KR101809031B1 - Composition fire detection processing apparatus and video processing method - Google Patents

Abstract

Disclosed are an image processing device and an image processing method. The image processing device according to the present invention includes: a receiving unit which receives an image photographed by an imaging device in real time; a color probability image generating unit which calculates a color probability by modeling the color distribution of pixels included in the received image in a color space of at least two dimensions based on color and brightness information and generates a color probability image by using the calculated color probability; a background image generating unit which generates a background image by modeling a background about the received image; a motion image generating unit which generates a motion image by using the received image and the background image; and an image correcting unit which corrects a candidate probability image by generating a candidate probability image using the color probability image and the motion image, extracting a plurality of characteristics about the candidate probability image, calculating a random probability by applying a random test algorithm about the extracted characteristics, and verifying the candidate probability image by using the calculated random probability. The present invention is provided to improve a smoke and flame recognition rate through complex detection.

Description

FIELD OF THE INVENTION [0001] The present invention relates to a composite fire detection image processing apparatus and an image processing method,

The present invention relates to a composite fire detection image processing apparatus and an image processing method. More particularly, the present invention relates to a composite fire detection image processing apparatus and an image processing method, And an image processing method for processing a detection function through image analysis.

Fire and smoke detection devices are widely used due to economic and casualties caused by fire and smoke. Conventionally, a sensor-based fire detection device has been widely used.

Sensor based detection devices use a thermal sensor and a smoke sensor to provide a warning when the temperature is sufficiently high or the smoke is thick enough. Sensor-based detection devices work well in a variety of building environments and provide reliable alerts, so they can be found in almost every building, especially in office buildings. However, warnings are only sent when the fire is strong enough, so it is often too late to evolve. In other words, the detection device can only help to reduce fire damage. In addition, sensor-based detection devices are not suitable for outdoor environments such as forest fires.

A fire detection system based on a charge-coupled device (CCD) camera has been developed to detect fire early and to completely prevent damage, rather than simply reducing fire damage. The CCD camera based fire detection system can be applied to the outdoor environment and the detected result can be confirmed remotely through the network using the captured image.

Conventional CCD camera-based fire detection devices detect fire colored-pixels and motion pixels and convert them into binary images, respectively. Then, a candidate fire is defined by ANDing the binary image of the non-color pixel and the binary image of the motion pixel. In addition, various classifiers are applied to classify each candidate defective pixel into a non-defective pixel or a non-defective pixel. The classification process depends on the previously detected candidate defective pixels. However, since the color of fire includes a large range of colors including white, red, orange, yellow, and the colors in between, it is difficult to detect non-color pixels. In addition, the motion detection algorithm for detecting motion pixels is difficult to detect because motion blinks at the same position, and the inner area of the non-area is determined to be a static area or background over time, A loss will occur.

Thus, since flicker will have different statistics when most classifiers in the prior art CCD camera based fire detection systems utilize the flicker characteristics of fire and the camera captures images at different frame rates, . ≪ / RTI > In the conventional CCD camera-based fire detection apparatus, it is difficult to accurately detect fire due to the above-mentioned problems, and there is a disadvantage that the accuracy of fire detection is greatly different according to the camera quality.

KR Patent Registration No. 10-1270718 B1

KR Patent Registration No. 10-1460440 B1

KR Patent Application No. 10-2010-0119457 A

SUMMARY OF THE INVENTION It is an object of the present invention to solve the above problems of the prior art.

More particularly, the present invention relates to a smoke detection method and a smoke detection method which detect smoke and flame which are parallel and ascending moving objects at a low speed and a high speed due to a fire, extract an image, correct the extracted image, And an image processing method and an image processing method in which the rate is improved.

According to an aspect of the present invention, there is provided an apparatus for processing a composite fire detection image, the apparatus comprising: a receiver for receiving an image captured by an image capture device in real time; Calculating a color probability by modeling a color distribution of pixels included in the received image image in at least two-dimensional color space based on color and luminance information, and generating a color probability image using the calculated color probability A probability image generating unit; A background image generation unit for modeling a background of the received video image to generate a background image; A motion image generation unit for generating a motion image using the received image and the background image; A candidate probability image is generated using the color probability image and the motion image, a plurality of characteristics of the candidate probability image are extracted, a randomness probability is calculated by applying a randomness test algorithm to the extracted characteristics, And an image corrector for correcting the candidate probabilistic image by verifying the candidate probabilistic image using the calculated random probability.

