Dual-vision driving safety warning device and method thereof

• US 8,723,660 B2
• Filed: 09/03/2010
• Issued: 05/13/2014
• Est. Priority Date: 06/08/2010
• Status: Active Grant

• Current Assignee: Automotive Research & Testing Center
• Original Assignee: Automotive Research & Testing Center
• Inventors: Su, Yi-Feng, Chen, Chia-Tseng, Chen, Yu-Sung
• Primary Examiner(s): GIRMA, FEKADESELASS
• Application Number:
  US12/875,331
• Publication Number:
  US 20110298602A1
• Time in Patent Office: 1,348 Days
• Field of Search: 340/435
• US Class Current: 340/435
• CPC Class Codes: B60Q 9/008 for anti-collision purposes
• 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
• 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: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

The present invention discloses a dual-vision driving safety warning device and a method thereof. The device of the present invention comprises an image capture unit, an image processing unit, a vehicle status sensing unit, a warning judgment logic, and at least one warning unit. The image capture unit includes at least two image capture devices installed in a user'"'"'s vehicle and capturing the images of the front traffic environment. The image processing unit processes the images and uses the vehicle status signals detected by the vehicle status sensing unit to calculate the distance between the user'"'"'s vehicle and a front vehicle in the image. The warning judgment logic sends out a control signal when the user'"'"'s vehicle deviates from a driving lane or approaches a front vehicle too much. The warning unit receives the control signal and sends out a warning signal, such as a sound or a flash, to remind the driver.

Claims

1. A dual-vision driving safety warning device comprising

an image capture unit including at least two image capture devices installed in a user'"'"'s vehicle, wherein said image capture devices respectively have different elevation angles and respectively capture a near-field image and a far-field image of a front traffic environment, and wherein said near-field image and said far-field image at least contain images of complete lane marks;

a vehicle status sensing unit sensing at least one status signal of said user'"'"'s vehicle, including a signal of speed, braking, or a direction light;

an image processing unit including a lane mark detection algorithm, a detection angle algorithm, a front vehicle detection algorithm, a distance estimation algorithm and a distance calibration algorithm, using them to process said near-field image and said far-field image and using said detection angle algorithm and said elevation angles with respect to a front vehicle in said near-field image and said far-field image to calculate a distance between said user'"'"'s vehicle and said front vehicle;

a warning judgement logic integrating said vehicle status signal and calculation results of said image processing unit to perform an adaptive cruise control function and sending out a control signal when said user'"'"'s vehicle deviates from a driving lane or approaches said front vehicle too much; and

at least a warning unit connected said image processing unit and said vehicle status sensing unit, and controlled by said control signal to send out a warning signal.

2. The dual-vision driving safety warning device according to claim 1, wherein said distance estimation algorithm roughly estimates distances of said front vehicle in said near-field image and said far-field image captured by said image capture devices, and wherein said distance calibration algorithm intercompares and calibrates said distances to obtain a correct distance to said front vehicle.

3. A dual-vision driving safety warning method comprising steps:

using an image capture unit including at least two image capture devices installed in a user'"'"'s vehicle and respectively having different elevation angles to respectively capture a near-field image and a far-field image of a front traffic environment, wherein said near-field image and said far-field image at least contains images of complete lane marks;

using an image processing unit to process said near-field image and said far-field image by using a lane mark detection algorithm, a detection angle algorithm, a front vehicle detection algorithm, a distance estimation algorithm and a distance calibration algorithm, wherein said processing unit makes use of processing results, at least one vehicle status signal detected by a vehicle status sensing unit, said detection angle algorithm and said elevation angles with respect to a front vehicle in said near-field image and said far-field image to calculate distances between said user'"'"'s vehicle and said front vehicle in said near-field image and said far-field image; and

using a warning judgement logic to output a control signal to enable at least a warning unit to send out a warning signal when said user'"'"'s vehicle deviates from a driving lane or approaches said front vehicle too much.

4. The dual-vision driving safety warning method according to claim 3, wherein said image capture devices are CMOS (Complementary Metal Oxide Semiconductor) elements or CCD (Charge Coupled Device) elements.

5. The dual-vision driving safety warning method according to claim 3, wherein said front vehicle detection algorithm uses a Sobel edge detection method to detect horizontal edges and vertical edges of a front object and determine whether a width and a height of said front object match dimensions of a normal vehicle, and wherein if said width and said height of said front object match said dimensions of said normal vehicle, said distance estimation algorithm is used to estimate a distance to said front vehicle.

6. The dual-vision driving safety warning method according to claim 3, wherein said distance estimation algorithm roughly estimates distances of said front vehicle in said near-field image and said far-field image images captured by said image capture devices, and wherein said distance calibration algorithm intercompares and calibrates said distances to obtain a correct distance to said front vehicle.

7. The dual-vision driving safety warning method according to claim 3, wherein distances are respectively worked out from said near-field image and said far-field image, and wherein said distances are intercompared and calibrated to obtain a correct distance.