angles with respect to the host vehicle. Then, when any deviation is less than the third predetermined threshold value ρ ₀₃ , η ₀₃ , φ _{r 03} , the control device 10 does not have a branch lane or a merge lane on the road on which the vehicle travels, and normally It is determined that the vehicle traveling lane and the position of the vehicle can be recognized, and the process proceeds to step S206. In step S <b> 206, the first relative lateral position of the host vehicle with respect to the first lane marker that divides the first travel lane in which the host vehicle travels is calculated, and this is output to the travel control device 80.

On the other hand, if any of the deviations of the first road parameter is greater than or equal to the third predetermined threshold ρ ₀₃ , η ₀₃ , φ _r03 in step _S203C , the control device 10 proceeds to step S205. Step S205 determines that a branch lane or a merge lane exists in the first travel lane in which the host vehicle travels. The processing in step 207 is common to the first and second methods.

  Another method of the third method will be described with reference to FIG. 7D. The third method described with reference to FIG. 7C determines whether there is a branch lane or a merged lane in the first travel lane. In the method illustrated in FIG. 7D, the travel includes the first travel lane and the second travel lane. It is determined whether there is a branch lane or a merge lane in any of the lanes.

Similarly to step S203C described above, in step S203D of FIG. 7D, the control device 10 determines the first road parameters ρ ₁ , φ _r1 , η ₁ of the first travel lane and the second road parameters of the plurality of second travel lanes. _{(ρ 2, φ r2, η} 2), (ρ 3, φ r2, η 3), (ρ 4, φ r4, η 4) ... (ρ n, φ rn, η n) obtaining a. And the control apparatus 10 was calculated based on the 1st evaluation value calculated based on these 1st road parameters, and the 2nd road parameter ((rho) _n , (phi) _rn , (eta) _n : n is a natural number including 1). Using the second evaluation value as a population, the deviation of each evaluation value is calculated. Then, when any deviation is less than the fourth predetermined threshold ρ ₀₄ , η ₀₄ , φ _{r 04} , the control device 10 does not have a branch lane or a merge lane on the road on which the _host vehicle travels, and It is determined that the vehicle traveling lane can be normally recognized, and the process proceeds to step S206. In step S <b> 206, the first relative lateral position of the host vehicle with respect to the first lane marker that divides the first travel lane in which the host vehicle travels is calculated, and this is output to the travel control device 80.

On the other hand, if either the first road parameter or the deviation of each road parameter is equal to or greater than the fourth predetermined threshold ρ ₀₄ , η ₀₄ , φ _r04 in step _S203D , the control device 10 proceeds to step S205. . Step S205 determines that a branch lane or a merge lane exists on the road including the first travel lane in which the host vehicle travels. The processing in step 207 is common to the first and second methods.

  In the third method, when the second road parameters of two or more second lanes are calculated, the deviation is considered with the road parameters for a plurality of lanes as a population. If the first road parameter of the first traveling lane is significantly different from the second road parameter of the plurality of second traveling lanes other than the first traveling lane on which the host vehicle is traveling (a large deviation is observed), It can be determined that a branch lane or a merge lane exists in the first travel lane in which the vehicle travels. In this way, by comparing the road parameters of the first travel lane and the plurality of second travel lanes, there is a deviation in the road parameters of any travel lane, and further, there is a deviation in the road parameters of which travel lane. Can be determined. If there is a deviation in the first road parameter of the first traveling lane in which the host vehicle is traveling, the first lane marker of the first traveling lane is not recognized as a normal lane having a constant width, or the first lane marker is It can be determined that there is a possibility that it has not been detected correctly. According to this process, by stopping the output of road parameters, it is possible to stop driving support such as lane keeping control, and to prevent the driving of the host vehicle from being controlled based on inaccurate road parameters. .

  In the present embodiment, “when it is determined that the road includes a branching lane or a merged lane” refers to a traveling lane belonging to the road including the first traveling lane (the first traveling lane and the second traveling lane). Including a case where it is determined that a branch lane or a merge lane is included in any of the above and a case where it is determined that a branch lane or a merge lane is included in the first travel lane,

  Returning to FIG. 4, in the road parameter output process S <b> 5, the control device 10 is subject to the calculated vehicle relative lateral position, the first or second road parameter as necessary, and the vehicle position recognition process. The lane specific information is output to the driving support device 80. In the driving support process S <b> 6, the driving support device 80 performs driving support of the host vehicle using the road parameters acquired from the host vehicle position recognition device 100.

  Hereinafter, the driving support process S6 will be described. In the present embodiment, the relative lateral position calculated according to the determination result of whether or not the road includes a branch lane or a merged lane is used in the travel support device 80.

