JPH08263768A - Device and method for detecting flame - Google Patents

Abstract

PURPOSE: To efficiently and reliably detect flames in a fire by simple picture processing even in the case of using a CCD device having a CCD light receiving part as an image pickup device. CONSTITUTION: A CCD device 11 is constituted of arranging a CCD light receiving part 32 in a holder 31 and applying a protection member 33 consisting of a material having transparency for light in an ultraviolet area to the upper face of the holder 31. A lens holder 36 is fixed so as to cover the device 11 and optical lenses 12a, 12b are arranged in a lens casing 37 engaged with the holder 36. As optical lenses 12a and 12b, the one having transparency used. The casing 37 is also provided with an optical filter 38 e.g. for cutting off light other than light in the ultraviolet area as an ultraviolet-ray transparent means having transparency only for light in the ultraviolet area.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a flame detecting device and a flame detecting method for detecting a flame in a fire or the like.

[0002]

2. Description of the Related Art In recent years, a CCD device has been used as an image pickup device for detecting a flame in the event of a fire or the like because of a demand for downsizing and cost reduction. FIG. 15 is a schematic configuration diagram of a general CCD device. This CCD device includes a CCD light receiving unit (CC
D sensor) 302 is arranged, and in order to protect the CCD light receiving portion 302, the protective member 3 made of ordinary glass (for example, silicate glass) is provided on the upper surface of the holder 301.
03 is provided. Reference numeral 304 is a circuit board provided with a circuit for performing a predetermined process on the electric signal photoelectrically converted by the CCD light receiving section 302. In the example of FIG. 15, the holder 301 is mounted on the circuit board 304. It is supported.

FIG. 16 shows the spectral sensitivity characteristics of a typical CCD light receiving section (CCD sensor) normally used in the above-mentioned CCD device. As can be seen from FIG.
A typical CCD sensor has the highest sensitivity characteristic with respect to light in the visible region, and the sensitivity decreases in the ultraviolet region.

Further, the protective member 303 used for the general CCD device as described above, that is, the ordinary glass has a characteristic of transmitting light in the visible region and the near infrared region well, It does not have good transmission characteristics for light in the range.

As described above, the above-mentioned general CCD device is designed mainly for satisfactorily capturing an image in the visible region, and the protective member 303 is made of an ordinary glass.
Even when (for example, silicate glass) is used, since it has a property of transmitting light in the visible region well, it does not hinder capturing an image in the visible region.

[0006]

However, when the above-mentioned CCD device is used to detect a flame in the event of a fire, the light emitted from the flame is mainly in the ultraviolet region as shown in FIG. Therefore, it is blocked by the protective member 304 made of ordinary glass (that is, the intensity of light from the flame is significantly attenuated by the protective member 304), and further, due to the spectral sensitivity characteristic of the CCD light receiving unit 303, The image is not captured with good sensitivity. Therefore, the conventional general CCD device has a problem that it is not possible to properly capture an image of the flame.

Further, since this CCD device also captures images in the visible region and near-infrared region, that is, images other than the flame, not only the CCD device cannot capture the flame well, but also the flame. There is a problem that images and images of other parts, for example, images of the surrounding environment are mixed.

Therefore, in the conventional flame detection apparatus using the CCD device, a very complicated and sophisticated image processing technique must be used to extract only the image of the flame portion from the captured image. Further, even if an advanced image processing technique is used, only the flame portion cannot be imaged well depending on the CCD device as described above, so that there is a limit in favorably detecting the flame.

According to the present invention, even when a CCD device having a CCD light receiving portion is used as an image pickup device, a flame detection apparatus capable of detecting flames in a fire or the like satisfactorily and reliably by simple image processing. And a flame detection method.

[0010]

In order to achieve the above object, according to the present invention, the CCD light receiving section is made to cut off light other than the ultraviolet region to pick up an image, and a change in image data picked up by the CCD light receiving section is changed. It should be detected and detected as a flame when the changed portion of the image data is at least of a reasonable size as a flame and has a reasonable temporal change as a flame. There is. This allows
Even when a CCD device having a CCD light receiving unit is used as an image pickup device, flames in a fire or the like can be satisfactorily and reliably detected by simple image processing.

[0011]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a diagram showing a configuration example of a flame detection device according to the present invention. Referring to FIG. 1, this flame detection device outputs an image pickup unit 1, a calculation unit 3 that performs image processing calculation relating to flame detection based on image data taken by the image pickup unit 1, and a flame detection result. It has an output unit 4 and a power supply unit 5 for supplying power.

The image pickup section 1 has a predetermined viewing angle (angle of view).
And an image pickup device 11, and a CCD device is used as the image pickup device 11.

FIG. 2 is a diagram showing a configuration example of the image pickup section 1.
In the configuration example of FIG. 2, in the CCD device 11, a CCD light receiving portion (CCD sensor) 32 is arranged in a predetermined holder 31, and in order to protect the CCD light receiving portion 32, a predetermined amount is provided on the upper surface of the holder 31. The protective member 33 made of the above material is provided.

In this CCD device 11, the CCD
The light receiving section 32 is a CCD sensor having the same spectral sensitivity characteristic as the CCD light receiving section 302 of FIG. 15, that is, a general CCD having the spectral sensitivity characteristic as shown in FIG.
Although a sensor can be used, the protective member 33 is made of a material that is transparent to light in the ultraviolet region, such as a silica-based material, quartz glass, or an optical crystal such as quartz, fluorite, or calcite. There is.

Further, in FIG. 2, the holder 31 containing the CCD light receiving section 32 is supported by a predetermined circuit board 34, for example, a circuit board 34 on which the arithmetic section 3 and the like are mounted.

Further, in the configuration example of FIG. 2, an optical lens is used for the optical means 12, and a CC as an image pickup device is used.
An optical lens is incorporated in the D device 11. That is, a lens holder 36 is attached to the circuit board 34 so as to cover the CCD device 11, and a lens housing 37 is slidably fitted in the lens holder 36 in the direction of arrow A, for example. An optical lens having a predetermined viewing angle (angle of view) in the body 37 (see FIG. 2).
In the example, two lenses 12a and 12b) are arranged. Here, as the optical lenses 12a and 12b, those having transparency to light in the ultraviolet region, for example, silica stone materials, quartz glass, and optical crystals such as quartz, fluorite, and calcite are used. The optical lenses 12a and 12b are CC
The D light receiving unit 32 is installed so that an image of the subject (for example, an inverted image) is well formed.

