Underwater video monitoring for swimming pool

1. A monitoring system that is configured to monitor a property, the monitoring system comprising:

a light device that is located at a pool of the property and that includes a camera that is configured to capture video data; and

a monitoring control unit that is configured to:

determine an armed status of the property;

based on the armed status of the property, receive data from one or more sensors and one or more cameras located throughout the property;

based on the armed status of the property and the data from the one or more sensors and one or more cameras, determine an occupancy status of the property;

based on determining the occupancy status of the property, adjust a threshold of a confidence score criteria;

receive, from the light device, the video data;

determine that an object in the pool of the property is likely a person;

based on determining that an object in the pool of the property is likely a person, determine a confidence score that reflects a likelihood that the person is swimming;

determine that the confidence score does not satisfy the adjusted threshold of the confidence score criteria; and

perform a monitoring system action based on determining that the confidence score does not satisfy the adjusted threshold of the confidence score criteria.

2. The monitoring system of claim 1 , wherein the monitoring control unit is configured to perform the monitoring system action by outputting an audible alarm.

3. The monitoring system of claim 1 , wherein the monitoring control unit is configured to perform the monitoring system action by contacting emergency authorities.

4. The monitoring system of claim 1 , wherein the monitoring control unit is configured to:

receive, from the light device, a second set of video data;

determine that an object in the pool is likely a non-human object;

compare a size of the object to a size threshold; and

based on determining that the size of the object satisfies the size threshold, communicate a notification to a user device of a resident of the property indicating that an object is in the pool.

5. The monitoring system of claim 1 , wherein the monitoring control unit is configured to:

determine a brightness level of the video data;

compare the brightness level of the video data to a brightness level threshold; and

based on determining that the brightness level of the video data does not satisfy the brightness level threshold, communicate a notification to a user device of a resident of the property indicating that maintenance of the pool is required.

6. The monitoring system of claim 5 , wherein the monitoring control unit is further configured to switch a LED light in the pool to light red.

7. The monitoring system of claim 1 , wherein the monitoring control unit is configured to:

receive, from the light device, a second set of video data;

determine that an object in the pool of the property is likely a person;

based on determining that an object in the pool of the property is likely a person, determine a confidence score that reflects a likelihood that the person is swimming;

determine that the confidence score satisfies a confidence score criteria;

determine a number of laps the person swims; and

communicate a notification to a user device of a resident of the property indicating the number of laps the person swims.

8. The monitoring system of claim 7 , wherein the monitoring control unit is configured to:

determine that an additional person is in the pool of the property; and

communicate a notification to the user device of the resident of the property, indicating a number of persons in the pool.

9. The monitoring system of claim 1 , wherein the monitoring control unit is configured to analyze the video data using one or more algorithms based on one or more deep learning based models.

10. The monitoring system of claim 1 , wherein the monitoring control unit is further configured to:

receive, from the light device, a second set of video data;

determine that an object in the pool of the property is likely a person;

determine a current time; and

based on determining that the current time is after a set time, communicate a notification to a user device of a resident of the property, a notification indicating that a person is in the pool.

11. The monitoring system of claim 1 , wherein the monitoring control unit is configured to determine that an object in the pool of the property is likely a person by analyzing the video data to identify one or more limbs and identify a head.

12. The monitoring system of claim 1 , wherein the monitoring control unit is configured to:

identify a surface of the pool as shown in the video data; and

determine that the surface of the pool has been broken by an object,

wherein determining that the object in the pool is likely a person is in response to determining that the surface of the pool has been broken by an object.

13. A monitoring system that is configured to monitor a property, the monitoring system comprising:

a light device that is located at a pool of the property and that includes a camera that is configured to capture video data; and

a monitoring control unit that is configured to:

determine an armed status of the monitoring system;

based on determining that the monitoring system is armed away, receive data from one or more sensors and one or more cameras located throughout the property;

determine that the property is unoccupied based on the data from the one or more sensors and one or more cameras;

based on determining that the property is unoccupied, increase a threshold of a confidence score criteria;

receive, from the light device, the video data;

determine that an object in the pool of the property is likely a person;

based on determining that an object in the pool of the property is likely a person, determine a confidence score that reflects a likelihood that the person is swimming;

determine that the confidence score does not satisfy the increased threshold of the confidence score criteria; and

perform a monitoring system action based on determining that the confidence score does not satisfy the increased threshold of the confidence score criteria.

14. The monitoring system of claim 13 , wherein the monitoring control unit is configured to:

based on determining that the object in the pool of the property is likely a person,

communicate a notification to a user device of a resident of the property that includes the video data;

receive, from the user device of the resident, a response indicating that the person in the pool of the property is an unknown person; and

based on receiving, from the user device of the resident, a response indicating that the person in the pool of the property is an unknown person, output a voice command instructing the person to vacate the pool.

15. A computer-implemented method comprising:

determining an armed status of a property;

based on the armed status of the property, receiving data from one or more sensors and one or more cameras located throughout the property;

based on the armed status of the property and the data from the one or more sensors and one or more cameras, determine an occupancy status of the property;

based on determining the occupancy status of the property, adjusting a threshold of a confidence score criteria;

receiving, from a light device that is located at a pool of the property and that includes a camera, video data;

determining that an object in the pool of the property is likely a person;

based on determining that an object in the pool of the property is likely a person, determining a confidence score that reflects a likelihood that the person is swimming;

determining that the confidence score does not satisfy the adjusted threshold of the confidence score criteria; and

performing a monitoring system action based on determining that the confidence score does not satisfy the adjusted threshold of the confidence score criteria.

16. The method of claim 15 , wherein performing a monitoring system action based on determining that the confidence score does not satisfy the adjusted threshold of the confidence score criteria comprises outputting an audible alarm.

17. The method of claim 15 , wherein performing a monitoring system action based on determining that the confidence score does not satisfy the adjusted threshold of the confidence score criteria comprises contacting emergency authorities.

18. The method of claim 15 , further comprising:

receiving, from the light device, a second set of video data;

determining that an object in the pool is likely a non-human object;

comparing a size of the object to a size threshold; and

based on determining that the size of the object satisfies the size threshold, communicating a notification to a user device of a resident of the property indicating that an object is in the pool.

19. The method of claim 15 , comprising:

identifying a surface of the pool as shown in the video data; and

determining that the surface of the pool has been broken by an object,

wherein determining that the object in the pool is likely a person is in response to determining that the surface of the pool has been broken by an object.