WO2018212287A1 - 測定装置、測定方法およびプログラム - Google Patents
測定装置、測定方法およびプログラム Download PDFInfo
- Publication number
- WO2018212287A1 WO2018212287A1 PCT/JP2018/019146 JP2018019146W WO2018212287A1 WO 2018212287 A1 WO2018212287 A1 WO 2018212287A1 JP 2018019146 W JP2018019146 W JP 2018019146W WO 2018212287 A1 WO2018212287 A1 WO 2018212287A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- white line
- reliability
- measurement
- predetermined range
- existing
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3602—Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
Definitions
- the present invention relates to a technique for estimating the position of a moving body based on the position of a feature.
- Patent Document 1 describes an example of a method for estimating a vehicle position using a feature position detected using LiDAR and a feature position of map information.
- Patent Document 2 discloses a technique for transmitting an electromagnetic wave to a road surface and detecting a white line based on the reflectance.
- the number of data that can be measured by LiDAR varies depending on the type of white line (continuous line, broken line, etc.) and paint deterioration. For this reason, when the vehicle position is estimated using the white line, the detection accuracy of the white line changes depending on whether the number of LiDAR data used to detect the white line is small or large, and as a result, the accuracy of the vehicle position estimation changes. Come.
- An object of the present invention is to prevent a decrease in the accuracy of vehicle position estimation by utilizing the reliability of white lines extracted as features.
- the invention according to claim 1 is a measuring device, a first acquisition unit that acquires position information of a measurement object stored in a storage unit, and a point group of points indicating surrounding features obtained by an external sensor
- a second acquisition unit that acquires information, and an output unit that outputs reliability of position information indicating a predetermined position of the measurement target existing in the predetermined range based on point cloud information existing in the predetermined range; It is characterized by providing.
- the invention according to claim 8 is a measuring method executed by the measuring apparatus, the first obtaining step for obtaining the position information of the measurement object stored in the storage unit, and the surrounding features obtained by the external sensor. Based on the second acquisition step of acquiring point cloud information of the point indicating the point and the point cloud information existing in the predetermined range, the reliability of the position information indicating the predetermined position of the measurement target existing in the predetermined range is output. And an output step.
- the invention according to claim 9 is a program executed by a measurement apparatus including a computer, and includes a first acquisition unit that acquires position information of a measurement object stored in a storage unit, and a surrounding ground obtained by an external sensor.
- a second acquisition unit that acquires point cloud information of a point indicating an object, and outputs reliability of position information indicating a predetermined position of the measurement object existing in the predetermined range based on the point cloud information existing in the predetermined range
- the computer is caused to function as an output unit that performs the above-described operation.
- the measuring device includes a first acquisition unit that acquires position information of a measurement target stored in the storage unit, and a point cloud of points indicating surrounding features obtained by an external sensor.
- a second acquisition unit that acquires information, and an output unit that outputs reliability of position information indicating a predetermined position of the measurement target existing in the predetermined range based on point cloud information existing in the predetermined range; Prepare.
- the above-described measuring apparatus acquires the position information of the measurement target stored in the storage unit, and also acquires point cloud information of points indicating surrounding features obtained by the external sensor. Then, based on the point cloud information existing in the predetermined range, position information indicating the predetermined position of the measurement target existing in the predetermined range is obtained, and the reliability is output. Thereby, the use method of position information can be changed in consideration of reliability, and it can prevent that a precision falls using position information with low reliability.
- the measurement target may be a division line such as a white line or a yellow line painted on the road, or a linear road marking such as a stop line or a pedestrian crossing.
- the output unit increases the reliability as the number of points or the number of points existing within the predetermined range increases.
- the reliability can be set based on the number of points existing within the predetermined range.
- the measurement target is a road line
- the output unit calculates an ideal number of points on an ideal road line based on the width information of the road line.
- the reliability is determined based on a ratio between the number of points existing in the predetermined range and the ideal number of points.
- the reliability is set based on the number of points actually measured within the predetermined range and the ideal number of points.
- the output unit increases the reliability as the ratio of the number of points existing in the predetermined range to the ideal number of points is larger.
- the “road line” in the present specification is a marking line such as a white line or a yellow line to be measured, and a linear road marking such as a stop line or a pedestrian crossing.
- a determination unit is provided.
- the predetermined range is determined based on the predicted position of the measurement target.
- the output unit outputs position information indicating a predetermined position of the measurement target.
- the position information of the measurement object and its reliability are output.