Further, the lens housing 37 is further provided with an ultraviolet transmitting means having a transmitting property only in the ultraviolet region, for example, an optical filter 38 for cutting the light other than the ultraviolet region.

In such a structure, when light having a spectral characteristic as shown in FIG. 16, that is, light mainly in the ultraviolet region is radiated from the flame during a fire, the light in the ultraviolet region is
The CCD device 1 is satisfactorily transmitted through the optical lenses 12a and 12b and also transmitted through the ultraviolet transmission means (filter) 38.
Light in 1. In the CCD device 11 as well, since the protective member 33 is made of a material that transmits light in the ultraviolet region, light from the flame also passes through the protective member 33 well, and therefore is not attenuated to a great extent. CCD with sufficient light intensity
The light is incident on the light receiving portion (CCD sensor) 32, and the CCD light receiving portion 3
2. Form a good image on 2.

As a result, in the CCD light receiving section 32, even when a general CCD sensor having the spectral sensitivity characteristic as shown in FIG. 16 is used, a flame image can be captured well.

The optical lenses 12a and 12b also receive light other than light emitted from the flame, that is, for example, light other than the ultraviolet region from the surrounding environment, but the light other than the ultraviolet region transmits ultraviolet light. Since it is cut by the means (for example, an optical filter) 38 and hardly enters the CCD device 11, the CCD light receiving unit 32 can satisfactorily capture only the image of the flame.

FIG. 3 is a diagram showing another example of the structure of the image pickup section 11. In FIG. 3, the same parts as those in FIG. 2 are designated by the same reference numerals.

In the configuration example of FIG. 3, the image pickup device 11 is exactly the same as the CCD device of FIG. 2, while the optical means 12 uses a pinhole instead of an optical lens. That is, the dark box 46 is attached to the circuit board 34 supporting the CCD device 11 so as to cover the CCD device 11.
A pinhole 47 is formed at a predetermined position. Here, the pinhole 47 is provided on the CCD light receiving unit 3 so that an image of the subject (inverted image) is well formed on the CCD light receiving unit 32.
2 is provided at a predetermined distance.

In the configuration example of FIG. 3 as well, as in the configuration example of FIG. 2, the CCD device 11 is provided with a protective member 33 having transparency to light in the ultraviolet region, and the pinhole 47 is provided at the pinhole 47. Of the light passing through the pinhole 47, an ultraviolet transmitting means (for example, an optical filter) that has a transparency only to light in the ultraviolet region and cuts light other than the ultraviolet region.
38 are provided.

Also in the configuration of FIG. 3, when light having a spectral characteristic as shown in FIG. 16, that is, light mainly in the ultraviolet region is emitted from the flame in the event of a fire, the light in the ultraviolet region is The light passes through the hole 47, the ultraviolet transmitting means (optical filter) 38, and enters the CCD device 11. In the CCD device 11 as well, since the protective member 33 is made of a material that transmits light in the ultraviolet region, light from the flame also passes through the protective member 33 well, and therefore is not attenuated to a great extent. To the CCD light receiving unit (CCD sensor) 32 with sufficient light intensity,
Form a good image on top.

As a result, in the CCD light receiving section 32, even when a general CCD sensor having the spectral sensitivity characteristic as shown in FIG. 16 is used, a flame image can be captured well.

Further, from the pinhole 47, light other than light emitted from the flame, that is, light other than the ultraviolet region from the ambient environment, for example, enters, but the light other than the ultraviolet region is transmitted by the ultraviolet transmitting means ( Optical filter) 38, CCD,
Since almost no light enters the device 11, the CCD light receiving unit 32 can satisfactorily capture only the image of the flame.

2 and 3, both the protective member 33 and the ultraviolet light transmitting means (for example, filter) 38 are provided, the ultraviolet light transmitting means 38 is the lens holder 3
6 or the dark box 46, it also has a function as a protective member for protecting the CCD light receiving portion 32, so that the ultraviolet transmitting means (optical filter) is provided at the optical means 12 (optical lenses 12a, 12b and pinhole 47). ) 38 is provided, the protective member 33 is not necessarily provided in the CCD device 11.

Further, the protective member 33 of the CCD device 11
, As an optical filter that transmits only light in the ultraviolet region, or as a glass member (or optical crystal) that is transparent to light in the ultraviolet region coated with a material that transmits only light in the ultraviolet region. Alternatively, in this case, since the protection member 33 itself functions as an ultraviolet transmitting means, the optical means 12 (optical lens 12a,
Ultraviolet transmission means 38 is provided at 12b and pinhole 47).
Need not be provided separately.

In other words, according to the present invention, the image pickup section 1 receives the light transmitted through the ultraviolet transmitting means and the ultraviolet transmitting means which is transparent to the light in the ultraviolet region and cuts the light other than the ultraviolet region. Any structure may be used as long as it is provided with a CCD light-receiving part for capturing an image (that is, it may be any structure that cuts out light other than the ultraviolet region from the light entering and allows the CCD light-receiving part to receive the light). As long as it has such a configuration, FIG.
It is not limited to that of FIG.

The CCD light receiving section (CCD sensor) 32
It is also possible to use a CCD sensor other than a general CCD sensor having a spectral sensitivity characteristic as shown in FIG. 16 (for example, a CCD sensor having a high sensitivity in the ultraviolet region), and in this case, a higher sensitivity is obtained. Capable of capturing images of flames. However, even when a general CCD sensor is used, as described above, only the flame image can be captured well,
If a typical CCD sensor is used, the device can be kept low cost.

As described above, in this embodiment, the general CC
Even when the D sensor is used, only the image of the flame can be captured well, so in order to obtain (detect) information about the flame such as the size, shape and position of the flame, the calculation unit 3
It is possible to detect information about a flame satisfactorily and reliably by simple image processing without requiring complicated and sophisticated image processing technology as in the past.

Next, using the flame detection device of this embodiment,
For example, a method of detecting a flame generated during a fire will be described.

