WO2014034187A1 - レーンマーク認識装置 - Google Patents
レーンマーク認識装置 Download PDFInfo
- Publication number
- WO2014034187A1 WO2014034187A1 PCT/JP2013/063008 JP2013063008W WO2014034187A1 WO 2014034187 A1 WO2014034187 A1 WO 2014034187A1 JP 2013063008 W JP2013063008 W JP 2013063008W WO 2014034187 A1 WO2014034187 A1 WO 2014034187A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- lane mark
- vehicle
- edge
- mark recognition
- image
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
Definitions
- the present invention relates to a lane mark recognition device for recognizing a lane mark such as a white line formed on a traveling road ahead of a vehicle.
- JP11-147473A Japanese Patent Laid-Open No. 11-147473
- JP11-147473A Japanese Patent Laid-Open No. 11-147473
- An edge image which is differential data, is obtained by differentiating in the horizontal direction (horizontal direction), and the interval corresponding to the change in luminance is within a range that seems to be appropriate as a white line with respect to the interval in which the differential value changes from positive to negative.
- the combination is extracted as horizontal line candidate horizontal data (JP11-147473A, [0019] to [0021]).
- white lines are recognized by sequentially verifying the continuity in the vertical direction of the white line candidates in the horizontal direction data from the bottom of the screen with respect to the edge image (JP11-147473A, [0023], [0023] 0024]).
- a known straight line recognition process such as a Hough transform is applied to the edge image.
- the edge image obtained by differentiating the captured image includes edges of other vehicles traveling in front of the vehicle (own vehicle), that is, edges other than the white line.
- the straight line recognition process by the Hough transform is a process for extracting the slope and intercept of a line segment from an image with noise, and is not a process for detecting the length of the line segment.
- the edge of a true white line candidate (continuous line candidate) that continuously extends from the bottom to the top of the screen can be recognized as a straight line.
- the present invention has been made in consideration of such problems, and provides a lane mark recognition device that prevents an edge of another vehicle (front vehicle) that is not a lane mark from being erroneously detected as a lane mark candidate. With the goal.
- the lane mark recognition device is mounted on a vehicle and has an imaging unit that captures an image including a traveling road ahead of the vehicle, and an edge that performs edge extraction processing on the image captured by the imaging unit
- a lane mark recognition apparatus comprising: an extraction unit; and a lane mark recognition unit that recognizes a lane mark based on the edge extracted by the edge extraction unit.
- the lane mark candidate determination unit includes a lane mark candidate determination unit. Among the edges extracted by the edge extraction unit, the edge detected and detected in the short distance area in front of the vehicle, and the far distance area in front of the vehicle from within the short distance area Lane mark candidates are determined based on the edges that are continuous with the edges, and the lane mark recognition unit is determined by the lane mark candidate determination unit. And performing lane mark recognition processing on the serial lane mark candidate.
- the edge detected and detected in the short distance area in front of the vehicle, and the edge that is in the far distance area in front of the vehicle and continuous with the edge from within the short distance area Since the lane mark candidate is determined based on the image, the edge of the other vehicle (previous vehicle) staying in the long-distance area is not detected as the lane mark candidate (excluded as a non-lane mark candidate) in the captured image. It is possible to prevent erroneous detection of an edge of the other vehicle (the preceding vehicle) or the like as a lane mark candidate.
- the lane mark candidate determination unit approaches the vehicle every predetermined time, and the edge that has entered the short distance area from the long distance area in front of the vehicle is in the short distance area. It can be detected as the edge.
- the lane mark candidate determination unit is detected when the edge is detected at least once in the short-distance region in front of the vehicle in a plurality of consecutive images captured by the imaging unit.
- the edge may be detected as the edge in the short distance region.
- the vehicle further includes a yaw rate sensor of the vehicle and / or a steering angle sensor for steering, and the front of the vehicle is determined based on an output of the yaw rate sensor and / or the steering angle sensor. Can do.
- the lane mark candidate determination unit sets the image range in the vehicle front direction set in the short distance region to be smaller as the vehicle speed of the vehicle increases.
- the relative speed is close to the vehicle by removing the edge that is in the long-distance area in front of the vehicle and that is in the long-distance area after a predetermined time is excluded from the lane mark candidate object.
