JP6552448B2 - Vehicle position detection device, vehicle position detection method, and computer program for vehicle position detection - Google Patents

Description

  The present invention relates to a vehicle position detection apparatus, a vehicle position detection method, and a computer program for vehicle position detection that detect the position of the vehicle using an image and a map taken by a camera mounted on the vehicle.

  2. Description of the Related Art Conventionally, for the purpose of navigation or driving assistance, it has been performed to detect the position of a host vehicle while traveling by using a Global Positioning System (GPS) signal. However, if there is a structure near the vehicle, such as a high-rise building, that blocks the positioning signal from the GPS positioning satellite, it will be difficult for the vehicle to receive the positioning signal and the vehicle's position can not be detected accurately There was a thing. Then, the method of improving the detection accuracy of the position of self-vehicles is proposed by matching the information of a vehicle circumference, etc. which were picturized with the in-vehicle camera, and the map prepared beforehand (for example, patent) References 1-3 and Non-Patent References 1 and 2).

  For example, the positioning device described in Patent Document 1 specifies the current position based on the road markings in the image captured by the imaging unit for capturing the front of the vehicle.

  In addition, the moving body position measuring device described in Patent Document 2 includes feature information extracted from an image captured by an imaging unit mounted on a moving body in the vicinity of a reference point on the map, and the vicinity of the reference point on the map. The present position of the mobile object is estimated according to the positions of a plurality of features in the vicinity of the reference point estimated by matching with the feature information extracted from the image of.

  Further, the method described in Patent Document 3 determines the position of the vehicle with respect to the optical index identified in the image by applying template matching to the image data in the traveling direction of the vehicle.

  Furthermore, the method described in Non-Patent Document 1 detects the position of the vehicle by matching a map including line segments representing curbs and road markings with feature points extracted from an image obtained by a stereo camera.

  Furthermore, the method described in Non-Patent Document 2 generates a high-resolution environment map using information acquired by a vehicle-mounted device, such as GPS, IMU, odometry, and LIDAR. The method then utilizes a particle filter to correlate the LIDER measurements with the map when positioning the vehicle on these maps.

JP 2007-108043 A JP 2012-127896 A JP 2005-136946 A

Schreiber et al., "LaneLoc: Lane Marking based Localization Using Highly Accurate Maps", Intelligent Vehicles Symposium (IV), 2013 IEEE, IEEE, 2013 Lenvision et al., "Map-Based Precision Vehicle Localization in Urban Environments", Robotics: Science and Systems (RSS), 2007

  However, the device described in Patent Document 1 may not be able to accurately identify the position of the host vehicle if detection of the feature points of the road marking is difficult due to the influence of the environment at the time of shooting. In particular, the device described in Patent Document 1 extracts the end point of a road marking or the like as a feature point and determines the current position of the vehicle using the feature point, so the end point of the road marking Even if the position is slightly deviated, the positions of the extracted feature points are shifted, which causes a decrease in the detection accuracy of the position of the host vehicle.

  Further, although the device described in Patent Document 2 uses an image taken near the reference point of the map for specifying the position of the vehicle, the building in the vicinity of the reference point is reconstructed or the environment at the time of shooting (for example, Depending on the weather, shooting time zone, etc.), even if the image was taken at the same place, it is shown in the image taken at the time of pre-registration and in the image taken at the time of detection of the vehicle position. The scenery can vary greatly. In such a case, there is a high possibility that the matching between the images fails, and therefore, there is a possibility that the position of the vehicle can not be accurately identified.

  Furthermore, the method described in Patent Document 3 utilizes template matching. In template matching, it is necessary to repeatedly perform matching calculations while changing the position between the image to be compared and the template, so the amount of calculation required to detect the position of the host vehicle is large. Further, in the method described in Non-Patent Document 1, different algorithms are used for detecting a curb and detecting a road marking, and since stereo images are used for detecting them, the amount of calculation is large. Therefore, in these methods, hardware resources necessary for detecting the position of the own vehicle increase, or time is required for detecting the position of the own vehicle, so that the update interval of the position of the own vehicle becomes long. . Furthermore, in the method described in Non-Patent Document 2, a laser ranging system is required to detect the position of the host vehicle, and the cost of the entire system is increased.

  Then, this invention aims at providing the vehicle position detection apparatus which can estimate the position of the own vehicle correctly with low processing load, the vehicle position detection method, and the computer program for vehicle position detection.

According to the first aspect of the present invention, a vehicle position detecting device is provided as one aspect of the present invention. The vehicle position detection device includes a storage unit (41) that stores the position of a line marked on the road and map information representing the type of the line, and the current position of the vehicle estimated from the position immediately before the vehicle (10). A line marked on the road is extracted from the map information according to the predicted position at the time, and for each of the extracted lines, a particle representing a change in luminance in a direction crossing the line according to the type of the line With respect to each of the plurality of particles for each of the particle generation unit (23) that generates a plurality of positions while changing the position according to the direction along the line, and changing the predicted position within an expected error range A projection unit (24) which finds a position based on the vehicle (10) and projects the image at the current time obtained by the imaging unit (2) mounted on the vehicle (10) according to the position A selection unit (25) for selecting a particle having a predetermined degree of coincidence with the image among a plurality of particles for each of the extracted lines; And a position updating unit (26) for obtaining an estimated position of the vehicle (10) in accordance with the sum of errors when projected onto a corresponding road on the basis of the estimated position of 10).
The vehicle position detection device according to the present invention can accurately estimate the position of the host vehicle with low processing load by having the above configuration.

Further, according to the second aspect of the present invention, the position updating unit (26) makes it possible to minimize the sum of errors when projecting each of the selected particles onto a line marked on the corresponding road. Preferably, the estimated position of 10) is determined.
By having this configuration, the vehicle position detection device can estimate the position of the host vehicle more accurately.

According to the third aspect of the present invention, the position updating unit (26) adds the sum of the errors when projecting each of the selected particles onto the line marked on the corresponding road, and the time of the past plural times. The current time is calculated so that the sum of the error between the position of the vehicle at the next time predicted from the estimated position of the vehicle (10) and the estimated position of the vehicle at the next time is minimized. It is preferable to obtain the estimated position of the vehicle (10) at each of a plurality of past times.
With this configuration, the vehicle position detection device also uses odometry information, so that the position of the host vehicle can be estimated more accurately.

Furthermore, according to the fourth aspect of the present invention, the particle generation unit (23) displays a mark on the road corresponding to the case where there is a dotted line or a broken line block if the extracted line type includes a dotted line or a broken line. Create a first particle representing the change in brightness across the line being drawn and a second particle representing the change in brightness across the line marked on the road that corresponds in the absence of the dotted or dashed block It is preferable to do.
With this configuration, the vehicle position detection device can generate particles that are highly likely to coincide with a line that is actually marked on the road.

