Lane recognition system

• US 20030072471A1
• Filed: 10/17/2002
• Published: 04/17/2003
• Est. Priority Date: 10/17/2001
• Status: Active Grant

• Current Assignee: Hitachi Astemo Ltd. (Hitachi, Ltd.)
• Original Assignee: Hitachi, Ltd.
• Inventors: Otsuka, Yuji, Muramatsu, Shoji, Takenaga, Hiroshi, Takezaki, Jiro, Monjii, Tatsuhiko
• Granted Patent: US 7,295,682 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: B60T 2201/08 Lane monitoring; Lane Keeping Systems
• CPC Class Codes: B60T 2201/089 using optical detection
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G06V 30/244 using graphical properties, e.g. alphabet type or font

Abstract

A driving lane recognition system which can improve the lane recognition accuracy by stably detecting the various kinds of lane markers is disclosed. An image processing means 6 for image-processing a road image taken by a camera 5 has a plurality of different kinds of image processing algorithms 9 to 11. A driving lane is detected by selecting an image processing algorithm suitable for the driving lane out of the plurality of different kinds of image processing algorithms 9 to 11 corresponding to a road on which a vehicle is running.

Claims

1. A driving lane recognition system, which comprises:

an imaging means for taking an image of a road in front of a vehicle, said imaging means being mounted on said vehicle;

an image processing means for detecting the driving lane of said vehicle from the image of road taken by said imaging means, said image processing means having a plurality of different kinds of image processing algorithms individually corresponding to various kinds of lane markers of the driving lane arranged on said road; and

an image processing algorithm selection means for identifying the lane marker kind on the road on which said vehicle is running, and for selecting one of the image processing algorithms used by said image processing means to detect the driving lane.

2. A driving lane recognition system, which comprises:

an imaging means for taking an image of a road in front of a vehicle, said imaging means being mounted on said vehicle;

an image processing means for detecting the driving lane of said vehicle from the image of road taken by said imaging means, said image processing means having a plurality of different kinds of image processing algorithms individually corresponding to various kinds of lane markers of the driving lane arranged on said road; and

an image processing algorithm selection means for identifying the lane marker kind on the road on which said vehicle is running, and for selecting one of the image processing algorithms used for detecting the driving lane using the said image processing means, wherein

said image processing means comprises a road surface pattern recognition algorithm for executing road pattern recognition processing of said road when the driving lane can not be detected by said plurality of image processing algorithms.

3. A driving lane recognition system, which comprises:

an imaging means for taking an image of a road in front of a vehicle, said imaging means being mounted on said vehicle;

an image processing means for detecting the driving lane of said vehicle from the image of road taken by said imaging means, said image processing means having a plurality of different kinds of image processing algorithms individually corresponding to various kinds of lane markers of the driving lane arranged on said road;

an image processing algorithm selection means for identifying the lane marker kind on the road on which said vehicle is running, and for selecting one of the image processing algorithms used for detecting the driving lane using the said image processing means;

a position detection means for detecting a position of road on which said vehicle is running;

a road map data file for storing said lane marker kinds individually for said roads; and

a lane marker kind identification means for capturing and identifying the lane marker kind on the road on which said vehicle is running based on positional information of said position detection means, and for selecting the image processing algorithm used by said image processing means to detect the driving lane.

4. A driving lane recognition system, which comprises:

a camera for taking an image of a road in front of a vehicle, said camera being mounted on said vehicle;

an image processing means for detecting the driving lane of said vehicle from the image of road taken by said camera, said image processing means having a plurality of different kinds of image processing algorithms individually corresponding to various kinds of lane markers of the driving lane arranged in said road;

a GPS receiving means for receiving positional information of the road on which said vehicle is running from a satellite;

a road map data file for storing said lane marker kinds individually for said roads; and

a lane marker kind identification means for capturing and identifying the lane marker kind on the road on which said vehicle is running based on positional information of said GPS receiving means, and for selecting one of the image processing algorithms used by said image processing means to detect the driving lane.

5. A driving lane recognition system, which comprises:

a camera for taking an image of a road in front of a vehicle, said camera being mounted on said vehicle;

an image processing means for detecting the driving lane of said vehicle from the image of road taken by said camera, said image processing means having a plurality of different kinds of image processing algorithms individually corresponding to various kinds of lane markers of the driving lane arranged in said road;

a beacon receiving means for receiving lane marker shape information of the road on which said vehicle is running from a road-to-vehicle communication system; and

a lane marker kind identification means for capturing and identifying the lane marker kind on the road on which said vehicle is running based on said lane marker shape information received by said beacon receiving means, and for selecting one of the image processing algorithms used by said image processing means to detect the driving lane.

6. A driving lane recognition system, which comprises:

a camera for taking an image of a road in front of a vehicle, said camera being mounted on said vehicle;

an image processing means for detecting the driving lane of said vehicle from the image of road taken by said camera, said image processing means having a plurality of different kinds of image processing algorithms individually corresponding to various kinds of lane markers of white line, raised pavement marker and post cone arranged on said road;

a position detection means for detecting a position of road on which said vehicle is running;

a road map data file for storing said lane marker kinds of the white line, the raised pavement marker and the post cone individually for said roads; and

a lane marker kind identification means for capturing and identifying the lane marker kind on the road on which said vehicle is running based on positional information of said position detection means, and for selecting one of the image processing algorithms used by said image processing means to detect the driving lane.

7. A driving lane recognition system, which comprises:

a camera for taking an image of a road in front of a vehicle, said camera being mounted on said vehicle;

an image processing means for detecting the driving lane of said vehicle from the image of road taken by said camera, said image processing means having a plurality of different kinds of image processing algorithms individually corresponding to various kinds of lane markers of white line, raised pavement marker and post cone arranged on said road;

a position detection means for detecting a position of road on which said vehicle is running;

a road map data file for storing said lane marker kinds of the white line, the raised pavement marker and the post cone individually for said roads; and

a lane marker kind identification means for capturing and identifying the lane marker kind on the road on which said vehicle is running based on positional information of said position detection means, and for selecting one of the image processing algorithms used by said image processing means to detect the driving lane, wherein

said image processing algorithm of said image processing means includes detection of the lane based on edge information of lane marker, detection of the lane based on pattern matching using a pattern shape of lane marker and detection of the lane based on density projection information of a road surface.

8. A driving lane recognition system, which comprises:

a camera for taking an image of a road in front of a vehicle, said camera being mounted on said vehicle;

an image processing means for detecting the driving lane of said vehicle from the image of road taken by said camera, said image processing means having a plurality of different kinds of image processing algorithms individually corresponding to various kinds of lane markers of the driving lane arranged in said road;

an image processing selection means which selects one of the image processing algorithms employed for detecting the driving lane of the vehicle in this time based on a recognition confidence by an image processing algorithm employed for detecting the driving lane of the vehicle in the precedent time by said image processing means.

9. A driving lane recognition system according to claim 8, wherein said image processing algorithm selection means comprises an algorithm recognition confidence result file for storing a history on kinds and confidences of the image processing algorithms selected in the past, and selects one of said image processing algorithms based on said history.