- the measurement method executed by the measurement apparatus includes a first acquisition step of acquiring position information of a measurement object stored in the storage unit, and surrounding features obtained by an external sensor. Based on the second acquisition step of acquiring point cloud information of the point indicating the point and the point cloud information existing in the predetermined range, the reliability of the position information indicating the predetermined position of the measurement target existing in the predetermined range is output. An output process. Thereby, the use method of position information can be changed in consideration of reliability, and it can prevent that a precision falls using position information with low reliability.
- a program executed by a measurement apparatus including a computer includes a first acquisition unit that acquires position information of a measurement target stored in a storage unit, and a surrounding ground obtained by an external sensor.
- a second acquisition unit that acquires point cloud information of a point indicating an object, and outputs reliability of position information indicating a predetermined position of the measurement object existing in the predetermined range based on the point cloud information existing in the predetermined range
- the computer is caused to function as an output unit.
- the above measurement apparatus can be realized by executing this program on a computer. This program can be stored and handled in a storage medium.
- FIG. 1 is a diagram illustrating a white line extraction method.
- White line extraction refers to detecting a white line painted on a road surface and calculating a predetermined position, for example, a center position.
- the vehicle 5 exists in the map coordinate system (X m , Y m ), and the vehicle coordinate system (X v , Y v ) is defined based on the position of the vehicle 5. Specifically, the traveling direction of the vehicle 5 and X v-axis of the vehicle coordinate system, a direction perpendicular to it and Y v axis of the vehicle coordinate system.
- white lines that are lane boundary lines on the left and right sides of the vehicle 5.
- the position of the white line in the map coordinate system that is, the white line map position is included in the advanced map managed by the server or the like, and is acquired from the server or the like.
- white line data is stored in the advanced map as a coordinate point sequence.
- the LiDAR mounted on the vehicle 5 measures scan data along the scan line 2.
- the scan line 2 indicates a trajectory of scanning by LiDAR.
- the coordinates of the points constituting the white line WL1 on the left side of the vehicle 5, that is, the white line map position WLMP1 is (mx m1 , my m1 ), and the coordinates of the points constituting the white line WL2 on the right side of the vehicle 5, ie, the white line.
- the map position WLMP2 is (mx m2 , my m2 ).
- the predicted host vehicle position PVP in the map coordinate system is given by (x ′ m , y ′ m ), and the predicted host vehicle azimuth angle in the map coordinate system is given by ⁇ ′ m .
- the white line predicted position WLPP (l′ x v , l′ y v ) indicating the predicted position of the white line is the white line map position WLMP (mx m , my m ) and the predicted host vehicle position PVP (x ′ m , y).
- m the white line map position
- PVP the predicted host vehicle position
- the white line predicted position WLPP1 (l′ x v1 , l′ y v1 ) is obtained for the white line WL1 and the white line predicted position WLPP2 (l′ x v2 , l′ y v2 ) is obtained for the white line WL2 by Expression (1). It is done. Thus, for each of the white lines WL1 and WL2, a plurality of white line predicted positions WLPP1 and WLPP2 corresponding to the white lines WL1 and WL2 are obtained.
- the white line predicted range WLPR is determined based on the white line predicted position WLPP.
- the white line prediction range WLPR indicates a range in which a white line is considered to exist on the basis of the predicted vehicle position PVP.
- the white line prediction range WLPR is set at four locations on the vehicle 5 at the right front, right rear, left front, and left rear at the maximum.
- FIG. 2 shows a method for determining the white line prediction range WLPR.
- A set forward reference point to any position in front of the vehicle 5 (distance alpha v forward position) to ( ⁇ v, 0 v). Then, based on the front reference point ( ⁇ v , 0 v ) and the white line predicted position WLPP, the white line predicted position WLPP closest to the front reference point ( ⁇ v , 0 v ) is searched.
- the white line WL1 based on the forward reference point ( ⁇ v , 0 v ) and a plurality of white line predicted positions WLPP1 (l′ x v1 , l′ y v1 ) constituting the white line WL1, the following The distance D1 is calculated by the equation (2), and the white line predicted position WLPP1 at which the distance D1 is the minimum value is set as the prediction range reference point Pref1.
- the white line WL2 based on the forward reference point ( ⁇ v , 0 v ) and a plurality of white line predicted positions WLPP2 (l′ x v2 , l′ y v2 ) constituting the white line WL2, the following formula
- the distance D2 is calculated by (3), and the white line predicted position WLPP2 at which the distance D2 is the minimum value is set as the predicted range reference point Pref2.
