Methods and systems including computer programs encoded on a computer storage medium, for receiving, for a multi-tenant dwelling unit (MDU), a map of the MDU, where the map includes locations corresponding to multiple sensors at the MDU and defines multiple sub-areas of the MDU, receiving sensor data from one or more sensors of the plurality of sensors, where the sensor data is indicative of a fire event at the MDU, determining, from the sensor data, one or more sub-areas of the multiple sub-areas included in the fire event, generating, based on the sensor data, a targeted fire event response for the one or more sub-areas of the multiple sub-areas of the MDU, and providing, to the one or more sub-areas of the multiple sub-areas, the targeted fire event response.

Multispectral imaging and related techniques are provided to detect thermal and non-thermal anomalies at reduced false detection rates. A multispectral imaging system includes an infrared light imaging sensor that captures infrared image data in a first spectral band, of a scene and an ultraviolet light imaging sensor that captures ultraviolet image data in a second spectral band, of the scene. The system also includes a processor that combines the ultraviolet image data and the infrared image data to generate composite image data, determines a ratio of a first radiant intensity in the first spectral band to a second radiant intensity in the second spectral band, from the composite image data, and determines whether the ratio corresponds to a predetermined radiant intensity ratio of a known thermal or electrical anomaly. The processor can detect the thermal or electrical anomaly when the determined ratio corresponds to the predetermined radiant intensity ratio.

A monitoring system that is configured to monitor a property is disclosed. The monitoring system includes a thermal camera that is configured to generate a thermal image of the property. The monitoring system further includes a monitor control unit that is configured to receive, from the thermal camera, the thermal image. The monitor control unit is further configured to, based on the thermal image, determine a temperature of a portion of the property depicted in the thermal image. The monitor control unit is further configured to determine that the temperature of the portion of the property depicted in the thermal image satisfies a temperature threshold. The monitor control unit is further configured to, based on determining that the temperature of the portion of the property depicted in the thermal image satisfies the temperature threshold, select and perform a monitoring system action.

A method for monitoring a dangerous situation in a space based on a frequency response pattern according to an embodiment includes loading, by a processing unit of a mobile terminal located in the arbitrary space, a setting value corresponding to an operational mode selected through control software installed on the mobile terminal, controlling, by the processing unit, a speaker of the mobile terminal to generate a frequency corresponding to the loaded setting value, receiving the frequency which was generated in the controlling and reflected in the space through a microphone of the mobile terminal, determining, by the processing unit, whether the dangerous situation occurred in the space by comparing the frequency response pattern with a preset reference value, and taking, by the processing unit, a follow-up action when it is determined that the dangerous situation occurred in the space by the determining.

A system and method for detecting in real-time high risk lightning (HRL) strikes and sending out alerts to responsible personnel to allow for earlier responses to lightning caused fire ignitions to help maintain and/or reduce the chance of spread by the wildfire. The system and method allow for HRL events and fire ignitions to be detected preferably within seconds. The system and method can use a network of detectors, data from environmental satellites and/or other environmental data sources, and novel AI/algorithms for signal processing to relatively quickly locate fire ignition spots. Thus, the system and method provide for actionable wildfire intelligence in real-time and to relatively quickly and accurately send out alerts when an HRL event has been determined. Cameras and drones can be used to provide real-time visualization at the location of the HRL event to verify or monitor any fire ignition or smoldering at the area of the HRL event.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a temporal range of a fire. In some implementations, a server obtains a date when a fire occurred within a region. The server obtains satellite imagery of the region from before the date when the fire occurred. The server generates a first statistical distribution from the satellite imagery. The server determines a start date of the fire using the first statistical distribution. The server obtains second satellite imagery of the region from before and after the start date. The server selects a second set of imagery from the second satellite imagery from before the start date. The server generates a second statistical distribution from the second set of imagery. The server determines an end date of the fire using the second statistical distribution. The server provides the start date and the end date for output.

In accordance with various aspects of the present disclosure, methods and systems for fire detection are disclosed. In some embodiments, a method for fire detection includes: acquiring data related to a monitored area, wherein the data comprises image data related to the monitored area; determining, based on the acquired data, whether a first mode or a second mode is to be executed for fire detection, wherein the first mode comprises a first smoke detection, and the second mode comprises a first flame detection; and executing, by a hardware processor, at least one of the first mode or the second mode based on a result of the determination.

Disclosed herein is a system for facilitating managing incidents occurring in areas monitored by low data-rate monitoring devices using the low data-rate monitoring devices, in accordance with some embodiments. Accordingly, the system comprises a processor, a device server, and a data visualization device. Further, a camera of a low data-rate monitoring device is configured for capturing video of an area. Further, the processor comprises a machine learning (ML) hardware accelerator configured for performing machine learning processing of the video. Further, the processor is configured for generating processed data. Further, the device server is configured for receiving the processed data based on the transmitting of the processed data from a low data-rate transceiver of the low data-rate monitoring device and transmitting a notification to a device. Further, the data visualization device is configured for visualizing the processed data, identifying an incident in the area, and generating the notification for the incident.

The present invention relates to: a smart fire-extinguishing device for automatically performing a fire-extinguishing operation by detecting the outbreak of a fire; and a smart fire-extinguishing system including same, and provides a smart fire-extinguishing device comprising: a chemical storage part in which fire-extinguishing chemicals are filled; a fuse part for exhibiting explosive force so that the fire-extinguishing chemicals of the chemical storage part are jetted to the outside; and a fire detection part, which detects at least one from among temperature, flames and smoke, compares a detection result with a pre-set fire outbreak reference value so as to determine whether a fire breaks out, and operates the fuse part according to a determination result so as to jet out the fire-extinguishing chemicals.

Among other things, techniques are described for preventing and mitigating fire risks on a vehicle. For example, multiple sensor inputs are provided to a predictive model which determines fire scenarios. A first fire risk data and second fire risk data are received from the sensors, and data indicative of fire prevention and fire mitigation is received. At least one fire prevention measure applicable to the first imminent fire risk condition and the second imminent fire risk condition is determined. The first fire risk data and the second fire risk data are compared to the fire mitigation thresholds. At least one fire mitigation measure applicable to the first imminent fire risk condition and the second imminent fire risk condition is determined. The at least one fire prevention measure or the at least one fire mitigation measure is activated.