An image in a monitor region (14) image-captured by a monitor camera (16), input a multi-layer-type neural network of a determination device (10) to determine whether it is a fire or a non-fire state, and in the case when it is determined as a fire state, flame warning is given from a receiver (12). In a recording device of the determination device, motion images in a monitor region (14) captured by a monitor camera are recorded. When a fire decision operation is carried out in the receiver, a learning control part of the determination device reads out the recorded image at that time from the recording device, and inputs the multi-layer-type neural network as a fire image so as to subject it to learning by back propagation. In a case when a recovery operation is carried out, without any fire decision operation being carried out in the receiver, non-fire images are inputted to the multi-layer-type neural network so as to be subjected to learning.

A method, an apparatus, and a device for determining smoke, and a computer-readable storage medium are provided. The method includes: obtaining a video image of a photographed region by using a camera apparatus, where the photographed region is irradiated by a laser with a predetermined wave band emitted by a laser unit, and the camera apparatus is configured with a filter allowing the laser with the predetermined wave band to pass through; determining, based on a plurality of frames of images in the video image, a motion region in the plurality of frames of images; and determining whether the photographed region includes smoke based on a feature of the motion region.

The present disclosure relates to real-time surveillance/monitoring of an environment using an Internet of Things (IoT) based integrated device. The integrated device comprises replaceable sensors and programmable image/video capturing device, that are communicatively connected to a processor. The processor correlates sensor data and data related to the images, audios and videos received from the replaceable sensors and the programmable image/video capturing device to validate occurrence of event in the environment. Later, information related to the validated events are transmitted to edge nodes, cloud servers, user devices or other sensor nodes for effective monitoring of occurred events. The integration of programmable image/video capturing device with the replaceable sensors helps in reducing chances of false event detection, as well as allows users to program the image capturing device for detection of various events. Also, integration of various sensors helps in reducing electrical wirings and overall complexity of the device.

The present disclosure relates to a system and method for predicting and detecting the outbreak of a fire. In particular, the present disclosure includes a management server configured to store and output data, a state detection unit disposed in a given space (hereinafter referred to as a “detection space”) becoming a target of detection and configured to transmit, to the management server, a detected value of a normal state or an abnormal state within the detection space, a detection space photographing unit configured to transmit, to the management server, a first screen obtained by photographing the detection space in the normal state in which a detected value detected by the state detection unit is less than a set value and a second screen obtained by photographing the detection space in the abnormal state in which a detected value detected by the state detection unit is the set value or more, an abnormal state determination unit configured to determine a dangerous situation when a detected value transmitted by the state detection unit is the set value or more and to transmit, to a management terminal, thermal image data measured through the second screen, and the manager terminal configured to communicate with the management server. Accordingly, the present disclosure provides an advantage in that a manager can predict and identify a fire outbreak danger point in advance.

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 system includes a processing device and memory device storing instructions that result in accessing a first dataset including aerial imagery data and infrared data, accessing a second dataset including property boundary data, and identifying property boundaries associated with a geographic area. A plurality of models is applied to the datasets to identify and compute information of interest. Based on the first dataset and constrained by the property boundaries, a building detection model can be applied to identify a building, and a vegetation detection model can be applied to identify one or more areas of vegetation. An estimated distance can be determined between each of the areas of vegetation and the building as separation data, which can be compared to a defensible space guideline to determine a defensible space adherence score. A wildfire risk map can be generated, including the defensible space adherence score associated with the geographic area.

A method and system is disclosed that can automatically detect smoking conditions for industrial flares. It can analyze live or historical video images to identify smoking conditions and generate a “Smoke Level” value in the range of 0 to 10 to represent the seriousness of the smoking events. The Smoke Level data can be sent to the plant distributed control system (DCS) or other control devices so alarms can be generated and automatic or manual control actions can be taken to stop the flare from smoking quickly. The Smoke Level data can also be saved in historical files for reporting and smoke event tracking purposes. Using the described method and system, industrial plants can comply with EPA regulations at all times, improve flare control and monitoring, be better prepared for EPA reporting and auditing, and save energy and manpower.

A cooking control system accesses a set of training data used to train a machine learned model configured to detect smoke in a kitchen environment based on image data of a stovetop. The cooking control system receives real-time image data of a stovetop from a camera in the kitchen environment and applies the machine learned model to the image data to determine a likelihood that the image data includes smoke. If the cooking control system determines that the received images contain smoke, the cooking control system may perform one or more actions, such as disabling operation of the stovetop and sending an alert indicative of smoke to a user of he cooking control system or a local emergency department.

A fire safety system particularly adapted for commercial kitchen applications provides control of exhaust levels for energy efficiency and intelligently responds to fires or fire risks. In embodiments, systems may provide early warning of fire hazards or impending fires. Embodiments employ probabilistic estimates with alarms that can be canceled. Embodiments employ classifiers that can make use of alarm cancellations as a mechanism for supervised learning.

A system and method of preparing an augmented reality (AR) composite view, configured to create, edit, store, and display fire safety information, hazards, and location information. The system includes an AR editing tool such that a user may edit and input information into an electronically stored database. The system includes an AR viewing tool, where the relevant information from the electronically stored database is determined based on each user's location, and optionally view direction. The AR viewing tool displays a composite image representative of each user's view and incorporating icons representative of useful information, including fire protection features and hazards.