Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; 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
  • 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
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
  • G06V10/00—Arrangements for image or video recognition or understanding
  • G06V10/40—Extraction of image or video features
  • G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
  • G06V10/507—Summing image-intensity values; Histogram projection analysis
• • B—PERFORMING OPERATIONS; TRANSPORTING
  • B60—VEHICLES IN GENERAL
  • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
  • B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
  • B60R2300/10—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used
  • B60R2300/102—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the type of camera system used using 360 degree surveillance camera system
• • B—PERFORMING OPERATIONS; TRANSPORTING
  • B60—VEHICLES IN GENERAL
  • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
  • B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
  • B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
  • B60R2300/804—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for lane monitoring
• • 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

Definitions

• a method for determining a lane course for a vehicle The invention relates to a method for determining a lane course for a vehicle according to the preamble of Pa ⁇ tent labors.
• Such a method is, for example, from DE 10207013023 Al, in which the detected vehicle environment by means of a bung Conversely ⁇ sensors and for detecting objects in the vehicle environment divided into lattice cells.
• This grid cells are each assigned a value that indicates the Occupation ⁇ probability of the presence of an object in this lattice cell.
• the value 0 or a lower probability value near 0 is assigned, while for a busy grid cell a high value, for example between 0.5 and 1 is used becomes.
• each grid cell is assigned a value that depends on the distance of a free grid cell from the vehicle, ie, the farther the free grid cell is located, the higher the occupation probability is selected.
• the coordinate system of the grid-based environment map generated by this known method according to DE 10 207 013 023 Al is non-rotatably connected to the global coordinate system, so that during a movement of the vehicle, the vehicle is moved on the two-dimensional grid structure of the surroundings map.
• This lattice-based environment map generated in accordance with DE 10 207 013 023 A1 is used to detect a roadway, a driving tube and / or roadway boundaries.
• an area on the gitterba ⁇ overbased Map is first determined, in which the cast International ⁇ probabilities below a predetermined value, for example. 0.1 are.
• a running in the longitudinal ⁇ direction of the vehicle center line is determined, which is divided into several sub-lines. These partial lines ⁇ then shifted to perpendicular to the direction of the center line on both sides of the vehicle until they moved to mesh cells whose occupation probabilities exceed a certain value, for example. 0.5.
• Road markings or boundaries of a roadway such as crash barriers and the like.
• the image processing algorithms used detect markings mainly due to the dark-light / light-dark transitions between the road surface ⁇ and the lane markings. Furthermore, one moment in the images of structures with the highest contrast, as they are generated mostly by the aforementioned transitions he ⁇ .
• the object of the invention is to provide a comparison with the prior art improved method for determining a lane course for a vehicle, which is possible in particular a tracking of the lane course even at slow speeds or low speeds and hidden areas for the environment sensor.
• Such a method for determining a lane course for a vehicle in which a drivable space limiting structures are detected by at least one image capture unit and these structures are registered in an environment ⁇ map, which divides the vehicle environment into a two-dimensional grid structure of cells, draws
• ⁇ map which divides the vehicle environment into a two-dimensional grid structure of cells
• the position in the grid structure of the surroundings map is determined by means of odometric data of the vehicle and updated continuously,
• the distance and the direction of the vehicle to the cell of the grid structure of the surroundings map is determined, which have the roadway and / or the lane delimiting structures, - detected light-dark and dark-light transitions in the generated by the Bil ⁇ der DCsaku image data and entered into the cells of the grid structure of the Area, and
• the lane course is determined from the cells with the detected light-dark and dark-light transitions.
• Structures delimiting a trafficable space are structures defining a lane as well as, for example, structures bounding a parking space, such as lane boundaries, for example curbs, green strips, lane markings or line markings on the lane center or lane side etc. and traffic signs , including guide posts, etc. understood.
• the lane information is obtained at very low speeds and also at short distances to the vehicle in front, through which, for example, line markings are obscured.
• the lane markers can be tracked ("tracked"), wherein advantageously all forms of lane markings can be detected, ie also bright -dark-and dark-light transitions that are from other road markings ent ⁇ such.
• Tracked traffic signs with Ge ⁇ schwindtechniks very or crosswalks, etc.
• the error rate in the detection of lane marker is extremely low since the deviation of the vehicle relative to the track center, the angular position of the vehicle and the curvature of a Spurmar ⁇ k ist is updated continuously.
• Vehicle lying environment of certain lane course is extrapolated in the front of the vehicle environment.
• the thus estimated further course of the lane or the driving ⁇ web is particularly advantageous when the vehicle is moving in urban transport, in particular in dense traffic or in densely built.
• a stationary coordinate system is used for the area map. This will discretization errors in the
• the method according to the invention is rendered particularly efficient by detecting light-dark and dark-light transitions which are present in a line structure. As a result, in particular road edges and road edges or lane boundaries in the form of line markings are detected quickly and easily.
• the method according to the invention is particularly robust if the grid cells of the surroundings map are classified as passable or not passable.
• the structures and objects of the environment that can be detected from the image data of the image acquisition unit are recorded and entered into the grid cells.
• the odometrical data are determined according to training by means of vehicle sensors, which are usually already present in vehicles, especially motor vehicles.
• the optical flow from the image data of the image acquisition unit is used to determine the position of the vehicle in the grid structure of the environment map in addition to the odometric data.
• vehicle conditions such as wheel spin or Rut ⁇ rule of the vehicle are taken into account.
• Direction of travel of the vehicle to the parallel moving vehicles determined and the determined distances to the parallel moving vehicles are used to verify the specific lane course.
• the track recognition is supported in an advantageous manner.
• FIG. 1 shows a schematic representation of a vehicle with an image acquisition unit for explaining the method according to the invention
• FIG. 2 shows a schematic illustration of a grid-based environment map of a vehicle produced by the method according to the invention
• FIG. 3 shows a flow chart for generating a grid-based environment map according to FIG. 2 by means of the vehicle-mounted image recording system according to FIG. 1 as an exemplary embodiment according to the invention.
• the vehicle diagrammatically illustrated in Figure 1 10, and in particular ⁇ sondere a motor vehicle comprising an imaging system 1 with a camera 2 as an image sensing unit, a reer ⁇ detection unit 3 for detecting objects from the images taken by the camera 2 the image data, wherein the object recognition ⁇ unit 3 a Memory 4 is assigned.
• the object recognition unit 3 has a classifier 3a with which by means of a pattern recognition algorithm a classification of recognized structures and objects, in particular of objects detected in the image data generated by the camera 2, is made at the roadside.
• the roadway or lane delimiting structures such as lane markings, lane boundaries, such as crash barriers and curbs and traffic signs, but, for example, driving out or parallel vehicles, taillights, headlights, etc. can be detected.
• the lane course or the lane course of the vehicle 10 is also determined by the image acquisition system 1 and used for driver assistance functions.
• a driver assistance system 6 is, for example, is provided, which is formed as Spurhalteas- sistenzsystem, the required for the tracking information is supplied with respect to the detected course of the road and possibly interference with the braking and / or steering system of the vehicle 10 takes over actuators 6a before ⁇
• the vehicle 10 includes a display 5, which represents, for example. A portion of a central display and control unit of the driving ⁇ zeugs 10 or a combination instrument of the vehicle 10, which projects the ekterkennungshim of the Whether 3 detected Obwalden, indicating for example. Signs and is therefore connected to dersel ⁇ ben.
• optical and / or acoustic warnings to the driver are displayed or he witnesses ⁇ when an unintentional exit of the detected lane and the lane is detected.
• odometric data of the vehicle 10 are also supplied to the image acquisition system 1 for its motion estimation, for which purpose vehicle sensors 7 detect, for example, the yaw rate, the steering angle and the wheel speeds of the vehicle.
• a first step Sl the captured by the camera 2 vehicle environment is scanned 20 in the form of the image data by means of a stationary or global grid 20a with each moving ⁇ cher mesh size in grid cells 21st
• a grid-based environment map 20 shown in FIG. 2 discretizes the surroundings detected by the camera 1, with only every tenth grid line being entered for reasons of clarity.
• objects from the image data of the camera 2 are detected, classified by the classifier 3a and entered into the grid cells 21 with a ⁇ occupancy probability.
• the grid cells 21 receive the status not passable (grid cells 21a) and "passable" (grid cells 21b). According to FIG. 2, the passable grid cells 21a are shown darker than the non-passable grid cells 21b.
• the odometric data generated by the sensors 7 is detected according to a next process step S3, and the position of the vehicle 10 in the corresponding grid cell 21aLetra ⁇ gene. With the continuously generated odometric data is estimated motion of the vehicle 10 and its Position moved on the environment map 20 according to the motion estimation.
• the distance and the direction of the vehicle 10 to the non-reachable lattice cells 21b which have structures defining the lane and / or lane, can be determined by a further method step S4.
• a subsequent method step S5 all light-dark and dark-light transitions present in a line structure are detected and likewise entered into the environment map 20 (see FIG. 2) and in a last method step S7 as lane markings 22a and 22b of a lane 22 and identified as a right lane marker 23 and tracked by using a particulate filter; besides, also the already passed by the vehicle 10 Spurmarkie ⁇ stanchions 22a, 22b and the roadway limiting structures 23 in the determination of the lane-course of the vehicle 10 are to be included. Even at low speeds, the described method enables tracking of the lane markers 22a, 22b and the lane delimiting structures 23.
• the hitherto determined lane course 22 or lane course 23 is extrapolated into the environment ahead of the vehicle 10.
• the illustrated method can also be improved with respect to the determination of the lane course of the vehicle 10, that parallel-moving vehicles are detected, so that it can be prevented that such parallel running ⁇ object is touched at a lane narrowing by the vehicle 10.
• the image acquisition unit used is a video image-producing camera 2, which can also be a stereo camera. Instead of such a camera 2 can be used to carry out the invention
• a laser scanner-data-generating laser can also be used.