Furthermore, according to the fifth aspect of the present invention, the imaging unit (2) is a stereo camera including two cameras, and the selection unit (25) is a unit obtained at the current time by one of the two cameras. It is preferable to select particles in which the coincidence degree satisfies the coincidence condition on one image and the coincidence degree satisfies the coincidence condition on the second image obtained at the current time by the other of the two cameras.
With this configuration, the vehicle position detection device can reduce the possibility of erroneously selecting a particle projected on a road surface hidden by occlusion by another vehicle or the like.

According to the description of claim 6, a vehicle position detection method is provided as another embodiment of the present invention. This vehicle position detection method extracts the line marked on the road from the map information according to the predicted position at the current time of the vehicle estimated from the position immediately before the vehicle (10), and for each of the extracted lines Generating a plurality of particles representing a change in luminance in a direction crossing the line according to the type of the line represented in the map information, changing the position according to the direction along the line, and extracting the line For each of a plurality of particles for each of the above, the position based on the vehicle (10) is determined while changing the predicted position within the assumed error range, and the imaging unit mounted on the vehicle (10) according to the position The step of projecting onto the image at the current time obtained by (2), and among the plurality of particles for each of the extracted lines, the degree of coincidence with the image is a predetermined one According to the sum of the errors when selecting the particles that satisfy the conditions and projecting each of the selected particles on a line marked on the corresponding road based on the estimated position of the vehicle (10) at the current time Determining the estimated position of the vehicle (10).
The vehicle position detection method according to the present invention can accurately estimate the position of the host vehicle with low processing load by having the above configuration.

According to the sixth aspect of the present invention, a computer program for detecting a vehicle position is provided as another aspect of the present invention. The computer program for vehicle position detection extracts the line marked on the road from the map information according to the predicted position at the current time of the vehicle estimated from the position immediately before the vehicle (10) In each of the steps, according to the type of the line represented in the map information, a plurality of particles representing a change in luminance in the direction crossing the line are generated while changing positions corresponding to the direction along the line; For each of a plurality of particles for each of the above-mentioned lines, the position based on the vehicle (10) is determined while changing the predicted position within an assumed error range, and mounted on the vehicle (10) according to the position The step of projecting on the image at the current time obtained by the imaging unit (2), and the image among the plurality of particles for each of the extracted lines When the step of selecting a particle whose coincidence degree satisfies a predetermined coincidence condition and each of the selected particles is projected on a line marked on the corresponding road based on the estimated position of the vehicle (10) at the current time Determining an estimated position of the vehicle (10) in accordance with the sum of the errors of (1) and (2), and instructing the processor (43) mounted on the vehicle (10) to execute.
The computer program for detecting a vehicle position according to the present invention has the above configuration, so that the position of the host vehicle can be accurately estimated with a low processing load.

  The reference numerals in parentheses attached to the above-described portions are an example showing the correspondence with specific means described in the embodiments to be described later.

1 is a schematic configuration diagram of a vehicle position detection system according to an embodiment of the present invention. It is a figure which shows the relationship of a map coordinate system, a vehicle coordinate system, and a camera coordinate system. (A)-(d) is a figure which shows an example of map information. It is a functional block diagram of the control part of a vehicle position detection system. It is a figure which shows an example of a particle in case the kind of map line segment is "white solid line (thin)." It is a figure which shows an example of a particle in case the kind of map line segment is "white solid line (thin) + right deceleration mark." It is a figure which shows an example of a particle in case the kind of map line segment is a "white dotted line (thin) + both sides deceleration sign." It is a figure which shows an example of the image which each particle projected. It is a figure showing an example of an error ellipse equivalent to a covariance matrix about each selected particle in a vehicle coordinate system. It is an operation | movement flowchart of a vehicle position detection process. It is a figure which shows an example of the relationship between the particle produced | generated by a modification, and the line marked on the road.

Hereinafter, the vehicle position detection system will be described with reference to the drawings.
This vehicle position detection system refers to map information including information on the type of line marked on the road such as a dividing line or a road marking, and estimates the predicted position at the current time estimated from the position of the own vehicle immediately before A plurality of particles having a luminance profile representing a luminance change in a direction crossing the line according to the type of the line are generated along a line on the map around the area. Then, the vehicle position detection system converts each particle represented by the coordinate system on the map into a position in the coordinate system based on the vehicle according to the predicted position and the predicted direction at the current time of the vehicle. Project onto an image obtained by a camera mounted on a vehicle. Then, the vehicle position detection system selects particles among the particles projected on the image that satisfy the predetermined coincidence condition with the image, and the projection error of the selected particles onto the line on the map is small. Thus, the position and orientation of the vehicle at the current time are estimated.

  FIG. 1 is a schematic block diagram of a vehicle position detection system according to one embodiment. As shown in FIG. 1, a vehicle position detection system 1 is mounted on a vehicle 10 and has a camera 2 and a controller 4. The camera 2 and the controller 4 are connected to each other by a control area network (hereinafter referred to as CAN) 3. In addition, in FIG. 1, for convenience of description, each component of the vehicle position detection system 1 and the shape, size, and arrangement of the vehicle 10 are different from actual ones.

  The camera 2 is an example of an imaging unit, captures an area in front of the vehicle, and generates an image of the area in front of the vehicle. For that purpose, the camera 2 is a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as a CCD or C-MOS, and the ground existing ahead of the vehicle 10 on the two-dimensional detector. Alternatively, an imaging optical system that forms an image of a structure or the like is included. The camera 2 is disposed, for example, in the compartment of the vehicle 10 such that the optical axis of the imaging optical system is substantially parallel to the ground and faces the front of the vehicle 10. Then, the camera 2 captures an image at predetermined time intervals (for example, 1/30 seconds) and generates a color image obtained by capturing an area in front of the vehicle 10. The camera 2 may have a two-dimensional detector having sensitivity to near-infrared light, and may generate a monochrome image according to the illuminance of the near-infrared light within the imaging range.