- the accuracy of not erroneously detecting an edge of the other vehicle (the preceding vehicle) or the like as a lane mark candidate can be further increased.
- an edge that does not enter the near distance area in front of the vehicle that is, an edge that remains in the far distance area in front of the vehicle can be excluded from the lane mark candidates, another vehicle that remains in the far distance area (previous vehicle) And the like can be prevented from being erroneously detected as lane mark candidates (excluded as non-lane mark candidates).
- the preceding vehicle the preceding vehicle
- FIG. 3A is an explanatory diagram of the entire image composed of edges extracted from the captured image
- FIG. 3B is an explanatory diagram illustrating the entire image divided into a short-distance region and a long-distance region.
- FIG. 4A is an explanatory diagram of edge extraction processing within a short-distance region
- FIG. 4B is an explanatory diagram of lane mark candidate extraction processing. It is explanatory drawing of the exclusion process of the edge showing reflection. It is explanatory drawing of a lane mark recognition process.
- FIG. 1 shows a schematic configuration of a vehicle 12 in which a lane mark recognition apparatus 10 according to this embodiment is incorporated.
- the lane mark recognizing device 10 has functions of a driving support device 14 mounted on the vehicle 12 in order to support a steering operation, a braking operation, and the like by a driver of the vehicle 12 traveling along the lane mark provided on the traveling road. Configured as part.
- the lane mark is a mark that indicates the lane boundary, in addition to continuous lines such as continuous white lines (also referred to as deemed continuous lines), solid white lines, etc. Also included are continuous marks made up of botsdots, cat's eyes, etc. (which can also be regarded as deemed continuous lines).
- the lane mark recognition apparatus 10 basically includes a camera 16 (imaging unit) that images the front of the vehicle 12, and an electronic control unit 20 that recognizes a lane mark from an image captured by the camera 16 ( Electronic Control Unit (hereinafter referred to as ECU 20)).
- a camera 16 imaging unit
- ECU 20 Electronic Control Unit
- the camera 16 is mounted on the upper part of the front windshield of the vehicle 12 and images the front of the vehicle 12 through the front windshield, and images an image including a traveling path ahead of the vehicle.
- the camera 16 is, for example, a digital video camera, and captures, for example, several tens of images (for example, an image of 30 frames) per second.
- the camera 16 has its mounting portion as the origin, the vehicle width direction (horizontal direction) of the vehicle 12 is the X axis, the axle direction (traveling direction, forward direction) is the Y axis, and the vehicle height direction (vertical direction, vertical direction).
- a real space coordinate system with the (direction) as the Z axis is defined.
- the lane mark recognition apparatus 10 includes a speed sensor 22, a yaw rate sensor 24, and a rudder angle sensor 26 in addition to the camera 16 and the ECU 20 described above.
- the speed sensor 22 outputs a vehicle speed [m / s] that is a speed signal of the vehicle 12.
- the yaw rate sensor 24 outputs a yaw rate [deg / s] that is a rotation speed signal indicating a change in the rotation angle of the vehicle 12 in the turning direction.
- the steering angle sensor 26 outputs a steering angle [deg] that is a steering angle signal of the steering device (steering) of the vehicle 12.
- the ECU 20 determines the traveling direction of the vehicle 12 from the output of the yaw rate sensor 24 or the steering angle sensor 26 ⁇ the vehicle width direction of the vehicle 12 is the X axis, and the Y axis direction in front of the vehicle 12 is 0 [deg] (reference).
- the inclination in the X-axis direction on the plane, that is, the steering angle ⁇ is calculated.
- the ECU 20 is a computer including a microcomputer, and includes a CPU (Central Processing Unit), a ROM (including EEPROM) as a memory, a RAM (Random Access Memory), an A / D converter, a D / A converter, and the like. Input / output device, a timer as a timer, and the like, and the CPU functions as various function realization units (function realization means) by reading and executing a program recorded in the ROM.
- a CPU Central Processing Unit
- ROM including EEPROM
- RAM Random Access Memory
- Input / output device a timer as a timer, and the like
- the CPU functions as various function realization units (function realization means) by reading and executing a program recorded in the ROM.
- the ECU 20 functions as the edge extraction unit 32, the short distance setting unit 36, the candidate filtering unit 40, the lane mark candidate determination unit 41, the lane mark recognition unit 42, and the like.
