A system (41) for activating an infrared light source is configured to receive input indicating human presence in a space, determine a type and/or probability of the human presence based on the input, decide whether to activate an infrared light source (12) or a visible-light light source (11) in the space based on the type and/or probability of the human presence, and activate the infrared light source or the visible-light light source in dependence on the decision.

Techniques for video analytics of captured video content are described. An apparatus may comprise a flash memory, a serial bus, and a processor circuit coupled to the flash memory and the serial bus. The processor circuit may comprise a multi-core central processing unit (CPU) and an integrated graphics processing unit (GPU). The processor circuit may receive captured video content via a local communication link, perform video analytics on the captured video content; and send data associated with the performed video analytics to a network interface, for communication to a remote device via a network communication link. Other examples are described and claimed.

A process for tagging incident data captured by non-public-safety agency controlled cameras. In operation, an electronic computing device detects an occurrence of an incident and obtains an incident identifier associated with the incident. The electronic computing device determines that a non-public-safety agency controlled camera is available for capturing incident data corresponding to the incident. The electronic computing device then controls a public-safety agency controlled internet-of-things (IoT) infrastructure deployed at an incident location to emit a signal including one of an audible signal, visible signal, or a combination of audible and visible signals to enable the non-public-safety agency controlled camera to tag incident data using the emitted signal. The electronic computing device links a unique tag representing the emitted signal to the incident identifier. The electronic computing device then searches the incident data captured by the non-public-safety agency controlled camera using the unique tag representing the emitted signal.

A camera orientation control system for changing one or more camera orientations of one or more cameras towards a potential incident that is not currently in a field of view of the one or more cameras. The camera control system processes image frames for head orientation extraction, determines an amount of synchronous alignment in a proportion of head objects of the head objects to computationally assess that they are towards a new direction, and controls at least one camera to move the field of view of at least one camera of the one or more cameras towards the new direction. The system is useful for incident detection and extending or augmenting the capabilities of CCTV infrastructure.

The application is directed at a method and system for selective anonymization, wherein the method comprises the steps of capturing visual streaming data, identifying an anonymizable object in the visual data, for which a quantized identity (y) and an individual private key (n) is determined. Based on the individual private key (n) and the quantized identity (y), the first set of encryptions (E1) is calculated, comprising at least two distinct encryptions of the quantized identity. The first set of encryptions (E1) of the quantized identity (y) is sent to a central server, which, in return, sends an exception information indicating if an exception list of the central server comprises a set of exception encryptions (E2) which corresponds to the first set of encryptions (E1). The anonymizable object is then selectively anonymized in the streaming visual data depending on the exception information and an operating mode of the edge device, thereby generating selectively modified visual streaming data and the selectively modified visual streaming data is transmitted to a remote database.

Provided are a doorbell system and a method of operating the same. The doorbell system includes a doorbell which includes: a camera configured to obtain at least one of an image of a first object in a first region and an image of a second object in a second region closer to the doorbell than the first region; an image processor configured to detect the first object from the image of the first object, and identify the second object from the image of the second object; and an alert generator configured to select and transmit to a user terminal an alert sound or alert sound information corresponding to the identified second object.

Devices, systems and methods for controlling cameras, by processing recorded image frames to record head orientations corresponding to head objects identified for individuals in image frames over a first duration of time, and controlling an orientation of one camera to move to a field of view corresponding to the new direction. In alternate embodiments, the system may conduct further detection processes and generate further stage alerts thereby increasing the system confidence in the new camera direction.

An object monitoring method and device are provided. The object monitoring method includes: a sound production reason for the target sound is determined when a target sound exists in acquired sounds; and sound production information is pushed to a mobile terminal, the sound production information comprising the sound production reason.

An embodiment of the invention provides a surveillance system with intelligently interchangeable cameras. The system includes multiple bases, each with a respective base identifier, and multiple cameras configured to learn the respective base identifiers while in proximity with a respective base. The cameras in the system are configured to employ a camera configuration corresponding with the respective learned base identifier. Each camera in the system employs the appropriate camera configuration for its placement in the system because each camera employs the camera configuration associated with the base identifier learned by the camera. This allows the cameras to be easily replaced, swapped, and moved throughout the surveillance system.

The various implementations described herein include systems and methods for recognizing persons in video streams. In one aspect, a method includes: obtaining images collected by video cameras in a smart home environment, each image including a detected person; for each image, obtaining first information that identifies an attribute of the detected person, the first information generated from analysis of the image; grouping the images into a first group of a plurality of groups based on the first information, each group of the plurality of groups representing a unique person; receiving a request to remove a first image from the first group; removing the first image from the first group; and disassociating the first information from the first group.