FIG. 2 is a diagram illustrating the relationship among the map coordinate system, the vehicle coordinate system, and the camera coordinate system. In this embodiment, a map coordinate system (Xm, Ym, Zm) whose origin is an arbitrary position on the map, a vehicle coordinate system (Xv, Yv, Zv) whose origin is the vehicle 10, and the camera 2 are provided for convenience. Use the camera coordinate system (Xc, Yc, Zc) as the origin. In the present embodiment, the vehicle coordinate system (Xv, Yv, Zv) uses the middle point between the left and right rear wheels of the vehicle 10 and the point on the ground as the origin. A traveling direction of the vehicle is taken as a Zv axis, a direction perpendicular to the Zv axis, a direction parallel to the ground is taken as an Xv axis, and a vertical direction is taken as an Yv axis. Also in the map coordinate system (Xm, Ym, Zm), the Xm axis and the Zm axis are set in a plane parallel to the ground without inclination, and the Ym axis is set in the vertical direction with respect to the ground. In the camera coordinate system (Xc, Yc, Zc), the center of the imaging plane at a position above the origin of the vehicle coordinate system along the vertical direction and at the height at which the camera 2 is installed, for simplicity of explanation. It is assumed that the center of the imaging plane is the origin. Then, as in the vehicle coordinate system, the traveling direction of the vehicle 10 is taken as the Zc axis, the direction orthogonal to the Zc axis, parallel to the ground is taken as the Xc axis, and the vertical direction is taken as the Yc axis.
Although the position where the camera 2 is actually attached may be offset from above the middle point between the left and right rear wheels of the vehicle 10, this offset may be corrected by a simple parallel movement.

  The vehicle position detection system 1 may have, as an imaging unit, a rear camera for imaging the rear area of the vehicle, instead of or together with the camera for imaging the front area of the vehicle 10.

  The camera 2 sequentially transmits the generated images to the controller 4. In addition, when the camera which image | photographs the front area | region of the vehicle 10, and the camera which image | photographs the back area | region of the vehicle 10 are attached, the controller 4 selects only the image from the camera which image | photographs the direction which the vehicle 10 is advancing. May be acquired automatically. To that end, the controller 4 obtains a shift position signal representing the position of the shift lever from the electronic control unit (ECU) 11 of the vehicle 10 via the CAN 3. Then, when the shift position signal indicates a drive position or the like indicating that the vehicle 10 moves forward, the controller 4 acquires an image from a camera that captures an area in front of the vehicle 10. On the other hand, when the shift position signal is in the reverse position indicating that the vehicle 10 moves backward, the controller 4 obtains an image from a camera that captures an area behind the vehicle 10.

  The controller 4 is an example of a vehicle position detection device, and includes a storage unit 41, a communication unit 42, and a control unit 43. The storage unit 41 includes, for example, semiconductor memories such as electrically rewritable non-volatile memory and volatile memory. The storage unit 41 stores various programs for controlling the vehicle position detection system 1, map information, camera position information such as height from the ground of the camera 2 and optical axis direction, focal length and angle of view of the imaging optical system. And various parameters such as camera parameters, and temporary calculation results by the control unit 43. In addition, the storage unit 41 is a parameter for correcting distortion by the imaging optical system of the camera 2, for example, a correction amount of distortion for each pixel (that is, a movement amount of pixels on an image for canceling distortion). And the moving direction) may be stored.

Hereinafter, map information used for vehicle position detection will be described.
Fig.3 (a)-FIG.3 (d) are figures which show an example of map information. The map information 300 shown in FIG. 3A is associated with latitude / longitude information indicating the position of the area represented by the map information. The map information 300 includes information related to the line 301 marked on the road such as a lane marking represented by a white line, a yellow line, or the like.

There are multiple types of lines marked on the actual road. For example, a line 311 indicated by a dotted line in FIG. 3B is represented by a combination of a solid white line and a broken line decelerating mark provided on one side. A line 312 indicated by a dotted line in FIG. 3C is represented by a combination of a dotted white line and deceleration signs provided on both sides thereof. Further, the line 313 indicated by a dotted line in FIG. 3D is represented only by a relatively thick solid white line. Thus, there are various types of lines that are marked on the road. However, in the map information 300, for example, a line on each road may be represented by one solid line, and each line may be labeled to indicate the type of the line. For example, in the example illustrated in FIG. 3B, the line 311 is represented by a solid line 321 and a label of (white line (thin) + right deceleration mark). Further, in the example shown in FIG. 3C, the line 312 is represented by a solid line 322 and a label (white dotted line (thin) + both-side deceleration sign). In the example shown in FIG. 3D, the line 313 is represented by a solid line 323 and a label of a white line (thick). Furthermore, in the map information 300, for each line marked on the road, three-dimensional coordinates of both end points thereof are included.
In addition, below, the line marked on the road included in map information is called a map line segment.

  The communication unit 42 includes a communication interface that communicates with the various sensors such as the camera 2, the ECU 11 and a wheel speed sensor (not shown), the CAN 3, and a control circuit thereof. Then, the communication unit 42 receives an image from the camera 2 and passes the image to the control unit 43. In addition, the communication unit 42 acquires the speed and movement amount of the vehicle 10 from the ECU 11 as odometry information or acquires the wheel speed from the wheel speed sensor as odometry information for each cycle in which the position estimation process is performed. Pass to section 43.

The control unit 43 includes one or a plurality of processors (not shown) and their peripheral circuits. Then, the control unit 43 controls the entire vehicle position detection system 1.
FIG. 4 shows a functional block diagram of the control unit 43. As shown in FIG. As shown in FIG. 4, the control unit 43 includes an initial value setting unit 21, a predicted position calculation unit 22, a particle generation unit 23, a projection unit 24, a selection unit 25, and a position update unit 26. Each of these units included in the control unit 43 is implemented as a functional module realized by a computer program executed on a processor included in the control unit 43, for example.

The initial value setting unit 21 sets an initial value of the position of the host vehicle at the start of the detection of the position of the vehicle 10, that is, the detection of the position of the host vehicle according to the present embodiment. For example, the initial value setting unit 21 acquires, for example, from the navigation system, the position obtained from the positioning signal when the GPS positioning signal was finally received, and, based on the position, the initial position of the vehicle. Set the value Then, the obtained position and direction are set to the initial value of the position of the host vehicle.
Note that the initial value set by the initial value setting unit 21 may be a value obtained with detection accuracy lower than the detection accuracy of the position of the host vehicle according to the present embodiment.

In the present embodiment, the initial value μ _t = (x _t , z _t , θ _t ) ^t of the position of the vehicle at time t is represented by the following equation according to the Gaussian distribution.
Here, (x _t , z _t ) is the position of the vehicle 10 in the x and z directions in the map coordinate system obtained from the positioning signal etc., where t is the time to calculate the initial value, ie, Represents the position of the host vehicle. θ _t represents the direction of the vehicle 10 at time t. Note that the direction of the vehicle 10 is, for example, that the control unit 43 receives, via the CAN 3 and the communication unit 42, a signal from a sensor (not shown) that measures the direction of the traveling direction of the vehicle 10 that the vehicle 10 has. Obtained by Alternatively, the control unit 43 may use, for example, the navigation system, the heading of the subject vehicle calculated from the change in the position of the subject vehicle obtained from the positioning signal of the GPS received at different times immediately before starting detection of the position of the subject vehicle. You may receive from. Further, in equation (1), Σ _t is a covariance matrix. Further, the position in the vertical direction, that is, the altitude y _t is not included in the equation (1), but can be calculated by the following equation.
Here, a _x ^t , a _z ^t , and a _c ^t are each a constant, for example, assuming that the circumference of map coordinates (x _t , z _t ) is a plane, map coordinates (x _t , z _When the map coordinates (x _i , y _i , z _i ) of each point at equal intervals on each map line segment included in a predetermined range (for example, within 10 m) around _t ) are substituted in the equation (2) For example, the least square method is used so that the square error is minimized.