As described above, according to the various embodiments of the present invention, smoke and flame images moving at a low speed and a high speed due to fire occurrence are imaged and image correction is performed in real time to reduce distortion phenomenon such as image blurring and image blurring, , The recognition rate of the flame is increased.

FIG. 1 schematically illustrates an intelligent image processing system according to an embodiment of the present invention. FIG.
2 is a block diagram for explaining an image processing apparatus according to an embodiment of the present invention,
3A to 3D are diagrams illustrating a histogram of Cb and Cr distributions according to an embodiment of the present invention,
Figure 4 is a graphical representation of smoke from an imaged image according to an embodiment of the present invention. A drawing for explaining a process of extracting an image,
FIGS. 5A and 5B are views for explaining an embodiment of restoring smoke and flame images from original smoke and flame images according to an embodiment of the present invention; FIGS.
6 is a flowchart illustrating an image processing method according to another embodiment of the present invention,
7 is a flowchart for explaining a real-time smoke and flame information acquisition method according to another embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings, but the present invention is not limited by the scope of the present invention.

An image processing system (10) according to the present invention includes an image processing apparatus (100), a fire detection sensor for detecting a fire, and an image pickup device having a drive unit for synchronizing a photographing direction by a sensing data of the fire detection sensor Device 200 and a video stream communication device 300. [ In addition, the image processing system 10 can perform wired / wireless communication with the remote server 400. The image processing system 10 may be implemented in various types of mobile terminals such as a cellular phone, a PDA, a smart phone, a tablet, and a laptop.

The image processing apparatus 100 processes images captured by the image capturing apparatus 200, analyzes information such as smoke and flames included in the images, and transmits the analyzed information to the remote server 400.

The image capture device 200 is an image capture device capable of capturing an image of a subject at a full-HD or higher resolution. The image capturing apparatus 200 may be composed of a plurality of digital cameras based on the RTP / RTSP protocol.

The video stream communication apparatus 300 can perform data streaming communication between the video processing apparatus 100 and the image capturing apparatus 200. [ The video stream communication apparatus 300 can transmit an image sequence of image data captured by the image capturing apparatus 200 to the image processing apparatus 100 in real time.

The remote server 400 may comprise a remote database for collecting, processing, and storing information about the image processed by the image processing apparatus 100.

Hereinafter, for convenience of explanation, the image processing apparatus 100 will be described focusing on an embodiment in which image data picked up by the image pickup apparatus 200 is received through the video stream communication apparatus 300. FIG. It will be apparent to those of ordinary skill in the art that these embodiments are illustrative only and can be modified in various ways.

2 is a block diagram for explaining an image processing apparatus according to an embodiment of the present invention. 2, the image processing apparatus 100 includes a receiving unit 110, an image processing unit 130, a smoke and flame processing unit 150, a transmitting unit 170, and a control unit 190.

The receiving unit 110 receives the image data photographed from the image capturing apparatus 200. For example, the receiving unit 110 may be implemented as a communication module based on the RTP / RTSP protocol. The receiving unit 110 may be implemented as a video streaming communication module to receive the image data sequence.

The image processing unit 130 includes a color probability image generating unit 131, a background image generating unit 132, a motion image generating unit 133, and an image correcting unit 134. Each configuration of the image processing unit 130 may be configured as an independent module or in the form of an integrated module. Each configuration of the image processing unit 130 will be separately described below.

The smoke and flame processing unit 150 can extract information from smoke and flames included in the image processed by the image processing unit 130. [

The transmitting unit 170 transmits information about the smoke / flame data to the remote server through wired / wireless communication. The transmitter 170 may be implemented as a wired / wireless communication module. For example, the transmission unit 170 may be implemented by various types of wired / wireless communication modules such as the Internet, an intranet, a wireless LAN, a WiFi, and the like.

The control unit 190 can control the overall operation of the image processing apparatus 100. [ That is, the control unit 190 may control the overall operation of the image processing apparatus 100 to operate the image processing apparatus 100 such as image data reception, image image processing, data transmission, and power supply.

