870 results about "Flame detection" patented technology

The invention discloses a video flame-detecting method based on multi-features fusion, which is characterized in that: a fast Gaussian hybrid model is established and a pixel counter is arranged when a computer reads a first frame image a monitoring site captured by a colored camera; when the computer reads new images of a second frame and the following frames, a fast Gaussian hybrid method is firstly used for carrying out motion detection so as to extract a moving object and then a flame color decision is carried out to the moving object to obtain an alternative flame area; and finally, flicker analysis is carried out on the alternative flame area so as to identify a real flame object. The video flame-detecting method carries out modeling to flame color characteristics, motion characteristics and flickering characteristics in flame areas; various flame detection interfering resources are gradually and rapidly eliminated in accordance with the recognition sequence of motion, color and flickering. The test results show that the method has relatively strong robustness; in addition, based on an AMD 2.04GHz processor, the processing speed can reach 22 frames per second for video images with pixels of 320 multiplied by 240.

A flame detection system includes a plurality of sensors for generating a plurality of respective sensor signals. The plurality of sensors includes a set of discrete optical radiation sensors responsive to flame as well as non-flame emissions. An Artificial Neural Network may be applied in processing the sensor signals to provide an output corresponding to a flame condition.

The invention relates to a smoke / flame detection method based on video image analysis. The existing fire monitoring mode is limited by a plurality of geographic conditions and infrastructure constructions. The method comprises the following steps: firstly performing the motion detection on an acquired video image by using a Kalman filter; secondly analyzing the colors of smoke and flame to obtain a smoke pixel region and a flame pixel region; then using a decision machine to determine whether a corresponding region is detected, and extracting the feature of the determined region; and finally performing normalization conversion on the extracted feature so as to adapt to hidden Markov model flame detection and neural network smoke detection. The outdoor smoke and flame can be detected simultaneously by using the smoke / flame detection method based on the video image analysis so as to warn the forest fire; and the effect predicting the forest fire at an early stage is achieved, and the economic loss caused by the fire can be reduced.

A long range optical sensor and system for detecting the flame of forest fires or other fires while rejecting false alarms due to solar radiation is described. The sensor utilizes a collector optic that collects energy from a wide field of view and concentrates the energy onto a detector. The collector may be a non-imaging collector and may match to a non-planar sensor. In one embodiment the sensor may be arrayed to achieve larger area coverage. In another, the sensor system may be scanned to increase the encompassed viewing area. Larger areas may be covered by RF radio links or networks interconnecting multiple arrayed sensor modules. UVC reflective coatings may include enhanced aluminum with silicon dioxide, silicon monoxide, or magnesium fluoride, or high phosphorous nickel phosphorous. In one embodiment a UVC sensitive Geiger Mueller tube may be coupled to a non-imaging spherical reflective collector. A catadioptric UVC / infra-red flame sensor is disclosed. Refractive or reflective designs are considered.

The invention proposes an indoor fire and flame detection method based on high-definition video images. Firstly, a background image is established and updated in video monitoring images; sample picture elements are trained by a Fisher classifier so that a color model of flames is acquired; a foreground moving image is acquired through a background differencing method; flame suspected pixels are detected through color features of the fire flames, that is, pixel points (that is, suspected flame pixel points) with the color features of the flames are found in the foreground moving image and all of the suspected flame pixel points form a flame area; pixel connection areas are combined so that an external rectangle of the suspected flame area is acquired; circularity of the connection areas in the external rectangle is calculated according to morphological characteristics of the flames and a suspected flame area is judged according to the circularity, jitter analysis and flame continuity analysis and the like in the external rectangle; and if preset requirements are met, the suspected flame area is a real flame area and an alarm signal is sent out.

The invention discloses an automatic positioning flame detection system for a three-dimensional space. The automatic positioning flame detection system comprises a front-end monitoring unit connected with a fire scene, a control center connected with the front-end monitoring unit as well as a firefighting linking unit connected with the control center. According to the automatic positioning flame detection system, image acquisition is carried out on the scene at different orientations by adopting more than two sensors in high-resolution infrared CCD (Charge Coupled Device) image type flame detectors; and intelligent fire identification processors are used for analyzing a video image by using a fire flame image identification algorithm and an image three-dimensional algorithm, capturing fire flame information of the scene, analyzing flame position, fire alarm information, the positions of the flame detectors and the flame orientation, transmitting the analysis result to a fire monitoring and managing platform and outputting a signal to an automatic fire alarming control host to the firefighting linking unit. The automatic positioning flame detection system has the characteristics of high positioning precision, long monitoring distance, great protection area and quick speed response and can better meet the requirement of great-space occasions on fire monitoring.

