Dynamic calibration of surveillance devices
Methods and systems including computer programs encoded on a computer storage medium, for receiving, from a camera, a set of images in which the camera detected a particular event based on a first set of camera settings, determining that false detections in the set of images made by the camera based on the first set of camera settings were caused by localized errors, and in response, generating a second set of camera settings based on the localized errors and providing the second set of camera settings to the camera.
1. A computer-implemented method comprising:
receiving, from a camera, a set of images in which the camera detected a particular event based on a first set of camera settings;
determining that false detections in the set of images made by the camera based on the first set of camera settings were caused by localized errors;
in response to determining that the false detections in the set of images made by the camera were caused by localized errors, generating a second set of camera settings based on the localized errors; and
providing the second set of camera settings to the camera, wherein the second set of camera settings includes one or more filters including instructions to the camera to ignore one or more of changes within a specific pixel value range, changes within a specific frequency range, or changes within a specific pixel region of a field of view of the camera.
2. The method of claim 1 , further comprising verifying future detections of the particular event in images from the camera, wherein the detections are based on the first set of camera settings, and wherein the verification of detections are based on the second set of camera settings.
3. The method of claim 1 , wherein the localized errors comprise one or more of spatially localized or temporally localized error.
4. The method of claim 1 , wherein the localized error is a confuser.
5. The method of claim 1 , wherein the second set of camera settings includes a rule.
6. The method of claim 5 , wherein the one or more rules include instructions to the camera to exclude an area of pixels in images captured by the camera.
7. The method of claim 1 , further comprising:
determining to evaluate the second set of camera settings, the evaluation of the second set of camera settings including:
receiving a sample set of images from the camera in which the camera detected the particular event based on the first set of camera settings;
determining that a number of false positives in the sample set of images from the camera satisfies a camera setting reversion criteria; and
providing instructions to the camera that cause the camera to revert to the first set of camera settings.
8. The method of claim 7 , wherein determining that the number of false positives in the sample set of images from the camera satisfies the camera setting reversion criteria comprises determining that the number of false positives in the sample set of images from the camera is less than a threshold number of false positives.
9. The method of claim 1 , wherein the image in which the camera detected the particular event based on the first set of camera settings is one of a plurality of images or a frame of a plurality of frames of a video captured by the camera.
10. A system comprising:
a data processing apparatus; and
a non-transitory computer readable medium storing instructions executable by the data processing apparatus and thus upon such execute cause the data processing apparatus to perform operations comprising:
receiving, from a camera, a set of images in which the camera detected a particular event based on a first set of camera settings;
determining that false detections in the set of images made by the camera based on the first set of camera settings were caused by localized errors;
in response to determining that the false detections in the set of images made by the camera were caused by localized errors, generating a second set of camera settings based on the localized errors; and
providing the second set of camera settings to the camera, wherein the second set of camera settings includes one or more filters including instructions to the camera to ignore one or more of changes within a specific pixel value range, changes within a specific frequency range, or changes within a specific pixel region of a field of view of the camera.
11. The system of claim 10 , further comprising verifying future detections of the particular event in images from the camera, wherein the detections are based on the first set of camera settings, and wherein the verification of detections are based on the second set of camera settings.
12. The system of claim 10 , wherein the localized errors comprise one or more of spatially localized or temporally localized error.
13. The system of claim 12 , wherein the localized error is a confuser.
14. The system of claim 10 , wherein the second set of camera settings includes a rule.
15. The system of claim 14 , wherein the one or more rules include instructions to the camera to exclude an area of pixels in images captured by the camera.
16. The system of claim 10 , further comprising:
determining to evaluate the second set of camera settings, the evaluation of the second set of camera settings including:
receiving a sample set of images from the camera in which the camera detected the particular event based on the first set of camera settings;
determining that a number of false positives in the sample set of images from the camera satisfies a camera setting reversion criteria; and
providing instructions to the camera that cause the camera to revert to the first set of camera settings.
17. The system of claim 16 , wherein determining that the number of false positives in the sample set of images from the camera satisfies the camera setting reversion criteria comprises determining that the number of false positives in the sample set of images from the camera is less than a threshold number of false positives.
18. At least one non-transitory computer-readable storage medium having stored thereon instructions which, when executed by at least one processor, cause performance of operations comprising:
receiving, from a camera, a set of images in which the camera detected a particular event based on a first set of camera settings;
determining that false detections in the set of images made by the camera based on the first set of camera settings were caused by localized errors;
in response to determining that the false detections in the set of images made by the camera were caused by localized errors, generating a second set of camera settings based on the localized errors;
providing the second set of camera settings to the camera; and
determining to evaluate the second set of camera settings, the evaluation of the second set of camera settings including:
receiving a sample set of images from the camera in which the camera detected the particular event based on the first set of camera settings;
determining that a number of false positives in the sample set of images from the camera satisfies a camera setting reversion criteria; and
providing instructions to the camera that cause the camera to revert to the first set of camera settings.