Input image data

According to the embodiment of the present invention, the image processing apparatus 100 can receive the image data picked up from the image pickup apparatus 200 in real time.

Specifically, the image processing apparatus 100 can receive the image data sequence from the image capturing apparatus 200 through the video stream communication apparatus 300. [

The image capturing apparatus 200 can be realized by a digital camera capable of capturing a high-resolution image of a full-HD or higher level. The image sensing apparatus 200 includes an image sensor capable of converting light energy into electrical energy, and the image sensor can be implemented in various types such as a CMOS and a CCD. The image capturing apparatus 200 captures a label attached to a moving object moving at high speed in real time. The video stream communication apparatus 300 can transmit the captured video data sequence to the video processing apparatus 100. [

The video stream communication apparatus 300 is a communication apparatus to which a real-time streaming technology based on the RTP / RTSP protocol is applied. The video stream communication apparatus 300 may be integrally installed in the image processing apparatus 100 or the image capturing apparatus 200, or may be configured as an independent apparatus.

The video stream communication apparatus 300 can convert the video data captured by the image capturing apparatus 200 into BGR24 type data and transmit the converted data to the video processing apparatus 100. [ At this time, the BGR 24 type data is sRGB format data having 24 bits per pixel. The video stream communication apparatus 300 can convert the video data into image data of various formats in addition to the data of the BGR24 type.

Image of color probability distribution according to light reflection angle movement modelling

The color probability image generating unit 131 may calculate a color probability for pixels constituting image data in a YCbCr color space and generate a color probability image using the calculated color probability.

Specifically, the color probability image generating unit 131 may model a histogram of Cb and Cr of a pixel using the input image data. The chrominance probability image generation unit 131 analyzes the histograms of Cb and Cr to analyze the chrominance probability distribution of the pixels of the input image data, and calculates a minimum value, a maximum value, and a Cb / Cr value of Cb and Cr Value can be calculated.

3A to 3D are diagrams illustrating a histogram of Cb and Cr distributions according to an embodiment of the present invention.

FIG. 3A is a histogram of Cb and Cr distributions for color pixels. In FIG. 3A, the horizontal axis represents pixel values, and the vertical axis represents the number of pixels. The line Cb distribution is indicated by a dotted line, and the line Cr distribution is indicated by a solid line.

FIG. 3B is a histogram of Cb and Cr distributions. In FIG. 3B, the horizontal axis represents pixel values and the vertical axis represents the number of pixels. In FIG. 3B, the line Cb distribution is represented by a first line (Line 1), the line Cr distribution is represented by a second line (Line 2), the non-line Cb distribution is represented by a third line (Line 3) And the non-line Cr distribution is represented by the fourth line (Line 4).

3C is a histogram of the Cb / Cr distribution for the color pixel, the horizontal axis of FIG. 3C is the ratio of Cb / Cr, and the vertical axis is the number of pixels.

FIG. 3D is a histogram of the Cb / Cr distribution. In FIG. 3D, the horizontal axis indicates the ratio of Cb / Cr, and the vertical axis indicates the number of pixels. In FIG. 3D, the line Cb / Cr distribution is represented by the first line, and the non-line Cb / Cr distribution is represented by the second line.

The color probability image generation unit 110 defines a pixel color probability P _line (x, y) at a specific coordinate (x, y) of a pixel of the input image data according to Equation (1).

Here, rate means Cb / Cr, and each pixel in the inputted image data satisfies the following condition.

If the above condition is not satisfied, the color probability of the pixel of the coordinate is zero.

The color probability image generation unit 110 calculates a color probability for pixels of the image data, and generates a color probability image for the calculated color probability.

Background image modelling

The background image generation unit 132 may generate a background image by modeling the background of a specific frame of the image image. That is, the background image generation unit 132 generates a background image by modeling the background of the frame before generating the motion image. The background image generating unit 132 may calculate the pixel value B _{n + 1} (i, j) of the background image by the following Equation 2 and generate the background image by the pixel value of the calculated background image have.

Here, B _n (i, j) is n and the pixel value of the nearest second in the background image of frame (i, j), I _n (i, j) is in the input video image (i, j) position Pixel value. The pixel value (B ₁ ) of the background image of the first frame is initialized to 0 along with the pixel value (I ₁ ) of the first input image. The input image image and background image used here are all gray images.

