JPH09293185A - Object detection device/method and object monitoring system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent erroneous detection owing to a cause except for flame and an invasion object (invader, for example) and to detect the object of flame and the invasion object with high reliability. SOLUTION: An image pickup part 1, an image processing part 2 extracting the image area of the object from an image which is image-picked up by the image pickup part 1 and detecting information on the object based on image information of the image area of the object and a judgment part 3 for judging whether the object is the prescribed object, namely, a detection object (flame or invader) or not based on information on the object detector by the image processing part 2 are provided.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an object detection device, an object detection method, and an object monitoring system for detecting an object such as a flame or an intruder (for example, an intruder).

[0002]

2. Description of the Related Art Conventionally, as an object detecting device for detecting a flame generated in a fire or the like, a device using an ultraviolet type or infrared type sensor has been generally known. Here, the ultraviolet type sensor uses a discharge tube such as a UV tron having a high sensitivity to ultraviolet rays to detect light in the ultraviolet region emitted from the flame and to detect the amount of light in the ultraviolet region. It has the function of outputting a number of discharge pulses.In a flame detection device that uses an ultraviolet sensor, it is possible to detect whether or not there is a flame based on the number of discharge pulses output from the ultraviolet sensor. Are doing. In addition, the infrared sensor
It has a function to detect light in the infrared region emitted from a flame, particularly light having a wavelength of about 4.3 μm, which is the resonance radiation of carbon dioxide, and in a flame detection device using an infrared type sensor,
Whether or not a flame is present is detected based on the amount of light in the infrared region detected by an infrared sensor and its fluctuation.

[0003]

However, the ultraviolet type sensor is also sensitive to the light emitted from the arc discharge such as welding, and therefore, in the flame detecting device using the ultraviolet type sensor, When a work such as welding is performed, a false detection may be made. In addition, infrared sensors are also sensitive to sunlight, including the infrared region, so
In a flame detection device using an infrared sensor, for example, the sunlight (fluctuation) reflected by the water surface with ripples
False detection may occur due to (flickering infrared light). In particular, an infrared flame detector that uses a pyroelectric element as a sensor uses an amplifier with a high amplification degree to detect flicker of a flame, and thus is susceptible to various noises. In particular, popcorn noise is generated when electronic parts such as operational amplifiers (operational amplifiers), capacitors, and pyroelectric sensors are subjected to abrupt temperature changes and mechanical stress. Popcorn noise generated by the mold element has the greatest effect.

Further, as a flame detecting device, there is one using a thermal imaging device, and in a flame detecting device using a thermal imaging device,
Among the pixels captured as a thermal image, the number of pixels (pixel number, that is, area) having a pixel value equal to or greater than a predetermined threshold value is obtained, and whether or not a flame is detected is detected based on this pixel number (area). ing. However, in a flame detection device using a thermal imager, the thermal imager has high sensitivity characteristics to a high-temperature object, so that a high-temperature object other than a flame is also imaged, which may result in erroneous detection. is there.

The above-mentioned problems in the flame detecting device are as follows.
The same applies to an intruder detection device (for example, an intruder detection device) used in a security system. That is, as an intruder detection device, if an infrared thermal sensor module (pyroelectric element) that detects the difference between the emitted energy due to the background temperature and the emitted energy due to the human body or the like is used, false alarm due to popcorn noise or the like peculiar to the pyroelectric element, Small animals
False alarms due to (cats, mice, etc.) or false temperature changes may occur.

The present invention prevents an erroneous detection due to a factor other than a flame or a predetermined intruder (for example, an intruder), and can detect an object such as a flame or an intruder with high reliability. The object is to provide a target detection method and a target monitoring system.

The present invention also provides a target detection device and a target monitoring system capable of both flame detection and intruder (eg intruder) detection with a single device having a simple structure. It is an object.

[0008]

In order to achieve the above object, the invention according to claim 1 extracts an object image area from an image picked up by an image pick-up means and an image picked up by the image pick-up means. Image processing means for calculating information on the object based on the pixel information of 1., and judgment means for judging whether or not the object is an intruding object based on the information on the object calculated by the image processing means. The image processing means includes, as the information, at least one of a shape similarity rate of the object image area, a circularity of the object image area, a size of the object image area, and a moving speed of the object image area. Of the shape similarity of the object image area, the circularity of the object image area, the size of the object image area, and the moving speed of the object image area, which are determined by the image processing means. Object based on at least one is characterized by determining whether a intruder.

