Driver assistance system and method with object detection facility

• US 8,093,999 B2
• Filed: 03/04/2009
• Issued: 01/10/2012
• Est. Priority Date: 09/07/2006
• Status: Active Grant

• Current Assignee: Bayerische Motoren Werke AG
• Original Assignee: Bayerische Motoren Werke AG
• Inventors: Bauer, Guenter, Thoma, Stephan
• Primary Examiner(s): Wu, Daniel
• Assistant Examiner(s): Mahase, Pameshanand
• Application Number:
  US12/397,803
• Publication Number:
  US 20090160630A1
• Time in Patent Office: 1,042 Days
• Field of Search: 340/435, 340/540
• US Class Current: 340/435
• CPC Class Codes: G01S 17/86 Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• CPC Class Codes: G01S 17/89 for mapping or imaging
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G01S 3/7865 using correlation of the live video image with a stored image

Abstract

A method is provided for attracting the attention of a motor vehicle driver to a potential hazardous spot in an image, which is illustrated in a real form on a display of the motor vehicle or in a virtual form in a region of the motor vehicle. At least one laser scanner provided in the vehicle scans the surroundings in front of the vehicle and determines the shape of an object and the distance of the object from the vehicle. At least one infrared camera, in particular a thermal imaging camera, is provided on the vehicle. It records the surroundings in front of the vehicle and makes available the real or virtual image of the surroundings for display to the driver. The object is compared with at least a first reference object within the scope of a first pattern recognition process. If there is significant correspondence between the object and the reference object, that area on the real or virtual image displayed to the driver in which the object is to be found is determined. The respective area of the image and/or the respective object is highlighted in the image.

Claims

1. A method for attracting attention of the driver in a motor vehicle to a potential hazardous spot, the method comprising the acts of:

scanning surroundings in front of the vehicle using at least one laser scanner in the vehicle and determining a shape of an object and a distance of the object from the vehicle;

recording the surroundings in front of the vehicle using at least one thermal imaging camera provided in the vehicle and making available a real image or a virtual image of the surroundings for display;

comparing the shape of the object with at least a first reference object utilizing a first pattern recognition process;

if, based on said comparing, a significant correspondence occurs between the shape of the object and the at least first reference object, determining an area on the real or virtual image displayed to the driver in which the object is to be found; and

highlighting, if the significant correspondence occurs between the shape of the object and the at least first reference object, at least one of the determined area of the real or virtual image and the respective object to be found in that area.

2. The method according to claim 1, wherein the image is an infrared image acquired by the thermal imaging camera.

3. The method according to claim 1, wherein the determined area of the image and/or the respective object in the image is compared with at least a second reference object utilizing a second pattern recognition process, and further wherein the determined area of the image and/or the respective object is highlighted in the image if both the first and the second comparisons show significant correspondence.

4. The method according to claim 2, wherein the determined area of the image and/or the respective object in the image is compared with at least a second reference object utilizing a second pattern recognition process, and further wherein the determined area of the image and/or the respective object is highlighted in the image if both the first and the second comparisons show significant correspondence.

5. The method according to claim 1, wherein the first reference object has an L-shape in order to determine whether and, if so, where the laser scan has at least an L-shaped object.

6. The method according to claim 1, wherein the first reference object has two spaced L-shapes in order to determine whether and, if so, where the laser scan has at least two spaced L-shapes.

7. The method according to claim 1, wherein a shape of a moving object is compared with a moving first reference object utilizing the first pattern recognition process.

8. The method according to claim 7, wherein the shape of the object moving in the real or virtual image is compared with a moving second reference object utilizing a second pattern recognition process.

9. The method according to claim 1, wherein the first pattern recognition process is carried out continuously.

10. The method according to claim 3, wherein the first and the second pattern recognition processes are carried out continuously.

11. The method according to claim 7, wherein the first pattern recognition process is carried out continuously.

12. The method according to claim 8, wherein the first and the second pattern recognition processes are carried out continuously.

13. The method according to claim 1, wherein the virtual image is generated by a head-up display in front of a windshield of the vehicle.

14. The method according to claim 1, wherein the laser scanner scans objects using laser beams having a wavelength located in a near or far infrared range.

15. The method according to claim 1, wherein the laser scanner determines the size and/or the speed of objects and an examination is carried out utilizing the first pattern recognition process as to whether the object has a size and/or speed, which corresponds to a typical size of a first reference object and/or the speed of a first reference object.

16. The method according to claim 14, wherein the laser scanner determines the size and/or the speed of objects and an examination is carried out utilizing the first pattern recognition process as to whether the object has a size and/or speed, which corresponds to a typical size of a first reference object and/or the speed of a first reference object.

17. A driver assistance system for a motor vehicle, comprising:

at least one laser scanner arranged in the vehicle, the scanner scanning surroundings in front of the vehicle and determining a shape of an object and a distance of the object from the vehicle;

a thermal imaging camera arranged in the vehicle, the thermal imaging camera recording surroundings in front of the vehicle and generating a real or virtual image of the surroundings; and

a display for displaying the real or virtual image of the surroundings, wherein if there is a significant correspondence between the shape of the object and the first reference object, an area on the display in which the object is found is determined and the determined area and/or the object is highlighted in the image on the display,

wherein the driver assistance system processor is further configured to compare the shape of the object with at least a first reference object to determine whether there is a significant correspondence between the shape of the object and the first reference object.

18. The driver assistance system according to claim 17, wherein the determined area and/or the object in the image is compared with at least a second reference object utilizing a second pattern recognition process, and further wherein the determined area of the image and/or the respective object is highlighted if both the first and the second comparisons find a significant correspondence.

19. The driver assistance system according to claim 18, wherein the first reference object has an L-shape, which L-shape is compared against the object determined by the at least one laser scanner.

20. The driver assistance system according to claim 17, wherein the first reference object has two spaced L-shapes, which two spaced L-shapes are compared against the object determined by the at least one laser scanner.