Negative image for sign placement detection

Patent metadata

Field	Value
Publication number	US-9530313-B2
Application number	US-201414524606-A
Country	US
Kind code	B2
Filing date	Oct 27, 2014
Priority date	Oct 27, 2014
Publication date	Dec 27, 2016
Grant date	Dec 27, 2016

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.

First claim

I claim:

1. A method comprising:
receiving optical data, wherein the optical data is collected along a current path by an optical sensor;
identifying one or more false positive locations for signs along the current path, wherein the one or more false positive locations are calculated based on at least one previously confirmed sign position in an adjacent path, wherein the adjacent path is adjacent to the current path;
identifying a potential sign position from the optical data;
analyzing the optical data based on the one or more false positive locations to locate at least one sign position along the current path in the optical data, wherein when a distance between the potential sign position and a closest of the one or more false positive locations exceeds a threshold, applying a first algorithm to the optical data; and
when the distance between the potential sign position and the closest of the one or more false positive locations is less than the threshold, applying a second algorithm to the optical data.

2. The method of claim 1 , further comprising:
providing the at least one confirmed sign position to an assisted driving device.

3. The method of claim 1 , further comprising:
identifying a speed value detected from a sign at the at least one confirmed sign position.

4. The method of claim 3 , further comprising:
receiving speed data for a vehicle traveling on the path;
performing a comparison of the speed data to the speed value; and
generating a warning based on the comparison.

5. The method of claim 1 , further comprising:
receiving a set of map data including the one or more false positive locations along the current path.

6. The method of claim 5 , wherein a size of the set of map data is selected as a function of a characteristic of the optical sensor.

7. The method of claim 1 , wherein the optical sensor is a light detection and ranging (LIDAR) device.

8. A method comprising:
receiving optical data, wherein the optical data is collected along a path by a collection device;
identifying one or more false positive locations for signs along the path;
identifying a potential sign position from the optical data;
comparing the potential sign position to the one or more false positive locations; and
analyzing the optical data based on the one or more false positive locations to confirm the potential sign position as a confirmed sign position along the path,
when a distance between the potential sign position and a closest of the one or more false positive locations exceeds a threshold, identifying the potential sign position as the confirmed sign position; and
when the distance between the potential sign position and the closest of the one or more false positive locations is less than the threshold, deleting the potential sign position.

9. An apparatus comprising:
at least one processor; and
at least one memory including computer program code for one or more programs;
the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least:
receive optical data collected optically along a first path and a second path by a collection device;
identify at least one confirmed sign position along the second path;
identify one or more false positive locations along the first path based on the at least one confirmed sign position for the second path, wherein the second path is adjacent to the first path;
generate a false positive profile based on the false positive locations along the first path based on the at least one confirmed sign position along the second path; and
analyze the optical data for the first path with first processing for the false positive locations and with second processing for locations other than the false positive locations.

10. The apparatus of claim 9 , wherein data values for the at least one confirmed sign position are sent to an assisted driving device.

11. The apparatus of claim 9 , wherein the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least:
determine the one or more false positive locations based on user input for a visual inspection of historical data.

12. The apparatus of claim 9 , wherein the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least:
identify the one or more false positive locations based on an angle, position, or orientation of a sign detected in the optical data.

13. The apparatus of claim 9 , wherein the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least:
identify a road link for the first path; and
store the one or more false positive locations as attributes for the road link.

14. A non-transitory computer readable medium including instructions that when executed are operable to cause a processor to:
receive optical data, wherein the optical data is collected along a first road link and a second road link by a collection device;
identify one or more false positive locations along the first road link from the optical data for the second road link;
generate a false positive profile for the one or more false positive locations in association with the first road link; and
analyze the optical data differently for the one or more false positive locations than for locations along the first road link other than the false positive locations.

15. The non-transitory computer readable medium of claim 14 , further comprising instructions that when executed are operable to:
send the false positive profile to a mobile device in response to location data.

16. The non-transitory computer readable medium of claim 14 , further comprising instructions that when executed are operable to:
send the false positive profile to a geographic database.

Assignees

• Here Global Bv

Inventors

• Dannenbring Aaron J

Classifications

• G06V10/774

  Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G01C21/3602

  Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera · CPC title

• G01C21/3697

  Output of additional, non-guidance related information, e.g. low fuel level (G01C21/3679 takes precedence) · CPC title

• G08G1/09626

  where the origin of the information is within the own vehicle, e.g. a local storage device, digital map · CPC title

• G06F16/29

  Geographical information databases · CPC title