Negative image for sign placement detection

• US 9,978,274 B2
• Filed: 11/17/2016
• Issued: 05/22/2018
• Est. Priority Date: 10/27/2014
• Status: Active Grant

• Current Assignee: HERE Global B.V. (Nokia Corporation)
• Original Assignee: HERE Global B.V. (Nokia Corporation)
• Inventors: Dannenbring, Aaron J.
• Primary Examiner(s): MULLEN, THOMAS J
• Application Number:
  US15/353,904
• Publication Number:
  US 20170069206A1
• Time in Patent Office: 551 Days
• Field of Search: 340905, 340903, 340435, 382103, 701 28, 348148
• CPC Class Codes: G01C 21/3602 Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
• CPC Class Codes: G01C 21/3697 Output of additional, non-guidance related information, e.g. low fuel level G01C21/3679 takes precedence
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 10/774 Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/582 of traffic signs
• CPC Class Codes: G08G 1/09623 Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle G08G1/0967 takes precedence
• CPC Class Codes: G08G 1/09626 where the origin of the information is within the own vehicle, e.g. a local storage device, digital map
• CPC Class Codes: G08G 1/096783 where the origin of the information is a roadside individual element

Abstract

Systems, methods, and apparatuses are described for a negative image or false positive profile for sign locations. Image data or another type of optical data is collected along a path by a collection device such as a camera. The data is analyzed to identify one or more false positive locations along the path at which signs for other paths may be detected. The false positive locations may be described in the negative image or false positive profile. Additional or subsequent optical data may be analyzed based on the negative image or false positive profile may be analyzed to identify at least one confirmed sign position.

Claims

1. A method comprising:

receiving sensor data optically collected along a path by a collection device;

identifying one or more false positive locations for one or more signs associated with the path;

identifying a potential position from the sensor data;

comparing the potential position to the one or more false positive locations; and

analyzing the sensor data based on the one or more false positive locations to identify the potential position as a confirmed position in response to a distance between the potential position and at least one of the one or more false positive locations exceeding a threshold distance.

2. The method of claim 1, further comprising:

modifying the identified potential position in response to the distance between the potential position and the at least one of the one or more false positive locations being less than the threshold distance.

3. The method of claim 1, wherein analyzing the sensor data based on the one or more false positive locations comprises:

defining a bounding box for the sensor data according to the one or more false positive locations.

4. The method of claim 3, further comprising:

blocking analysis of the sensor data in the bounding box.

5. The method of claim 3, further comprising:

generating a warning message indicative of a risk of false positives based on the bounding box.

6. The method of claim 3, further comprising:

increasing the threshold distance for the bounding box.

7. The method of claim 1, further comprising:

receiving a set of map data including the one or more false positive locations along the path.

8. A method comprising:

receiving sensor data optically collected along a path by an autonomous vehicle;

identifying one or more false positive locations for one or more signs associated with the path;

identifying a potential position from the sensor data;

comparing the potential position to the one or more false positive locations;

analyzing the sensor data based on the one or more false positive locations to confirm the potential position as a confirmed position; and

generating a command for the autonomous vehicle in response to the confirmed position.

9. The method of claim 8, wherein the command includes data indicative of a road sign for the path.

10. The method of claim 8, wherein the command is a speed warning.

11. The method of claim 8, wherein the command is a command for operation of the autonomous vehicle.

12. The method of claim 8, wherein analyzing the sensor data based on the one or more false positive locations comprises:

defining a bounding box for the sensor data according to the one or more false positive locations.

13. The method of claim 12, further comprising:

blocking analysis of the sensor data in the bounding box.

14. The method of claim 12, further comprising:

generating a warning message indicative of a risk of false positives based on the bounding box.

15. The method of claim 12, further comprising:

increasing the size for the bounding box.

16. A method comprising:

identifying a path;

identifying a potential position from sensor data optically collected along the path by a collection device;

performing a comparison of the potential position to a threshold value with respect to the path;

identifying the potential position as a false positive location for a sign based on the comparison; and

storing data indicative of the false positive location in a geographic database.

17. The method of claim 16, wherein the threshold value is a threshold distance between the potential position and the path.

18. The method of claim 16, wherein the threshold value is an orientation angle threshold for the potential position.

19. The method of claim 16, further comprising:

defining a bounding box for the sensor data according to the false positive location; and

storing the bounding box in the geographic database.

20. The method of claim 16, wherein the threshold value includes an angle, position, or orientation of a sign detected in the optical data.