Multi-sensor motion detection

1. A method comprising:

determining, by one or more processors, an indication of motion of an object in an area using a first sensor;

determining, by the one or more processors, a lack of motion in the area using a second sensor;

determining, by the one or more processors, that the indication of motion of the object in the area using the first sensor is a false positive determination based on the lack of motion in the area determined using the second sensor;

refraining, by the one or more processors, from sending video data from the first sensor to a server based on determining that the indication of motion of the object is a false positive determination;

adjusting, by the one or more processors, motion detection thresholds of at least one of the first sensor or the second sensor using machine learning applied to a discrepancy between determinations made by the first sensor and the second sensor;

determining, by the one or more processors, motion of objects in the area using the motion detection thresholds; and

sending, by the one or more processors, the video data from the first sensor to the server for viewing the motion of the objects in the area.

2. The method of claim 1 , wherein the second sensor is an infrared (IR) sensor, the first sensor is an image sensor, and the IR sensor and the image sensor are part of a camera having a field of view including the area.

3. The method of claim 2 , further comprising:

adjusting, by the one or more processors, motion detection thresholds of the IR sensor to modify sensitivity of the IR sensor to the motion of the objects in the area.

4. The method of claim 1 , wherein the second sensor is a radar sensor.

5. The method of claim 4 , further comprising:

powering on, by the one or more processors, the radar sensor to determine the lack of motion in the area responsive to determining the indication of the motion of the object using the first sensor.

6. The method of claim 1 , wherein adjusting the motion detection thresholds comprises causing, by the one or more processors, the at least one of the first sensor or the second sensor to determine the motion of the objects in the area based on a trajectory of the objects in the area.

7. The method of claim 1 , wherein adjusting the motion detection thresholds comprises causing, by the one or more processors, the at least one of the first sensor or the second sensor to determine the motion of the objects in the area based on a distance of the objects in the area from the at least one of the first sensor or the second sensor.

8. The method of claim 1 , wherein determining the motion of the objects in the area is based on channel state information (CSI) of a wireless communications link between the one or more processors and a wireless access point (AP).

9. The method of claim 8 , wherein determining the motion of the objects in the area is further based on deviations from an expected amplitude or phase indicated by the CSI.

10. An electronic device, comprising:

one or more processors; and

memory storing instructions, wherein the processor is configured to execute the instructions such that the processor and memory are configured to:

determine an indication of motion of an object in an area using a first sensor;

determine a lack of motion in the area using a second sensor;

determine that the indication of motion of the object in the area using the first sensor is a false positive determination based on the lack of motion in the area determined using the second sensor;

refrain from sending video data from the first sensor to a server based on determining that the indication of motion of the object is a false positive determination;

adjust motion detection thresholds of at least one of the first sensor or the second sensor using machine learning applied to a discrepancy between determinations made by the first sensor and the second sensor;

determine motion of objects in the area using the motion detection thresholds; and

send the video data from the first sensor to the server for viewing the motion of the objects in the area.

11. The electronic device of claim 10 , wherein the second sensor is an infrared (IR) sensor, the first sensor is an image sensor, and the IR sensor and the image sensor are part of a camera having a field of view including the area.

12. The electronic device of claim 11 , wherein the processor and memory are further configured to:

adjust motion detection thresholds of the IR sensor to modify sensitivity of the IR sensor to the motion of the objects in the area.

13. The electronic device of claim 10 , wherein the second sensor is a radar sensor.

14. The electronic device of claim 13 , wherein the processor and memory are further configured to:

power on the radar sensor to determine the lack of motion in the area responsive to determining the indication of the motion of the object using the first sensor.

15. The electronic device of claim 10 , wherein the instructions to adjust the motion detection thresholds cause the at least one of the first sensor or the second sensor to determine the motion of the objects in the area based on a trajectory of the objects in the area.

16. The electronic device of claim 10 , wherein the instructions to adjust the motion detection thresholds cause the at least one of the first sensor or the second sensor to determine the motion of the objects in the area based on a distance of the objects in the area from the at least one of the first sensor or the second sensor.

17. The electronic device of claim 10 , wherein determining the motion of the objects in the area is based on channel state information (CSI) of a wireless communications link between the one or more processors and a wireless access point (AP).

18. A computer program product including one or more non-transitory computer-readable media storing computer program instructions, execution of which by a processing system causes the processing system to:

determine an indication of motion of an object in an area using a first sensor;

determine a lack of motion in the area using a second sensor;

determine that the indication of motion of the object in the area using the first sensor is a false positive determination based on the lack of motion in the area determined using the second sensor;

refrain from sending video data from the first sensor to a server based on determining that the indication of motion of the object is a false positive determination;

adjust motion detection thresholds of at least one of the first sensor or the second sensor using machine learning applied to a discrepancy between determinations made by the first sensor and the second sensor;

determine motion of objects in the area using the motion detection thresholds; and

send the video data from the first sensor to the server for viewing the motion of the objects in the area.