Monocular computer vision aided road vehicle driving for safety

• US 20030030546A1
• Filed: 04/10/2002
• Published: 02/13/2003
• Est. Priority Date: 07/12/2001
• Status: Active Grant

• Current Assignee: Din-Chang Tseng
• Original Assignee: Din-Chang Tseng
• Inventors: Tseng, Din-Chang
• Granted Patent: US 6,765,480 B2
• Time in Patent Office: Days
• US Class Current: 340/425.5
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads

Abstract

The present invention is a monocular computer vision technique. The technique is used to aid road vehicle driving for safety. An camera (e.g., camera or TV camera or camcorder) is installed in a vehicle facing to the road in front of the vehicle to capture a sequence of road/scene images for analyzing the driving situation. The situation includes the distance to a front obstacle or vehicle, the speed of the vehicle, and the left/right location of the vehicle in a road lane.

Claims

1. A monocular computer vision method to aid road vehicle driving for safety, a camera being installed in a vehicle facing to a road in front of said vehicle, said method comprising steps of:

i. using said camera to capture a sequence of road/scene images;

ii. processing said sequence of road/scene images;

iii. analyzing a driving situation from said processing results.

2. A method according to claim 1 wherein said camera is a digital camera or camcorder.

3. A method according to claim 1 wherein said vehicle is a car, bus, or truck.

4. A method according to claim 1 wherein said camera is fixed near a center of a windshield of said vehicle and an upper border of said windshield;

said camera faces to said road in front of said vehicle;

a contents of said sequence of road/scene images are said road and scene in front of said vehicle.

5. A method according to claim 1 wherein said driving situation includes:

a distance to a front obstacle or vehicle,

a speed of said vehicle, and

a left/right location of said vehicle in a road lane.

6. A method according to claim 5 wherein said distance to a front obstacle or vehicle is determined from steps of:

i. from said sequence of road/scene images to extract two lines on both side of said road lane and then find an intersection point of said two lines;

said intersection point is just a vanishing point of said two lines;

ii. from said vanishing point and a known focal length of a lens of said camera to find a pitch and yaw angles of said two lines with respect to a camera coordinate system;

iii. from said pitch angle and a height of said camera to calculate a distance from a location of said camera to a point which is said intersection point of an optical axis of said camera and a road plane;

iv. from said images to find horizontal lines that indicates said intersection point of rear wheels of front vehicles and said road, select a nearest horizontal line that overlaps said road lane, and judge that said horizontal line is located above or below an image center; and

v. from said known camera focal length, camera height, pitch angle, and a vertical distance from said horizontal line to said image center to find said distance from said camera location to said rear wheel of said front vehicle or obstacle.

7. A method according to claim 6 wherein said vehicle speed is computed based on a determination of said distance to a front vehicle;

at first, a terminal point of a dashed lane line is found in said sequence of road/scene images;

for said images, said distances from said camera location to said terminal point are calculated respectively;

said vehicle speed is just derived from said distance difference dividing by a time difference for said images.

8. A method according to claim 6 wherein said left/right location of said vehicle in a road lane is computed from a ratio of two distances which are from a midpoint of an image lower border to said intersection points of an extended image lower border and two lines of said road lane.