- any range based on the expected range reference point Pref for example ⁇ [Delta] X from the expected range reference point Pref in X v-axis direction, a range of ⁇ [Delta] Y to Y v-axis direction
- the white line prediction range WLPR is set.
- white line prediction ranges WLPR1 and WLPR2 are set at the left and right positions in front of the vehicle 5.
- white line prediction ranges WLPR3 and WLPR4 are set at the left and right positions behind the vehicle 5 by setting the rear reference point behind the vehicle 5 and setting the prediction range reference point Pref.
- four white line prediction ranges WLPR1 to WLPR4 are set for the vehicle 5.
- FIG. 3 shows a method of calculating the white line center position WLCP.
- FIG. 3A shows a case where the white line WL1 is a solid line.
- the white line center position WLCP1 is calculated by the average value of the position coordinates of the scan data constituting the white line.
- the white line scan data WLSD1 (wx ′ v , wy) existing in the white line prediction range WLPR1 among the scan data output from the LiDAR. ' v ) is extracted.
- the scan data obtained on the white line is data with high reflection intensity.
- scan data that exists within the white line prediction range WLPR1 and on the road surface and whose reflection intensity is greater than or equal to a predetermined value is extracted as white line scan data WLSD.
- the coordinates of the white line center position WLCP1 (sx v1 , sy v1 ) are obtained by the following equation (4).
- the white line center position WLCP2 is similarly calculated.
- the white line center position WLCP is calculated by the same method.
- the white line WL is a broken line, depending on the positional relationship between the white line WL and the white line predicted range WLPR, the number of white line scan data WLSD existing in the white line predicted range WLPR decreases.
- FIG. 4 shows an example of the positional relationship between the white line WL and the white line prediction range WLPR when the white line WL is a solid line and a broken line.
- the white line WL is a solid line
- the white line prediction range WLPR is located at a portion where the white line WL is interrupted
- the number of white line scan data WLSD obtained in the white line prediction range WLPR is reduced.
- the accuracy of the calculated white line center position WLCP decreases.
- the white line center position WLCP is calculated by the same method whether the number of white line scan data WLSD is large or small.
- the white line center position WLCP is calculated based on the number of white line scan data WLSD.
- a reliability R indicating the calculation accuracy is calculated. Basically, the reliability R is higher as the number of white line scan data WLSD in the white line prediction range WLPR is larger, and the reliability R is lower as the number of white line scan data WLSD is smaller.
- the reliability R may be calculated based on the number of scan lines or layers based on LiDAR instead of the number of white line scan data. In this case, the reliability R is higher as the number of scan lines or layers is larger, and the reliability R is lower as the number is lower.
- the scan data corresponds to a “point indicating a feature” or “point group” of the present invention, and the scan line or layer corresponds to a “set of points”.
- the reliability R is calculated by the following equation.
- n is the number of white line scan data existing in the white line prediction range WLPR
- N is the ideal number of white line scan data existing in the white line prediction range WLPR.
- the ideal number N of white line scan data is calculated based on the size of the white line prediction range WLPR and the width of the white line WL. Specifically, first on the basis of the size and the white line of the width of the white line estimated range WLPR, it calculates the area S occupied by the white line in the case where the white line is present throughout the X v-axis direction of the white line prediction range WLPR. For example, when the white line prediction range WLPR has a "2 ⁇ X" length to the X v-axis direction as shown in FIG.
- the width of the white line is "W”
- the area of the white line "S” S 2 ⁇ X ⁇ W
- N the ideal white line scan data number
- the ideal white line scan data number N the white line is present throughout X v-axis direction of the white line estimated range WLPR, and the number of white line scan data when high scan data reflection intensity throughout the white line is obtained It becomes. Then, as shown in the equation (5), the reliability R is given by the ratio of the scan line scan data number n actually obtained within the white line prediction range WLPR and the ideal scan line scan data number N.
- the reliability R is calculated by the following formula.
- m is the number of white line scan lines existing in the white line prediction range WLPR.
- the “white line scan line” refers to a scan line composed of white line scan data.
- M is an ideal number of white line scan lines existing in the white line prediction range WLPR.
- the ideal number M of white line scan lines is the number of white line scan lines in the case where a white line exists over the entire Xv-axis direction of the white line prediction range WLPR and high-intensity scan data is obtained for the entire white line. Then, as shown in Expression (6), the reliability R is given by the ratio between the number m of white line scan lines actually obtained within the white line prediction range WLPR and the number M of ideal white line scan lines.