FIG. 4 is a perspective view showing an example of a room in the building, and the image pickup unit 1 of the flame detecting apparatus of the present embodiment is, for example, as shown in FIG. Ceiling 1
02 or a high position of the wall surface 103, and the CCD device 11 (CCD light receiving unit 3
The screen imaged by 2) is the viewing angle of the optical means 12.
(Angle of view) and installation conditions of the imaging unit 1 (height h of the imaging unit 1 from the floor 104 of the room 101, and installation angle (tilt angle) θ of the imaging unit 1). Therefore, room 101
When trying to monitor a desired monitoring area in the room, the optical means 12 (optical lenses 12a and 12b in the example of FIG. 2) having a predetermined viewing angle is used, and a predetermined position in the room 101 is used. It is necessary to previously install the image pickup unit 1 at the angle θ.

5 (a) and 5 (b) are cross-sectional views in the x-axis direction and the y-axis direction of FIG. 4, respectively. FIGS. 5 (a) and 5 (b) show the desired monitoring area in the room 101. To monitor 105,
The imaging unit 1 having a predetermined viewing angle θ ₀ (θ _x0 , θ _y0 ) has a predetermined tilt angle (a tilt angle from the vertical line z) θ at a predetermined position.
The installation state is shown at (θ _x , θ _y ). Note that θ
_x and θ _y are the x-axis direction component and the y-axis direction component of the tilt angle θ, and θ _x0 and θ _y0 are the x-axis direction component and the y-axis direction component of the viewing angle θ ₀ , respectively.

Further, in FIG. 6, the image pickup unit 1 is shown in FIG.
When installed as shown in (b), the CCD light receiving unit 32
An example of a screen imaged by is shown. In the example of FIG. 6, this screen is, for example, the number of pixels (the number of elements) N × M (for example, 64 × 60 pixels) of the CCD light receiving unit (CCD sensor).
Corresponding to N in the x-axis direction and N in the y-axis direction, M
It is divided into (for example, 64 and 60) pixels. That is, one pixel of the imaged screen corresponds to one pixel of the CCD sensor.

CCD sensors include those with high resolution of several hundreds of thousands of pixels to those with low resolution of several tens of pixels, and any of these can be used. In this case, when a low-resolution CCD sensor is used, the output of each pixel of this CCD sensor can be directly used as the image data to be processed, and in this case, each pixel of the screen is as described above. Each pixel has a one-to-one correspondence. Further, when a high-resolution CCD sensor is used, each pixel output of this CCD sensor can be directly used as image data to be processed, but in order to simplify the subsequent image processing, in the image pickup unit 1 or In the arithmetic unit 3, a plurality of pixel outputs of the CCD sensor may be collected (for example, by taking the average of the plurality of pixel outputs) to form one pixel as image data. For example, when the CCD sensor has 64 × 64 pixels, that is, 4096 pixels, by compressing 4 pixels into 1 pixel (for example, taking the average value of the levels of 4 pixels and setting this as the level of 1 pixel) 16 × 1)
Since the image data has 6 pixels, that is, 256 pixels, the time required for image processing can be shortened. However, the resolution decreases accordingly.

The computing section 3 periodically (at a fixed time interval T ₁ , for example 0.5 to
Monitoring (collection) (at intervals of about 1.0 second), basically, comparing the image data of the current screen with the image data of the previous screen, the image data of the current screen and the previous screen When there is a changed portion between the changed image data and the image data, it is determined whether or not the changed portion is a flame (for example, a flame caused by a fire).

In the example shown in FIG. 1, the arithmetic unit 3 has the analog image data (that is, the CCD device 11 (C
For each pixel output from the CD light receiving section 32)), analog-
An A / D converter 20 that performs digital conversion, a processor (CPU) 21 that performs the above-described monitoring processing, determination processing, and the like based on digitally converted image data, a ROM 22 that stores a processing program of the processor 21, and the like. It has a RAM 23 functioning as a work area of the processor 21, and the image data of the screen at the present time, the image data of the screen at the previous time, and the like used in the above-mentioned determination processing are stored in the RAM 23.

The A / D converter 20 may be built in the processor 21, and the A / D converter 2 may be used.
As 0, for example, one that converts analog image data into binary digital image data by a predetermined threshold value can be used. In this case, the processor 21 performs predetermined image processing on the binary digital image data. The calculation can be performed to perform flame detection processing. Further, the comparison between the image data at the present time and the image data at the previous time for determining whether or not the image data has changed can be performed by taking the difference between them and making the difference image data.

As the A / D converter 20, instead of using the one for converting analog image data into binary digital image data, an A / D converter having a function of converting into multivalued digital image data is used. By using the multi-valued digital image data, it is possible to detect and judge the information about the flame in more detail and more accurately. In this case, it is necessary to use, as the processor 21, a processor capable of processing multivalued digital image data.

Specifically, the flame detection process is performed as follows, for example. That is, for example, when the height h and the installation angle θ (θ _x , θ _y ) of the image capturing unit 1 are given in advance as the installation conditions, the calculation unit 3 first sets the conditions shown in FIG. 6 based on these installation conditions. On the screen as shown, the imaging unit 1
Where the position (x _C , y _C ) immediately below is located, and then from the installation position of the imaging unit 1 to the position of the object OBJ (see FIG. 4) corresponding to the changed portion CH of the image data. Information about the angle ψ and the distance L from the installation position of the imaging unit 1 to the object OBJ corresponding to the changed portion of the image data.
_XY and object OB corresponding to the changed part of the image data
The size of J is calculated, and the object OBJ corresponding to the changed portion of the image data is calculated based on the calculated information.
Determine the scale (size) and position of the
It is designed to judge whether or not the BJ has a precondition for a flame generated in a fire.

Here, the position (x _C , y _C ) immediately below the image pickup unit 1 on the screen is calculated as follows. That is, as shown in FIGS. 5 (a) and 5 (b), for example, the imaging unit 1
_Has viewing angles θ _x0 and θ _y0 in the x-axis direction and the y-axis direction, respectively, and is installed with an inclination angle θ _{x in} the x-axis direction and an inclination angle θ _y in the y-axis direction. The angles dθ _x and dθ of one pixel (one section) on the x-axis and y-axis of the screen as shown in FIG.
Each _y is calculated by the following equation.