  The initial value of the position of the host vehicle set by the initial value setting unit 21 is stored in the storage unit 41.

The predicted position calculation unit 22 predicts the own vehicle at the current time based on the initial value of the position of the own vehicle or the position of the own vehicle immediately before obtained by the position update unit 26, the wheel speed of the vehicle 10, and the like. Calculate the position.
In the present embodiment, the predicted position of the host vehicle at the current time t is expressed as a Gaussian distribution with an average value μ _p ^t and a covariance Σ _p ^t . Therefore prediction position calculation unit 22, according to the following equation, the covariance and the average value mu _p ^t = predicted azimuth and predicted position in the horizontal direction of the vehicle at the current time ^{_{t (x p t, z p}} t, θ p t) Calculate the matrix _{p p} ^t .
Here, the Gaussian distribution represented by the average value μ _t-1 and the covariance Σ _t-1 represents the estimated position of the vehicle at time (t-1). If the current time t is the first time when the control unit 43 detects the position of the host vehicle, N (x _{t -1} , z _{t -1} , θ _{t -1} | μ _{t -1} , _{t t-1} ) is The initial value of the position of the host vehicle set by the initial value setting unit 21. In addition, when the control unit 43 detects the vehicle position at time (t-1), N (x _t-1 , z _t-1 , θ _t-1 | μ _t-1 , _{t t-1} ) Is the estimated position of the host vehicle detected by the control unit 43 at time (t-1).

In equation (3), u _t = (v _t , ω _t ) ^t represents a control input determined from the wheel speed. v _t is the speed of the vehicle 10 at the present time t, and the latest right rear wheel wheel speed v ^R _t and left rear received from the wheel speed sensors attached to the left and right rear wheels via the communication unit 42 The average value (v ^R _t + v ^L _t ) / 2 of the wheel speed v ^L _t of the wheel is calculated. Further, ω _t is an angular velocity of the vehicle 10 at the current time t, and is ωt = (v ^R _t −v ^L _t ) / 2da. da is the distance between the left and right rear wheels.
Δt is a time interval between the current time t and the immediately preceding time (t−1), that is, a time interval at which the control unit 43 performs the detection processing of the host vehicle position. Matrix Q _t represents the degree of error contained in the predicted position of the vehicle by the rear wheel speed. The elements σ _x , σ _z , and σ _θ of the matrix Q _t are the standard deviation of the position error in the Xm direction, the standard deviation of the position error in the Zm direction, and the standard deviation of the orientation error in the map coordinate system, respectively. Correspondingly, for example, σ _x = σ _z = 1 (m) and σ _θ = 10 (°) are set.
The predicted position calculation unit 22 may calculate the altitude y _t of the host vehicle at the current time t, for example, according to the equation (2).

The predicted position calculation unit 22 stores μ _p ^t and Σ _p ^t in the storage unit 41.

  The particle generation unit 23 is a particle that is a luminance pattern having a luminance profile that represents a luminance change in a direction across the map line segment included in the shooting range of the camera 2 at the predicted position based on the predicted position of the vehicle 10 at the current time. Are generated according to the type of the map line segment included in the map information.

  In the present embodiment, the particle generation unit 23 sets the generation range and density of the particles appropriately in a predetermined range around the predicted position (for example, within 30 m) and the camera 2 with the predicted position as a reference. Each map line segment within the imaging range is extracted from the map information, and each extracted map line segment is projected onto an image obtained by the camera 2. In addition, for the map line segment where one end is within the predetermined range and the photographing range and the other end is out of the predetermined range or the photographing range, the particle generating unit 23 determines the boundary between the predetermined range and the photographing range. The map line segment is projected onto the image, with the point intersecting with the near side from the predicted position as the other end of the map line segment. Hereinafter, since the same process is performed on each map line segment, the r-th map line segment will be described as an example.

The relationship between a point p _m = (x _m , y _m , z _m ) on the map represented by the map coordinate system and a point u _c = (u, v) on the image is represented by the following equation.
Here, p _v is a point of the vehicle coordinate system corresponding to the point p _m, p _c is a point in the camera coordinate system corresponding to the point p _m. The matrix {R _slope ^t R _vm ^t } represents a rotation component in the coordinate transformation from the vehicle coordinate system to the map coordinate system at time t. Here, the rotation matrix R _slope ^t representing the rotation component of the roll pitch is calculated from (a _x ^t , a _z ^t , a _c ^t ) in equation (2). The translation matrix t _vm ^t = (x _vm ^t , y _vm ^t , z _vm ^t ) represents a translation component in coordinate conversion from the vehicle coordinate system to the map coordinate system at time t. And h (p _c , k _c ) represents the relationship with the point u _c on the image obtained by the camera 2 from the point p _c = (x _c , y _c , z _c ) in the camera coordinate system, and k _c is , Represents the transformation parameters from the camera coordinate system to the image. When the distortion aberration of the camera 2 can be ignored, h (p _c , k _c ) is expressed by the following equation.

The particle generation unit 23 sets (x _vm ^t , z _vm ^t , θ _vm ^t ) based on μp _t, and according to the equation (4), both end points (m _s ^r , m _{e of the} r-th map line segment ^{Project r} ) onto the image obtained by the camera 2. Then, the particle generation unit 23 obtains the length l _img ^r of the map line segment on the image. The particle generation unit 23 divides each of the positions obtained by equally dividing the length l _img ^r of the map line segment by the total number of particles (for example, 500 to 1000) to be generated per one map line segment. It is a candidate for the position to be generated. The particle generator 23 randomly selects a predetermined number of candidates from each candidate according to a uniform distribution. Then, the particle generation unit 23 generates particles at three-dimensional positions in the map coordinate system corresponding to the selected candidate. Alternatively, the particle generator 23 may generate particles for all candidates.

  The particle generation unit 23 determines the type of particle according to the type of map line segment that generates the particle. The type of map line segment is included in the map information as described above. At this time, depending on the type of map line segment, the particle generation unit 23 generates a plurality of types of particles according to the probability according to the type of particles.