  The driving support device 80 of the present embodiment corresponds to the first or second lane marker calculated by the vehicle information acquisition function for acquiring vehicle information related to driving from the vehicle and the own vehicle relative lateral position calculation function of the own vehicle position recognition device 100. It has a relative position acquisition function for acquiring the first or second relative lateral position of the host vehicle. The driving support device 80 may acquire the first or second road parameter and lane specifying information for specifying the first or second driving lane corresponding to the first or second road parameter.

  The driving support device 80 has a target lateral position setting function for setting a target lateral position with respect to the first or second traveling lane based on the acquired vehicle information, the first or second road parameter, and the lane identification information; A travel support function for supporting travel of the vehicle so that a relative positional relationship between the target lateral position of the first or second travel lane and the host vehicle is maintained;

Based on FIG. 8, the driving assistance process of this embodiment is demonstrated.
In step S <b> 301, the driving support device 80 acquires each sensor signal as vehicle information from the various sensors 51 of the vehicle controller 50. Specifically, the vehicle signal includes signals from a current sensor of a vehicle speed sensor, a steering angle sensor, and a steering actuator.

  In step S302, the driving support device 80 specifies the relative lateral position of the host vehicle calculated by the host vehicle position recognition device 100, the first or second road parameter, and the lane to be subjected to host vehicle position recognition processing. Get information.

In step S303, the driving support device 80 uses the first or second road parameter acquired in step S302 and the lane specifying information for specifying the lane to be subjected to the vehicle position recognition process when the host vehicle is driven. Set the target lateral position. For example, when the first road parameter of the first travel lane is acquired, the center of the lane can be set as the target lateral position by setting y _r = −W / 2. When the second road parameter based on the right adjacent lane is acquired, y _r = W / 2 is the center of the lane. Of course, the position offset from the center of the lane can be set as the target lateral position according to the situation. In addition, when the lane to be recognized is switched, if the already acquired value is used, the target lateral position may change abruptly. For this reason, when the lane is switched, by setting the lateral displacement amount immediately after the switching as the target lateral position, the previous lateral position can be maintained and driving support can be continued.

  In step S <b> 304, the driving support device 80 calculates a steering control amount corresponding to the first or second relative lateral position, the sensor signal, the road parameter, and the target lateral position calculated by the vehicle position recognition device 100. Based on the calculated steering control amount, a vehicle control command is sent to the vehicle controller 50 and / or the steering device 70.

  In step S305, the vehicle controller 50 and / or the steering device 70 drives the steering actuator 71 according to the steering control amount included in the control command. Thereby, the own vehicle which exists in the 1st or 2nd relative lateral position can drive | work in the state which maintained the predetermined positional relationship with respect to the target lateral position of a predetermined travel lane.

  Specifically, FIG. 9A shows a scene in a branch lane where the driving support system 1 of this embodiment effectively functions. FIG. 9B shows a scene in the merge lane where the driving support system 1 of the present embodiment also functions effectively. As shown in FIG. 9A, the lane markers that delimit the main line are not the same width. Focusing on the right lane, the width of the two lane markers that delimit the right lane is wide on the near side, but branches off on the far side, which is the traveling direction, and suddenly becomes narrow. As shown in FIG. 9B, the lane markers that delimit the main line are not the same width. When paying attention to the central main line, the width of the two lane markers is narrow on the front side of the merging, but merges with the merging lane on the far side, which is the traveling direction, and suddenly widens. In addition, the “branch lane” in the present embodiment means a lane in which the number of lanes decreases, and the “merging lane” in the present embodiment means a lane in which the number of lanes increases.

  Furthermore, concretely, taking the branch lane as an example, the operation of the vehicle position recognition processing of the present embodiment will be described based on FIG. 10A. As shown in FIG. 10A, a scene is set in which a branch lane exists in the first lane of the road on which the host vehicle travels, and the lane marker P1L on one side of the first lane deviates from the main lane. In the scene shown in the figure, the second travel lane on the right side of the first travel lane does not include a branch lane or a merge lane.

  As shown in FIG. 10A, the intervals Q11 and Q12 between the lane markers P1L and P1R of the first lane change along the traveling direction E of the host vehicle V. The intervals Q21 and Q22 between the lane markers P2L and P2R in the second lane do not change along the traveling direction E of the host vehicle V.

  Moreover, FIG. 10B is a figure for demonstrating the effect | action of the own vehicle position recognition process in a merge lane. As shown in FIG. 10B, there is a merge lane that merges with the first travel lane of the road on which the host vehicle travels. For this reason, the lane marker P1L on one side of the first lane is interrupted in the middle, and then the lane marker P1L ′ of the merging lane is connected to the lane marker P1L on one side of the first lane in the forward direction of travel. In the scene shown in the figure, the second travel lane on the right side of the first travel lane does not include a branch lane or a merge lane.

