Object detection to determine road priority

• US 8,704,682 B1
• Filed: 06/29/2011
• Issued: 04/22/2014
• Est. Priority Date: 06/29/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Chau, Stephen
• Primary Examiner(s): Lim, Steven
• Assistant Examiner(s): Fan, Hongmin
• Application Number:
  US13/172,006
• Time in Patent Office: 1,028 Days
• Field of Search: 340/995.19, 340/995.13, 340/995.14, 340/995.22, 340/995.23, 340/995.24, 701/201, 701/200, 382/104, 382/105
• US Class Current: 340/995.19
• CPC Class Codes: G01C 21/3453 Special cost functions, i.e. other than distance or default speed limit of road segments
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

Embodiments relate to road priority and driving directions. In one embodiment, a system includes an object detector module configured: (i) to detect objects of a type in photographic images associated with first and second tracks, and (ii) to determine a first number of times objects of the type appear in photographic images geocoded along the first track, and a second number of times objects of the type appear in photographic images geocoded along the second track. The system also includes a priority score module configured: (i) to generate a first priority score associated with the first track based at least on the first number, and (ii) to generate a second priority score associated with the second track based at least on the second number. The system further includes a driving direction module configured: (i) to select a driving route that includes the track associated with a greater priority score.

Claims

1. A system for determining a driving route that includes a first track or alternatively a second track, comprising:

a first object detector module configured to detect objects of a first type in photographic images associated with the first and second tracks,

the first object detector module configured to determine a first number of times objects of the first type appear in photographic images geocoded along the first track, and to determine a second number of times objects of the first type appear in photographic images geocoded along the second track;

a priority score module configured to generate a first priority score associated with the first track based at least on the first number, the priority score module further configured to generate a second priority score associated with the second track based at least on the second number; and

a driving direction module configured to select a driving route that includes the first track when the first priority score is greater than the second priority score, and to select a driving route that includes the second track when the second priority score is greater than the first priority score, wherein when the first number is greater than the second number, the first priority score is greater than the second priority score.

2. The system of claim 1, wherein the first object detector module is configured to detect faces.

3. The system of claim 1, wherein the first object detector module is configured to detect license plates.

4. The system of claim 1, wherein the first object detector module is configured to detect text designating a business.

5. The system of claim 1, further comprising:

a second object detector module is configured to detect objects of a second type, different from the first type, in photographic images associated with the first and second tracks,

the second object detector module further configured to determine a third number of times objects of the second type appear in photographic images associated with the first track, and further configured to determine a fourth number of times objects of the second type appear in photographic images associated with the second track,

wherein the priority score module is configured to generate the first priority score based at least on the third number, the score generator further configured to generate the second priority score based at least on the fourth number.

6. The system of claim 5, wherein the first object detector module is configured to detect faces and the second object detector module is configured to detect license plates.

7. The system of claim 1, wherein the photographic image is taken from a camera rosette that takes panoramic images.

8. The system of claim 1, wherein the photographic image is at least a portion of a street-level panoramic image.

9. The system of claim 1, further comprising:

a tile generation module configured to serve map tiles rendered from map data.

10. The system of claim 9, wherein the tile generation module is further configured to alter an appearance of a track based on the priority score.

11. A method for determining a driving route that includes a first track or a alternatively a second track, comprising:

(a) detecting, on a computing device, objects of a first type in photographic images associated with the first and second tracks;

(b) determining a first number of times objects of the first type appear in photographic images geocoded along the first track;

(c) determining a second number of times objects of the first type appear in photographic images geocoded along the second track;

(d) generating a first priority score associated with the first track based at least on the first number;

(e) generating a second priority score associated with the second track based at least on the second number;

(f) when the first priority score is greater than the second priority score, selecting a driving route that includes the first track; and

(g) when the second priority score is greater than the first priority score, selecting a driving route that includes the second track,

wherein when the first number is greater than the second number, the first priority score is greater than the second priority score.

12. The method of claim 11, further comprising:

collecting photographic images associated with the first track and the second track.

13. The method of claim 11, further comprising:

collecting photographic images associated with the first track and the second track from public sources.

14. The method of claim 11, wherein detecting objects of the first type comprises detecting faces.

15. The method of claim 11, wherein detecting objects of the first type comprises detecting license plates.

16. The method of claim 11, wherein detecting objects of the first type comprises detecting text designating a business, further comprising:

determining a type of the business based on the detected text,

wherein the generating the first priority score (d) comprises generating the first priority score based on the determined type of the business.

17. The method of claim 11, wherein the priority scores are dependent on a context.

18. The method of claim 17, wherein the context is a time of day.

19. The method of claim 11, further comprising:

detecting objects of a second type, different from the first type, in photographic images associated with the first and second tracks;

determining a third number of times objects of the second type appear m photographic images geocoded along the first track; and

determining a fourth number of times objects of the second type appear in photographic images geocoded along the second track,

wherein the generating (d) comprises generating the first priority score based at least on the third number, and the generating (e) comprises generating the second priority score based at least on the fourth number.

20. An apparatus comprising at least one non-transitory computer readable storage medium encoding instructions thereon that, in response to execution by a computing device, cause the computing device to perform operations comprising:

detecting objects of a first type in photographic images associated with the first and second tracks;

determining a first number of times objects of the first type appear in photographic images geocoded along the first track;

determining a second number of times objects of the first type appear in photographic images geocoded along the second track;

generating a first priority score associated with the first track based at least on the first number;

generating a second priority score associated with the second track based at least on the second number;

selecting a driving route that includes the first track when the first priority score is greater than the second priority score; and

selecting a driving route that includes the second track when the second priority score is greater than the first priority score,

wherein when the first number is greater than the second number, the first priority score is greater than the second priority score.

21. The apparatus of claim 20, the operations further comprising:

detecting objects of a second type, different from the first type, in photographic images associated with the first and second tracks;

determining a third number of times objects of the second type appear in photographic images associated with the first track;

determining a fourth number of times objects of the second type appear in photographic images associated with the second track;

generating the first priority score based at least on the third number; and

generating the second priority score based at least on the fourth number.