  FIG. 5 is a view showing an example of the particle in the case where the type of map line segment is "white line (thin)". In FIG. 5, the horizontal axis represents a position along the direction orthogonal to the map line segment, with the position of the white line being a solid line as the origin, and the vertical axis represents luminance. A profile 500 represents a luminance profile of particles to be generated. When the type of map line segment is "white line (thin)", one white line is marked on the road, so the map line segment is crossed regardless of the position in the direction along the map line segment. The luminance profile in the direction does not change. Therefore, in this case, the particle generation unit 23 has a high luminance only in the central portion corresponding to the position of the white line represented by the profile 500 and having the same width as the width of the white line with the occurrence probability p1 = 1.0. And generate particles with low brightness on both sides.

  FIG. 6 is a view showing an example of the particle in the case where the type of map line segment is “white line (thin) + right deceleration mark”. In FIG. 6, the horizontal axis represents a position along the direction orthogonal to the map line segment, with the position of the white line which is a solid line as the origin, and the vertical axis represents luminance. Profiles 600 and 610 respectively represent luminance profiles of particles to be generated. When the type of map line segment is "white line (thin) + right deceleration mark", not only one white line but also a broken line that is a deceleration mark is displayed on the road, so Depending on the position in the different direction, the brightness profile in the direction crossing the map line segment changes depending on the presence or absence of the block of the deceleration marking. Therefore, in this case, the particle generation unit 23 corresponds to the position of the white line, which corresponds to the case where only the white line exists, represented by the profile 600, with the occurrence probability p1 = 0.4, and the width of the white line. In the case where a central portion having the same width has high luminance and both sides generate particles with low luminance, and there is a block of deceleration marking with a white line represented by profile 610 with occurrence probability p2 = 0.6 The particle having a relatively high brightness is generated at two positions corresponding to the white line and the position corresponding to the block of the deceleration marking. The occurrence probabilities p1 and p2 are preset according to the ratio of the block length of the deceleration marking and the length between the blocks.

  FIG. 7 is a view showing an example of the particle in the case where the type of the map line segment is "white dotted line (thin) + both-side deceleration sign". In FIG. 7, the horizontal axis represents a position along the direction orthogonal to the map line segment, with the position of the white dotted line as the origin, and the vertical axis represents luminance. Profiles 700 to 720 respectively represent luminance profiles of particles to be generated. When the type of map line segment is "white dotted line (thin) + both-side deceleration marking", not only one white dotted line but also broken lines that are deceleration markings are displayed on the road on both sides of the white dotted line Therefore, depending on the position in the direction along the map line segment, the brightness profile in the direction crossing the map line segment changes depending on the presence or absence of the white dotted block and the presence or absence of the deceleration marking block. Therefore, in this case, the particle generation unit 23 is high only in the central portion corresponding to the white dotted line, which corresponds to the case where only the white dotted line block represented by the profile 700 exists at the occurrence probability p1 = 0.3. Produces particles that have luminance and low luminance on both sides. Further, the particle generation unit 23 corresponds to the block of the white dotted line and the block of the deceleration sign corresponding to the case of the block of the deceleration sign with the block of the white dotted line represented by the profile 710 with the occurrence probability p2 = 0.2. Generate particles with relatively high brightness at three locations. The particle generation unit 23 has high luminance at two locations corresponding to the block of the deceleration marking, which corresponds to the case where only the block of the deceleration marking represented by the profile 720 exists with the occurrence probability p3 = 0.5. Generate particles. The occurrence probabilities p1 to p3 are preset according to the ratio of the block length of the white dotted line to the length between the blocks and the ratio of the block length of the deceleration marking to the length between the blocks.

  The particle generation unit 23 passes the generated particles to the projection unit 24.

The projection unit 24 projects each particle onto the image obtained at the current time by the camera 2. When the execution cycle of the vehicle position detection process and the shooting cycle of the camera 2 are not synchronized, the latest image obtained by the camera 2 may be the image obtained at the current time. At this time, the projection unit 24 takes the predicted position and the predicted direction for each particle according to the normal distribution represented by the covariance matrix at the time of calculating the predicted position in consideration of the uncertainty of the predicted position of the vehicle 10. Fix it. For example, the corrected predicted position and predicted direction μ _q ^ti = (x _q ^ti , z _q ^ti , θ _q ^ti ) are expressed by the following equations.
Here, ε ⁱ represents the correction amount of the predicted position and the predicted direction for the i-th particle, and is obtained by inputting a random number generated for each particle in the normal distribution N (0, _{p p} ^t ).

The projection unit 24 calculates the position of each particle in the vehicle coordinate system based on the corrected predicted position and predicted direction according to the following equation.
Here, g ⁱ represents the position of the ith particle in the map coordinate system (for example, the positions of both end points of the particle or the position where the luminance value changes on the particle), and q ⁱ is the ith Represents the position of the particle in the vehicle coordinate system. Further, the rotation matrix R _mv ^ti is a rotation component in coordinate conversion from the map coordinate system to the vehicle coordinate system at time t, and is determined based on the corrected predicted orientation θ _q ^ti for the i-th particle. Similarly, the translation matrix t _mv ^ti is a translation component in the coordinate transformation from the map coordinate system to the vehicle coordinate system at time t, and the corrected predicted position (x _q ^ti , z _q for the ith particle) It is determined based on ^ti ).

  The projection unit 24 projects each particle represented by the position on the vehicle coordinate system onto the image obtained by the camera 2 at time t according to the equation (5).

  FIG. 8 is a view showing an example of an image on which each particle is projected. In the image 800 shown in FIG. 8, for each of the white lines 801 to 803 on the road, a plurality of particles 810 are projected so as to intersect the white lines. In this example, the particle generation unit 23 generates up to 1000 particles for each white line. It can be seen from the particle 810 that the position in the direction orthogonal to the white line and the angle formed with the white line change little by little. In each particle 810, a relatively white portion indicates relatively low luminance, and a relatively black portion indicates relatively high luminance.

  The projection unit 24 passes each particle projected on the image to the selection unit 25.

  The selection unit 25 calculates, for each of the particles projected on the image, an evaluation value representing the degree of coincidence with the image. Then, the selection unit 25 selects particles whose evaluation value satisfies a predetermined match condition.

  For example, for each particle, the selection unit 25 calculates a normalized cross-correlation value between the luminance value at a predetermined number (for example, 50 points) on the luminance profile of the particle and the luminance value at the corresponding position of the image. Calculated as an evaluation value. Then, the selection unit 25 selects a particle whose evaluation value is equal to or more than a predetermined threshold value (for example, 0.8) as the matching condition is satisfied. The predetermined threshold value is obtained by, for example, multiplying the maximum evaluation value by a predetermined number less than 1 (for example, 0.8) so that a certain number of particles or more are selected even if the image quality is poor. It may be a value.