- the reliability R obtained in this way is output in association with the calculation result of the white line center position WLCP, and is used for vehicle position estimation. For example, in the vehicle position estimation, weighting is performed based on the reliability R when the vehicle position is estimated based on the white line center position WLCP. Thereby, the white line center position WLCP with low reliability is not used for the vehicle position estimation or is used with low weighting. Thus, it is possible to prevent the vehicle position estimation with low accuracy from being performed based on the white line center position WLCP with low reliability.
- FIG. 5 shows a schematic configuration of a host vehicle position estimation apparatus to which the measurement apparatus of the present invention is applied.
- the own vehicle position estimation device 10 is mounted on a vehicle and configured to be able to communicate with a server 7 such as a cloud server by wireless communication.
- the server 7 is connected to a database 8, and the database 8 stores an advanced map.
- the advanced map stored in the database 8 stores landmark map information for each landmark.
- the white line map position WLMP indicating the coordinates of the point sequence constituting the white line and the width information of the white line are stored.
- the own vehicle position estimation device 10 communicates with the server 7 and downloads white line map information related to the white line around the own vehicle position of the vehicle.
- the own vehicle position estimation device 10 includes an inner world sensor 11, an outer world sensor 12, an own vehicle position prediction unit 13, a communication unit 14, a white line map information acquisition unit 15, a white line position prediction unit 16, and scan data extraction.
- the vehicle position prediction unit 13, the white line map information acquisition unit 15, the white line position prediction unit 16, the scan data extraction unit 17, the white line center position / reliability calculation unit 18, and the vehicle position estimation unit 19 are actually This is realized by a computer such as a CPU executing a program prepared in advance.
- the inner world sensor 11 measures the position of the vehicle as a GNSS (Global Navigation Satellite System) / IMU (Inertia Measurement Unit) combined navigation system, and includes a satellite positioning sensor (GPS), a gyro sensor, a vehicle speed sensor, and the like. Including.
- the own vehicle position prediction unit 13 predicts the own vehicle position of the vehicle by GNSS / IMU combined navigation based on the output of the internal sensor 11 and supplies the predicted own vehicle position PVP to the white line position prediction unit 16.
- the external sensor 12 is a sensor that detects an object around the vehicle, and includes a stereo camera, LiDAR, and the like.
- the external sensor 12 supplies the scan data SD obtained by the measurement to the scan data extraction unit 17.
- the communication unit 14 is a communication unit for wirelessly communicating with the server 7.
- the white line map information acquisition unit 15 receives white line map information related to white lines existing around the vehicle from the server 7 via the communication unit 14 and supplies the white line map position WLMP included in the white line map information to the white line position prediction unit 16. To do.
- the white line position prediction unit 16 calculates the white line predicted position WLPP by the above-described equation (1) based on the white line map position WLMP and the predicted vehicle position PVP acquired from the vehicle position prediction unit 13.
- the white line position prediction unit 16 determines the white line prediction range WLPR based on the above-described formulas (2) and (3) based on the white line prediction position WLPP and supplies the white line prediction range WLPR to the scan data extraction unit 17. Further, the white line position prediction unit 16 supplies the white line width W included in the white line map information to the white line center position / reliability calculation unit 18.
- the scan data extraction unit 17 extracts the white line scan data WLSD based on the white line prediction range WLPR supplied from the white line position prediction unit 16 and the scan data SD acquired from the external sensor 12. Specifically, the scan data extraction unit 17 extracts scan data included in the white line prediction range WLPR and having a reflection intensity equal to or higher than a predetermined value, as white line scan data WLSD, from the scan data SD.
- the white line center position / reliability calculation unit 18 is supplied.
- the white line center position / reliability calculation unit 18 calculates the white line center position WLCP from the white line scan data WLSD according to the equation (4). In addition, the white line center position / reliability calculation unit 18 calculates the reliability R based on the number n of white line scan data and the ideal number N of white line scan data using Expression (5). Then, the white line center position / reliability calculation unit 18 supplies the calculated white line center position WLCP and reliability R to the vehicle position estimation unit 19.
- the own vehicle position estimating unit 19 estimates the own vehicle position and the own vehicle azimuth angle based on the white line map position WLMP in the advanced map and the white line center position WLCP that is white line measurement data by the external sensor 12. .
- the vehicle position estimation unit 19 applies the weight of the white line center position WLCP with the reliability R to estimate the vehicle position and the vehicle azimuth.
- the white line center position WLCP with a high reliability R is applied to the estimation of the own vehicle position and the own vehicle azimuth at a large ratio
- the white line center position WLCP with a low reliability R is an estimation of the own vehicle position and the own vehicle azimuth. Therefore, it is possible to prevent a decrease in the estimation accuracy of the vehicle position and the vehicle azimuth angle.