- the short distance setting unit 36 and the candidate filtering unit 40 are used when executing processing for determining lane mark candidates, so that one function of the lane mark candidate determining unit 41, that is, the lane mark candidate determining unit 41 May be included.
- the ECU 20 includes an image memory 30, a lane mark candidate memory 34, and a short distance memory 38 as storage devices.
- the driving support device 14 is configured by adding a steering device 50, a braking device 52, and an acceleration device 54 to the lane mark recognition device 10 described above.
- the driving support device 14 controls the steering device 50, the braking device 52, and the acceleration device 54 under predetermined conditions based on the lane mark recognized by the lane mark recognition device 10, so that the vehicle 12 is sandwiched between the lane marks.
- the driving assistance of the driver is executed so that the vehicle 12 can run substantially in the center of the lane.
- step S1 the ECU 20 captures the captured image (a grayscale image that is a multi-valued image) into the image memory 30 every predetermined time, in this embodiment, every time an image in front of the vehicle is captured by the camera 16.
- the captured image a grayscale image that is a multi-valued image
- step S2 the edge extraction unit 32 performs a binarization process after capturing an image having a predetermined luminance or higher (lightness on the road surface is higher than a predetermined lightness) from the image captured by the camera 16, Differentiating processing is performed while the entire image is scanned in the horizontal direction line by line (and in the forward direction as necessary) to extract edges (edge images) of the entire image.
- step S2 the extracted edge of the entire image is further taken into the lane mark candidate memory 34 as a lane mark candidate (stored).
- planar view edge image planar view edge image
- processing is performed using the planar view edge image. It may be.
- FIG. 3A schematically shows an image 60 (also referred to as an edge image) including edges 62a to 62d, 64a to 64d, 66 as the label candidates taken into the lane mark candidate memory 34.
- FIG. 60 also referred to as an edge image
- a curved image 60 (edges 62a to 62d, 64a to 64d) along the curved road is simulated based on the outputs of the yaw rate sensor 24 and / or the steering angle sensor 26. It is preferable to perform the lane mark candidate determination process after correcting to a linear image 60 along a straight road, in other words, correcting the traveling direction in the Y-axis direction (forward direction).
- the lane mark candidate determination process may be performed based on the output of the yaw rate sensor 24 and / or the steering angle sensor 26 without correcting the image 60 to a straight line along a simulated straight road.
- the horizontal Xmax [number of pixels] generally corresponds to an image of the entire horizontal width (X-axis width) of the captured image
- the vertical Ymax [number of pixels] generally corresponds to an image of the entire vertical width (Y-axis width) of the captured image.
- the origin of the camera 16 corresponds to a pixel position of Xmax / 2 on the X axis and a pixel position of 0 on the Y axis.
- the edge image 60 stored in the lane mark candidate memory 34 includes edges (also referred to as edge images) 62a to 62d and 64a to 64d as lane mark candidates that are true lane marks, as well as non-lanes.
- An edge (also referred to as an edge image) 66 that is a mark and is actually a preceding vehicle (another vehicle) but is a lane mark candidate is included.
- a large number of other noise edges are included in the edge image 60 as lane mark candidates.
- a short distance setting unit 36 (also referred to as a short distance region image range setting unit) is used to extract (detect) an edge (lane mark candidate edge) in the short distance region from the edge image 60.
- the image range of the short-distance area Dn set according to the vehicle speed from the speed sensor 22 is set in the image 60, and the lane mark candidate is included in the set short-distance area Dn.
- the edge image 60n is taken into the short distance memory 38.
- the image range of the short distance area Dn may be set to a fixed area in consideration of the fact that the vehicle speed of the vehicle 12 is maintained at substantially the same speed on an expressway or the like where the maximum speed is defined.
- the image range (0 to the number of pixels Y1) in the vehicle front direction (Y-axis direction) to be set is set short (the number of pixels Y1 is set to a small value). That is, since the image capturing period of one image captured by the camera 16 is the same, when the vehicle speed increases, the distance in the vehicle front direction that enters (appears in) one image increases (FIG. 3A).
