Assisted creation of video rules via scene analysis

1. A computer-implemented method comprising:

obtaining images of a scene captured by a camera at a property;

identifying a shape of an object that forms at least part of ground shown in the images of the scene;

obtaining user input that defines a shape of a region of interest used in a video rule;

determining that a similarity, between the shape of the region defined by the user input and the shape identified of the object that forms at least part of the ground plane shown in the images of the scene, satisfies a reshape criteria; and

based on determining that the similarity, between the shape of the region defined by the user input and the shape identified of the object that forms at least part of the ground shown in the images of the scene, satisfies the reshape criteria, generating the video rule based on the shape of the object that forms at least part of the ground shown in the images of the scene.

2. The method of claim 1 , wherein determining that a similarity satisfies a reshape criteria comprises:

determining that the similarity of the shape of the region to the shape of the element in the ground plane satisfies a similarity threshold; and

in response to determining that the similarity of the shape of the region to the shape of the element in the ground plane satisfies the similarity threshold, determining that the shape of the region satisfies the reshape criteria.

3. The method of claim 2 , wherein determining that the similarity of the shape of the region to the shape of the element in the ground plane satisfies a similarity threshold comprises:

determining that the similarity of the shape of the region to a trapezoid shape of a driveway identified in the ground plane satisfies the similarity threshold.

4. The method of claim 1 , comprising:

providing the video rule based on the reshaped region to the camera that captured the images of the scene.

5. The method of claim 1 , comprising:

providing an indication of the shape of the object that forms at least part of the ground shown in the images of the scene to a user; and

receiving second user input that indicates to use the shape of the object that forms at least part of the ground shown in the images of the scene for the video rule,

wherein generating the video rule based on the shape of the object that forms at least part of the ground shown in the images of the scene is in response to receiving the second input that indicates to use the reshaped region for the video rule.

6. The method of claim 1 , wherein generating a video rule based on the shape of the object that forms at least part of the ground shown in the images of the scene occurs without additional input from a user after obtaining the user input that defines the shape of the region of interest used in the video rule.

7. The method of claim 1 , wherein obtaining user input that defines a shape of a region of interest used in a video rule comprises:

obtaining another image of the scene after the shape of the element in the ground plane shown in the images of the scene is identified;

providing the another image of the scene from which the shape of the element in the ground plane shown in the images of the scene was not identified; and

obtaining the user input while the another image of the scene is displayed.

8. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

obtaining images of a scene captured by a camera at a property;

identifying a shape of an object that forms at least part of ground shown in the images of the scene;

obtaining user input that defines a shape of a region of interest used in a video rule;

determining that a similarity, between the shape of the region defined by the user input and the shape identified of the object that forms at least part of the ground plane shown in the images of the scene, satisfies a reshape criteria; and

based on determining that the similarity, between the shape of the region defined by the user input and the shape identified of the object that forms at least part of the ground shown in the images of the scene, satisfies the reshape criteria, generating the video rule based on the shape of the object that forms at least part of the ground shown in the images of the scene.

9. The system of claim 8 , wherein determining that a similarity satisfies a reshape criteria comprises:

determining that the similarity of the shape of the region to the shape of the element in the ground plane satisfies a similarity threshold; and

in response to determining that the similarity of the shape of the region to the shape of the element in the ground plane satisfies the similarity threshold, determining that the shape of the region satisfies the reshape criteria.

10. The system of claim 9 , wherein determining that the similarity of the shape of the region to the shape of the element in the ground plane satisfies a similarity threshold comprises:

determining that the similarity of the shape of the region to a trapezoid shape of a driveway identified in the ground plane satisfies the similarity threshold.

11. The system of claim 8 , the operations comprising:

providing the video rule based on the reshaped region to the camera that captured the images of the scene.

12. The system of claim 8 , the operations comprising:

providing an indication of the shape of the object that forms at least part of the ground shown in the images of the scene to a user; and

receiving second user input that indicates to use the shape of the object that forms at least part of the ground shown in the images of the scene for the video rule,

wherein generating the video rule based on the shape of the object that forms at least part of the ground shown in the images of the scene is in response to receiving the second input that indicates to use the reshaped region for the video rule.

13. The system of claim 8 , wherein generating a video rule based on the shape of the object that forms at least part of the ground shown in the images of the scene occurs without additional input from a user after obtaining the user input that defines the shape of the region of interest used in the video rule.

14. The system of claim 8 , wherein obtaining user input that defines a shape of a region of interest used in a video rule comprises:

obtaining another image of the scene after the shape of the element in the ground plane shown in the images of the scene is identified;

providing the another image of the scene from which the shape of the element in the ground plane shown in the images of the scene was not identified; and

obtaining the user input while the another image of the scene is displayed.

15. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

obtaining images of a scene captured by a camera at a property;

identifying a shape of an object that forms at least part of ground shown in the images of the scene;

obtaining user input that defines a shape of a region of interest used in a video rule;

determining that a similarity, between the shape of the region defined by the user input and the shape identified of the object that forms at least part of the ground plane shown in the images of the scene, satisfies a reshape criteria; and

based on determining that the similarity, between the shape of the region defined by the user input and the shape identified of the object that forms at least part of the ground shown in the images of the scene, satisfies the reshape criteria, generating the video rule based on the shape of the object that forms at least part of the ground shown in the images of the scene.

16. The medium of claim 15 , wherein determining that a similarity satisfies a reshape criteria comprises:

determining that the similarity of the shape of the region to the shape of the element in the ground plane satisfies a similarity threshold; and

in response to determining that the similarity of the shape of the region to the shape of the element in the ground plane satisfies the similarity threshold, determining that the shape of the region satisfies the reshape criteria.

17. The medium of claim 16 , wherein determining that the similarity of the shape of the region to the shape of the element in the ground plane satisfies a similarity threshold comprises:

determining that the similarity of the shape of the region to a trapezoid shape.

18. The medium of claim 15 , the operations comprising:

providing the video rule based on the reshaped region to the camera that captured the images of the scene.

19. The medium of claim 15 , the operations comprising:

providing an indication of the shape of the object that forms at least part of the ground shown in the images of the scene to a user; and

receiving second user input that indicates to use the shape of the object that forms at least part of the ground shown in the images of the scene for the video rule,

wherein generating the video rule based on the shape of the object that forms at least part of the ground shown in the images of the scene is in response to receiving the second input that indicates to use the reshaped region for the video rule.

20. The medium of claim 15 , wherein generating a video rule based on the shape of the object that forms at least part of the ground shown in the images of the scene occurs without additional input from a user after obtaining the user input that defines the shape of the region of interest used in the video rule.