Doorbell camera package detection

1. A method for a security and automation system of a premises, comprising:

monitoring, by an image sensor of the security and automation system, an area of the premises;

analyzing one or more images captured by the image sensor based at least in part on the monitoring;

detecting an object within the area of the premises based at least in part on the analyzing of the one or more images;

analyzing one or more characteristics of the object based at least in part on the detecting of the object;

computing a probability that the detected object is a package based at least in part on the analyzing of the one or more characteristics of the object;

determining the probability satisfies a threshold;

determining the object is a package based at least in part on determining the probability satisfies the threshold;

querying a database based at least in part on determining the object is a package; and

identifying package information associated with the premises based at least in part on the querying.

2. The method of claim 1 , further comprising:

sending a notification to a device associated with a user based at least in part on the probability satisfying the threshold.

3. The method of claim 1 , further comprising:

configuring the threshold based at least in part on a calibration of the image sensor, or a sensitivity of the image sensor, or a user profile, or a prior probability calculation, or a probability feedback loop, or a quality of the one or more images, or any combination thereof.

4. The method of claim 1 , further comprising:

detecting a person approaching the object based at least in part on the monitoring;

analyzing images of the person approaching the object captured by the image sensor based at least in part on the detecting of the person approaching the object; and

identifying one or more characteristics of the person approaching the object based at least in part on the analyzing.

5. The method of claim 4 , wherein the one or more characteristics of the person include at least one of a detected uniform color, or a detected uniform pattern, or a detected company logo, or a detected nametag, or a detected delivery truck, or a detected identification badge, or a detected barcode, or a detected facial feature, or a detected walking pattern, or a spoken passcode, or any combination thereof.

6. The method of claim 4 , further comprising:

adjusting the probability based at least in part on the one or more characteristics of the person.

7. The method of claim 1 , further comprising:

adjusting the probability based at least in part on the package information associated with the premises.

8. The method of claim 1 , wherein the package information includes at least one of a delivery time of a scheduled package delivery, or a pickup time of a scheduled package pickup, or a status of the scheduled package delivery, or a status of the scheduled package pickup, or a combination thereof.

9. The method of claim 1 , further comprising:

determining the object is associated with a scheduled package pickup based at least in part on the probability and the identified package information;

determining the object is being taken by an unauthorized person based at least in part on the one or more characteristics of the person approaching the object; and

sounding an alarm at the premises based at least in part on determining the object is being taken by the unauthorized person.

10. The method of claim 2 , further comprising:

identifying feedback from the user associated with the notification; and

adjusting the probability based at least in part on the identified feedback.

11. The method of claim 1 , further comprising:

detecting an environmental condition associated with the premises; and

increasing or decreasing the threshold based at least in part on the environmental condition associated with the premises.

12. The method of claim 1 , wherein the probability is computed by at least one of a processor in a device enclosing the image sensor, or by a processor of a computing device at the premises, or by a processor of a control panel at the premises, or by a processor of a remote server that remote from the premises, or any combination thereof.

13. An apparatus for a security and automation system of a premises, comprising:

a processor;

memory in electronic communication with the processor; and

instructions stored in the memory, the instructions being executable by the processor to:

monitor, by an image sensor of the security and automation system, an area of the premises;

analyze one or more images captured by the image sensor based at least in part on the monitoring;

detect an object within the area of the premises based at least in part on the analyzing of the one or more images;

analyze one or more characteristics of the object based at least in part on the detecting of the object;

compute a probability that the detected object is a package based at least in part on the analyzing of the one or more characteristics of the object;

determine the probability satisfies a threshold;

determine the object is a package based at least in part on determining the probability satisfies the threshold;

query a database based at least in part on determining the object is a package; and

identify package information associated with the premises based at least in part on the querying.

14. The apparatus of claim 13 , the instructions being executable by the processor to:

send a notification to a device associated with a user based at least in part on the probability satisfying the threshold.

15. The apparatus of claim 13 , the instructions being executable by the processor to:

configure the threshold based at least in part on a calibration of the image sensor, or a sensitivity of the image sensor, or a user profile, or a prior probability calculation, or a probability feedback loop, or a quality of the one or more images, or any combination thereof.

16. The apparatus of claim 13 , the instructions being executable by the processor to:

detect a person approaching the object based at least in part on the monitoring;

analyze images of the person approaching the object captured by the image sensor based at least in part on the detecting of the person approaching the object; and

identify one or more characteristics of the person approaching the object based at least in part on the analyzing.

17. The apparatus of claim 16 , wherein the one or more characteristics of the person include at least one of a detected uniform color, or a detected uniform pattern, or a detected company logo, or a detected nametag, or a detected delivery truck, or a detected identification badge, or a detected barcode, or a detected facial feature, or a detected walking pattern, or a spoken passcode, or any combination thereof.

18. A non-transitory computer-readable medium storing computer-executable code for a security and automation system of a premises, the code executable by a processor to:

monitor, by an image sensor of the security and automation system, an area of the premises;

analyze one or more images captured by the image sensor based at least in part on the monitoring;

detect an object within the area of the premises based at least in part on the analyzing of the one or more images;

analyze one or more characteristics of the object based at least in part on the detecting of the object;

compute a probability that the detected object is a package based at least in part on the analyzing of the one or more characteristics of the object;

determine the probability satisfies a threshold;

determine the object is a package based at least in part on determining the probability satisfies the threshold;

query a database based at least in part on determining the object is a package; and

identify package information associated with the premises based at least in part on the querying.

19. The non-transitory computer-readable medium of claim 18 , the code executable by the processor to:

send a notification to a device associated with a user based at least in part on the probability satisfying the threshold.