- the distance ymax [m] corresponding to the pixel position Ymax on the Y axis shown in FIG. 6 becomes longer), and accordingly, the image range (0 to Y1) in the vehicle front direction set in the short distance area Dn can be set smaller accordingly. it can.
- Y1 on the Y-axis indicates the number of vertical pixels Y1 [pixel] corresponding to the distance y1 [m].
- the edge image 60 includes an edge image 60n in the short distance area Dn and an edge image 60f in the long distance area Df located in front of the short distance area Dn.
- the short distance area Dn and the long distance area Df are collectively referred to as an entire area Dall.
- the lane mark candidate memory 34 includes a short-distance memory 38 that captures the edge image 60n of the short-distance region Dn and a long-distance memory 39 that captures the edge image 60f of the long-distance region Df.
- step S3 when the lane mark candidate edge is extracted from the edge image 60n in the short distance area Dn, it is determined whether or not there is a lane mark candidate edge in the short distance area Dn. For this determination, for example, each edge image 60n in the short-distance region Dn for several consecutive frames is filtered by the candidate filtering unit 40 using an FIR filter or an IIR filter.
- strip-shaped hatching areas 72 and 74 in the short distance area Dn are extracted as areas where the lane mark candidate edges 62a, 62b, 64a and 64b exist.
- step S4 the lane mark recognizing unit 42 extracts a straight line from the entire edge image 60 by Hough transform.
- FIG. 4B shows straight lines 75, 76, and 77 detected by the straight line detection process such as the Hough transform in step S4.
- step S5 the lane mark candidate determination unit 41 is on and near the straight lines 75, 76, 77, and lane mark candidate edges 62a, 62b, 64a, 64b exist in the short distance area Dn.
- the straight lines 75 and 77 to be extracted are extracted as lane mark candidates.
- the straight line 76 detected based on the edge (edge image) 66 of the preceding vehicle (other vehicle) staying in the long-distance area Df has no lane mark candidate edge in the short-distance area Dn, the lane mark Not extracted as a candidate (the straight line 76 and the edge 66 are excluded as non-lane mark candidates).
- the edge 68 related to the reflection, etc. that remains in the long-distance region Df is also on the straight line 78 by the Hough transform and in the vicinity thereof in the short-distance region Dn. Therefore, the straight line 78 and the edge 68 are not extracted as lane mark candidates (the straight line 78 and the edge 68 are excluded as non-lane mark candidates).
- step S6 the lane mark recognition unit 42 causes the lane mark candidate edges 62a to 62d and 64a to 64d on and near the straight lines 75 and 77 that are lane mark candidates shown in FIG. It is recognized as lane marks 82 and 84 (see FIG. 6) that are actually traveling in the center (lane).
- the driving support device 14 ensures that the vehicle 12 does not deviate from the lane (between the lane marks 82 and 84) under a predetermined condition.
- the steering device 50 and the like are controlled so that the vehicle can run in the center of the lane, and the driver's driving assistance is executed.
- the lane mark recognition apparatus 10 is mounted on the vehicle 12 and includes the camera 16 serving as an imaging unit that captures an image including a traveling path ahead of the vehicle 12, and the camera 16. Based on the edge extraction unit 32 that performs edge extraction processing on the captured image and the edge image (edge) 60 extracted by the edge extraction unit 32, lane marks 82 (edges 62a to 62d), 84 (64a To 64d), a lane mark recognition unit 42 and a lane mark candidate determination unit 41 are provided.
- the lane mark candidate determination unit 41 substantially includes a short distance setting unit 36 and a candidate filtering unit 40, and among the edge images (edges) 60 extracted by the edge extraction unit 32, FIG. As shown, the edges 62a, 62b, 64a, 64b detected and detected in the short distance region Dn in front of the vehicle 12 and the edges 62a, 62b, 64a, 64b are detected.
- the straight lines 75 and 77 as the lane mark candidates and the edges 62a to 62d and 64a to 64d are determined based on the edges 62c, 62d, 64c, and 64d in the long distance area Df in front of the vehicle 12 that are continuous with each other.
- the lane mark recognition unit 42 performs lane mark recognition processing on the straight lines 75 and 77 and the edges 62a to 62d and 64a to 64d as the lane mark candidates determined by the lane mark candidate determination unit 41, and the lane mark 82, 84 is recognized.
