LANE RECOGNITION SYSTEM AND METHOD USING DEFOG SENSOR

• US 20150181173A1
• Filed: 06/26/2014
• Published: 06/25/2015
• Est. Priority Date: 12/24/2013
• Status: Active Grant

• Current Assignee: HL Mando Corporation (Halla Holdings Corporation)
• Original Assignee: Mando Corporation (Halla Holdings Corporation)
• Inventors: PAEK, Seung Bum
• Granted Patent: US 9,275,288 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60H 1/00785 by the detection of humidity or frost
• CPC Class Codes: B60K 2360/1868 according to driving situations
• CPC Class Codes: B60K 2360/21 using cameras
• CPC Class Codes: B60K 35/00 Instruments specially adapted for vehicles; Arrangement of instruments in or on vehicles
• CPC Class Codes: B60K 35/29 Instruments characterised by the way in which information is handled, e.g. showing information on plural displays or prioritising information according to driving conditions
• CPC Class Codes: B60W 10/30 including control of auxiliary equipment, e.g. air-conditioning compressors or oil pumps
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• 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

Abstract

Disclosed herein is a lane recognition system using a defog sensor, including: a defog sensor mounted in a defogging system of a vehicle; an imaging unit mounted on a windshield of the vehicle so as to image the front of the vehicle; and an integrated control unit configured to analyze a defog sensor signal received from the defog sensor, process an image signal received from the imaging unit based on the analyzed defog sensor signal, and acquire lane information.

Claims

1. A lane recognition system using a defog sensor, comprising:

a defog sensor mounted in a defogging system of a vehicle;

an imaging unit mounted on a windshield of the vehicle so as to image the front of the vehicle; and

an integrated control unit configured to analyze a defog sensor signal received from the defog sensor, process an image signal received from the imaging unit based on the analyzed defog sensor signal, and acquire lane information.

2. The lane recognition system according to claim 1, wherein the defog sensor senses the temperature of the windshield and the external temperature.

3. The lane recognition system according to claim 2, wherein when processing the image signal, the integrated control unit analyzes the defog sensor signal, and highlights edges of the image in case where a difference between the temperature of the windshield and the external temperature is less than a predetermined value.

4. The lane recognition system according to claim 2, wherein when processing the image signal, the integrated control unit analyzes the defog sensor signal, and sets a reference vanishing point region such that only an edge corresponding to a vanishing point in a predetermined region is recognized as a lane edge, in case where a difference between the temperature of the windshield and the external temperature is less than a predetermined value.

5. The lane recognition system according to claim 2, wherein when processing the image signal, the integrated control unit analyzes the defog sensor signal, and highlights edges of the image or sets a reference vanishing point region such that only an edge corresponding to a vanishing point in a predetermined region is recognized as a lane edge, in case where a difference between the temperature of the windshield and the external temperature is less than a predetermined value.

6. The lane recognition system according to claim 3, wherein the integrated control unit extracts edges expected as lines on the basis of one or more of the highlighted edges of the image and the reference vanishing point region, clusters the extracted edges through a predetermined algorithm, and removes unnecessary edge groups which do not correspond to the lane information, thereby acquiring lane information.

7. The lane recognition system according to claim 3, wherein the predetermined reference value is set to three degrees.

8. The lane recognition system according to claim 4, wherein the reference vanishing point region is set in the range of above 20 pixels at the center point of the image to below 5 pixels at a point corresponding to 50 m to the front, in the case of a quarter video graphics array (QVGA).

9. The lane recognition system according to claim 3, wherein the integrated control unit transmits the acquired lane information to a lane recognition-based advanced driver assistance system (ADAS) of the vehicle.

10. The lane recognition system according to claim 1, wherein the imaging unit comprises a charge-coupled device (CCD) camera.

11. The lane recognition system according to claim 1, wherein the defog sensor, the imaging unit, and the integrated control unit are implemented on the basis of a single ECU.

12. A lane recognition method using a defog sensor, comprising:

a signal reception step of receiving a defog sensor signal from a defog sensor provided in a defogging system of a vehicle, and receiving an image signal from an imaging unit which is mounted on a windshield of the vehicle so as to image the front of the vehicle;

an image processing step of analyzing the defog sensor signal received at the signal reception step and processing the image signal based on the analyzed defog sensor signal; and

acquiring lane information from the image processed at the image processing step.

13. The lane recognition method according to claim 12, wherein the image processing step comprises:

a processing reference setting step of analyzing the defog sensor signal and highlighting edges of the image or setting a reference vanishing point region when a difference between the temperature of the windshield and the external temperature is less than a predetermined reference value;

an edge extraction step of extracting edges expected as lanes on the basis of the reference set at the processing reference setting step;

a clustering step of clustering the edges extracted at the edge extraction step through a predetermined algorithm; and

a filtering step of removing unnecessary edge groups which do not correspond to the lane information among the edge groups formed at the clustering step.

14. The lane recognition method according to claim 12, wherein the predetermined reference value is set to three degrees.

15. The lane recognition method according to claim 12, wherein the reference vanishing point region is set in the range of above 20 pixels at the center point of the image to below 5 pixels at a point corresponding to 50 m to the front, in the case of a QVGA.

16. The lane recognition method according to claim 12, further comprising transmitting the acquired lane information to a lane recognition-based ADAS of the vehicle, after the lane information acquisition step.

17. The lane recognition method according to claim 12, wherein the signal reception step, the image processing step, and the lane information acquisition step are implemented on the basis of a single ECU.