Bidirectional statistical consolidation of multi-modal grouped observations
Implementations generally relate to estimating grouped observations. In some implementations, a method includes detecting a license plate of a vehicle. The method further includes capturing a plurality of images of the license plate. The method further includes computing candidate regions associated with the license plate based on the images of the license plate. The method further includes computing candidate characters of the license plate based on the candidate regions and the images of the license plate. The method further includes selecting target characters from the candidate characters based on one or more predetermined selection criteria.
1. A system comprising:
one or more processors; and
logic encoded in one or more non-transitory computer-readable storage media for execution by the one or more processors and when executed operable to cause the one or more processors to perform operations comprising:
detecting a license plate of a vehicle;
capturing a plurality of images of the license plate;
computing candidate regions associated with the license plate based on the images of the license plate;
computing candidate characters of the license plate based on the candidate regions and the images of the license plate; and
selecting target characters from the candidate characters based on one or more predetermined selection criteria, wherein the one or more predetermined selection criteria comprises selecting target characters from among the candidate characters based on cross correlation over the plurality of images.
2. The system of claim 1 , wherein the plurality of images show the license plate at different perspectives.
3. The system of claim 1 , wherein the logic when executed is further operable to perform operations comprising determining the candidate characters based on one or more character recognition techniques.
4. The system of claim 1 , wherein the one or more predetermined selection criteria comprises selecting target characters from among the candidate characters based on one or more longest common subsequence (LCS) techniques.
5. The system of claim 1 , wherein, to select the target characters, the logic when executed is further operable to perform operations comprising:
comparing a first string of characters of a first image of the plurality of images of the license plate to a second string of characters of a second image of the plurality of images of the license plate;
identifying matched characters between the first string of characters and the second string of characters; and
selecting the target characters based on the identifying of the matched characters.
6. The system of claim 1 , wherein the logic when executed is further operable to perform operations comprising outputting a string of the selected target characters, and wherein the string of the selected target characters represents actual characters of the license plate.
7. A non-transitory computer-readable storage medium with program instructions stored thereon, the program instructions when executed by one or more processors are operable to cause the one or more processors to perform operations comprising:
detecting a license plate of a vehicle;
capturing a plurality of images of the license plate;
computing candidate regions associated with the license plate based on the images of the license plate;
computing candidate characters of the license plate based on the candidate regions and the images of the license plate; and
selecting target characters from the candidate characters based on one or more predetermined selection criteria, wherein the one or more predetermined selection criteria comprises selecting target characters from among the candidate characters based on cross correlation over the plurality of images.
8. The computer-readable storage medium of claim 7 , wherein the plurality of images show the license plate at different perspectives.
9. The computer-readable storage medium of claim 7 , wherein the instructions when executed are further operable to perform operations comprising determining the candidate characters based on one or more character recognition techniques.
10. The computer-readable storage medium of claim 7 , wherein the one or more predetermined selection criteria comprises selecting target characters from among the candidate characters based on one or more longest common subsequence (LCS) techniques.
11. The computer-readable storage medium of claim 7 , wherein, to select the target characters, the instructions when executed are further operable to perform operations comprising:
comparing a first string of characters of a first image of the plurality of images of the license plate to a second string of characters of a second image of the plurality of images of the license plate;
identifying matched characters between the first string of characters and the second string of characters; and
selecting the target characters based on the identifying of the matched characters.
12. The computer-readable storage medium of claim 7 , wherein the instructions when executed are further operable to perform operations outputting a string of the selected target characters, and wherein the string of the selected target characters represents actual characters of the license plate.
13. A computer-implemented method comprising:
detecting a license plate of a vehicle;
capturing a plurality of images of the license plate;
computing candidate regions associated with the license plate based on the images of the license plate;
computing candidate characters of the license plate based on the candidate regions and the images of the license plate; and
selecting target characters from the candidate characters based on one or more predetermined selection criteria, wherein the one or more predetermined selection criteria comprises selecting target characters from among the candidate characters based on cross correlation over the plurality of images.
14. The method of claim 13 , wherein the plurality of images show the license plate at different perspectives.
15. The method of claim 13 , further comprising determining the candidate characters based on one or more character recognition techniques.
16. The method of claim 13 , wherein the one or more predetermined selection criteria comprises selecting target characters from among the candidate characters based on one or more longest common subsequence (LCS) techniques.
17. The method of claim 13 , wherein, to select the target characters, the method further comprises:
comparing a first string of characters of a first image of the plurality of images of the license plate to a second string of characters of a second image of the plurality of images of the license plate;
identifying matched characters between the first string of characters and the second string of characters; and
selecting the target characters based on the identifying of the matched characters.