- the area designation of the short distance area Dn excludes the recognition process for the edge 66 of the other vehicle (previous vehicle) or the like remaining in the same position of the long distance area Df in the captured image. It is possible to prevent erroneous detection of the edge 66 of the other vehicle (previous vehicle) or the like remaining inside as a lane mark candidate (exclude it as a non-lane mark candidate). As a result, it is possible to prevent other vehicles (the preceding vehicle) from being erroneously recognized as lane marks.
- the candidate filtering unit 40 of the lane mark candidate determining unit 41 approaches the vehicle 12 every predetermined time, and the edges 62b and 64b that enter the short-distance region Dn from the long-distance region Df in front of the vehicle 12 (see FIG. 4A) can be detected as an edge in the short distance region Dn.
- the candidate filtering unit 40 of the lane mark candidate determining unit 41 includes the edges 62a, 62b or at least once in the short distance region Dn in front of the vehicle 12 in a plurality of continuous images captured by the camera 16.
- the detected edges 62a and 62b or 64a and 64b can be detected as the edges 62a and 62b or 64a and 64b in the short distance region Dn.
- the front of the vehicle 12 can be determined based on the outputs of the yaw rate sensor 24 and / or the steering angle sensor 26.
- the lane mark candidate determination unit 41 may determine the size of the image range in the vehicle forward direction set in the short distance area Dn as the vehicle speed of the vehicle 12 detected by the speed sensor 22 increases. . This is because, when the vehicle speed is high, the edges 62a and 62b and the edges 64a and 64b surely enter the image range (short distance region Dn) even if the image range of the short distance region Dn is reduced.
- the edge images (edges) 60 (62a to 62d, 64a to 64d, 66) extracted by the edge extraction unit 32 are within the short distance region Dn in front of the vehicle 12.
- the edge image (edge) 60n (62a, 62b, 64a, 64b) detected and detected by the edge image (edge) 60n (62a, 62b, 64a, 64b), and the edge image (edge) 60n (62a, 62b, 64a, 64b), lane mark candidates are determined based on continuous edge images (edges) 60f (62b to 62d, 64b to 64d) in the long distance region Df ahead of the vehicle 12.
- the lane mark candidate determination unit 41 uses the edge image (edge) 60 (62a to 62a) extracted by the edge extraction unit 32. 2d, 66, 64a to 64f), the edge image (edge) 60f (62b to 62d, 64b to 64d, 66) in the long distance region Df in front of the vehicle 12 is detected and detected.
- edge images (edges) that are within the short distance region Dn near the vehicle 12 from the edge image (edge) 60f and that are continuous with the edge images (edges) 60f (62b to 62d, 64b to 64d)
- straight lines 75 and 77 and edge images (edges) 62a to 62d and 64a to 64d are determined as lane mark candidates, and the lane mark recognition unit 42
- the straight lines 75 and 77 and edge images (edges) 62a to 62d and 64a to 64d as the lane mark candidates determined in the above It is also possible to recognize the lane mark 82, 84 performs a lane mark recognition process is.
