Validation of a camera cleaning system
Devices, systems, and methods are provided for testing and validation of a camera. A device may capture a first image of a target using a camera, wherein the camera is in a clean state, and wherein the target is in a line of sight of the camera. The device may apply an obstruction to a portion of a lens of the camera. The device may apply a camera cleaning system to the lens of the camera. The device may capture a post-clean image after applying the camera cleaning system. The device may determine a post-clean SSIM score based on comparing the post clean image to the first image. The device may compare the post-clean SSIM score to a validation threshold. The device may determine a validation state of the camera cleaning system based on the comparison.
1. A method comprising:
capturing, by one or more processors, a first image of a target using a camera, wherein the camera is in a clean state, and wherein the target is in a line of sight of the camera;
applying an obstruction to a portion of a lens of the camera;
initiating a camera cleaning system to the lens of the camera;
capturing a post-clean image after applying the camera cleaning system;
determining a post-clean structural similarity index measurement (SSIM) score based on comparing the post-clean image to the first image;
comparing the post-clean SSIM score to a validation threshold;
determining a validation state of the camera cleaning system based on the comparison;
adjusting one or more parameters of the camera cleaning system in response to the validation state indicating that the post-clean SSIM score is less than the validation threshold;
determining a first down-sampled image based on down-sampling the post-clean image;
determining a first local SSIM score based on comparing the first image and the post-clean down-sampled image;
determining a second down-sampled image based on down-sampling of the first down-sampled image; and
determining a second local SSIM score based on comparing the first down-sampled image and the second down-sampled image.
2. The method of claim 1 , further comprising determining a global SSIM score, wherein the global SSIM score is an average of the first local SSIM score and the second local SSIM score.
3. The method of claim 1 , further comprising:
determining a first region of the post-clean image having SSIM scores below a validation threshold;
determining a second region of the post-clean image having SSIM scores below the validation threshold; and
determining the first region and the second region are connected together.
4. The method of claim 3 , further comprising displaying a box around the first region and the second region.
5. The method of claim 4 , further comprising flagging the displayed box as a degraded area that has a worse SSIM score than an area without a box around it.
6. The method of claim 5 , further comprising performing one or more adjustments to the camera cleaning system to mitigate the degraded area.
7. A device, the device comprising processing circuitry coupled to storage, the processing circuitry configured to:
capture a first image of a target using a camera, wherein the camera is in a clean state, and wherein the target is in a line of sight of the camera;
apply an obstruction to a portion of a lens of the camera;
initiate a camera cleaning system to the lens of the camera;
capture a post-clean image after applying the camera cleaning system;
determine a post-clean structural similarity index measurement (SSIM) score based on comparing the post-clean image to the first image;
compare the post-clean SSIM score to a validation threshold;
determine a validation state of the camera cleaning system based on the comparison;
adjust one or more parameters of the camera cleaning system in response to the validation state indicating that the post-clean SSIM score is less than the validation threshold;
determine a first down-sampled image based on down-sampling the post-clean image;
determine a first local SSIM score based on comparing the first image and the post-clean down-sampled image;
determine a second down-sampled image based on down-sampling of the first down-sampled image; and
determine a second local SSIM score based on comparing the first down-sampled image and the second down-sampled image.
8. The device of claim 7 , wherein the processing circuitry is further configured to:
determine a global SSIM score, wherein the global SSIM score is an average of the first local SSIM score and the second local SSIM score.
9. The device of claim 7 , wherein the processing circuitry is further configured to:
determine a first region of the post-clean image having SSIM scores below a validation threshold;
determine a second region of the post-clean image having SSIM scores below the validation threshold; and
determine the first region and the second region are connected together.
10. The device of claim 9 , wherein the processing circuitry is further configured to display a box around the first region and the second region.
11. The device of claim 10 , wherein the processing circuitry is further configured to flag the displayed box as a degraded area that has a worse SSIM score than an area without a box around it.
12. The device of claim 11 , wherein the processing circuitry is further configured to perform one or more adjustments to the camera cleaning system to mitigate the degraded area.
13. A non-transitory computer-readable medium storing computer-executable instructions which when executed by one or more processors result in performing operations comprising:
capturing a first image of a target using a camera, wherein the camera is in a clean state, and wherein the target is in a line of sight of the camera;
applying an obstruction to a portion of a lens of the camera;
initiating a camera cleaning system to the lens of the camera;
capturing a post-clean image after applying the camera cleaning system;
determining a post-clean structural similarity index measurement (SSIM) score based on comparing the post-clean image to the first image;
comparing the post-clean SSIM score to a validation threshold;
determining a validation state of the camera cleaning system based on the comparison;
adjusting one or more parameters of the camera cleaning system in response to the validation state indicating that the post-clean SSIM score is less than the validation threshold;
determining a first down-sampled image based on down-sampling the post-clean image;
determining a first local SSIM score based on comparing the first image and the post-clean down-sampled image;
determining a second down-sampled image based on down-sampling of the first down-sampled image; and
determining a second local SSIM score based on comparing the first down-sampled image and the second down-sampled image.
14. The non-transitory computer-readable medium of claim 13 , further comprising determining a global SSIM score, wherein the global SSIM score is an average of the first local SSIM score and the second local SSIM score.
15. The non-transitory computer-readable medium of claim 13 , wherein the operations further comprise:
determining a first region of the post-clean image having SSIM scores below a validation threshold;
determining a second region of the post-clean image having SSIM scores below the validation threshold; and
determining the first region and the second region are connected together.
16. The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise displaying a box around the first region and the second region.
17. The non-transitory computer-readable medium of claim 16 , wherein the operations further comprise flagging the displayed box as a degraded area that has a worse SSIM score than an area without a box around it.