A vortex burner of combustible micropowder i.e pulverized coal is prepared by setting primary cooling jacket with an ignition device at the centre of it and a flame detection device at jacket top cover ; arranging primary , secondary and tertiary cooling jackets in sequence coaxially as radial outwards to form primary and secondary air channel and cooling channel , tertiary micropowder channel and tertiary channel ; connecting primary air-channel to fuel gas inlet tube and gasifying agent inlet tube after they are combined for switching over two gases by valve ; setting spiral - flow device at secondary air-channel outlet and jetting out pulverized coal in spiral - flow way at its conveying tube outlet.

A semiconductor device for flame detection, including: a semiconductor body having a first conductivity type conductivity, delimited by a front surface and forming a cathode region; an anode region having a second conductivity type conductivity, which extends within the semiconductor body, starting from the front surface, and forms, together with the cathode region, the junction of a photodiode that detect ultraviolet radiation emitted by the flames; a supporting dielectric region; and a sensitive region, which is arranged on the supporting dielectric region and varies its own resistance as a function of the infrared radiation emitted by the flames.

An intelligent image smoke / flame / complex intelligent image smoke / flame sensor, and an intelligent image smoke / flame detection system formed of such an intelligent image smoke / flame / complex intelligent image smoke / flame sensor. The intelligent image smoke / flame sensor is formed of an image sensor, for example, CCD (Charge-coupled Device), a DSP Processor, an input / output circuit, an infrared lamp and filter assembly, a casing, a window glass, a front cover, and a rear cover. The intelligent image smoke / flame detection system accurately detects fire characteristics including smoke and flame, producing an early alarm to lower catastrophe.

The invention discloses a method for identifying and detecting the fire flame in a big space, including: pretreating the input video streams, performing movement detection for the video streams to obtain the movement pixel, performing color detection for the video streams to obtain the pixel with the flame characteristic color, performing frequency domain analysis for all the pixels according with the movement detection and the color detection flame characteristic, searching the communicating areas formed by mutually connecting the pixels according with the same characteristic, calculating the circumferences and the areas of the obtained communicating areas to perform the shape analysis, performing the area change variable analysis for each communicating area, at last judging whether the fire happens. In the method, the real flame in the big space is distinguished from the flashy car light, so that the device is not only for the flame detection in the tunnel, but also used in the big-space fire flame detecting sites such as a gymnasium, a museum, a warehouse and the like.

This invention relates to a flame detection method and apparatus. More specifically, this invention relates to a flame d on method and apparatus designed for simultaneously monitoring several flames of different types such as pilot flames and main flames of differing sizes and intensity. These detected flames can be in one combustion unit or in several combustion units such as industrial furnaces or ground flares. The underlying principle of the invention is to collect and transmit light from each of the flames by use of optical fibers and to insect the collected light by a video camera vision system at the other end of the optical fibers and to transmit the “live” images of the glows as well as the “on / off” status of the burners to the control room, through modern electronic communication techniques such as Ethernet and / or wireless radio units.

The invention discloses a thermostatic gas water heater controller, characterized by comprising a signlechip, a gas valve drive / detection circuit, an igniter control / flame detection circuit, a blower drive / feedback circuit, a gas proportion valve drive / detection circuit, an air pressure detection circuit, a water flow sensor circuit, a water inlet / outlet temperature sensor circuit and an overheat protection circuit. The gas valve drive / detection circuit also comprises a gas valve drive circuit and a valve detection circuit, and the igniter control / flame detection circuit further comprises an igniter control circuit and a flame detection circuit. The invention aims to overcome the shortcomings of low control accuracy, high failure rate and poor interference resistance of a traditional controller, and provide the thermostatic gas water heater controller with reliable control, low failure rate and no current surge.