  As shown in FIG. 10B, intervals Q11, Q11 ′, Q12 between the lane markers P1L ′ (later P1L) and P1R of the first travel lane change along the traveling direction E of the host vehicle V. Specifically, when the road width of the first travel lane is Q11, it increases to Q11 ′ due to the presence of the merge lane. At the merge completion point, it again narrows to Q12, which is almost the same as Q11. The intervals Q21 and Q22 between the lane markers P2L and P2R in the second lane do not change along the traveling direction E of the host vehicle V.

  10A and 10B, the relative position and road parameters between the second lane markers P2L and P2R of the second traveling lane and the host vehicle traveling in the first traveling lane or the second traveling lane are calculated a plurality of times. However, it is difficult for variations to occur in each process. For this reason, the road parameter calculated in the current process for the second travel lane of this example substantially matches the road parameter of the second travel lane calculated in the past.

  On the other hand, in the situation shown in FIG. 10A and FIG. 10B, the distance between the lane markers P1L (P1L ′) and P1R on both sides of the first travel lane in which the host vehicle travels changes. Large variations tend to occur. For this reason, a difference arises between the road parameter calculated by the current process for the first travel lane of this example and the road parameter of the first travel lane calculated in the past.

  In this embodiment, the first road parameter of the first travel lane and the second road parameter of the second travel lane are compared, and based on the evaluation result, a branch lane or a merge lane is present in the first travel lane or the second travel lane. Judge whether it is included.

  Incidentally, when only the first road parameter of the first lane is used, that is, when the process for evaluating the change between the first road parameter calculated in the past and the first road parameter calculated this time is performed, the evaluation is performed. The reference threshold value must be large. This is because, in the first road parameter of the first travel lane including the branch lane or the merge lane, variations in the actually calculated yaw angle, pitch angle, and curvature change are large. That is, if the road parameter evaluation threshold is set to be small, the accuracy of the determination of the presence or absence of a branch lane or a merged lane is lowered.

  However, if the road parameter evaluation threshold is set to be large on the assumption that a branch lane or a merge lane is included, the timing for determining whether a branch lane or a merge lane exists is delayed. After it is determined that a branch lane or a merge lane exists, it is necessary to correct the target lateral position that is a reference for the vehicle position in the driving support process. If the timing of the presence / absence determination of the branch lane or the merge lane is delayed, the correction process of the target lateral position is also delayed, and the correction amount increases. As described above, when the timing for determining whether a branch lane or a merge lane is present is delayed and the target lateral position is significantly corrected in the driving support process, the occupant feels that the behavior of the vehicle has changed rapidly and greatly. In this embodiment, the presence / absence of a branch lane or a merge lane is determined quickly and accurately, so the target lateral position in the driving support process can be corrected quickly and in small amounts, so that the passenger does not feel uncomfortable. Can do.

  In the present embodiment, the second road parameter of the second traveling lane adjacent to the first traveling lane as well as the first traveling lane in which the host vehicle travels is calculated, and the difference from the first road parameter of the first traveling lane is calculated. By evaluating the above, whether or not there is a branch lane or a merge lane can be quickly and accurately performed. As a result, since a scene (a scene as shown in FIG. 10A or FIG. 10B) in which a branch lane or a merge lane exists and a road parameter cannot be accurately calculated is detected quickly, a driving support process based on an inaccurate road parameter is performed. Can be prevented from being executed.

  Since the vehicle position recognition device 100 of the present embodiment is configured and operates as described above, the following effects can be obtained.

  [1] The vehicle position recognition device 100 of the present embodiment has a first evaluation value obtained from the road parameter of the first traveling lane on which the vehicle travels and a second evaluation value obtained from the road parameter of the second traveling lane. By evaluating the evaluation comparison value obtained by comparing the lane marker, it can be estimated that the shape of the lane marker corresponding to the traveling lane expands or narrows to the left and right. Therefore, whether the traveling lane of the host vehicle includes a branching lane or a merged lane Whether or not can be determined quickly and accurately. When the traveling lane of the host vehicle includes a branching lane or a merged lane, the first relative lateral position with respect to the first lane marker that divides the first traveling lane is calculated, and the traveling lane of the host vehicle does not include the branching lane or the merging lane. In this case, since the second relative lateral position with respect to the second lane marker that divides the second lane is calculated, it is possible to quickly calculate a reliable relative lateral position based on the lane marker whose width does not change.

  [2] According to the vehicle position recognition device 100 of the present embodiment, the first difference between the current and past first road parameters is calculated as the first evaluation value, and the second difference between the current and past second road parameters is calculated. Is calculated as a second evaluation value, and an evaluation comparison value, which is a comparison result between the first evaluation value and the second evaluation value, is evaluated. Thereby, it is possible to suppress erroneous determination due to variations in detection results, and to quickly and accurately determine whether or not the traveling lane of the host vehicle includes a branch lane or a merged lane. As a result, the above effects can be achieved.