Smoke  Motion image extraction algorithm

4 is a view for explaining a process of extracting a smoke image from a captured image according to an embodiment of the present invention.

Referring to FIG. 4, the image processing apparatus 100 may extract a smoke / flame image 403 from an input original image 401.

The input original image 401 includes a background image and a smoke / flame image 403. The motion image generation unit 133 can generate a motion image using the background image and the input image image generated by the background image generation unit 132. [

Specifically, the motion image generating unit 133 calculates the pixel value M (i, j) of the motion image using the following Equation (3) and outputs the calculated motion image pixel value M (i, j) To generate a motion image.

Here, M (i, j) is the pixel value of the motion image, I (i, j) is the pixel value of the input image, and B (i, j) is the pixel value of the background image.

Moving image generation unit 133 calculates the calculated motion image pixel value (M (i, j)) for a first image pixel value (M _b (i, j)) by a threshold value. The motion image generating unit 133 may remove the noise through an open operation of the calculated first image pixel value _Mb (i, j).

The motion image generation unit 133 binarizes the second image pixel value M _m (i, j) by the second threshold value with respect to the noise-removed first image pixel value M _b (i, j) can do.

The motion image generating unit 133 may calculate the final motion image by finally normalizing the second image pixel value M _m (i, j) and finally binarizing the value to 1 or 0.

Image correction algorithm

The image correction unit 134 generates a candidate probability image using the color probability image and the motion image. The image correction unit 134 extracts a plurality of characteristics for the candidate probability image.

The plurality of features means the characteristic of discriminating the light reflection line of smoke and flame. For example, the plurality of features include the start reflection zone of smoke and flame, the end zone of light reflection, the width of the reflection angle, the width of the smoke boundary line, the resolution, the illuminance and the width of the flame including smoke.

The image correcting unit 134 calculates a random probability by applying a random test algorithm for the extracted plurality of characteristics.

The image corrector 134 may use the Wald-Wolfowitz test algorithm as a randomness test algorithm. The image correcting unit 134 may calculate the random test result through the following Equations (4) to (6).

Here, n ₁ and n ₂ are the numbers of 0 and 1, which are the bits of the characteristic to be subjected to the random test.

Here, R denotes the number of times of changing between 0 and 1, and Z denotes the randomness test result on the characteristic.

After the randomness test is completed, the test result Z may be used as a threshold value to provide a random probability P calculated using the following equation (7).

The image correcting unit 134 may calculate the random probability P calculated by Equation (7) for each characteristic. That is, the random probability P ₁ to P ₇ are calculated for the light reflection start zone, the light reflection end zone, the width of the smoke boundary line, the width of the reflection angle line, the resolution, the illuminance and smoke, and the width of the reflection angle including the flame .

The image correction unit 134 calculates randomness probabilities (P ₁ to P ₇ ) for _seven characteristics and calculates a random probability average (P ₁ to P ₇ ) using the _seven randomness probabilities (P ₁ to P ₇ ) P _F ) can be calculated.

Here, F _i denotes a probability of randomness for seven features in a specific frame.

That is, the image correction unit 134 calculates the randomness probability for seven features in a specific frame to determine the smoke and flame boundary line. Among the seven characteristics, the horizontal and vertical length of the carrier (the flame light reflection angle of the rising smoke) can be obtained by a random test to determine the bit combination group associated with the color of the edge of the smoke of the smoke.

On the other hand, to average the combination of the bits 0 and 1 of the outer boundaries of the bearer (the flame light reflection angle of the rising smoke), the non-parametric T-test algorithm of the Wald-Wolfowitz algorithm is used to determine the minimum and maximum values of the bit group, The average of the number of cases is obtained.

The image correction unit 134 repeatedly performs the restoration probabilities calculated by Equation (8) on N ₂ consecutive frames, respectively. Using the N ₂ before restoration of the probability calculated for each frame to calculate a probability (Pw) and then restored by the following equation (9) of the.

Here, P _F (i) denotes an arithmetic mean of the restoration probability calculated for each of N ₂ consecutive frames. The post-restoration probability Pw calculated by the equation (9) can be used as a threshold value for determining a line of the smoke-flame image in the following equation (10).

