Methods, systems, and apparatus, including computer programs encoded on a storage device, for using a drone to monitor a community. The drone may include a processor and a storage device storing instructions that, when executed by the processor, cause the one or more processors to perform operations. The operations may include receiving an instruction to deploy based on a determination, by a community monitoring system that an event was detected at a property of the community, navigating towards the property along an initial navigation path, obtaining local monitoring system data from a local monitoring system of a property of the community, generating based on the local monitoring system data a navigational model that identifies a location of each of one or more surveillance objectives, determining an adjusted navigation path to a location of a surveillance objective of the one or more surveillance objectives, and navigating along the adjusted navigation path.

A monitoring system for a vehicle includes surveillance sensors configured to capture sensor data proximate to the vehicle. A position sensor is configured to detect a location of the vehicle. A controller is in communication with the surveillance sensors and the position sensor. The controller calculates a security score in response to security data based on the location of the vehicle and selects an active mode for the surveillance sensors in response to the security score. The active mode is selected from a plurality of surveillance modes that vary an active operation of the plurality of surveillance sensors. The controller may change or escalate the active mode and a corresponding monitoring operation (e.g., from a first mode to a second mode) in response to a security detection.

A system for detecting a man-overboard event, comprising a plurality of first computing units having at least one optical sensor with a predetermined detection range and a second computing unit connected to the plurality of computing units, characterized in that each first computing unit is designed, independently of the others, to evaluate the data sensed by the at least one optical sensor of the respective first computing unit to determine whether a man-overboard event is present on the basis of these data and, when a man-overboard event (event) is present, to report this to the second computing unit, wherein the second computing unit is designed to output an alarm and/or a control command to carry out a man-overboard manoeuvre.

An apparatus comprising a camera sensor and a processor. The camera sensor may be configured to generate video data of an area of interest. The processor may be configured to (A) analyze the video data, (B) generate control signals and (C) adjust a status of a plurality of security responses. The control signals may be generated in response to (a) the analysis of the video data and (b) the status of the security responses. The control signals may adjust an activation of the security responses. A first of the security responses may be activated in response to an event detected by the analysis of the video data. A first communication to a first contact may be initiated based on the analysis of the video data of the event. A second communication to a second contact may be initiated based on a response to the first communication.

Systems and methods for processing surveillance video streams using image classification and object detection are described. Video data from a video image sensor may be processed using an image classifier to determine whether an object type is present in a video frame. If the object type is present, the video frame and/or subsequent video frames may be processed using an object detector to provide additional object data, such as position information, for use in other video surveillance processes. In some examples, an event message may be generated and sent to a video surveillance application in response to selective object detection.

A monitoring system for a vehicle includes a plurality of surveillance sensors in connection with the vehicle and configured to capture sensor data proximate to the vehicle. A position sensor is configured to detect a location of the vehicle. A controller determines a surveillance mode for the vehicle based on the sensor data and a plurality of security factors associated with the location of the vehicle. The controller activates the surveillance mode in response to the security factors and monitors the sensor data. The controller further filters a plurality of security events from a plurality of benign events and selectively outputs alerts in response to the security events and the benign events.

A computer-implemented method includes detecting, by operation of video analytics, an object within a portion of initial video captured by a security camera. The security camera is within and forms a part of a security system site. The computer-implemented method also includes transmitting, to at least one computing device that is remote from the security system site, a request that includes video data. The request relates to the object and the initial video. A response is received from the at least one computing device. The response includes computer readable instructions, retrieved from storage remote from the security system site, for at least one temporary analytic. The at least one temporary analytic is initiated to act upon the initial video or subsequent video captured by the security camera.

A monitoring system and a method for operating the monitoring system in an inmate tracking system in a controlled environment is disclosed. The monitoring system receives video and audio data from devices located within the controlled environment and organizes the video and audio data within profiles that allow for searches of the video and audio to be performed. The monitoring system analyzes the video and audio data and generates the profiles to include identified objects associated with the video and audio data.

A surveillance system may comprise one or more computing devices and a plurality of robotic surveillance devices. The one or more computing devices may be configured to obtain video data captured by one or more cameras. The one or more computing devices may analyze the video data to identify two or more conditions, and associate results of the identification with respect to the two or more conditions to determine an activity category. The one or more computing device may assign tasks to the plurality of robotic surveillance devices based on the determined activity category. The plurality of robotic surveillance devices may be configured to perform responding actions in response to receiving the tasks.

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.