- Japanese Patent Laid-Open No. 2017-72422 discloses an example of a method for estimating the vehicle position by matching the landmark position information of the advanced map and the measured position information of the landmark by the external sensor.
- the white line map information acquisition unit 15 is an example of the first acquisition unit of the present invention
- the scan data extraction unit 17 is an example of the second acquisition unit of the present invention
- the white line center position / reliability calculation unit. 18 is an example of the output unit of the present invention
- the white line position prediction unit 16 is an example of the range determining unit of the present invention.
- FIG. 6 is a flowchart of the vehicle position estimation process. This process is realized by a computer such as a CPU executing a program prepared in advance and functioning as each component shown in FIG.
- the host vehicle position prediction unit 13 acquires the predicted host vehicle position PVP based on the output from the internal sensor 11 (step S11).
- the white line map information acquisition part 15 connects to the server 7 through the communication part 14, and acquires white line map information from the advanced map memorize
- the white line position prediction unit 16 calculates the white line predicted position WLPP based on the white line map position WLMP included in the white line position information obtained in step S12 and the predicted host vehicle position PVP obtained in step S11. (Step S13). Further, the white line position prediction unit 16 determines a white line prediction range WLPR based on the white line prediction position WLPP and supplies the white line prediction range WLPR to the scan data extraction unit 17 (step S14).
- the scan data extraction unit 17 converts the scan data SD obtained from the LiDAR as the external sensor 12 into the white line predicted range WLPR, the scan data on the road surface, and the reflection intensity is a predetermined value or more as a white line It is extracted as scan data WLSD and supplied to the white line center position / reliability calculator 18 (step S15).
- the white line center position / reliability calculation unit 18 calculates the white line center position WLCP and the reliability R based on the white line predicted position WLPP and the white line scan data WLSD, and supplies the white line center position / reliability calculation unit 18 to the vehicle position estimation unit 19 (step S16). ). Then, the vehicle position estimation unit 19 performs vehicle position estimation using the white line center position WLCP and the reliability R (step S17), and outputs the vehicle position and the vehicle azimuth (step S18). Thus, the own vehicle position estimation process ends.
- the white line that is the lane boundary indicating the lane is used, but the application of the present invention is not limited to this, and even if a linear road marking such as a pedestrian crossing or a stop line is used. Good. Further, a yellow line or the like may be used instead of the white line. These lane markings such as white lines and yellow lines, road markings, and the like are examples of road lines of the present invention.