A device and method for detecting flame using real-time continuous imaging and pattern recognition of infrared (IR) images of a flame region. Infrared emissions radiated from the region pass through a wide field-of-view lens and are detected by a Charged-Coupled Device (CCD) array sensitive to the near IR range. The system then digitizes the image, extracts characteristic parameters from the measurement and stores both the image and characteristic information for pattern recognition. To accomplish the pattern recognition function, the derived real-time characteristics of the current measurement are statistically compared to pre-stored patterns representative of images of radiation emitted from the region while known flame conditions prevail within the region. Based on this comparison, an assessment is made to determine the presence or absence of flame. The characteristic measurements are also used for evaluating the quality of flame.

A device and method for detecting flame using real-time continuous imaging and pattern recognition of infrared (IR) images of a flame region. Infrared emissions radiated from the region pass through a wide field-of-view lens and are detected by a Charged-Coupled Device (CCD) array sensitive to the near IR range. The system then digitizes the image, extracts characteristic parameters from the measurement and stores both the image and characteristic information for pattern recognition. To accomplish the pattern recognition function, the derived real-time characteristics of the current measurement are statistically compared to pre-stored patterns representative of images of radiation emitted from the region while known flame conditions prevail within the region. Based on this comparison, an assessment is made to determine the presence or absence of flame. The characteristic measurements are also used for evaluating the quality of flame.

The invention provides a fire monitoring system which comprises at least two fire detection devices, a wireless transmission base station, a wireless network server and a monitoring system. The fire detection devices compose a wireless fire detection and fire alarm information transmission network, the wireless transmission base station is arranged inside the wireless fire detection and fire alarm information transmission network, and the fire detection device detects and sends the information of environmental flames, smoke concentrations, temperature and humidity back to the monitoring system through the wireless transmission base station and the wireless network server. The fire detection devices comprise a flame detection sensor, an A / D (analog to digital) conversion module, a micro DSP (digital signal processor) and a wireless transmission module. An independent code of the fire detection device in the system and other geographic information are stored in the micro DSP, the output end of the flame detection sensor is connected with the A / D conversion module, the output end of the A / D conversion module is connected with the micro DSP, and the output end of the micro DSP is connected with the wireless transmission module.

The invention provides a flame detection method based on image target detection, which belongs to the field of image processing, fire detection and video monitoring. The method comprises steps: firstly, a flame detection data set containing flame images and annotation information of each image is built, and the flame detection data set is divided to a training set and a test set; a deep convolution neural network model is built, the training set is used to carry out iterative updating on the model, the test set is used to calculate a loss function for the updated model, and if the loss function for the current model does not drop any more, the model completes training; and a real-time video is photographed, the model which completes training is used to detect each frame of image, if flameexists, the coordinate position of the flame in the image is outputted by the model, and a rectangular frame is used for marking. The phenomenon that features are manually designed for generating a candidate area for suspected flame is not needed, the deep convolution neural network model can be directly used for carrying out flame detection on the whole image, the position information of the flame is obtained, early warning of a fire is thus carried out, and hazards brought by fire can be reduced maximally.

The invention discloses a fire flame video monitoring and early warning system and a fire flame detection method. The fire flame video monitoring and early warning system comprises a network video CCD (Charge Coupled Device) camera, a video management module, a fire flame detection subsystem and an early warning subsystem. The fire flame detection method performs information integration of the static and dynamic features of fire flames and provides a fire judgment algorithm based on a neural network and D-S (Dempster-Shafer) evidence judgment, the algorithm can provide three early warning threshold values according to the magnitude of a fire, and the three early warning threshold values correspond to three levels of early warning modes, i.e. on-scene sound and light warning, remote short message warning and network warning. The invention provides the fire flame video monitoring system which monitors early small fire sources and judges the fire flame level on the basis of multi-feature information integration, and has the advantages of strong anti-interference capability, high space adaptability, high fire early warning accuracy and low false warning rate.

The invention discloses an intelligent fire monitoring system based on depth learning and a method thereof. The system includes an image acquisition module performing real-time monitoring through a binocular camera, an image analysis module utilizing a deep learning model to perform real-time flame detection of monitoring video images, an alarm module used for prompting monitoring personnel to observe the fire in the monitoring video images, a flame positioning module used for receiving the flame pixel position information detected by the deep learning model and mapping the flame pixel position information to the space through the binocular stereo visual positioning algorithm to obtain the flame space position information, and a fixed point fire extinguishing module used for receiving theflame space position information at preset time intervals under the condition that the alarm module has no response and the alarm continues. The system is advantaged in that through combination of depth learning and the camera positioning algorithm for flame identification, a new convolutional kernel module is proposed, feature extraction capability is stronger, alarm can be performed when the flame is detected, and fixed point fire extinguishing for the flame area in the event of no reaction of the monitoring personnel is performed.