  Alternatively, the selection unit 25 may select a predetermined number of particles (for example, 1/5 to 1/10 of the total number of generated particles) in order from the highest evaluation value as the matching condition.

  The selection unit 25 may calculate an error sum of squares (SSD) or an error absolute sum (SAD) as an evaluation value instead of calculating the normalized cross-correlation value for each particle. In this case, the selecting unit 25 selects a particle whose evaluation value is equal to or less than a predetermined threshold value as the matching condition is satisfied.

The selection unit 25 estimates a position detection error for each selected particle. The detection error of the position for the i-th particle includes, for example, an error component due to distortion aberration of the imaging optical system of the camera 2 on the image, or an error component due to being divided in pixel units. _It shall be represented by _I ⁱ . The covariance matrix R _I ⁱ is represented by, for example, the following equation when it is assumed that the second order is larger as the distance from the center of the image, ie, the optical axis of the camera 2 increases.
Here, n ⁱ = (n _u ⁱ , n _v ⁱ ) (n _u ⁱ = (c _u -u ⁱ ) / f _u , n _v ⁱ = (c _v -v ⁱ ) / f _v ) is a normalization Represents the center position on the image of the i-th particle in the camera coordinate system. Note that (u ⁱ , v ⁱ ) is the center coordinate of the ith particle on the image, and (c _u , c _v ) is the center coordinate on the image, (f _u , f _v ) Is a parameter representing the focal length of the camera 2. c1 and c2 are constants according to the distortion of the imaging optical system of the camera 2 and the like, and are set to c1 = 0.001 and c2 = 0.005, for example. Also, I is a 2-by-2 identity matrix.

The selection unit 25 converts, for each selected particle, the covariance matrix of the detection error on the image into a covariance matrix in the vehicle coordinate system. In this case, the selection unit 25 can calculate the covariance matrix R _q ^{i at} the position q ⁱ of the particle in the vehicle coordinate system as a bird's-eye view transformation of the covariance matrix R _I ⁱ of the corresponding detection error on the image. . This bird's-eye-view conversion is expressed, for example, by the following equation.
Here, it is assumed that the optical axis direction of the camera 2 is attached so as to be parallel to the road surface. Further, yc represents the height from the road surface to the camera 2. In this example, components related to the y axis of the vehicle coordinate system that are unrelated to the estimation of the position of the vehicle 10 are omitted. At this time, the covariance matrix R _q ⁱ is expressed by the following equation.
Here, B is a Jacobian.

FIG. 9 is a diagram illustrating an example of an error ellipse corresponding to the covariance matrix R _q ⁱ for each selected particle in the vehicle coordinate system. In FIG. 9, the horizontal axis represents the position in the direction orthogonal to the traveling direction of the vehicle 10, and the vertical axis represents the distance from the vehicle 10 along the traveling direction of the vehicle 10. In addition, it is assumed that the upper side is away from the vehicle 10. Each ellipse 901 corresponds to a covariance matrix R _q ⁱ corresponding to one particle. The center point 902 of each ellipse 901 represents the center position of the corresponding particle. As shown in FIG. 9, it can be seen that the error ellipse 901 becomes larger as the position of the particle moves away from the vehicle 10.

The selection unit 25 transmits the position q ⁱ and the covariance matrix R _q ⁱ in the vehicle coordinate system of the center position of the selected particle and the corresponding map line number to the position update unit 26 for each of the selected particles.

  The position update unit 26 estimates the position of the vehicle 10 at the current time based on the estimated position of the vehicle 10 at the latest one or more times and the selected particles at the current time.

For example, the position update unit 26 calculates the evaluation value E according to the following equation, and calculates the estimated position of the vehicle at the latest one or more times and the current time so that the evaluation value E becomes minimum.
Here, time tε {τ _{s to} τ _e } is a time for estimating the position of the vehicle 10, and τ _e corresponds to the current time t. μ ^t and μ ^t−1 represent the estimated positions of the vehicle 10 at times t and (t−1), respectively. Incidentally, in the calculation of the evaluation value E, for mu ^t-1, the estimated position of the vehicle 10 determined in the preceding time (t-1) is input. That is, μ ^t-1 is treated as a known constant. U ^t is odometry information corresponding to u _t in equation (3). And, δ _x (μ ^t , μ ^{t -1} , u ^t ) represents an error in the prediction of the position of the vehicle 10 by odometry, and is expressed by the following equation from equation (3).
It is to be noted that the function g (μ ^t-1 , u ^t ) is the equation (3) except that the input variables are the estimated position of the vehicle 10 at time (t-1) and the odometry information at time t. It is the same function as the function g (μ _t-1 , u _t ). That is, the first term on the right side of the equation (11) represents the sum of squares of the error in predicting the position of the vehicle 10 based on the odometry information.

Further, δ _I (μ ^cj , q ^j , χ ^rj ) in the second term of the right side is the time c j (that is, the time corresponding to the selected j-th particle), and any of the times τ _{s to} τ _e at the estimated position mu ^cj of the vehicle 10), j-th (j∈ {1, ..., I }, I is the map segment r ^j particles total) selected at the time τ _s ~τ _e Represents the projection error in the map coordinate system when the particle q ^j is projected onto the map line segment r ^j using the estimated position μ ^cj . That is, the second term represents the sum of squares of the projection error for the selected particle. Here, cj represents the time corresponding to the number j. Also, R _δ ^j represents a covariance matrix of errors in the map coordinate system. The projection error δ _I (μ ^cj , q ^j , χ ^rj ) and the covariance matrix R _δ ^j are expressed by the following equations.
Here, χ _x , χ _z , and χ _c are coefficients and constants when the map line segment in the map coordinate system is expressed by a linear equation, and the linear equation is expressed by the following equation.
Note that x _m and z _m are coordinate values in the x _m direction on the map coordinate system and coordinate values in the z _m direction.

The position updating unit 26 calculates the estimated position {μ ^τs ,..., Μ ^τe } of the vehicle 10 at each time so that the evaluation value E is minimized. That is, in the equation (11), the first term μ ^t and the second term μ ^cj are variables. At that time, the position update unit 26 applies, for example, the gradient method, the Levenberg-Markert method, or the Newton method to the equation (11) to estimate the estimated position {μ ^τs,. We can calculate ^{τ e} }. Alternatively, the position update unit 26 calculates the estimated position {μ ^τs ,..., Μ ^τe } of the vehicle 10 at each time by applying the RANSAC method or a robust estimation method such as M estimation to equation (11). May be As a result, the position updating unit 26 can obtain the minimum value of the evaluation value E so that the evaluation value E does not become a local solution by particles having multimodality.