[0043]

## EQU1 ## dθ _x = θ _x0 / N dθ _y = θ _y0 / M

N and M are the numbers of pixels (the number of sections) in the x-axis direction and the y-axis direction, respectively. 1 pixel on x-axis and y-axis
When the angles dθ _x and dθ _{y of} (one section) are calculated by Equation 1, the position (x _C , y _C ) immediately below the image pickup unit 1 on the screen is obtained by the following equation.

[0045]

[Number 2] _{x C = N / 2-θ} x / dθ x y C = M / 2-θ y / dθ y

FIG. 6 shows the position (x _C , y _C ) immediately below the image pickup unit 1 on the screen thus obtained. As can be seen from FIG. 6, when the tilt angles θ _x and θ _y are 0, that is, when the image pickup unit 1 is not tilted, the position (x _C , y _C ) immediately below the position is the center of the screen. , Tilt angle θ _x
Alternatively, the larger θ _y , the closer (x _C , y _C ) is to the edge of the screen.

In this way, the image pickup unit 1 on the screen
When the position (x _C , y _C ) immediately below is calculated, the angle ψ (vertical line from the installation position of the image pickup unit 1 to the position of the object OBJ corresponding to the changed portion of the image data is used as a reference. z
Can be obtained. More specifically, it is assumed that an A / D converter 20 that converts binary digital image data is used, and the object OBJ does not exist at the previous time and the screen at the previous time is shown in FIG. As shown in (a), the object OBJ appears at the present time as shown in FIG. 4, the current screen becomes as shown in FIG. 7 (b), and the image data changes on the screen. When it is detected that the portion is the portion of the code CH, that is, as shown in FIG. 7C by taking the difference between the image data of FIG. 7B and the image data of FIG. 7A, for example. If different difference image data is obtained and a portion (pixel portion in the example of FIG. 7C, which is a black pixel) CH having a pixel value other than “0” in this difference image data is detected as a changed portion of the image data. When the actual object OBJ corresponding to this changed portion CH is It can be obtained information about the angle ψ as follows.

That is, the changed portion CH of the image data on the screen is (x ₁ , y ₁ ) as shown in FIG. 7 (c).
In the range of to (x ₂ , y ₂ ), the angular range ψ _{x1 to} ψ _x2 in the x-axis direction from the installation position of the imaging unit 1 to the actual object OBJ corresponding to the portion CH where the image data has changed, The angle ranges ψ _{y1 to} ψ _y2 in the y-axis direction can be obtained by the following equations, respectively.

[0049]

Equation 3] _{ψ x1 = dθ x × (x} 1 -x C) ψ x2 = dθ x × (x 2 -x C) ψ y1 = dθ y × (y 1 -y C) ψ y2 = dθ y × ( y ₂ -y _C)

Further, from the installation position of the image pickup unit 1 to the object OB
The distance L _{XY to} J (the distance to the farthest portion of the object OBJ) can be obtained by the following equation.

[0051]

## EQU4 ## L _XY = (h / cos ψ _x2 ) × (1 / cos ψ _y2 ).

Further, as a result, the actual sizes | X | and | Y | of the object OBJ in the x-axis direction and the y-axis direction and the actual size S of the object OBJ are expressed by the following equation. It can be calculated.

[0053]

[Expression 5] | X | = L _XY × (ψ _x2 −ψ _x1 ) | Y | = L _XY × (ψ _y2 −ψ _y1 ) S = | X | × | Y |

In this way, S, | X |, | Y | can be obtained as information on the size of the object OBJ,
As information on the position of the object OBJ, L _XY , ψ can be obtained.

Each piece of information about the object OBJ as described above is stored in the floor 104 which should be the monitoring area 105 of the room 101.
The portion is a flat plane, and it is obtained on the assumption that the object OBJ is along the flat plane of the floor 104, and the portion of the floor 104 to be the monitoring area 105 has irregularities such as stairs. In this case, it is necessary to make a corresponding correction on each piece of information of the object OBJ. In the following description, for convenience of explanation, it is assumed that the portion of the floor 104 to be the monitoring area 105 is a flat plane.

In the above example, the image pickup unit 1 can be mounted at any tilt angle θ (θ _x , θ _y ), but if necessary, this tilt angle θ (θ _x , θ _y). ) Can be restricted. That is, the CCD device 11 is generally rectangular, and one of the x-axis direction and the y-axis direction is longer than the other and the number of pixels is large. Now, for example, when the length in the x-axis direction is long, when the inclination angle θ _{x in the} x-axis direction is not “0 °” (that is, the x-axis of this CCD device 11 is the floor 1
(When it is not parallel to 04), a shortage occurs in the actual monitoring area in the x-axis direction, or the calculation of the characteristic parameter (size etc.) of the object OBJ becomes complicated, and an error occurs in the characteristic parameter. When the object OBJ is displayed on the monitor, it may be difficult to see the object. Therefore, in the above example, the image pickup unit 1 should be attached so that the x axis of the CCD device 11 is parallel to the floor (that is, the tilt angle θ _x is “0 °”). In other words, in the case of the above example, the CCD
At least one of the x-axis direction component θ _x and the y-axis direction component θ _y of the inclination angle θ of the device 11 from the vertical line z is preferably set to “0 °”. At this time, the position of x _C ,
Alternatively, the position of y _C becomes the center on the x-axis of the imaging screen or the center on the y-axis.

As described above, the calculation unit 3 monitors the change of the image data each time the image data of the screen is collected periodically (for example, at a constant time interval T ₁ ), and changes to the image data. When there is a partial CH, this changed partial CH
The information (size and position) as described above is obtained for the object OBJ corresponding to, and from this information (size and position), it is determined whether or not the object OBJ has a precondition as a flame generated in a fire. First, the judgment is made (first judgment process).

This first judgment processing is the scale (size, area) of the object OBJ when it is a flame due to a fire.
However, it is made on the basis of features such as a scale (size, area) that is considerably larger than the scale of flames such as cigarettes. That is, the calculation unit 3 may, for example, calculate the overall size of the object OBJ corresponding to the changed portion CH of the image data.
From the (area) S, check whether the size (area) of this part is of a proper scale as a fire flame, and determine whether the prerequisites for a fire flame are provided. It is like this.