The image correcting unit 134 performs the four-stage smoke / flare line restoration determination using the restoration probability Pw as a threshold value according to Equation (10). For example, if the probability Pw after recovery is greater than 0.1, the corresponding bit group is determined to be a line. If Pw is greater than 0.07, the corresponding bit group is determined as Should_line. If Pw is greater than 0.05, The group is determined as Maybe_line. If Pw is smaller than 0.05, the corresponding bit group is determined as Not_line.

More specifically, if the post-restoration probability Pw is larger than 0.1, it means that the bit group has almost no distortion, so it can be restored to a clear line (judged as a line). If the probability Pw after reconstruction is smaller than 0.1 and larger than 0.07, it means that the bit group is distorted slightly in focus but can be restored to the line (Judged as Should_line). If the probability of reconstruction (Pw) is less than 0.07 and greater than 0.05, the corresponding bit group is distorted by a grating line having a partial cascade lattice or a stepwise continuity at the moment of imaging due to the movement of the subject, This means that continuity can be restored to a line (judged as Maybe_line). If the probability Pw after reconstruction is less than 0.05, it means that the instantaneous blurring or warping distortion occurs due to the movement of the subject, and this blurring and warping distortion can be restored to blank (judged as Not_line).

Hereinafter, an example of restoring smoke and flame lines from an original smoke image will be described with reference to FIGS. 5A and 5B.

Referring to FIG. 5A, the graph of the top view of FIG. 5A is a Blab graph waveform of the smoke-flame image, Wald-Wolfowitz test T-test result is a line blur judgment (Should_line) and a grid line (maybe_line) . In the case of clouding, jumping and lattice generation, the graph waveforms are shown irregularly.

The graph in the bottom view of FIG. 5A is a regular blob graph waveform when having a normal smoke and flame pattern. Normal smoke. If you have a flame pattern, the waveform of the blob graph is regularly shown. This indicates that the lines are dark and suitable for image reading.

Referring to FIG. 5B, the top view of FIG. 5B is the captured original smoke and flame image, and the bottom view is the corrected smoke and flame image.

In the upper diagram of Fig. 5B, the line L1 has a blurring distortion due to the external illuminance at the time of imaging. When calculating the probability of restoration for the bit group, it is determined to be a blurred line (determined as Should_line) Is restored as shown by the line L1 'in the bottom view of FIG. 5B.

In the upper diagram of Fig. 5B, lines L2 and L3 show that the distortion of the lines and the step-like lattice shape occurred at the time of imaging due to the movement of the subject. When calculating the probability of restoration for the corresponding bit group, It is determined to be a grid line (determined as maybe_line), and is restored as shown by lines L2 'and L3' in the lower diagram of FIG. 5B.

5B, the line L4 indicates that blurring of the line has occurred due to the movement of the subject. When calculating the probability after restoration for the corresponding bit group, the line L4 has a value smaller than 0.03, quot; not_line "), and restores the blank space L4 'in the lower drawing of Fig. 5B .

The smoke and flame processing unit 150 can analyze the smoke and flame contained in the image corrected by the image correction unit 134. [ In other words, the smoke / flame processing unit 150 recognizes smoke and flames divided into a light reflection start zone and an end zone, reads smoke and flames in the image by a light reflection shift gradation conversion algorithm, You can create and record speed.

The smoke and flame treatment unit 150 is an algorithm for converting the smoke and flame in the image into the movement geometry of the ascending airflow.

6 is a flowchart illustrating an image processing method according to another embodiment of the present invention.

Referring to FIG. 6, the image processing method according to the present invention performs a step S601 in which the image processing apparatus 100 receives a video image captured by the image capturing apparatus 200.

The image processing apparatus 100 performs step S602 of calculating the color probability. In step 602, the color distribution of the pixels included in the received image image in at least two-dimensional color space is modeled based on the color and luminance information, and the color probability is calculated based on the modeled color distribution.

The image processing apparatus 100 performs step S603 of generating a color probability image. In step 603, a color probability image is generated using the calculated color probability.

The image processing apparatus 100 calculates a color probability using Cb, Cr, and Cr / Cb values of the pixels of the input image.

The image processing apparatus 100 performs step S604 of generating a background image. In step S604, a background image is generated by modeling the background of the received image image.