- the present invention is not limited to the above-described embodiment, and it is needless to say that various configurations can be adopted based on the contents described in this specification.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
Description
以上説明したように、上述した実施形態に係るレーンマーク認識装置10は、車両12に搭載され、前記車両12前方の走行路を含む画像を撮像する撮像部としてのカメラ16と、カメラ16にて撮像された前記画像に対してエッジ抽出処理を行うエッジ抽出部32と、エッジ抽出部32にて抽出されたエッジ画像(エッジ)60に基づき、レーンマーク82(エッジ62a~62d)、84(64a~64d)を認識するレーンマーク認識部42と、レーンマーク候補決定部41を備える。
Claims (6)
- 車両(12)に搭載され、前記車両(12)前方の走行路を含む画像を撮像する撮像部(16)と、
前記撮像部(16)にて撮像された前記画像に対してエッジ抽出処理を行うエッジ抽出部(32)と、
前記エッジ抽出部(32)にて抽出されたエッジ(60)に基づき、レーンマーク(82(62a~62d)、84(64a~64d))を認識するレーンマーク認識部(42)と、
を備えるレーンマーク認識装置(10)において、
レーンマーク候補決定部(41)を備え、
前記レーンマーク候補決定部(41)は、
前記エッジ抽出部(32)にて抽出された前記エッジ(60)のうち、前記車両(12)前方の近距離領域(Dn)内にあるエッジ(62a、62b、64a、64b)を検出し検出した該エッジ(62a、62b、64a、64b)と、前記近距離領域(Dn)内より前記車両(12)前方の遠距離領域(Df)内にあり前記エッジ(62a、62b、64a、64b)に連続するエッジ(62c、62d、64c、64d)と、に基づきレーンマーク候補(75、77、62a~62d、64a~64d)を決定し、
前記レーンマーク認識部(42)は、
前記レーンマーク候補決定部(41)にて決定された前記レーンマーク候補(75、77、62a~62d、64a~64d)に対してレーンマーク認識処理を行う
ことを特徴とするレーンマーク認識装置(10)。 - 請求項1記載のレーンマーク認識装置(10)において、
前記レーンマーク候補決定部(41)は、
所定時間毎に前記車両(12)に接近し、且つ前記車両(12)前方の前記遠距離領域(Df)内から前記近距離領域(Dn)内に入った前記エッジ(62b、64b)を前記近距離領域(Dn)内にある前記エッジとして検出する
ことを特徴とするレーンマーク認識装置(10)。 - 請求項1又は2に記載のレーンマーク認識装置(10)において、
前記レーンマーク候補決定部(41)は、
前記撮像部(16)にて撮像された連続する複数の画像中、前記車両(12)前方の前記近距離領域(Dn)内に、少なくとも1回前記エッジ(62a、62b又は64a、64b)が検出された場合に、検出された前記エッジ(62a、62b又は64a、64b)を、前記近距離領域(Dn)内にある前記エッジ(62a、62b又は64a、64b)として検出する
ことを特徴とするレーンマーク認識装置(10)。 - 請求項1~3のいずれか1項に記載のレーンマーク認識装置(10)において、
前記車両(12)は、該車両(12)のヨーレートセンサ(24)及び/又はステアリングの舵角センサ(26)をさらに、備え、
前記車両(12)前方は、前記ヨーレートセンサ(24)及び/又は前記舵角センサ(26)の出力に基づき決定される
ことを特徴とするレーンマーク認識装置(10)。 - 請求項1~4のいずれか1項に記載のレーンマーク認識装置(10)において、
前記レーンマーク候補決定部(41)は、
前記近距離領域(Dn)に設定する前記車両(12)前方方向の画像範囲を、前記車両(12)の車速が大きくなるに従い、小さく設定する
ことを特徴とレーンマーク認識装置(10)。 - 請求項1~5のいずれか1項に記載のレーンマーク認識装置(10)において、
前記車両(12)前方の遠距離領域(Df)内にあり、且つ所定時間後も前記遠距離領域(Df)内にあるエッジをレーンマーク候補対象外として除去する
ことを特徴とするレーンマーク認識装置(10)。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201380042458.7A CN104603841B (zh) | 2012-08-30 | 2013-05-09 | 行车线标识识别装置 |
JP2014532830A JP5855756B2 (ja) | 2012-08-30 | 2013-05-09 | レーンマーク認識装置 |
DE112013004267.3T DE112013004267T5 (de) | 2012-08-30 | 2013-05-09 | Fahrbahnmarkierungserkennungsvorrichtung |
US14/424,209 US9830518B2 (en) | 2012-08-30 | 2013-05-09 | Lane mark recognition device |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012190437 | 2012-08-30 | ||
JP2012-190437 | 2012-08-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014034187A1 true WO2014034187A1 (ja) | 2014-03-06 |
Family
ID=50183014
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/063008 WO2014034187A1 (ja) | 2012-08-30 | 2013-05-09 | レーンマーク認識装置 |
Country Status (5)
Country | Link |
---|---|
US (1) | US9830518B2 (ja) |
JP (1) | JP5855756B2 (ja) |
CN (1) | CN104603841B (ja) |
DE (1) | DE112013004267T5 (ja) |