The size of the object OBJ corresponding to the changed portion CH of the image data can be obtained by S, or the size | X |, | Y | in the x-axis direction and the y-axis direction.
Can also be obtained in each of the x-axis direction and the y-axis direction. Also, the sizes in the x-axis direction and the y-axis direction | X |, | Y
The information about the shape of the object OBJ can be obtained by the ratio of || Y | / | X |, and the information about the shape is added to the information about the size S and the position, so that it can be used as a flame at the time of a fire. It is also possible to judge whether or not the prerequisites are provided.

In this way, when it is judged that the object OBJ corresponding to the changed portion CH of the image data has the precondition as a flame depending on its size and position,
The arithmetic unit 3 further examines the temporal change (for example, examines temporal fluctuations) and determines whether or not this is a flame (second determination processing).

More specifically, this second determination processing is performed when the object OBJ is a flame, a predetermined fluctuation (for example, 8
Has a flicker of about Hz, and the position of the object does not change rapidly with time (for example, its moving speed is 0 depending on the distance L _XY to the image capturing unit 1).
cm / sec to 50 cm / sec)). That is, the calculation unit 3 further monitors the temporal change of the object OBJ, and calculates the object OBJ.
Whether the object has a proper time change as a flame, that is, whether the object OBJ has a predetermined fluctuation, or the time change of the position of the object is within a predetermined speed. It is designed to determine whether or not it is a flame at the time of fire by finally checking whether or not it is.

In the above example, the changed portion of the image data is only one pixel connected region CH, and therefore,
Although only one object OBJ has dealt with the case where the detected changed portion of the image data is a plurality of pixel connected region CH ₁ to CH _n as shown in FIG. 8, a plurality of objects OBJ ₁ ~ When OBJ _n is detected, the above-described first and second determination processes are performed on each of the pixel connection regions CH _{1 to} CH _n and each of the objects OBJ _{1 to} OBJ _n ,
It is determined whether each of the objects OBJ ₁ to OBJ _{n is} a flame.

9 and 10 are flowcharts showing an example of the processing operation of the arithmetic unit 3 (in particular, the processor 21). In the examples of FIGS. 9 and 10, the A / D converter 20 is assumed to convert analog image data into multi-valued digital image data, and the precondition for the object to be a flame at the time of fire is defined. In the first determination processing of whether or not it is provided, in the difference image data obtained by subtracting the multi-valued image data at the previous time point and the current time point, the number n _{1 of} pixels whose pixel value exceeds the predetermined threshold value TH ₁ is set to a predetermined value. made by the greater or whether than threshold n _a, and the target object when n ₁ is greater than n _a is sufficiently large as flame during a fire, with the prerequisites as flame It is supposed to be.

Referring to FIGS. 9 and 10, the processor 2
In step 1, first, initialization processing is performed. For example, the RAM 23 or the like functioning as a work area is initialized (step S1), and thereafter the image monitoring process is started.

In the image monitoring process, the processor 21 uses the image data from the image pickup unit 1 (more specifically, the A / D converter 2).
Multi-valued digital image data from 0) is fetched, for example, at every predetermined time interval T ₁ (for example, a time interval of about 0.5 second to 1 second) (steps S2 and S3). For example, as shown in FIG. 11, the start time of the image processing is t ₁ and the times t ₁ and t
The multivalued image data of ₂ , t ₃ , ... Is D _ij (t ₁ ), D _ij (t ₂ ),
, D _ij (t ₃ ), ..., The processor 21 causes the multivalued image data D _ij (t ₁ ), D at each time t ₁ , t ₂ , t ₃ ,.
_ij (t ₂ ), D _ij (t ₃ ), ... Are fetched and stored in the RAM 23.

At this time, basically, in order to save the capacity of the RAM 23, the image data D _ij (t _k ), D _ij (at time t _k , t _{k + 1} which are temporally adjacent to each other are basically set. t _{k + 1} ) is RA
To be held in M23. Specifically, when the processor 21 takes in the image data D _ij (t ₁ ) at time t ₁ ,
This is stored in the area WK ₁ of the RAM 23 as shown in FIG. 12A. Then, when the image data D _ij (t ₂ ) is fetched at time t ₂ , this is stored in the area WK ₂ of the RAM 23 as shown in FIG.
Store as shown in (b). At this point, the RAM 23 stores the image data D _ij (t ₁ ) and D 2 at the two times t ₁ and t _2.
ij (t ₂ ) is held. Next, at time t ₃ , the image data D
_{When ij} (t ₃ ) is fetched, the image data D _ij (t ₁ ) at time t ₁ held in the area WK ₁ of the RAM 23 is deleted,
Instead of this, the image data D _ij (t ₃ ) at time t ₃ is shown in FIG.
Store as shown in (c). In this way, the image data of the odd-numbered time is stored in the area WK ₁ of the RAM 23,
Area WK of RAM 23 for image data at even time
Store in ₂ .

In this way, when multi-valued image data D _ij (t _k ) and D _ij (t _{k + 1} ) at two times t _k and t _{k + 1} are acquired,
The processor 21 uses the two multivalued image data D
_ij (t _k ), D _ij (t _{k + 1} ) are compared, and multivalued image data D
_It is determined whether or not _ij (t _{k + 1} ) has changed with respect to the multi-valued image data D _ij (t _k ) (steps S4, S5, S6). That is, the difference between the two multivalued image data D _ij (t _{k + 1} ) and D _ij (t _k ) is calculated (step S4), and the difference image data (D _ij (t _k )
_{k + 1} ) −D _ij (t _k )), the pixel value is a predetermined threshold value TH ₁
The number n ₁ of pixels larger than that is obtained (step S5).
Whether or not it has a scale (size) as a flame at the time of fire depending on whether or not the number of pixels n ₁ is larger than _a predetermined threshold value n _a (that is, whether the preconditions as a flame are provided) It is determined (step S6).