The position update unit 26 stores the estimated position {μ ^τs ,..., Μ ^τe } of the vehicle 10 at each time obtained in the storage unit 41.

  FIG. 10 is an operation flowchart of the vehicle position detection process. The vehicle position detection system 1 estimates the position of the host vehicle according to the operation flowchart shown below, for example, for each shooting cycle of the camera 2 at predetermined cycles.

  The predicted position calculation unit 22 calculates the predicted position of the host vehicle at the current time t based on the position of the host vehicle at the previous time (t-1) and the odometry information (step S101). The position of the host vehicle at the previous time (t-1) is the initial value of the position of the host vehicle set by the initial value setting unit 21 when the vehicle position detection process performed at the current time t is the first process. . On the other hand, when the vehicle position detection processing has already been performed at the previous time (t-1), the position of the host vehicle is obtained by the position update unit 26 at the previous time (t-1).

  The particle generation unit 23 extracts, based on the map information, map line segments included in a predetermined range from the predicted position and within the imaging range of the camera 2 (step S102). Then, the particle generation unit 23 generates, for each of the extracted map line segments, a plurality of particles having a luminance profile in a direction crossing the map line segment according to the type of the map line segment along the map line segment (step S103). ).

  The projection unit 24 projects each particle onto the image at the current time obtained by the camera 2 in consideration of the fluctuation of the position due to the error of the predicted position of the vehicle 10 (step S104).

  The selection unit 25 calculates, for each particle projected on the image, an evaluation value representing the degree of coincidence between the particle and the image, and selects a particle whose evaluation value satisfies a predetermined coincidence (step S105). Then, the selection unit 25 calculates, for each of the selected particles, a covariance matrix representing a detection error in the vehicle coordinate system (step S106).

  The position updating unit 26 sums the errors between the estimated positions at a plurality of times in the past and the predicted positions of the vehicle based on the odometry information, and the sum of projection errors of the selected particles calculated based on the detection errors. The estimated position of the vehicle at each time is updated so as to minimize the evaluation value E based on the sum of (step S107). And the control part 43 complete | finishes a vehicle position detection process.

  As described above, the vehicle position detection system can detect the position of the host vehicle without the process of repeatedly trying like template matching. Therefore, this vehicle position detection system can suppress processing load. The vehicle position detection system also generates a plurality of particles having a luminance profile in the direction crossing the line marked on the road around the vehicle, projects it onto the actually captured image, and matches it with the image Since the position of the vehicle is updated using particles with a good degree, the position of the vehicle can be accurately detected. Furthermore, the vehicle position detection system refers to the map information and generates particles according to the type of line marked on the road around the vehicle, so that it matches the line actually marked on the road Probable particles can be generated. Therefore, since this vehicle position detection system can increase the number of particles useful for estimating the vehicle position, it is possible to improve the estimation accuracy of the vehicle position.

  Note that according to the modification, the particle generation unit 23 may generate particles in which the line thickness or the interval between the lines are different from each other for each of the map line segments to be particle generation targets. This is because the thickness of the line (white line, deceleration line, etc.) marked on the road may fluctuate within the range defined by the road standard, and the orientation of the camera 2 with respect to the lane This is because the thickness of the line may change. For example, assuming that the variation of the width of the line indicated on the road included in the map line segment of interest follows a normal distribution, the particle generation unit 23 determines the width of the lines or the interval between the lines according to the normal distribution. A plurality of changed particles may be generated. Thereby, the particle generation unit 23 can increase the number of particles that match the line marked on the road at the position where the vehicle 10 is actually traveling.

  According to another modification, the particle generation unit 23 may generate a particle for each set of the map line segment located on the left side of the vehicle 10 and the map line segment located on the right side as one set. . As a result, even if the shape of a part of the line drawn on the road is changed from the original shape due to a repair mark on the road or abrasion, etc., there is a low possibility of being selected erroneously. Can be generated. Further, in this case, the distance between the map line segment located on the left side of the vehicle 10 and the map line segment located on the right side may change due to the orientation of the camera 2 with respect to the lane or an error in calibration. Therefore, as in the above modification, the particle generation unit 23 follows the normal distribution on the assumption that the variation of the interval between the map segment located on the left side of the vehicle 10 and the map line located on the right follows the normal distribution. A plurality of particles with different intervals may be generated.

  Further, according to another modification, the particle generation unit 23 may generate planar particles parallel to the road surface of the road.

  FIG. 11 is a diagram showing an example of the relationship between particles generated by this modification and lines marked on the road. In FIG. 11, the line 1100 marked on the road has a sawtooth shape. The vertical axis represents the extending direction of the line 1100 (the position of the vertical axis corresponds to the center of gravity of the line 1100 in the direction orthogonal to the extending direction), and the horizontal axis represents the direction orthogonal to the extending direction of the line 1100. . In this example, a set of three lines having a profile having a luminance change along a direction perpendicular to the extending direction of the line 1100 is generated as one particle 1101, 1102. In FIG. 11, in the individual lines constituting the particles 1101 and 1102, a relatively bright part has a relatively low luminance, and a relatively dark part has a relatively high luminance. Then, in each line, a portion with high luminance is set according to the corresponding portion of line 1100. By generating such particles, the vehicle position detection system can appropriately select the particles coinciding with the line even if the line marked on the road has a complicated shape. Can be estimated.

  According to still another modified example, when the camera 2 generates a color image, the particle generation unit 23 corresponds to the part of the particle corresponding to the line marked on the road according to the type of the map line segment. May be set according to the color of the line. Alternatively, the particle generation unit 23 may set the color of the portion of the particle corresponding to the line marked on the road according to the probability distribution of the color of the line marked on the road.

  According to yet another variant, the camera 2 may be a stereo camera. In this case, the projection unit 24 projects each particle, for example, on each of the left and right images obtained by the stereo camera. Further, the selection unit 25 determines, for example, a road surface area corresponding to the road surface from each of the left and right images obtained by the stereo camera. Then, the selection unit 25 does not select particles in which a part of the particles is not included in the road surface area in any of the left and right images. Thereby, since the selection part 25 can exclude the particle | grains corresponding to the line on the road hidden in the preceding vehicle etc. from estimation of the position of the vehicle 10, the estimation accuracy of the position of the vehicle 10 can be improved more. In addition, as a method of determining the road surface area, the selection unit 25 may, for example, perform a "forward environment recognition of a vehicle using a stereo moving image", Information Processing Society research report computer vision and image media (CVIM) 2007, 1- 16, the method disclosed in 2007, etc. can be used.

