Abstract: Systems and techniques are described for utilizing video classification capabilities for providing accurate local weather. In some implementations, the techniques include the actions of obtaining images from cameras located at a monitored property. An expected weather forecast and an actual weather condition is obtained for the monitored property. A machine-learning model is trained to classify a current weather condition for the monitored property using the images from the cameras, the expected weather forecast, and the actual weather condition. A weather condition is obtained from the trained machine-learning model that indicates a particular weather condition at the monitored property based on one or more images from a camera and the expected local weather forecast at the monitored property.

Abstract: Methods and systems including computer programs encoded on a computer storage medium, for receiving, from a camera, an image in which the camera detected a particular event based on a first set of camera settings, determining, from the image, that the image is a false positive as the camera falsely detected the particular event, determining that a number of images uploaded by the camera that are false positives satisfies a camera setting generation criteria, and in response, generating a second set of camera settings and providing the second set of camera settings to the camera.

Abstract: 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.

Abstract: 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.