As a result of such determination, when the number n _{1 of} pixels having a pixel value larger than the threshold value TH ₁ is smaller than the predetermined threshold value n _a , the image data indicates the size of the flame when a fire occurs. It is considered that there is no reasonable change, and step S is performed again.
Returning to step 2, the same processing is performed for the next time. Specifically, in the example of FIG. 11, it is now determined that there is no appropriate change in the size of the flame between the multivalued image data D _ij (t ₁ ) and D _ij (t ₂ ) at the times t ₁ and t _2. At the times t ₂ and t ₃
Of the multi-valued image data D _ij (t ₂ ) and D _ij (t ₃ ) are compared, and there is no appropriate change in the size of the flame between the image data D _ij (t ₂ ) and D _ij (t ₃ ). If it is determined that the multi-valued image data D _ij (t ₃ ) and D _ij (t ₄ ) at the times t ₃ and t ₄ are compared, the multi-valued image data at the two times t _k and t _{k + 1} are compared. Image data D
The comparison of _ij (t _k ) and D _ij (t _{k + 1} ) is repeated (steps S2 to S6).

In such repetitive processing, for example, the multivalued image data D _ij (t ₄ ), D at the times t ₄ , t ₅
As a result of comparing _ij (t ₅ ), the difference image data (D
In _{ij (t 5) -D ij (} t 4)), the number n ₁ of pixels having large pixel value than a predetermined threshold value TH ₁ is greater than a predetermined threshold value n _a, a fire occurrence flame size However, if a proper change is recognized and it is determined that the precondition for the flame is provided, the processor 21 further determines whether or not the change in the image data is due to the flame. That is, it is determined whether or not the object OBJ corresponding to this changed portion has a temporal change appropriate as a flame.

In order to make this judgment, the processor 21
Is the time t when the change is recognized
₅ not only image data D _ij (t ₅₎ only, subsequent predetermined screen number, i.e., NB number of times t _6, ..., the image data D _ij (t ₆₎ of t _m, ..., D _ij ( t _m ).

That is, the image data D at the temporary point is simply used to perform the process of determining whether or not it is due to the flame.
Only _ij (t ₅ ) can obtain only information such as the size of the object OBJ, and it is not possible to accurately determine that the object OBJ is a flame. For example, a judgment based only on image data at a temporary point may cause an erroneous report due to the action of light such as a momentary light. Therefore, in order to make a more accurate and reliable determination, in step S6, when it is determined that a proper change in the size of the flame at the time of a fire occurs and the prerequisites for the flame are provided, Not only the image data D _ij (t ₅ ) at the time t ₅ but also the image data at the subsequent times t ₆ , ..., T _m are acquired,
The temporal change of the object OBJ is monitored based on the image data at a plurality of times including the image data D _ij (t ₅ ) at the time t ₅ . For example, it is determined whether or not the temporal change of the object OBJ has a fluctuation characteristic peculiar to the flame, and the object O
Detects whether BJ is a flame.

Therefore, in the processing examples of FIGS. 9 and 10, NB is set in advance as the number of screens required to determine whether or not the object OBJ is a flame.
When it is determined that the precondition for the flame at the time of fire is provided, the processor 21 determines the count value CN of the counter that counts the number of screens from this point.
Initialize T to "1" (step S7). Then, it is determined whether the number of screens CNT has become NB (step S
8) If the number of screens CNT has not reached NB, further image data at the subsequent time is taken in at a predetermined time interval T ₂ (steps S9 and S10). That is, when the processor 21 collects image data for one screen at a predetermined time interval T ₂ , it stores it in a predetermined area of the RAM 23. Then, the processor 21 analyzes the image data for one screen stored in the predetermined area of the RAM 23 (step S11). For example, in this image data, the number n ₂ of pixels whose pixel values are larger than a predetermined threshold value TH ₂ , the total TOT of the pixel values of these n ₂ pixels, and their average value AVR (= TOT / n ₂ ) calculate.

In this way, after the image data for one screen is analyzed, the count value CNT is incremented by "1".
(Step S12), the process returns to Step S8 again, and the image data for the next one screen is analyzed.
The processing from 8 to S12 is repeated until the number of screens CNT becomes NB.

FIG. 13 shows an example of the analysis result of the image data of each of the NB screens. Note that, in FIG. 13, as the pixel value of each pixel, only a pixel value larger than a predetermined threshold value TH ₂ is shown. Further, the analysis result on the NB screens as shown in FIG.
It is stored in the RAM 23 in a format as shown in FIG.

In step S8, the number of screens CNT becomes the number of screens NB sufficient to determine whether or not the flame is present, and N
When the analysis results on the B screens are obtained as shown in FIG. 14, the processor 21 determines whether or not it is a flame based on the analysis results of the image data on the NB screens (that is, in the case of a fire). It is determined whether or not there is any) (steps S13 to S21).

Specifically, in the processing examples of FIGS. 9 and 10, the number of NB pixels n ₂ (1) to n ₂ in the entire screen of the number NB of screens is n.
The maximum number of pixels n ₂ (max) and the minimum number of pixels n ₂ (mi
n) and the difference between them (DIF (n ₂ ) = n ₂ (max) −
n ₂ (min)) is obtained as the maximum fluctuation amount (maximum fluctuation amount) related to the size of the object OBJ (step S13), and the NB pixel value total average value A in all screens of the number NB of screens is calculated.
From VR (1) to AVR (NB), the maximum average value AVR (ma
x) and the minimum average value AVR (min), and the difference (DIF (AVR) = AVR (max) −AVR (min)) between
Maximum fluctuation amount of average intensity (average light intensity) of object OBJ
(Maximum fluctuation amount) (step S14), and the number of NB pixels n ₂ (1) to n in all screens NB
₂ (NB), the peak frequency PK (n ₂ ) of the number of pixels n ₂ is obtained as a fluctuation frequency related to the size of the object OBJ (step S15), and N in all screens of the number of screens NB.
From the B pixel value total sums TOT (1) to TOT (NB), the peak frequency PK (TOT) of the pixel value total sum TOT is determined as the object OBJ.
Is obtained as a fluctuation frequency related to the intensity (light intensity) (step S16).