The image processing apparatus 100 performs a step S605 of generating a motion image. In step S605, a motion image is generated using the image image received in step S601 and the background image generated in step S604.

In operation S605, a motion image is generated using the received image and background image in operation S605-1. In operation S605, a motion image is binarized to a first threshold value to calculate M _b (x, y) -2) and a motion image of the second binarized by a threshold value Mm (x, y), the final motion images by using the steps (S605-3), and M _b (x, y) and Mm (x, y) for calculating (M (x, y)) (S605-4).

The image processing apparatus 100 performs step S606 of generating a candidate probability image. In step S606, a candidate probability image is generated using the color probability image generated in step S603 and the final motion image generated in step S605.

The image processing apparatus 100 performs a step S607 of extracting a plurality of characteristics. In step S607, the plurality of characteristics for the candidate probabilistic image include the light reflection start zone, the light reflection end zone, the width of the line of the light reflection angle, the width of the white boundary line of smoke, resolution, And the like.

The image processing apparatus 100 performs step S608 of calculating the random probability. In step S608, a plurality of randomness probabilities are calculated by applying a randomness test algorithm to the plurality of characteristics extracted in step 607. [ Step S608 includes calculating a random probability average by arithmetically averaging the plurality of random probability S608-1, calculating N random probability averages by repeatedly calculating a random probability average over N frames of the received image data, And a step (S608-3) of setting a threshold value calculated by arithmetically averaging the N random probability averages (S608-3).

The image processing apparatus 100 performs step S609 of verifying the candidate probability image. In step S609, it is determined whether or not to restore the candidate probability image using the threshold value set after step S608-3. If the threshold value of the corresponding bit group is larger than 0.1, it is determined as a line. If the threshold value of the bit group is smaller than 0.1 and larger than 0.07, it is determined as a should line. If the threshold value of the bit group is smaller than 0.07 and larger than 0.05, it is judged as a lattice line (Maybe_line). If the threshold value of the corresponding bit group is smaller than 0.05, it is judged that it is not a line (Not_line).

The image processing apparatus 100 performs step S610 of correcting the candidate probability image. In step S610, image correction is performed on the candidate probabilistic image based on the verification result in step S609.

7 is a flowchart for explaining a real-time smoke and flame information acquisition method according to another embodiment of the present invention.

Referring to FIG. 7, the image processing apparatus 100 receives an image frame in real time (S701). The image processing apparatus 100 separates image frame data input by a background modeling algorithm into a background and a foreground. The image processing apparatus 100 may be configured to perform a background motion based on a background moving-image background modeling algorithm, an object moving without a large movement in a fixed place, and a minute motion due to a refraction of light on a natural illumination and an artificial illumination Forced to deny recognition by assimilation.

The image processing apparatus 100 extracts a still image of a region of interest from an image frame input in real time using an object histogram edge algorithm (S702).

The image processing apparatus 100 calculates the width, length, and RGB color information of the object by the object classification algorithm, specifies the logical coordinates on the pixels of the smoke and flame labels, , y) and end (x2, y2) coordinates to convert the bitmap image into a bitmap image, and then transfer the bitmap image to the memory of the system (S703).

The image processing apparatus 100 corrects the sensed image by removing the noise included in the digitally enlarged image (S704). The image processing apparatus 100 extracts a shape image included in the corrected image (S705). The image processing apparatus 100 extracts a label image from the extracted shape image (S706).

The image processing apparatus 100 extracts smoke and flame images from the label image using a background modeling algorithm (S707). The image processing apparatus 100 extracts characteristic information of smoke and flame images and performs a random test based on the extracted characteristic information to correct image bouncing and image blurring included in the extracted smoke and flame images S708).

The image processing apparatus 100 recognizes the corrected smoke and flame image (S709), and converts the coordinates of the recognized smoke, flame, and rising speed information of the Z-airflow into text information (S710). The image processing apparatus 100 transmits the converted text information to a remote server (S711).

The above-described methods according to various embodiments of the present invention may be stored as a code in a computer-readable storage medium. The code for performing the above-described methods according to various embodiments of the present invention may be stored in a memory such as a random access memory (RAM), a flash memory, a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an Electrically Erasable and Programmable ROM ), A register, a hard disk, a removable disk, a memory card, a USB memory, a CD-ROM, and the like.

