Method for the operation of an assistance system of a motor vehicle, as well as assistance system

• US 9,792,511 B2
• Filed: 07/24/2015
• Issued: 10/17/2017
• Est. Priority Date: 07/25/2014
• Status: Active Grant

• Current Assignee: Conti Temic Microelectronic GmbH (Continental AG)
• Original Assignee: Conti Temic Microelectronic GmbH (Continental AG)
• Inventors: Behrens, Alexander
• Primary Examiner(s): Conner, Sean
• Application Number:
  US14/808,257
• Publication Number:
  US 20160026882A1
• Time in Patent Office: 816 Days
• Field of Search: None
• CPC Class Codes: G06V 10/46 Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features colour feature extraction G06V10/56
• CPC Class Codes: G06V 20/582 of traffic signs

Abstract

A method is provided for operating a driver assistance system of a motor vehicle to detect a polygon-shaped (and especially rectangular) traffic sign with a number of edges. A camera acquires an image of the traffic sign. Within at least a portion of the image, a number of first line segments is determined, which is less than the number of edges of the traffic sign. Based on the first line segments, a reproduction of the traffic sign is identified.

Claims

1. A method of operating a driver assistance system of a motor vehicle for detecting a rectangular traffic sign bounded by four edges in an environment outside of the motor vehicle, comprising steps:

with a camera of the driver assistance system, acquiring an image of the traffic sign;

with a computing unit of the driver assistance system, analyzing only a portion of the image which comprises two vertically longitudinally extending rectangular areas that are arranged parallel and spaced apart relative to one another, and one horizontally longitudinally extending rectangular area that is arranged perpendicular to and in a spacing distance between the two vertically longitudinally extending rectangular areas, and thereby determining exactly three first line segments in the portion of the image of the traffic sign by detecting at least one substantially horizontal second line segment that exists in the horizontally longitudinally extending rectangular area in the image, detecting substantially vertical second line segments that exist in the vertically longitudinally extending rectangular areas in the image, and determining the three first line segments by selecting as the first line segments, a respective one of the second line segments that best satisfies at least one prescribed criterion in each one of the rectangular areas; and

with the computing unit, identifying a reproduction of the traffic sign based on and dependent on the three first line segments that were determined.

2. The method according to claim 1, wherein the analyzing of the portion of the image of the traffic sign comprises performing a gradient method to determine the first line segments in the image.

3. The method according to claim 1, wherein the second line segments comprise all of the substantially horizontal line segments and all of the substantially vertical line segments that exist within the rectangular areas in the image of the traffic sign.

4. The method according to claim 1, further comprising changing respective sizes of the rectangular areas.

5. The method according to claim 1, wherein the rectangular areas are arranged in a U-shape with respect to one another.

6. The method according to claim 5, wherein the U-shape is an upside-down U-shape, and wherein the horizontally extending rectangular area is located above the vertically extending rectangular areas to form the upside-down U-shape.

9. The method according to claim 1, further comprising, with a display device of the driver assistance system, displaying the reproduction of the traffic sign or a symbol based on the reproduction of the traffic sign.

10. The method according to claim 1, wherein the three first line segments respectively correspond to three of the four edges of the rectangular traffic sign.

11. The method according to claim 1, wherein the edges of the traffic sign include two substantially horizontal edges and two substantially vertical edges, and the two substantially vertical edges of the traffic sign in the image are partially within, longer than and extend out of the vertically extending rectangular areas.

12. The method according to claim 1, wherein the edges of the traffic sign include two substantially horizontal edges and two substantially vertical edges, and each one of the two substantially vertical edges of the traffic sign in the image is respectively shorter than and has an end terminating within a respective one of the vertically extending rectangular areas.

13. The method according to claim 1, wherein the method is not able to detect and not able to determine a height-to-width ratio of the rectangular traffic sign.

7. A driver assistance system of a motor vehicle for detecting a rectangular traffic sign bounded by four edges in an environment outside of the motor vehicle, said driver assistance system comprising:

a camera configured and adapted to acquire an image of the traffic sign, and

a computing unit configured and adapted to analyze only a portion of the image which comprises two vertically longitudinally extending rectangular areas that are arranged parallel and spaced apart relative to one another, and one horizontally longitudinally extending rectangular area that is arranged perpendicular to and in a spacing distance between the two vertically longitudinally extending rectangular areas, and thereby to determine exactly three first line segments in the portion of the image of the traffic sign by detecting at least one substantially horizontal second line segment that exists in the horizontally longitudinally extending rectangular area in the image, detecting substantially vertical second line segments that exist in the vertically longitudinally extending rectangular areas in the image, and determining the three first line segments by selecting as the first line segments, a respective one of the second line segments that best satisfies at least one prescribed criterion in each one of the rectangular areas, and wherein the computing unit is further configured and adapted to identify a reproduction of the traffic sign based on and dependent on the three first line segments that were determined.

8. The driver assistance system according to claim 7, further comprising a display device configured and arranged to display the reproduction of the traffic sign or a symbol based on the reproduction of the traffic sign.