Multi-sensor motion detection
A first one or more sensors are used to sense a presence of motion of one or more objects in an area. A second one or more sensors are used to sense an absence of motion in the area. One or more computer processors are used to generate information describing the presence of motion sensed using the first one or more sensors and the absence of motion sensed using the second one or more sensors. An artificial intelligence module is used to generate an adjustment to one or more motion detection thresholds of at least one of the first one or more sensors or the second one or more sensors based on the information. The at least one of the first one or more sensors or the second one or more sensors are caused to be configured using the adjustment to the motion detection thresholds.
1 . A computer-implemented method comprising:
sensing, using a first one or more sensors, a presence of motion of one or more objects in an area;
sensing, using a second one or more sensors, an absence of motion in the area;
generating, using one or more computer processors, first information describing the presence of motion sensed using the first one or more sensors and the absence of motion sensed using the second one or more sensors;
extracting, from the first information, a feature vector describing:
characteristics of the first one or more sensors,
characteristics of the second one or more sensors, and/or
characteristics of the sensed presence of motion of the one or more objects in the area;
generating, using an artificial intelligence module, an adjustment to one or more motion detection thresholds of at least one of the first one or more sensors or the second one or more sensors based on the feature vector; and
sending, to the at least one of the first one or more sensors or the second one or more sensors, second information describing the adjustment to the motion detection thresholds for the at least one of the first one or more sensors or the second one or more sensors to be configured using the adjustment.
2 . The method of claim 1 , comprising:
determining, by the artificial intelligence module, that the presence of motion sensed using the first one or more sensors is a false positive determination,
wherein generating the adjustment is performed responsive to determining that the presence of motion is a false positive determination.
3 . The method of claim 1 , comprising:
determining, by the artificial intelligence module, that the absence of motion sensed using the second one or more sensors is a false negative determination,
wherein generating the adjustment is performed responsive to determining that the absence of motion is a false negative determination.
4 . The method of claim 1 , wherein the feature vector indicates that the at least one of the first one or more sensors or the second one or more sensors includes an Infrared sensor, a radar sensor, and/or a camera.
5 . The method of claim 1 , wherein the characteristics of the sensed presence of motion of the one or more objects in the area include a trajectory of the one or more objects within a field of view of the first one or more sensors.
6 . The method of claim 1 , wherein the motion detection thresholds specify that the one or more objects must be within a threshold distance of the at least one of the first one or more sensors or the second one or more sensors to trigger a determination of motion.
7 . The method of claim 1 , wherein the motion detection thresholds prevent a determination of motion when the one or more objects are moving in a straight line.
8 . A base station, comprising:
one or more processors; and
a computer-readable, non-transitory memory storing instructions, wherein the one or more processors are configured to execute the instructions such that the base station is configured to:
sense, using a first one or more sensors, a presence of motion of one or more objects in an area;
sense, using a second one or more sensors, an absence of motion in the area;
generate, using one or more computer processors, first information describing the presence of motion sensed using the first one or more sensors and the absence of motion sensed using the second one or more sensors;
extract, from the first information, a feature vector describing characteristics of the one or more objects in the area;
generate, using an artificial intelligence module, an adjustment to one or more motion detection thresholds of at least one of the first one or more sensors or the second one or more sensors based on the feature vector; and
send, to the at least one of the first one or more sensors or the second one or more sensors, second information describing the adjustment to the motion detection thresholds for the at least one of the first one or more sensors or the second one or more sensors to be configured using the adjustment.
9 . The base station of claim 8 , wherein the base station is configured to:
determine, by the artificial intelligence module, that the presence of motion sensed using the first one or more sensors is a false positive determination,
wherein generating the adjustment is performed responsive to determining that the presence of motion is a false positive determination.
10 . The base station of claim 9 , wherein the base station is configured to:
responsive to determining that the presence of motion is a false positive determination, refrain from sending a notification of the presence of motion to a user device.
11 . The base station of claim 8 , wherein the base station is configured to:
determine, by the artificial intelligence module, that the absence of motion sensed using the second one or more sensors is a false negative determination,
wherein generating the adjustment is performed responsive to determining that the absence of motion is a false negative determination.
12 . The base station of claim 8 , wherein the feature vector describes
characteristics of the first one or more sensors,
characteristics of the second one or more sensors, and/or
characteristics of the sensed presence of motion of the one or more objects in the area.
13 . The base station of claim 8 , wherein the feature vector indicates that the at least one of the first one or more sensors or the second one or more sensors includes an Infrared sensor, a radar sensor, and/or a camera.
14 . The base station of claim 8 , wherein the feature vector indicates a trajectory of the one or more objects within a field of view of the first one or more sensors.
15 . A wireless access point, comprising:
one or more processors; and
a computer-readable, non-transitory memory storing instructions, wherein the one or more processors are configured to execute the instructions to cause the access point to:
sense, using a first one or more sensors, a presence of motion of one or more objects in an area;
sense, using a second one or more sensors, an absence of motion in the area;
generate, using one or more computer processors, information describing the presence of motion sensed using the first one or more sensors and the absence of motion sensed using the second one or more sensors;
determine, by an artificial intelligence module and based on the information, that the presence of motion sensed using the first one or more sensors is a false positive determination;
generate, using the artificial intelligence module, an adjustment to one or more motion detection thresholds of the first one or more sensors; and
cause the first one or more sensors to be configured using the adjustment to the motion detection thresholds.
16 . The access point of claim 15 , wherein the information indicates a speed of the one or more objects in the area, a size of the one or more objects in the area, and/or an acceleration of the one or more objects in the area.
17 . The access point of claim 15 , wherein determining that the presence of motion sensed using the first one or more sensors is a false positive determination is performed responsive to a size of the one or more objects in the area being less than a threshold size.
18 . The access point of claim 15 , wherein the artificial intelligence module performs unsupervised learning using the information describing the presence of motion sensed using the first one or more sensors and the absence of motion sensed using the second one or more sensors.
19 . The access point of claim 15 , wherein the instructions cause the access point to extract, from the information, a feature vector describing:
characteristics of the first one or more sensors,
characteristics of the second one or more sensors, and/or
characteristics of the sensed presence of motion of the one or more objects in the area.
20 . The access point of claim 15 , wherein the information indicates that the at least one of the first one or more sensors or the second one or more sensors includes an Infrared sensor, a radar sensor, and/or a camera.