Automatic detection of a calibration object for modifying image parameters
Embodiments provide for automated detection of a calibration object within a recorded image. In some embodiments, a system receives an original image from a camera, wherein the original image includes at least a portion of a calibration chart. The system further derives a working image from the original image. The system further determines regions in the working image, wherein each region comprises a group of pixels having values within a predetermined criterion. The system further analyzes two or more of the regions to identify a candidate calibration chart in the working image. The system further identifies at least one region within the candidate calibration chart as a patch. The system further predicts a location of one or more additional patches based on at least the identified patch.
1. A computer-implemented method performed by one or more digital processors for identifying image calibration data, the method comprising:
receiving an original image from a camera, wherein the original image includes at least a portion of a calibration chart;
deriving a working image from the original image;
determining regions in the working image, wherein each region comprises a group of pixels having values within a predetermined criterion;
analyzing two or more of the regions to identify a candidate calibration chart in the working image;
identifying at least one region within the candidate calibration chart as a patch; and
predicting a location of one or more additional patches based on at least the identified patch.
2. The method of claim 1 , further comprising filtering at least one portion of the regions based on shape.
3. The method of claim 1 , wherein the determining of regions includes checking a size of a region.
4. The method of claim 1 , further comprising adjusting an orientation of the candidate calibration chart.
5. The method of claim 1 , further comprising computing image data based on at least one pixel value from the identified patch.
6. The method of claim 1 , further comprising computing image data based on at least one pixel value from the identified patch, wherein the at least one pixel value is obtained from a middle area of the identified patch in the calibration chart to compute the image data.
7. The method of claim 1 , further comprising generating an image parameter, wherein the image parameter includes a white balance parameter.
8. The method of claim 1 , further comprising generating an image parameter, wherein the image parameter includes an exposure parameter.
9. A system for identifying image calibration data, the 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:
receiving an original image from a camera, wherein the original image includes at least a portion of a calibration chart;
deriving a working image from the original image;
determining regions in the working image, wherein each region comprises a group of pixels having values within a predetermined criterion;
analyzing two or more of the regions to identify a candidate calibration chart in the working image;
identifying at least one region within the candidate calibration chart as a patch; and
predicting a location of one or more additional patches based on at least the identified patch.
10. The system of claim 9 , wherein the logic when executed is further operable to cause the one or more processors to perform operations comprising filtering at least one portion of the regions based on shape.
11. The system of claim 9 , wherein the determining of regions includes checking a size of a region.
12. The system of claim 9 , wherein the logic when executed is further operable to cause the one or more processors to perform operations comprising adjusting an orientation of the candidate calibration chart.
13. The system of claim 9 , wherein the logic when executed is further operable to cause the one or more processors to perform operations comprising computing image data based on at least one pixel value from the identified patch.
14. The system of claim 9 , wherein the logic when executed is further operable to cause the one or more processors to perform operations comprising computing image data based on at least one pixel value from the identified patch, wherein the at least one pixel value is obtained from a middle area of the identified patch in the calibration chart to compute the image data.
15. The system of claim 9 , wherein the logic when executed is further operable to cause the one or more processors to perform operations comprising generating an image parameter, and wherein the image parameter includes a white balance parameter.
16. The system of claim 9 , wherein the logic when executed is further operable to cause the one or more processors to perform operations comprising generating an image parameter, and wherein the image parameter includes an exposure parameter.
17. 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:
receiving an original image from a camera, wherein the original image includes at least a portion of a calibration chart;
deriving a working image from the original image;
determining regions in the working image, wherein each region comprises a group of pixels having values within a predetermined criterion;
analyzing two or more of the regions to identify a candidate calibration chart in the working image;
identifying at least one region within the candidate calibration chart as a patch; and
predicting a location of one or more additional patches based on at least the identified patch.
18. The computer-readable storage medium of claim 17 , wherein the instructions when executed are further operable to cause the one or more processors to perform operations comprising filtering at least one portion of the regions based on shape.
19. The computer-readable storage medium of claim 17 , wherein the determining of regions includes checking a size of a region.
20. The computer-readable storage medium of claim 17 , wherein the instructions when executed are further operable to cause the one or more processors to perform operations comprising adjusting an orientation of the candidate calibration chart.