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Automation & Control Theory (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
- Navigation (AREA)
Abstract
Description
[白線抽出方法]
図1は、白線抽出方法を説明する図である。白線抽出とは、道路面にペイントされた白線を検出し、その所定位置、例えば中心位置を算出することをいう。
図示のように、地図座標系(Xm,Ym)に車両5が存在し、車両5の位置を基準として車両座標系(Xv,Yv)が規定される。具体的に、車両5の進行方向を車両座標系のXv軸とし、それに垂直な方向を車両座標系のYv軸とする。
次に、白線予測位置WLPPに基づいて、白線予測範囲WLPRが決定される。白線予測範囲WLPRは、予測自車位置PVPを基準として、白線が存在すると考えられる範囲を示す。白線予測範囲WLPRは、最大で車両5の右前方、右後方、左前方及び左後方の4か所に設定される。
次に、白線予測位置WLPPを用いて白線中心位置WLCPを算出する。図3は白線中心位置WLCPの算出方法を示す。図3(A)は、白線WL1が実線である場合を示す。白線中心位置WLCP1は、白線を構成するスキャンデータの位置座標の平均値により算出される。いま、図3(A)に示すように、白線予測範囲WLPR1が設定されると、LiDARから出力されるスキャンデータのうち、白線予測範囲WLPR1内に存在する白線スキャンデータWLSD1(wx’v,wy’v)が抽出される。白線上は通常の道路上と比較して反射率が高いので、白線上で得られたスキャンデータは、反射強度の高いデータとなる。LiDARから出力されたスキャンデータのうち、白線予測範囲WLPR1内に存在し、路面上、かつ、反射強度が所定以上値であるスキャンデータが白線スキャンデータWLSDとして抽出される。そして、抽出された白線スキャンデータWLSDの数を「n」とすると、以下の式(4)により、白線中心位置WLCP1(sxv1,syv1)の座標が得られる。
上記のように、白線WLが実線である場合でも破線である場合でも、白線中心位置WLCPは同じ方法で算出される。しかし、白線WLが破線である場合、白線WLと白線予測範囲WLPRとの位置関係によっては、白線予測範囲WLPR内に存在する白線スキャンデータWLSDの数が少なくなってしまう。図4は、白線WLが実線である場合と破線である場合の、白線WLと白線予測範囲WLPRとの位置関係の例を示す。図示のように、白線WLが実線である場合には、基本的にどのタイミングにおいても白線予測範囲WLPR内ではXv方向の全体にわたって白線が含まれているので、得られる白線スキャンデータWLSDの数は多い。これに対して、白線WLが破線である場合、白線予測範囲WLPRが白線WLの途切れた部分に位置するときには、白線予測範囲WLPR内で得られる白線スキャンデータWLSDの数は少なくなってしまう。そして、白線中心位置WLCPの算出に使用する白線スキャンデータWLSDの数が少なくなると、算出される白線中心位置WLCPの精度が低下してしまう。
S=2ΔX・W
で与えられる。次に、LiDARによるスキャン密度に基づいて、面積Sの領域で得られるスキャンデータ数を算出し、これを理想的な白線スキャンデータ数Nとする。
図5は、本発明の測定装置を適用した自車位置推定装置の概略構成を示す。自車位置推定装置10は、車両に搭載され、無線通信によりクラウドサーバなどのサーバ7と通信可能に構成されている。サーバ7はデータベース8に接続されており、データベース8は高度化地図を記憶している。データベース8に記憶された高度化地図は、ランドマーク毎にランドマーク地図情報を記憶している。また、白線については、白線を構成する点列の座標を示す白線地図位置WLMPと、白線の幅情報とを記憶している。自車位置推定装置10は、サーバ7と通信し、車両の自車位置周辺の白線に関する白線地図情報をダウンロードする。
次に、自車位置推定装置10による自車位置推定処理について説明する。図6は、自車位置推定処理のフローチャートである。この処理は、CPUなどのコンピュータが予め用意されたプログラムを実行し、図5に示す各構成要素として機能することにより実現される。
上記の実施例では、車線を示す車線境界線である白線を使用しているが、本発明の適用はこれには限られず、横断歩道、停止線などの線状の道路標示を利用してもよい。また、白線の代わりに、黄色線などを利用しても良い。これら、白線、黄色線などの区画線や、道路標示などは本発明の路面線の一例である。
7 サーバ
8 データベース
10 自車位置推定装置
11 内界センサ
12 外界センサ
13 自車位置予測部
14 通信部
15 白線地図情報取得部
16 白線位置予測部
17 スキャンデータ抽出部
18 白線中心位置・信頼度算出部
19 自車位置推定部
Claims (10)
- 記憶部に記憶された測定対象の位置情報を取得する第1取得部と、
外界センサにより得た周囲の地物を示す点の点群情報を取得する第2取得部と、
所定範囲に存在する点群情報に基づいて、前記所定範囲内に存在する前記測定対象の所定位置を示す位置情報の信頼度を出力する出力部と、
を備えることを特徴とする測定装置。 - 前記出力部は、前記所定範囲内に存在する点の数又は点の集合の数が多いほど、前記信頼度を高くすることを特徴とする請求項1に記載の測定装置。
- 前記測定対象は道路にペイントされていることを特徴とする請求項1又は2に記載の測定装置。
- 前記測定対象は路面線であり、
前記出力部は、前記路面線の幅情報に基づいて理想的な路面線における点の数である理想点数を算出し、前記所定範囲に存在する点の数と前記理想点数との比に基づいて前記信頼度を決定することを特徴とする請求項3に記載の測定装置。 - 前記出力部は、前記理想点数に対する前記所定範囲に存在する点の数の比が大きいほど前記信頼度を高くすることを特徴とする請求項4に記載の測定装置。
- 前記測定対象の位置情報と前記測定装置の位置とに基づいて前記測定対象の予測位置を算出し、当該予測位置に基づいて前記所定範囲を決定する範囲決定部を備えることを特徴とする請求項1乃至5のいずれか一項に記載の測定装置。
- 前記出力部は、前記測定対象の所定位置を示す位置情報を出力することを特徴とする請求項1乃至6のいずれか一項に記載の測定装置。
- 測定装置により実行される測定方法であって、
記憶部に記憶された測定対象の位置情報を取得する第1取得工程と、
外界センサにより得た周囲の地物を示す点の点群情報を取得する第2取得工程と、
所定範囲に存在する点群情報に基づいて、前記所定範囲内に存在する前記測定対象の所定位置を示す位置情報の信頼度を出力する出力工程と、
