Abstract: Systems and methods are described for improving audio quality. Sensor data is received from an accelerometer of a camera. Based on measurements captured by the sensor data, a position of a lens of the camera and a current field of view (FOV) of the camera is determined. Audio beamforming is performed based on the current FOV of the camera by selecting a subset of microphones disposed on the camera to record audio based on the position of the lens and the current FOV of the camera; and activating the subset of microphones disposed on the camera, where microphones outside the selected subset of microphones are excluded from activation so that audio originating outside of the current FOV is removed.

Abstract: Systems and methods for camera height detection include a time of flight (TOF) sensor included on a camera within a camera array that emits a signal in an array of points. After receiving a reflected signal at the TOF sensor, where the reflected signal is a bounce back of the emitted signal from at least a subset of the array of points, a distance to each respective point in the array is determined based on a time it takes to receive the reflected signal from each respective point in the array. A depth map is generated from each respective point, where the depth map provides distance measurements to objects within an environment of the camera. A vertical position of the camera is determined based on the depth map.

Abstract: Systems and methods are disclosed for intelligently activating light devices for optimized lighting conditions in a scene, where optimized illumination is provided by a subset of light devices within an array of light devices in communication with the camera. The systems and methods detect a target within a camera's field of view and determine an optimized illumination of the target according to a video analytics model. Lighting is adjusted in accordance with the determined optimized illumination.

Abstract: Systems, methods, and computer-readable media for prioritizing backups of data on cameras. In some examples, a camera records media content items captured by the camera and detects features within respective media content items captured by the camera. The camera tags the media content items with data identifying the features detected within the respective media content items and, based on the data identifying the features detected within the respective media content items, ranks the media content items to yield respective media content item rankings. Based on the respective media content item rankings, the camera selects one or more of the media content items for a prioritized remote backup and, in response to detecting a threat to the camera, sends, according to one or more rules defined for the prioritized remote backup, data associated with the one or more of the media content items to a network destination.

Abstract: Systems, methods, and computer-readable media for protecting critical data on cameras from physical attacks. In some examples, a camera at a particular site monitors data captured by the camera and, based on the data, detects one or more predetermined conditions indicating a threat to the camera. Based on the one or more predetermined conditions indicating the threat to the camera, the camera determines a threshold risk of damage to data stored at the camera. In response to determining the threshold risk of damage to the data stored at the camera, the camera selects, from a plurality of content items in the data stored at the camera, a subset of content items based on respective priorities associated with the plurality of content items, and sends, via a network, the subset of content items to one or more destinations to yield a prioritized backup of the plurality of content items.

Abstract: In one embodiment, a method includes: obtaining a power loss value for a cable that couples a device to a power source, where the power loss value is indicative of an amount of power lost through the cable during power transmission from the power source to the device; and determining, based at least in part on the power loss value for the cable, a power budget value indicative of an amount of power received by the device from the power source.

Abstract: Systems and methods are disclosed for managing power use of a camera and/or camera system. In response to a wakeup trigger, contents of a scene are captured by the camera. Based on a received energy budget for the camera, a scene analysis is performed on the scene, where the contents of the scene are analyzed according to one or more analytics models. Based on the output of the one or more analytics models and the received energy budget for the camera, it is determined whether the camera should continue capturing the contents of the scene or enter a power state lower than a previous power state (e.g., go to sleep).

Abstract: Systems, methods, and computer-readable media for protecting critical data on cameras from physical attacks. In some examples, a camera at a particular site monitors data captured by the camera and, based on the data, detects one or more predetermined conditions indicating a threat to the camera. Based on the one or more predetermined conditions indicating the threat to the camera, the camera determines a threshold risk of damage to data stored at the camera. In response to determining the threshold risk of damage to the data stored at the camera, the camera selects, from a plurality of content items in the data stored at the camera, a subset of content items based on respective priorities associated with the plurality of content items, and sends, via a network, the subset of content items to one or more destinations to yield a prioritized backup of the plurality of content items.