Lane image processing system for vehicle

• US 5,790,403 A
• Filed: 07/11/1995
• Issued: 08/04/1998
• Est. Priority Date: 07/12/1994
• Status: Expired due to Term

• Current Assignee: Honda Giken Kogyo Kabushiki Kaisha
• Original Assignee: Honda Giken Kogyo Kabushiki Kaisha
• Inventors: Nakayama, Shigeto
• Primary Examiner(s): NGUYEN, TAN QUANG
• Time in patent office: 1120 Days
• Field of Search: 364/424.027, 364/424.033, 364/447, 364/460, 364/461, 364/462, 364/436, 382/103, 382/104, 382/106, 382/168, 382/171, 382/199, 382/281, 340/437, 340/435, 340/436, 348/118
• US Class Current: 701/28
• 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: G05D 1/0251 extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision stereoscopic image analysis H04N13/00; depth recovery from images G06T7/593
• CPC Class Codes: G05D 1/0272 comprising means for registering the travel distance, e.g. revolutions of wheels measuring distance traversed on the ground by vehicles, e.g. using odometers G01C22/00
• CPC Class Codes: G06K 9/00798 Recognition of lanes or road borders, e.g. of lane markings, or recognition of driver's driving pattern in relation to lanes perceived from the vehicle; Analysis of car trajectory relative to detected road determination of trajectories G06T7/20
• CPC Class Codes: G06K 9/00805 Detecting potential obstacles recognising people G06K9/00362
• CPC Class Codes: G06K 9/4633 by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation

Abstract

A lane image processing system for a vehicle to recognize the lane on which the vehicle travels. The system has a CCD camera mounted on the vehicle for viewing a roadway scene ahead of the vehicle to output image data of the roadway scene including the lane on which the vehicle travels. Obstacles such as preceding vehicle are detected and a region for image data processing is determined so as to avoid the position of the obstacle and the lane on which the vehicle travels is recognized based on the processed result. More specifically, lane boundary positions estimated up to a preceding cycle are stored as historical information and in the region Hough transformation is limited in areas determined based on the historical information and the horizon in the roadway scene.

Claims

1. A system for processing lane images for a vehicle, including:

an image sensor mounted on the vehicle for viewing a roadway scene ahead of the vehicle to output image data of the roadway scene including a lane on which the vehicle travels;

image data processing means for processing the image data to output lane information; and

lane recognition means for recognizing the lane on which the vehicle travels based on the output lane information;

wherein the improvement comprises;

obstacle position determining means for determining a position of an obstacle present in the roadway scene;

nearest obstacle selecting means for selecting the position of a nearest obstacle when a plurality of obstacles are present;

lane boundary position storing means for storing a lane boundary position estimated up to a preceding image data processing as historical information;

processing region determining means for determining a region of the data image to be processed at least based on the detected position of the nearest obstacle and the historical information such that the region excludes the detected position of the nearest obstacle.

2. A system according to claim 1, wherein said processing region determining means determines the region such that the region is made up of a left half and a right half that overlap partially with each other.

3. A system according to claim 2, wherein said image sensor is a CCD camera.

4. A system according to claim 1, wherein said processing region determining means includes:

area determining means for determining an area in the region;

edge image extracting means for extracting edge images in the image date of the area;

Hough transforming means for carrying out Hough transformation on the edge images;

straight line detecting means for detecting one straight line from among straight lines obtained from the Hough transformation; and

said lane recognition means recognizes the lane on which the vehicle travels based on the detected straight line.

5. A system according to claim 4, wherein said image sensor is a CCD camera.

6. A system according to claim 1, wherein said image sensor is a CCD camera.

7. A system for processing lane images for a vehicle, including:

an image sensor mounted on the vehicle for viewing a roadway scene ahead of the vehicle to output image data of the roadway scene including a lane on which the vehicle travels;

image data processing means for processing the image data to output lane information; and

lane recognition means for recognizing the lane on which the vehicle travels based on the output lane information;

wherein the improvement comprises;

obstacle position determining means for determining position of an obstacle present in the roadway scene;

processing region determining means for determining a region of the data image to be processed at least based on the detected obstacle position such that the region excludes the detected obstacle position;

said image data processing means includes area determining means for determining an area in the region, edge image extracting means for extracting edge images in the image date of the area, Hough transforming means for carrying out Hough transformation on the edge images, straight line detecting means for detecting one straight line from among straight lines obtained from the Hough transformation, and said lane recognition means recognizes the lane on which the vehicle travels based on the detected straight line;

lane boundary position storing means for storing a lane boundary position estimated up to a preceding image data processing as historical information; and

said area determining means determines a first area based on the historical information and a second area based on a position where a new lane boundary can be expected to appear.

8. A system according to claim 7, wherein said area determining means determines the second area based on a position corresponding to a horizon in the roadway scene.

9. A system according to claim 8, wherein said straight line detecting means includes;

setting means initially setting centers of clusters of the straight lines obtained from the Hough transformation;

clustering means for clustering the straight lines obtained from the Hough transformation;

defining means for defining average in each cluster as new centers; and

uniting means for uniting proximate cluster to detect said straight line.

10. A system according to claim 7, wherein said straight line detecting means includes;

setting means initially setting centers of clusters of the straight lines obtained from the Hough transformation;

clustering means for clustering the straight lines obtained from the Hough transformation;

defining means for defining average in each cluster as new centers; and

uniting means for uniting proximate cluster to detect said straight line.

11. A system for processing lane images for a vehicle, including:

an image sensor mounted on the vehicle for viewing a roadway scene ahead of the vehicle to output image data of the roadway scene including a lane on which the vehicle travels;

image data processing means for processing the image data to output lane information; and

lane recognition means for recognizing the lane on which the vehicle travels based on the output lane information;

wherein the improvement comprises;

obstacle position determining means for determining position of an obstacle present in the roadway scene;

processing region determining means for determining a region of the data image to be processed at least based on the detected obstacle position such that the region excludes the detected obstacle position;

said image data processing means includes area determining means for determining an area in the region, edge image extracting means for extracting edge images in the image date of the area, Hough transforming means for carrying out Hough transformation on the edge images, straight line detecting means for detecting one straight line from among straight lines obtained from the Hough transformation, and said lane recognition means recognizes the lane on which the vehicle travels based on the detected straight line;

wherein said straight line detecting means includes setting means initially setting centers of clusters of the straight lines obtained from the Hough transformation, clustering means for clustering the straight lines obtained from the Hough transformation, defining means for defining an average in each cluster as new centers, and

uniting means for uniting proximate cluster to detect said straight line.