Here, the peak frequency P of the pixel number n ₂ is
K (n ₂ ) means the peak number of pixels, that is, the number of fluctuations. That is, the image data is collected at a time interval T ₂ that is sufficiently shorter than the flame fluctuation frequency so that the flame fluctuation frequency can be sufficiently detected. At this time, the number of pixels n ₂ of each collected image data is compared. The peak number is obtained as the peak frequency PK (n ₂ ) of the number of pixels n ₂ by performing the change, obtaining the change point, and finding the number of peaks. Specifically, when a change point is obtained from NB pieces of image data collected within the data collection time T (= T ₂ × NB) and the number of peaks (the number of peaks) is NP, the peak frequency PK (n ₂ ) is obtained as NP / T, which reflects the fluctuation frequency f related to the size of the object. Therefore, in step S15, the number of pixels n ₂
By determining the peak frequency PK (n ₂ ) of the object OBJ
Information on the fluctuation frequency f relating to the magnitude of is obtained.

Further, the peak frequency PK of the total pixel value TOT
(TOT) means the number of peaks of light intensity, that is, the number of fluctuations. The above-mentioned peak frequency PK of the pixel number n ₂
Apart from (n ₂ ), the peak frequency PK (T
OT) is required because when a flame is imaged by CCD,
The number of pixels n ₂ of the flame, which is the object, greatly differs depending on the distance between the flame and the CCD, but the intensity of light emitted from the flame is not directly related to the number of pixels n ₂ , and This is because even if the distance between the CCD and the CCD changes slightly, it does not change so much, so that whether or not the flame is present can be determined more accurately. Specifically, for example, when an image of a flame located at a distance from the CCD is taken, the number of detected pixels n ₂ itself is small, and the object is a flame depending on the peak frequency PK (n ₂ ) of the number of pixels n ₂ . Even if it is impossible to judge whether or not it is impossible to determine,
This is because it is possible to accurately determine whether or not the object is a flame based on the peak frequency PK (TOT) of OT.

The maximum fluctuation amount (maximum fluctuation amount) DIF (AVR) of the average intensity (average light intensity) of the object OBJ is used, for example, to distinguish the fluctuation of non-fire source from the fluctuation of flame. . Specifically, even when a CCD image of a halogen lamp or the like is used, the halogen lamp is AC 100.
When it is lit at V, some temporal change appears in the image data. However, in this case, the average light intensity fluctuation of a non-fire source such as a halogen lamp is greatly different from the average light intensity fluctuation of a flame, and therefore the average intensity of the object OBJ is
Based on the maximum fluctuation amount (maximum fluctuation amount) of (average light intensity), it is possible to accurately determine whether the object OBJ is a flame or a non-fire source.

In this way, after obtaining the maximum fluctuation (maximum fluctuation amount) relating to the size and intensity (light intensity) of the target object and the fluctuation frequency relating to the size and intensity (light intensity) of the target object, , It is determined whether the feature amount DIF (n ₂ ) is greater than a predetermined threshold value Q ₁ (step S17), and whether the feature amount PK (n ₂ ) is greater than a predetermined threshold value Q ₂ is determined. It is determined (step S18) and it is determined whether the feature amount DIF (AVR) is larger than a predetermined threshold value Q ₃ (step S18).
19) Also, it is determined whether the feature amount is larger than a predetermined threshold value Q ₄ (step S20).

As a result, in steps S17 to S20, for example, the feature quantities DIF (n ₂ ), PK (n ₂ ), DI
F (AVR), PK (TOT ) , each _{Q 1, Q 2, Q 3} ,
Only when it is judged that it is larger than Q ₄ , the object OB
J is detected as a flame at the time of a fire, and a fire alarm is output from the output unit 4 (step S21). Specifically, a warning lamp is turned on or an alarm sound is generated. Note that instead of steps S17 to S20, the condition is made more lenient and DIF (n ₂ ) is larger than Q ₁ , or PK
(n ₂ ) is larger than Q ₂ or DIF (AVR) is Q
_The object OBJ can also be detected as a flame at the time of fire if either one of the values greater than ₃ or PK (TOT) is greater than Q ₃ . That is, this determination process can be appropriately changed depending on the setting place, the installation place, the installation conditions, and the like.

As described above, in the processing examples of FIGS. 9 and 10,
In the first determination process of steps S2 to S6, it is determined whether the object OBJ is appropriate as the size of the flame at the time of a fire, and if it is determined as the appropriate size of the flame, further steps are performed. Second of S8 to S20
In the determination processing of (1), it is possible to detect the flame by determining from the temporal change of the target whether or not the target has a predetermined fluctuation as a flame.

For example, in the case where there is a lighting device such as a halogen lamp or an insecticidal lamp indoors, when these are turned on, the light emitted from them (including the light in the ultraviolet range) is received by the CCD light receiving unit. It is incident on 32, CCD light receiving section 3
2 also picks up an image of a halogen lamp, an insecticidal lamp, or the like, and the arithmetic unit 3 detects that the object is an object OBJ when it has a predetermined size. Since it has a unique temporal fluctuation different from that of a lamp or the like, after an object OBJ having a predetermined size is detected, an image of this object OBJ is displayed on a predetermined screen at predetermined time intervals T _2. By collecting several NB's worth and as described above, by examining the temporal fluctuation of this object OBJ, it is possible to accurately determine whether or not this object OBJ is a flame, and a false alarm due to a halogen lamp or an insecticidal lamp. Prevent
Only a flame can be detected reliably and a correct fire alarm can be given.

The time interval T ₂ is set to a time interval required to detect fluctuations peculiar to the flame, and the time interval for detecting whether or not the object OBJ of a predetermined size exists. It can be set to be different from the interval T ₁ . Specifically, in order to reliably detect the fluctuation peculiar to the flame, the time interval T ₂ is preferably about 0.5 seconds, and the predetermined screen number NB is, for example, 30.
About 50 to 50 are required.

Although not shown in the processing examples of FIGS. 9 and 10, in the second judgment processing, the temporal change of the position of the object is not unnatural as the temporal change of the flame. It may be determined whether or not. For example, the object O
In addition to determining whether or not the BJ has a predetermined fluctuation, the distance L _XY to the object OBJ and the temporal change of the angle ψ are monitored, and the object OBJ suddenly disappears from the screen. It detects whether the position of the object changes suddenly on the screen, moves back and forth on the screen, or does not move at all. It is also possible to judge whether or not the change is unnatural.