WO (1) | WO2014034187A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015210654A (ja) * | 2014-04-25 | 2015-11-24 | 本田技研工業株式会社 | レーンマーク認識装置及び方法並びに車両 |
JP2015215661A (ja) * | 2014-05-08 | 2015-12-03 | 本田技研工業株式会社 | 認識装置 |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9829888B2 (en) * | 2015-11-17 | 2017-11-28 | Ford Global Technologies, Llc | Distinguishing lane markings for a vehicle to follow |
JP6637399B2 (ja) * | 2016-09-30 | 2020-01-29 | 株式会社デンソー | 領域認識装置及び領域認識方法 |
CN107341478A (zh) * | 2017-07-11 | 2017-11-10 | 京东方科技集团股份有限公司 | 一种辅助驾驶***的车辆检测方法及其装置 |
CN108875603B (zh) * | 2018-05-31 | 2021-06-04 | 上海商汤智能科技有限公司 | 基于车道线的智能驾驶控制方法和装置、电子设备 |
CN109584706B (zh) * | 2018-10-31 | 2021-08-03 | 百度在线网络技术(北京)有限公司 | 电子地图车道线处理方法、设备及计算机可读存储介质 |
JP7255345B2 (ja) * | 2019-05-13 | 2023-04-11 | スズキ株式会社 | 走行車線認識装置、走行車線認識方法およびプログラム |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0624035B2 (ja) * | 1988-09-28 | 1994-03-30 | 本田技研工業株式会社 | 走行路判別装置 |
JP2001076147A (ja) * | 1999-09-03 | 2001-03-23 | Nec Corp | 道路白線検出システム、道路白線検出方法および道路白線検出用プログラムを記録した記録媒体 |
JP2003067752A (ja) * | 2001-08-28 | 2003-03-07 | Yazaki Corp | 車両周辺監視装置 |
JP2011221983A (ja) * | 2010-03-26 | 2011-11-04 | Nissan Motor Co Ltd | 車両用環境認識装置 |
JP2012014398A (ja) * | 2010-06-30 | 2012-01-19 | Fuji Heavy Ind Ltd | 車両用白線認識装置 |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5359666A (en) | 1988-09-28 | 1994-10-25 | Honda Giken Kogyo Kabushiki Kaisha | Driving way judging device and method |
JP3314698B2 (ja) | 1997-11-18 | 2002-08-12 | 三菱自動車工業株式会社 | 保舵力補助装置 |
US6819779B1 (en) * | 2000-11-22 | 2004-11-16 | Cognex Corporation | Lane detection system and apparatus |
US7831367B2 (en) * | 2002-11-21 | 2010-11-09 | Lucas Automotive Gmbh | System for influencing the speed of a motor vehicle |
KR100559870B1 (ko) * | 2003-11-04 | 2006-03-13 | 현대자동차주식회사 | 차량의 주행차로 변경방법 |
JP4437714B2 (ja) * | 2004-07-15 | 2010-03-24 | 三菱電機株式会社 | 車線認識画像処理装置 |
US8924078B2 (en) * | 2004-11-18 | 2014-12-30 | Gentex Corporation | Image acquisition and processing system for vehicle equipment control |
JP4659631B2 (ja) * | 2005-04-26 | 2011-03-30 | 富士重工業株式会社 | 車線認識装置 |
CN100429101C (zh) * | 2005-09-09 | 2008-10-29 | 中国科学院自动化研究所 | 汽车行驶安全监控***及监控方法 |
US8208021B2 (en) * | 2005-12-28 | 2012-06-26 | Honda Motor Co., Ltd. | Vehicle and lane mark detection device |
US8164628B2 (en) * | 2006-01-04 | 2012-04-24 | Mobileye Technologies Ltd. | Estimating distance to an object using a sequence of images recorded by a monocular camera |
JP4950858B2 (ja) * | 2007-11-29 | 2012-06-13 | アイシン・エィ・ダブリュ株式会社 | 画像認識装置及び画像認識プログラム |
JP5016073B2 (ja) * | 2010-02-12 | 2012-09-05 | 株式会社デンソー | 白線認識装置 |
JP6141787B2 (ja) * | 2014-04-01 | 2017-06-07 | 本田技研工業株式会社 | レーンマーク認識装置 |
JP6519262B2 (ja) * | 2014-04-10 | 2019-05-29 | 株式会社リコー | 立体物検出装置、立体物検出方法、立体物検出プログラム、及び移動体機器制御システム |
JP6141788B2 (ja) * | 2014-04-14 | 2017-06-07 | 本田技研工業株式会社 | レーンマーク認識装置 |