The invention relates to a flame detection method adaptive to large outdoor space. The method comprises the following steps: converting a video frame image to a grayscale image, and taking the mean image of previous N frames (N is greater than 50) as a temporary background frame; making difference between the current frame and the temporary background frame, and then carrying out mask treatment to obtain a mask binary image; carrying out binarization on the current frame to obtain a brightness target, making difference between the current frame and the background frame and carrying out binarization on an Otsu self-adaptive threshold value to obtain an object target, and getting intersection of the brightness target and the object target as a target binary image, wherein the communicated areas in the target binary image are the suspected flame target; marking the communicated areas and storing information of the communicated areas; establishing a target chain table for each communicated area, and chaining the target chain table; calculating information of a traced moving target and determining whether the target is flame or not according to flame alarm probability. The method provided by the invention is adaptive to changes of climate and illumination, can be adaptive to indoor and outdoor flame detection, and can immediately and accurately alarm an incipient fire.

The invention relates to an intelligent image smog and flame detector, a compound type intelligent image smog and flame detector and an intelligent image smog and flame detecting system. The detectorcomprises a camera or an imaging CCD component, a DSP core processing circuit, an input and output circuit, an infrared lamp and filter component, a shell packaged by metal or other materials, a window lens, and front and back covers, and is characterized by reliably monitoring fires happening in the early stage such as smog and flare, thereby realizing functions of alarming early and reducing theoccurrence of disaster.

The invention relates to a flame detection method based on video time and spatial information, which belongs to the technical field of image information processing. First, a prospect motion image is separated from a source image, and then pixels with flame color characteristics are found out from the prospect motion image to form a suspected flame area; then observation points are arranged in the pixels on the edge of the suspected flame area with the flashing characteristics of the pixels on the edge of a real flame area, a hidden markov model is built, and time and space pattern characteristics are extracted to form an observation characteristic value sequence; the observation characteristic value sequence is input into a hidden markov mode decision device which is trained in advance to obtain the decision result whether the observation points are real flame pixels; and when the observation points which account quite a big part of all the observation points are decided to be the real flame pixels, the suspected flame area is thought to be the real flame area, and alarm is given. The flame detection method based on video time and spatial information has lower missing detection rate and error detection rate, very good robustness and can be used for more fire monitoring occasions.

A system is disclosed that includes a combustor having an end cover and at least one fuel nozzle assembly extending from an inner face of the end cover. A cartridge may extend through the end cover and into the fuel nozzle assembly. The cartridge may define an opening for receiving light emitted from within the combustor. Additionally, a fiber optic cable may be disposed within the cartridge and may be configured to capture at least a portion of the light received through the opening.

The invention provides a flame detection method based on a video frame image, which is characterized by comprising the following steps of: S10) obtaining a video frame image; S20) according to a flame luminance threshold, obtaining binary foreground images, and obtaining an interested target chain by a plurality of binary foreground images; S30) according to the target characteristic of a target block in a target chain, calculating flame frequency, and judging whether flame exists in the video frame image in the target chain according to the flame frequency and the confidence coefficient, wherein the target characteristic comprises the average luminance variation, the area variation and the center position shake of the target block; S40) if the flame exists in the video frame image in the target chain, generating an alarm triggering signal; and otherwise, returning to step S10). According to the flame detection method based on the video frame image, which is disclosed by the invention, the flame can be accurately detected, so that the flame false alarm rate is greatly lowered so as to lighten the pressure of working personnel, and the working efficiency of the working personnel is improved.

Disclosed is a smoke and flame combined type automatic detection method based on a video image. According to different characteristics of video images in the daytime and at night, flames and smoke are detected at the same time and comprehensively judged by applying different methods. The method is characterized by comprising the steps that the input original video image is firstly processed and judged, whether the video image is the video image at night or the video image in the daytime is judged, and processing and detecting are carried out by combining a corresponding night video image smoke and flame detection algorithm and a corresponding daytime video image smoke and flame detection algorithm. Therefore, the processing efficiency of the method is improved, the false reporting rate and the missing reporting rate are reduced, and stability and accuracy of the smoke and flame detection effect are improved.