を備えることを特徴とする測定方法。 - コンピュータを備える測定装置により実行されるプログラムであって、
記憶部に記憶された測定対象の位置情報を取得する第1取得部、
外界センサにより得た周囲の地物を示す点の点群情報を取得する第2取得部、
所定範囲に存在する点群情報に基づいて、前記所定範囲内に存在する前記測定対象の所定位置を示す位置情報の信頼度を出力する出力部、
として前記コンピュータを機能させることを特徴とするプログラム。 - 請求項9に記載のプログラムを記憶した記憶媒体。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2019518870A JP6740470B2 (ja) | 2017-05-19 | 2018-05-17 | 測定装置、測定方法およびプログラム |
EP18802021.8A EP3637054B1 (en) | 2017-05-19 | 2018-05-17 | Measurement device, measurement method, and program |
US16/615,083 US11519736B2 (en) | 2017-05-19 | 2018-05-17 | Measurement device, measurement method and program |
US17/985,471 US11828603B2 (en) | 2017-05-19 | 2022-11-11 | Measurement device, measurement method and program |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2017100183 | 2017-05-19 | ||
JP2017-100183 | 2017-05-19 |
Related Child Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/615,083 A-371-Of-International US11519736B2 (en) | 2017-05-19 | 2018-05-17 | Measurement device, measurement method and program |
US17/985,471 Continuation US11828603B2 (en) | 2017-05-19 | 2022-11-11 | Measurement device, measurement method and program |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2018212287A1 true WO2018212287A1 (ja) | 2018-11-22 |
Family
ID=64273980
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2018/019146 WO2018212287A1 (ja) | 2017-05-19 | 2018-05-17 | 測定装置、測定方法およびプログラム |
Country Status (4)
Country | Link |
---|---|
US (2) | US11519736B2 (ja) |
EP (1) | EP3637054B1 (ja) |
JP (1) | JP6740470B2 (ja) |
WO (1) | WO2018212287A1 (ja) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6923750B2 (ja) * | 2018-03-28 | 2021-08-25 | パイオニア株式会社 | 自己位置推定装置、自己位置推定方法、プログラム及び記憶媒体 |
WO2020080088A1 (ja) * | 2018-10-15 | 2020-04-23 | 三菱電機株式会社 | 情報処理装置 |
JP7144504B2 (ja) * | 2020-12-28 | 2022-09-29 | 本田技研工業株式会社 | 車両制御システム |
JP7197554B2 (ja) * | 2020-12-28 | 2022-12-27 | 本田技研工業株式会社 | 車両制御システム及び区画線推定方法 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015222223A (ja) | 2014-05-23 | 2015-12-10 | 日産自動車株式会社 | 車両位置推定装置、及び車両位置推定方法 |
JP2017004176A (ja) * | 2015-06-08 | 2017-01-05 | 日産自動車株式会社 | 路面標示検出装置及び路面標示検出方法 |
JP2017037472A (ja) * | 2015-08-10 | 2017-02-16 | 富士重工業株式会社 | 車線認識装置 |
JP2017072422A (ja) | 2015-10-05 | 2017-04-13 | パイオニア株式会社 | 情報処理装置、制御方法、プログラム及び記憶媒体 |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3708653B2 (ja) * | 1997-01-23 | 2005-10-19 | ビステオン・ジャパン株式会社 | 物体認識装置 |
JP2003196798A (ja) * | 2001-12-25 | 2003-07-11 | Nissan Motor Co Ltd | 白線検出装置 |
DE102007034196A1 (de) * | 2007-07-23 | 2009-01-29 | Robert Bosch Gmbh | Verfahren und Vorrichtung für die Spurerfassung mit einem Fahrerassistenzsystem |
JP4232167B1 (ja) * | 2007-08-27 | 2009-03-04 | 三菱電機株式会社 | 対象特定装置、対象特定方法および対象特定プログラム |
AU2009211435A1 (en) * | 2008-02-04 | 2009-08-13 | Tele Atlas B.V. | Method for map matching with sensor detected objects |
DE102009009211A1 (de) | 2008-02-20 | 2009-09-10 | Continental Teves Ag & Co. Ohg | Verfahren und Assistenzsystem zum Erfassen von Objekten im Umfeld eines Fahrzeugs |
KR101096113B1 (ko) * | 2009-05-26 | 2011-12-30 | 한국교통연구원 | 신뢰도가 향상된 항법 시스템 및 그 제공방법 |
JP5346863B2 (ja) * | 2010-03-30 | 2013-11-20 | 大日本スクリーン製造株式会社 | 3次元位置・姿勢認識装置およびそれを用いたシステム、方法、プログラム |