JP6348758B2 (ja) * | 2014-04-15 | 2018-06-27 | 本田技研工業株式会社 | 画像処理装置 |
-
2013
- 2013-05-09 CN CN201380042458.7A patent/CN104603841B/zh active Active
- 2013-05-09 US US14/424,209 patent/US9830518B2/en active Active
- 2013-05-09 DE DE112013004267.3T patent/DE112013004267T5/de not_active Withdrawn
- 2013-05-09 JP JP2014532830A patent/JP5855756B2/ja active Active
- 2013-05-09 WO PCT/JP2013/063008 patent/WO2014034187A1/ja active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0624035B2 (ja) * | 1988-09-28 | 1994-03-30 | 本田技研工業株式会社 | 走行路判別装置 |
JP2001076147A (ja) * | 1999-09-03 | 2001-03-23 | Nec Corp | 道路白線検出システム、道路白線検出方法および道路白線検出用プログラムを記録した記録媒体 |
JP2003067752A (ja) * | 2001-08-28 | 2003-03-07 | Yazaki Corp | 車両周辺監視装置 |
JP2011221983A (ja) * | 2010-03-26 | 2011-11-04 | Nissan Motor Co Ltd | 車両用環境認識装置 |
JP2012014398A (ja) * | 2010-06-30 | 2012-01-19 | Fuji Heavy Ind Ltd | 車両用白線認識装置 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2015210654A (ja) * | 2014-04-25 | 2015-11-24 | 本田技研工業株式会社 | レーンマーク認識装置及び方法並びに車両 |
JP2015215661A (ja) * | 2014-05-08 | 2015-12-03 | 本田技研工業株式会社 | 認識装置 |
Also Published As
Publication number | Publication date |
---|---|
CN104603841A (zh) | 2015-05-06 |
JP5855756B2 (ja) | 2016-02-09 |
CN104603841B (zh) | 2017-10-24 |
US20150310282A1 (en) | 2015-10-29 |
US9830518B2 (en) | 2017-11-28 |
JPWO2014034187A1 (ja) | 2016-08-08 |
DE112013004267T5 (de) | 2015-06-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5855756B2 (ja) | レーンマーク認識装置 | |
JP4992990B2 (ja) | 区画線検出装置 | |
JP6416293B2 (ja) | 自動車に接近する対象車両を自動車のカメラシステムにより追跡する方法、カメラシステムおよび自動車 | |
US9544546B2 (en) | Cruising lane recognition in a tunnel | |
JP5276637B2 (ja) | 車線推定装置 | |
JP4607193B2 (ja) | 車両及びレーンマーク検出装置 | |
JP5747482B2 (ja) | 車両用環境認識装置 | |
JP3925488B2 (ja) | 車両用画像処理装置 | |
WO2014129312A1 (ja) | 車線境界線逸脱抑制装置 | |
JP5023872B2 (ja) | 画像表示制御装置及び画像表示制御システム | |
JP6468136B2 (ja) | 走行支援装置及び走行支援方法 | |
JP2007179386A (ja) | 白線認識方法及び白線認識装置 | |
JP4744537B2 (ja) | 走行レーン検出装置 | |
WO2014084122A1 (ja) | 車載用制御装置 | |
JP2005301603A (ja) | 走行車線検出装置 | |
JP5971020B2 (ja) | レーン認識装置 | |
US20160314359A1 (en) | Lane detection device and method thereof, and lane display device and method thereof | |
JP2008117073A (ja) | 割り込み車両検出装置 | |
JP5090313B2 (ja) | 路面標示認識装置 | |
JP2007018451A (ja) | 道路区画線検出装置 | |
JP2007310591A (ja) | 画像処理装置及び駐車場判定方法 | |
WO2014050285A1 (ja) | ステレオカメラ装置 | |
JP4995555B2 (ja) | 画像処理装置 | |
JP6722529B2 (ja) | 鉄道用障害物検知システム | |
JP2005329765A (ja) | 走行路認識装置 |
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: 13832622 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2014532830 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14424209 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 112013004267 Country of ref document: DE Ref document number: 1120130042673 Country of ref document: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 13832622 Country of ref document: EP Kind code of ref document: A1 |