As a result of these judgments, when the object OBJ is appropriate as the size of the flame and also as the temporal change of the flame (fluctuation, temporal change of the position, etc.),
When a fire occurs, it can be determined that the flame is present, and the output unit 4 can output a fire alarm.

As described above, in this embodiment, the light other than the ultraviolet region is cut off so that only the light in the ultraviolet region is mainly incident on the CCD light receiving unit 32. Therefore, the CCD light receiving unit 3
In No. 2, the influence of the surrounding environment can be eliminated, and only the image of the target object that emits ultraviolet light can be captured satisfactorily. Therefore, the calculation unit 3 can easily detect only an object that radiates ultraviolet rays, and whether or not this object is a flame does not require any complicated and advanced image processing,
With simple image processing, detection can be performed quickly with high reliability. That is, in the image processing of the conventional apparatus that images visible light to detect a flame, the labeling processing and the logical filtering that are necessary to eliminate the influence of the image change due to the change of the ambient brightness or the movement of the person. The flame can be reliably detected without the need for any treatment.

In the above example, an appropriate change is recognized in the image data as the size of the flame when a fire occurs, and the object corresponding to the changed portion of the image data has a predetermined feature as a flame. At that time, I decided to output a fire alarm,
As a preceding step, the image data at each time after the time when a proper change in the size of the flame is recognized in the image data can be displayed on the display or the like. That is, the changed portion of the image data can be visually displayed as a moving image on a display or the like.

Further, the information S, | X |, | Y | of the size of the object obtained for judging the flame and the information L _XY , ψ about the position are also output to inform the operator. Is also possible.

Further, in the above example, it is judged whether or not the size or the like of the object corresponding to the changed portion of the image data is appropriate as a flame (first judgment processing), and the size is judged. When it is appropriate as a flame, the temporal change of this object is further monitored to determine whether or not it is a flame (second determination process).
It is also possible to carry out the judgment processing of No. 2 and the second judgment processing at the same time. That is, when a predetermined change occurs in the image data, the change over time of the changed portion of the image data is monitored for a predetermined number of screens NB, and the size and other fluctuations are monitored from the monitoring result for the number of screens NB. It is also possible to detect such as at the same time and judge whether or not it is a flame.

Further, the processing examples of FIGS. 9 and 10, particularly the processing examples of steps S13 to S20 are merely one processing example for determining whether or not the object OBJ has the fluctuation peculiar to the disaster. In addition to the above, as long as it can accurately judge whether the object OBJ has fluctuations peculiar to the disaster,
Various techniques can be used.

Further, it is possible to determine whether or not the flame is present by any desired image processing other than the above-described image processing.

[0093]

As described above, according to the present invention, the CCD light receiving section is made to cut off the light other than the ultraviolet region to pick up the image, and the change of the image data picked up by the CCD light receiving section is monitored to detect the image data. Is detected as a flame when at least the changed portion has a reasonable size as a flame and has a reasonable temporal change as a flame. Even when a CCD device having a section is used as an imaging device, flames in a fire or the like can be satisfactorily and reliably detected by simple image processing.

[Brief description of drawings]

FIG. 1 is a diagram showing a configuration example of a flame detection device according to the present invention.

FIG. 2 is a diagram illustrating a configuration example of an imaging unit.

FIG. 3 is a diagram illustrating another configuration example of an imaging unit.

FIG. 4 is a perspective view showing an example of a room in a building.

5A and 5B are cross-sectional views in the x-axis direction and the y-axis direction of FIG. 4, respectively.

FIG. 6 is a diagram showing an example of an imaged screen.

7A to 7C are views for explaining a method of detecting a changed portion of image data.

FIG. 8 is a diagram showing a case where a changed portion of image data is composed of a plurality of pixel connection areas.

9 is a flowchart showing an example of the processing operation of the flame detection device of FIG.

FIG. 10 is a flowchart showing an example of processing operation of the flame detection device of FIG.

FIG. 11 is a time chart showing the timing of capturing image data.

12A to 12C are diagrams for explaining how to store image data in a RAM.

FIG. 13 is a diagram showing an example of an analysis result of image data of each of NB screens.

FIG. 14 is a diagram showing a storage example of an analysis result of image data of NB screens.

FIG. 15 is a schematic configuration diagram of a general CCD device.

FIG. 16 is a diagram showing a spectral sensitivity characteristic of a typical CCD light receiving unit (CCD sensor).

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Imaging part 3 Calculation part 4 Output part 5 Power supply part 11 Imaging device (CCD device) 12 Optical means 20 A / D converter 21 Processor 22 ROM 23 RAM 31 Holder 32 CCD light receiving part (CCD sensor) 33 Protective member 34 Circuit board 36 lens holder 37 lens housing 38 filter 46 dark box 47 pinhole 101 room 102 ceiling 103 wall surface 104 floor 105 surveillance area

Claims (5)

[Claims] 1. An image pickup means, and a calculation means for performing image processing calculation relating to flame detection based on image data picked up by the image pickup means. The image pickup means is transparent to light in the ultraviolet region. A flame detecting device comprising: an ultraviolet transmissive unit that cuts light other than the ultraviolet region and a CCD light receiving unit that receives and images the light transmitted through the ultraviolet transmissive unit. 2. The flame detection device according to claim 1, wherein the ultraviolet light transmitting means also functions as a protection member for the CCD light receiving portion. 3. The flame detection device according to claim 1, wherein the arithmetic means monitors a change in the image data picked up by the CCD light receiving unit and determines whether the changed portion of the image data is appropriate as a flame. A flame detection device, which judges and detects a flame. 4. The flame detection device according to claim 3, wherein the arithmetic means is such that the changed portion of the image data has at least a size that is appropriate as a flame, and a temporal change that is appropriate as a flame. A flame detection device, which detects that a flame is present. 5. A CCD light-receiving unit is made to cut off light other than the ultraviolet region to be imaged, and a change in the image data taken by the CCD light-receiving unit is monitored, and the changed portion of the image data is at least a reasonable size as a flame. A flame detection method, characterized in that the flame is detected when the flame has a proper temporal change as a flame.