A safety system for residential and commercial use includes a plurality of sensor modules that may be distributed about the environment, and that are in communication with a remote server environment and with other devices over a wireless communication network (e.g., cellular, Wi-Fi). Each sensor module includes a plurality of sensors that are capable of measuring or detecting characteristics of the environment such as smoke, small particulate, large particulate, chemicals, gasses, temperature, humidity, pressure, geolocation, and other characteristics. Analysis of sensor data is performed locally on the sensor module, as well as remotely on a server, in order to fuse and consider multiple sensor data points to identify emergency and non-emergency scenarios. By fusing and analyzing sensor data emergencies can be detected more quickly, and false alarms can be filtered out and avoided.

The invention relates to a method for determining a noteworthy sub-sequence (114a) of a monitoring image sequence (110) of a monitoring area comprising the following steps: providing an audio signal (S1) from the monitoring area, at least partially including a time period of the monitoring image sequence; providing the monitoring image sequence (S1) of the environment to be monitored, which has been generated by an imaging system; determining at least one segment of the audio signal from the provided audio signal, which has unusual noises (S2); determining at least one segment of the monitoring image sequence having unusual movements within the environment to be monitored (S3); determining a correlation between the at least one segment of the audio signal having unusual noises (114a) and the at least one segment of the monitoring image sequence with unusual movements (114a) in order to determine a noteworthy sub-sequence (114) of the monitoring image sequence (110).

Methods and systems for monitoring procedural compliance of staff in a facility. A system may include a plurality of sensors positioned adjacent a hand washing station. Each of the plurality of sensors may be configured to provide a corresponding sensor output signal that is indicative of whether a person is washing their hands at the hand washing station or not. A controller may be configured to fuse the sensor output signals from each of two or more of the plurality of sensors and to determine using the fused sensor output signals whether the person has washed their hands at the hand washing station in compliance with one or more predetermined criteria or not. The controller may be further configured to output a notification when the controller has determined that the person has washed their hands at the hand washing station in compliance with the one or more predetermined criteria.

Various embodiments include a carbon monoxide (CO) detection device and methods for operating a FDS or CO detection device to detect carbon monoxide and communicate information regarding CO detection events to a remote server via communication network. Various embodiments include receiving information from one or more CO sensors configured to detect CO, determining whether the information from the one or more CO sensors satisfies one or more threshold criteria indicative of fire event or CO detection, generating a CO warning message comprising a fire and/or CO alarm object in response to determining that the information received from the one or more CO sensors satisfy one or more threshold criteria indicative of CO detection, and sending the generated CO warning message to a remote server via a communication network.

Disclosed are systems and methods for providing distributed security event monitoring. The system can include a central monitoring system and sensor devices positioned throughout a premises that passively detect conditions and emit signals guiding people on the premises when a security event is detected. The sensor devices can include suites of sensors and can transmit detected conditions to the central monitoring system. The central monitoring system can combine the detected conditions to generate a collective of detected conditions, determine whether the collective of detected conditions exceeds expected threshold conditions, identify a security event on the premises based on the collective of detected conditions, classify the security event using machine learning models, generate instructions to produce audio or visual output at the sensor devices that notifies people on the premises about the security event, and transmit the instructions to the sensor devices to emit signals indicating information about the security event.

A gunshot detection system synchronizes timing information across gunshot sensor units and/or a control panel. The gunshot sensor units exchange timing information with each other and/or with the control panel, which is then used by the gunshot sensor units to generate the event data for detected gunshot events. In one embodiment, the gunshot sensor units are configured as master and slave nodes. The master node periodically distributes a master time reference to the slave nodes, and the slave nodes calibrate local times based on the master time reference. The slave nodes can detect whether the current master node has become non-functional (e.g. based on a time elapsed since the most recently sent master time reference) and configure a new master node based on exchanging predetermined priority information for the slave nodes.

A monitoring system for locating and classifying an event in a monitoring area by a computation unit including a visual 3D capturing unit providing geometric 3D information and an acoustic capturing unit providing an acoustic information of the monitoring area. An event detector is configured with an acoustic channel and a visual channel to detect the event. The acoustic channel is configured to detect the event as a sound event in the acoustic information and to determine a localization of the sound. The visual channel is configured to detect the event as a visual event in the geometric 3D information and to derive a localization of the visual event. The event detector provides detected events with a region of interest for detected event, which is analyzed in order to assign the detected event a class within a plurality of event classes.

Methods, systems, and apparatus for attempted entry detection are disclosed. A method for monitoring a property includes receiving, from a smart lock of a door located at a property monitored by a monitoring system, smart lock data that reflects a condition of the smart lock; receiving, from a sensor of the monitoring system, sensor data; analyzing the smart lock data and the sensor data; based on analyzing the smart lock data and the sensor data, determining that an attempted door entry is occurring; and in response to determining that an attempted door entry is occurring, performing a monitoring system action. Determining that an attempted door entry is occurring can include determining, based on the sensor data, that a person is located near the smart lock; and determining, based on analyzing the smart lock data, that the smart lock data satisfies criteria for an attempted door entry.

Computer-implemented systems utilizing sensor networks for sensing temperature and motion environmental parameters, and performing at least operations of electronically establishing, based on pattern recognition criteria, correspondence of a plurality of representative features a plurality of characteristics of an occurrence, where a first instance of the occurrence occurred within a first time period of a plurality of time periods; electronically discovering, based on the correspondence, a second instance of the occurrence in an environment during a second time period of the plurality of time periods; and electronically causing, based on the discovery of the second instance of the occurrence, a change in the environment via an electronically-controlled device.

Systems and methods for correlating access-system primitives generated by an access control system and semantic primitives generated by a sensor data comprehension system.