US10267640B2 (en) * | 2015-08-28 | 2019-04-23 | Nissan Motor Co., Ltd. | Vehicle position estimation device, vehicle position estimation method |
US10384679B2 (en) * | 2015-09-30 | 2019-08-20 | Nissan Motor Co., Ltd. | Travel control method and travel control apparatus |
DE102015220695A1 (de) | 2015-10-22 | 2017-04-27 | Robert Bosch Gmbh | Verfahren und Vorrichtung zum Bewerten des Inhalts einer Karte |
MX2018011509A (es) * | 2016-03-24 | 2019-01-10 | Nissan Motor | Metodo de deteccion de carril de circulacion y dispositivo de deteccion de carril de circulacion. |
EP3467802B1 (en) * | 2016-05-30 | 2020-09-30 | Nissan Motor Co., Ltd. | Object detection method and object detection device |
JP6649191B2 (ja) * | 2016-06-29 | 2020-02-19 | クラリオン株式会社 | 車載処理装置 |
KR20190031544A (ko) * | 2016-07-26 | 2019-03-26 | 닛산 지도우샤 가부시키가이샤 | 자기 위치 추정 방법 및 자기 위치 추정 장치 |
JP6515898B2 (ja) * | 2016-09-29 | 2019-05-22 | トヨタ自動車株式会社 | 物標レーン関係認識装置 |
JP6747269B2 (ja) * | 2016-12-06 | 2020-08-26 | トヨタ自動車株式会社 | 物体認識装置 |
-
2018
- 2018-05-17 JP JP2019518870A patent/JP6740470B2/ja active Active
- 2018-05-17 US US16/615,083 patent/US11519736B2/en active Active
- 2018-05-17 EP EP18802021.8A patent/EP3637054B1/en active Active
- 2018-05-17 WO PCT/JP2018/019146 patent/WO2018212287A1/ja active Application Filing
-
2022
- 2022-11-11 US US17/985,471 patent/US11828603B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015222223A (ja) | 2014-05-23 | 2015-12-10 | 日産自動車株式会社 | 車両位置推定装置、及び車両位置推定方法 |
JP2017004176A (ja) * | 2015-06-08 | 2017-01-05 | 日産自動車株式会社 | 路面標示検出装置及び路面標示検出方法 |
JP2017037472A (ja) * | 2015-08-10 | 2017-02-16 | 富士重工業株式会社 | 車線認識装置 |
JP2017072422A (ja) | 2015-10-05 | 2017-04-13 | パイオニア株式会社 | 情報処理装置、制御方法、プログラム及び記憶媒体 |
Also Published As
Publication number | Publication date |
---|---|
US20230074449A1 (en) | 2023-03-09 |
US20200103234A1 (en) | 2020-04-02 |
EP3637054A4 (en) | 2021-03-03 |
US11519736B2 (en) | 2022-12-06 |
US11828603B2 (en) | 2023-11-28 |
EP3637054B1 (en) | 2023-09-06 |
JP6740470B2 (ja) | 2020-08-12 |
EP3637054A1 (en) | 2020-04-15 |
JPWO2018212287A1 (ja) | 2020-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6740470B2 (ja) | 測定装置、測定方法およびプログラム | |
JP6806891B2 (ja) | 情報処理装置、制御方法、プログラム及び記憶媒体 | |
JP7155284B2 (ja) | 計測精度算出装置、自己位置推定装置、制御方法、プログラム及び記憶媒体 | |
US20220113139A1 (en) | Object recognition device, object recognition method and program | |
EP2052208A2 (en) | Determining the location of a vehicle on a map | |
JP2017211307A (ja) | 測定装置、測定方法およびプログラム | |
JP2023164553A (ja) | 位置推定装置、推定装置、制御方法、プログラム及び記憶媒体 | |
JP2024038322A (ja) | 測定装置、測定方法およびプログラム | |
JP7526858B2 (ja) | 測定装置、測定方法およびプログラム | |
JP2023126399A (ja) | 測定装置、測定方法およびプログラム | |
JP2023099851A (ja) | 測定装置、測定方法およびプログラム | |
WO2018212290A1 (ja) | 情報処理装置、制御方法、プログラム及び記憶媒体 | |
JP2022161965A (ja) | 地物認識装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18802021 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2019518870 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2018802021 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2018802021 Country of ref document: EP Effective date: 20191219 |