  In addition, for each particle, the selection unit 25 is the smaller of the evaluation values for the left and right images (when using a normalized cross-correlation value as the evaluation value, when using SSD or SAD as the evaluation value, , Or the larger one of the evaluation values of the left and right images) or the average value of the evaluation values may be selected to satisfy a predetermined matching condition. According to this modification, when an occlusion occurs in which the position where the focused particle is projected is hidden by the preceding vehicle, the position on the leading vehicle overlapping the projected position is different in each of the left and right images. The particle is not selected unless there is a pattern similar to the particle of interest at two or more places in the preceding vehicle. Therefore, robustness is improved.

  Even when the camera 2 is a stereo camera, the position updating unit 26 may calculate the estimated position of the vehicle 10 at each time so that the evaluation value E represented by equation (11) is minimized.

  According to still another modification, the particle generation unit 23 may generate a particle at the current time based on the particle selected at the immediately preceding time. In this case, the particle generation unit 23 may generate particles at the current time according to a general particle filter. Thereby, the particle generation unit 23 can reduce the number of generated particles. That is, the number of particles to be evaluated by the selection unit 25 can be reduced.

  According to still another modification, the position update unit 26 omits the first term in the equation (11) depending on the required accuracy, and the evaluation value E is minimized based on only the second term. In addition, the position of the vehicle 10 at the current time may be estimated. In this case, also in the second term, the position updating unit 26 may calculate the second term based on only the particles selected at the current time. Thereby, the position update part 26 can reduce the amount of calculations.

  The position of the host vehicle output from the vehicle position detection system according to the above embodiment or modification is transmitted to a control circuit (not shown) of the driving support system via, for example, the CAN 3. The control circuit of the driving support system compares, for example, the position of the host vehicle and information around the host vehicle, and detects a specific structure (for example, a toll booth on a highway, a route during navigation) within a predetermined distance from the host vehicle. If there is an intersection that requires a left turn or a right turn, etc., the driver is notified that the structure is near via a display or a speaker installed in the car. Alternatively, the control circuit of the driving support system may output an instruction to reduce the speed to the ECU 11.

  As described above, those skilled in the art can make various modifications to the embodiment to be implemented within the scope of the present invention.

1 Vehicle position detection system 2 Camera 3 Control area network (CAN)
4 Controller (vehicle position detection device)
10 vehicles 11 ECU
41 storage unit 42 communication unit 43 control unit 21 initial value setting unit 22 predicted position calculation unit 23 particle generation unit 24 projection unit 25 selection unit 26 position update unit

Claims (7)

A storage unit (41) for storing a position of a line marked on the road and map information representing the type of the line;
The line labeled on the road is extracted from the map information according to the predicted position of the vehicle at the current time estimated from the position immediately before the vehicle (10), and the type of the line is extracted for each of the extracted lines And a particle generation unit (23) that generates a plurality of particles representing a change in luminance in a direction crossing the line according to the change of the position according to the direction along the line.
For each of the plurality of particles for each of the extracted lines, a position based on the vehicle (10) is determined while changing the predicted position within an assumed error range, and the vehicle (according to the position ( 10) a projection unit (24) for projecting the image at the current time obtained by the imaging unit (2) mounted on
A selection unit (25) for selecting, among the plurality of particles for each of the extracted lines, a particle whose coincidence degree with the image satisfies a predetermined coincidence condition;
A position update unit (26) for obtaining the estimated position according to the sum of errors when each of the selected particles is projected onto the corresponding line based on the estimated position of the vehicle (10) at the current time ,
A vehicle position detection device characterized by having.   The vehicle position detection according to claim 1, wherein the position update unit (26) calculates the estimated position such that a sum of errors when projecting each of the selected particles onto the corresponding line is minimized. apparatus.   The position update unit (26) calculates the odometry information from the estimated sum of errors when projecting each of the selected particles onto the corresponding line and the estimated position of the vehicle (10) at each of a plurality of past times. To minimize the sum of the error between the position of the vehicle at the next time predicted using the equation and the estimated position of the vehicle at the next time, each of the current time and the plurality of times in the past The vehicle position detection device according to claim 1, wherein the estimated position of the vehicle (10) is determined.   The particle generation unit (23), when the type of the extracted line includes a dotted line or a broken line, indicates a change in luminance in a direction crossing the corresponding dotted line or a broken line. The vehicle position according to any one of claims 1 to 3, wherein a second particle is generated which represents the change of brightness in a direction crossing the line corresponding to the absence of the dotted line or the block of the dotted line. Detection device. The imaging unit (2) is a stereo camera including two cameras,
The selection unit (25) is configured such that the degree of coincidence satisfies the coincidence condition on the first image obtained at the current time by one of the two cameras, and by the other of the two cameras. The vehicle position detection device according to any one of claims 1 to 4, wherein a particle whose coincidence degree satisfies the coincidence condition is selected on a second image obtained at the current time. According to the predicted position of the vehicle at the current time estimated from the position immediately before the vehicle (10), a line labeled on the road is extracted from the map information, and each of the extracted lines is represented in the map information Generating a plurality of particles representing a change in luminance in a direction crossing the line according to the type of the line, changing a plurality of positions according to the direction along the line;
For each of the plurality of particles for each of the extracted lines, a position based on the vehicle (10) is determined while changing the predicted position within an assumed error range, and the vehicle (according to the position ( Projecting the image at the current time obtained by the imaging unit (2) mounted on 10);
Selecting a particle satisfying a predetermined matching condition with a degree of matching with the image from the plurality of particles for each of the extracted lines;
Obtaining the estimated position according to the sum of errors when each of the selected particles is projected onto the corresponding line based on the estimated position of the vehicle (10) at the current time;
A vehicle position detection method comprising: According to the predicted position of the vehicle at the current time estimated from the position immediately before the vehicle (10), a line labeled on the road is extracted from the map information, and each of the extracted lines is represented in the map information Generating a plurality of particles representing a change in luminance in a direction crossing the line according to the type of the line, changing a plurality of positions according to the direction along the line;
For each of the plurality of particles for each of the extracted lines, a position based on the vehicle (10) is determined while changing the predicted position within an assumed error range, and the vehicle (according to the position ( Projecting the image at the current time obtained by the imaging unit (2) mounted on 10);
Selecting a particle satisfying a predetermined matching condition with a degree of matching with the image from the plurality of particles for each of the extracted lines;
Obtaining the estimated position according to the sum of errors when each of the selected particles is projected onto the corresponding line based on the estimated position of the vehicle (10) at the current time;
A computer program for vehicle position detection, comprising: an instruction for causing a processor (43) mounted on the vehicle (10) to execute the program.