Landscapes

• Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Multimedia (AREA)
• Theoretical Computer Science (AREA)
• Remote Sensing (AREA)
• Radar, Positioning & Navigation (AREA)
• Automation & Control Theory (AREA)
• Traffic Control Systems (AREA)
• Navigation (AREA)
• Optical Radar Systems And Details Thereof (AREA)
• Image Processing (AREA)
• Mechanical Engineering (AREA)

Priority Applications (4)

Applications Claiming Priority (2)

Publications (1)

Family

ID=49225985

Family Applications (1)

Country Status (5)

Cited By (1)

Families Citing this family (17)

Citations (4)

Family Cites Families (57)

• 2012
  • 2012-08-27 DE DE102012107885.8A patent/DE102012107885A1/de not_active Withdrawn
• 2013
  • 2013-08-09 WO PCT/DE2013/200115 patent/WO2014032664A1/de not_active Ceased
  • 2013-08-09 US US14/409,051 patent/US9360332B2/en active Active
  • 2013-08-09 JP JP2015528874A patent/JP6353448B2/ja active Active
  • 2013-08-09 EP EP13765623.7A patent/EP2888604B1/de active Active
  • 2013-08-09 DE DE112013004196.0T patent/DE112013004196A5/de not_active Withdrawn

Patent Citations (4)

Also Published As

Similar Documents

Legal Events