While the present invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments.

Claims (10)

Fire detection sensor to detect fire;
An imaging device having a driving unit for synchronizing a photographing direction in a fire sensing direction by sensing data of the fire detection sensor;
A receiving unit for receiving a video image picked up by the image pickup apparatus in real time;
Calculating a color probability by modeling a color distribution of pixels included in a video image received by the receiving unit in a two- or two-dimensional or more color space based on the color and luminance information, and calculating a color probability image using the calculated color probability A color probability image generating unit for generating a color probability image;
A background image generation unit for generating a background image by modeling a background of the video image received by the receiving unit;
A motion image generation unit for generating a motion image using the video image received by the reception unit and the background image generated by the background image generation unit;
Generating a candidate probability image using the color probability image generated by the color probability image generating unit and the motion image generated by the motion image generating unit, extracting a plurality of characteristics of the candidate probability image, And an image correcting unit for correcting the candidate probability image by verifying the candidate probability image by using the calculated random probability,
Wherein the plurality of characteristics mean characteristics for discriminating light reflection lines of smoke and flame. The method according to claim 1,
Wherein the color probability image generating unit comprises:
And calculates a color probability based on the following equation.

(Where P _line (x, y) denotes the chromatic probability in the pixels of the x and y coordinates, and rate denotes Cr / Cb in the x and y coordinate pixels) The method according to claim 1,
Wherein the motion image generating unit comprises:
Generating a motion image using the received video image and the background image,
Calculating M _b (x, y) by binarizing the motion image to a first threshold value, binarizing the motion image to a second threshold value to calculate M m (x, y)
And generates a final motion image according to the following equation.

The method according to claim 1,
Wherein the image correction unit comprises:
A plurality of randomness probabilities are calculated for the plurality of characteristics,
Calculating a random probability average using the plurality of random probabilities,
Calculating N random probability averages by repeatedly calculating the random probability average for N frames of the received image data,
And a value obtained by averaging the N random probability averages is used as a threshold value for reconstructing the smoke and flame images included in the motion image. 5. The method of claim 4,
Wherein the image correction unit determines a restored image of the smoke and flame image using the following equation.

(Where W is the restoration smoke and flame image, Pw is the threshold value, line is a sure line, Should_line is the blurred line, Maybe_line is the grating line, and Not_line is the blank line) Receiving a video image picked up by an image pickup apparatus in real time;
Calculating a color probability by modeling a color distribution of pixels included in the received image in at least two-dimensional color space based on color and luminance information;
Generating a color probability image using the calculated color probability;
Generating a background image by modeling the background of the received video image;
Generating a motion image using the received image and the background image;
Generating a candidate probability image using the color probability image and the motion image;
Extracting a plurality of characteristics for the candidate probabilistic image;
Calculating a random probability by applying a random test algorithm to the extracted plurality of characteristics;
And correcting the candidate probability image by verifying the candidate probability image using the calculated randomness probability. The method according to claim 6,
Wherein the step of generating the color probability image comprises:
Wherein the color probability is calculated based on the following equation.

(Where P _line (x, y) represents the chromatic probability due to the movement of the light reflection angle at the x, y coordinate pixel, and rate represents Cr / Cb at the x, y coordinate pixel) The method according to claim 6,
Wherein the step of generating the motion image comprises:
Generating a motion image using the received image and the background image;
Binarizing the motion image to a first threshold to produce M _b (x, y);
Binarizing the motion image to a second threshold to produce Mm (x, y); And
And generating a final motion image by the following equation.

The method according to claim 6,
Wherein the correcting the image comprises:
Calculating a plurality of randomness probabilities for the plurality of characteristics;
Calculating a random probability average using the plurality of random probabilities;
Calculating N random probability averages by repeatedly calculating the random probability average over N frames of the received video data; And
And reconstructing a smoke / flame image included in the motion image using a value calculated by averaging the N random probability averages as a threshold value. 10. The method of claim 9,
Wherein the reconstructing the image comprises determining a reconstructed image of the smoke and flame image using the following equation:

(Where W is the restoration smoke and flame image, Pw is the threshold value, line is a sure line, Should_line is the blurred line, Maybe_line is the grating line, and Not_line is the blank line)

Images