The invention provides a convolutional neural network-based flame detection method. The method includes the following steps that: the sample image of a label is selected, the sample image is trained by using a convolutional neural network, so that a trained model can be obtained; a suspected flame point in a color scene image is extracted, and a binary image is obtained with the suspected flame point adopted as a foreground point; connected region processing is performed on the binary image through using a connected region method, so that a series of connected regions can be obtained; the connected regions are screened, so that candidate regions can be obtained; and the trained model is utilized to recognize the candidate regions, and a recognition result is outputted. Compared with an existing flame detection technology, the convolutional neural network-based flame detection method of the invention has the advantages of high flame detection accuracy and high robustness.

A flame-emitting apparatus is provided, whereby a burner has an inlet connected to a fuel source. Fuel burned by the burner provides a flame extending from an outlet of the burner. A flame ignition system detects the presence of the flame during operation of the apparatus and controls supply of fuel to the burner in response to flame detection.

The invention relates to a flame detection method based on a video image and solves the defects of the existing fire monitoring method. The method comprises the following steps that: the video image is acquired first, color detection is conducted to the video image according to the spatial domain features of a flame, a flame color region in the video image is extracted, and motion detection is conducted to the acquired video image according to the spatial domain features of the flame to realize the extraction of a motion region in the video image; pixel-by-pixel AND operation is conducted to the obtained flame color region and the video motion region, and spread rate analysis is conducted to exclude the interference of flame analogues and to obtain a final flame pixel region; and shake analysis is conducted to the final flame pixel region and finally the alarm confirmation of the flame is conducted. From the spatial domain and the time domain, in combination with the flame color detection method and the motion detection method to obtain a suspect fire region, the method realizes the accurate detection and extraction and the automatic tracking and alarm of the flame, and provides strong method supports for the intelligentization of fire monitoring devices.

An apparatus and method for performing first and second imaging processes contemporaneously, in particular where one of the processes is detecting fires based on images of the flames. The apparatus includes an image sensor for producing a video image, a frame grabber for capturing first frames and second frames, a processor for processing the data within the frames, and an output device. The apparatus may also include an adjustment mechanism for adjusting the image settings of the image sensor between settings suitable for flame imaging and non-flame imaging, and a control mechanism for controlling the image settings of the image sensor. In the method at least two first frames are obtained, and a plurality of second frames are obtained. The first and second frames are used for first and second processes. The first and second processes are contemporaneous, so that they are carried out within the same time period without interfering with one another. When the first process is flame detection, individual pairs of pixels having a property such as intensity that meets a first threshold are identified within the first frames, and are assembled into blobs. Additional properties of the pixel pairs and the blobs overall are evaluated in relation with additional thresholds. Blobs or pixels that do not meet the thresholds are excluded. Any blobs remaining after all evaluations are considered fires.

The invention provides an early forest fire detection method based on a video image, which relates to the technical field of video remote monitoring fire. The method includes flame detection and smokedetection. First, the suspected flame region of the forest video image is obtained by flame detection. The effective static and dynamic characteristics of the flame are extracted from the suspected flame area, and the characteristics are fused. Then the forest images are classified by support vector machine to judge whether there is flame or not. Smoke detection first obtains the suspected smog area of the forest video image. The effective static features of smoke are extracted from the suspected smoke area, and the features are fused. Then the support vector machine is used to classify the smoke image to determine whether there is smoke in the collected forest image. The early forest fire detection method based on a video image simultaneously takes into account the identification of smoke and flame, and can detect the fire in the video in real time, eliminate the influence of disturbances in the forest environment, and accurately discover the early fire situation.

The invention discloses a method and a device for flame detection based on video image analysis. The method includes: firstly, adopting a video image acquisition unit to acquire video images in a monitoring area, judging a type of a current frame image by the aid of an image information judgment unit, and adopting different processing modes for subsequent processing according to different image types; secondly, extracting a suspected flame area of the current frame image by the aid of a suspected area extraction unit, and removing false areas which do not match conditions by the aid of a screening unit; thirdly, adopting a match updating unit for match updating operations of suspected areas kept after screening; finally, adopting a judgment alarm unit to judge whether match times of each historical suspected area reaches a threshold or not so as to judge whether the suspected areas have fires or not. By the method and the device for flame detection based on video image analysis, classified judgment is carried out according to different features of flames in daytime and at night, so that alarm accuracy is greatly improved.