  [3] According to the vehicle position recognition device 100 of the present embodiment, the first evaluation value calculated from the first road parameter and the second evaluation value calculated from one or a plurality of second road parameters are included in the population. And an evaluation comparison value which is a deviation of the first evaluation value in this population. Thereby, even in a scene where there are a plurality of lanes extending in the same direction in parallel with the first traveling lane in which the host vehicle travels, whether or not the traveling lane of the host vehicle includes a branch lane or a merged lane can be quickly and It can be determined accurately. As a result, the above effects can be achieved.

  The embodiment described above is described for facilitating the understanding of the present invention, and is not described for limiting the present invention. Therefore, each element disclosed in the above embodiment is intended to include all design changes and equivalents belonging to the technical scope of the present invention.

  That is, in the present specification, the present invention will be described by taking a travel support system 1 for a vehicle including the vehicle position recognition device 100 and the in-vehicle device 200 including the travel support device 80 as an example. It is not limited.

  In this specification, the vehicle position recognition device 100 including the control device 10, the camera 20, and the output device 30 will be described as an example of the vehicle position recognition device according to the present invention. However, the present invention is not limited thereto. Is not to be done.

  In the present specification, as an example of the vehicle position recognition device according to the present invention including an image acquisition unit, a lane marker detection unit, and an evaluation value calculation unit, an image acquisition function, a lane marker detection function, and an evaluation value calculation function, The vehicle position recognition device 100 including the control device 10 that executes the vehicle relative position calculation function will be described as an example, but is not limited thereto.

DESCRIPTION OF SYMBOLS 1 ... Driving assistance system 100 ... Own-vehicle position recognition apparatus 10 ... Control apparatus 11 ... CPU
12 ... ROM
13 ... RAM
DESCRIPTION OF SYMBOLS 20 ... Camera 30 ... Output device 31 ... Display 31 ... Speaker 200 ... In-vehicle device 50 ... Vehicle controller 51 ... Various sensors 60 ... Drive system 70 ... Steering device 80 ... Driving support device 90 ... Navigation device 91 ... GPS
92 ... Map information, road information, road width information

Claims (3)

Image acquisition means for acquiring a captured image around the vehicle by a camera mounted on the host vehicle;
Based on the captured image, a pair of left and right first lane markers that distinguish the first traveling lane in which the host vehicle travels and a second lane marker that distinguishes the second traveling lane adjacent to the first traveling lane are detected. Lane marker detection means;
A first road that includes one or more of the road curvature of the first lane, the relative pitch angle with respect to the host vehicle, or the relative yaw angle with respect to the host vehicle, calculated based on the relative position of the first lane marker. A first evaluation value is calculated according to a parameter, and a road curvature of the second traveling lane, a relative pitch angle with respect to the host vehicle, or a relative yaw angle with respect to the host vehicle is calculated based on a relative position of the second lane marker. An evaluation value calculating means for calculating a second evaluation value by a second road parameter including any one or more;
When an evaluation comparison value calculated by comparing the first evaluation value and the second evaluation value is less than a first predetermined threshold value, a first relative lateral position of the host vehicle with respect to the detected first lane marker. A vehicle relative lateral position calculation unit that calculates a position and calculates a second relative lateral position of the host vehicle with respect to the detected second lane marker when the evaluation comparison value is equal to or greater than the first predetermined threshold. And a vehicle position recognition device. The evaluation value calculation means includes
The first evaluation value is calculated based on a first difference between the first road parameter calculated at the first timing and the first road parameter calculated at the second timing after the first timing. And
The second evaluation value is calculated based on a second difference between the second road parameter calculated at the first timing and the second road parameter calculated at the second timing after the first timing. And
When the evaluation comparison value calculated by comparing the first evaluation value and the second evaluation value is less than a second predetermined threshold, the vehicle relative lateral position calculation means is configured to detect the detected first first value. When the first relative lateral position of the host vehicle with respect to the lane marker is calculated and the evaluation comparison value is equal to or greater than the second predetermined threshold, the second relative lateral position of the host vehicle with respect to the detected second lane marker. The vehicle position recognition device according to claim 1, wherein:   The vehicle relative lateral position calculating means calculates the first evaluation value and the second evaluation value as a population, calculates a deviation of the first evaluation value in the population as the evaluation comparison value, and the evaluation comparison value is If it is less than a third predetermined threshold, a first relative lateral position of the host vehicle with respect to the detected first lane marker is calculated, and if the evaluation comparison value is greater than or equal to the third predetermined threshold, The own vehicle position recognition device according to claim 1, wherein a second relative lateral position of the own vehicle with respect to the detected second lane marker is calculated.