According to a second aspect of the present invention, in the object detecting apparatus according to the first aspect, the judging means includes the shape similarity rate of the object image area, the circularity of the object image area,
The membership function having the shape similarity, the circularity, the size, and the moving speed as parameters respectively corresponding to the size of the object image area and the moving speed of the object image area is set in advance. When the image processing means has determined each parameter value of the shape similarity rate of the object image area, the circularity of the object image area, the size of the object image area, and the moving speed of the object image area. , The certainty factor for each calculated parameter value is obtained by the membership function corresponding to each, and it is determined whether or not the object is an intruder based on the certainty factor obtained for each parameter value. It is characterized by that.

According to a third aspect of the present invention, in the object detecting apparatus according to the first aspect, one CCD having sensitivity to light in the visible region is used as the image pickup means.

According to a fourth aspect of the present invention, the object image area is extracted from the image pickup means and the image picked up by the image pickup means, and based on the pixel information of the object image area,
An object detection device including image processing means for calculating information on an object and determination means for judging whether or not the object is a predetermined object based on the information on the object calculated by the image processing means. And has both a flame detection function and an intruder detection function, and detects the processing functions of the image pickup means, the image processing means, and the determination means depending on whether the detection target is a flame or an intruder. On the function, or
Switching control means for performing control to switch to the intruding object detection function is further provided, and the target detecting device functions as a flame detecting device or functions as an intruding object detecting device by the switching control of the switching control means. It is characterized by being made to let.

The invention according to claim 5 is the object detecting apparatus according to claim 4, wherein the switching control means performs flame monitoring (or intruding object monitoring) while performing intruding object monitoring (or flame monitoring). It is characterized in that the state of the target detection device is switched and controlled as is the case.

According to a sixth aspect of the present invention, in the object detection apparatus according to the fourth aspect, the switching control means performs the switching control with the intruder and the flame as equal monitoring targets. It is characterized by being.

The invention according to claim 7 is the object detecting device according to claim 4, wherein the switching control means causes the object detecting device to function as, for example, a flame detecting device in a normal state, and a monitoring state is provided. Is characterized in that switching control is performed so as to function as an intruder / flame detection device that detects both a flame and an intruder.

The invention according to claim 8 is the object detecting device according to any one of claims 4 to 7, wherein the switching control means manually switches between intruder monitoring and flame monitoring. It is characterized by being controllable.

According to a ninth aspect of the present invention, in the object detecting apparatus according to the fourth aspect, one CCD having sensitivity to light in the visible region is used as the image pickup means, and the switching control means comprises: In the intruder monitoring state, the light in the visible region is allowed to enter the CCD as it is, while in the flame monitoring state, the light entering the CCD is controlled so that the light of the visible light cut is allowed to enter the CCD. Is characterized by.

Further, in the invention according to claim 10, information that well expresses the unique features of the intruder is calculated from the image data of the image of the object, and whether the object is the intruder or not is determined based on the information. It is characterized by determining.

The invention according to claim 11 is the same as the claim 1.
In the object detection method described in 0, the membership function is set in advance with the information that the characteristic unique to the intruder is well expressed as a parameter, and the information that the characteristic unique to the intruder is well expressed is determined. Then, the certainty factor that the object is an intruder is obtained from the membership function using the determined information as a parameter value, and whether the object is an intruder or not based on the obtained certainty factor. The feature is to judge.

The invention of claim 12 is the same as claim 1
The object detection device according to any one of claims 9 to 9 is connected to a receiver via a predetermined transmission line, and the object detection device detects an object in the receiver when called from the receiver. It is characterized by transmitting the result.

According to a thirteenth aspect of the present invention, there is provided a target monitoring system in which a target detecting device for detecting a predetermined target is connected to a receiver via a predetermined transmission line, wherein the target detecting device is , Having both a flame detection function and an intruder detection function, and switching the receiver to make the target detection device function as a flame detection device or an intrusion object detection device. A switching control means for performing control is provided, and the target detection device is caused to function as a flame detection device or an intruder detection device according to a switching control command from the switching control means of the receiver. It is characterized by being.

[0021]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a diagram showing a configuration example of an object detection device according to the present invention. Referring to FIG. 1, the object detection apparatus extracts an object image area from an image capturing section 1 and an image captured by the image capturing section 1, and obtains information about the object based on pixel information of the object image area. Based on the information about the image processing unit 2 for indexing and the object indexed by the image processing unit 2, the determination unit 3 for determining whether or not this is a predetermined object, that is, a detection target (flame or intruder).
And

Here, the image pickup unit 1 has an optical system 11 and a photoelectric conversion unit 12 which receives light from the optical system 11 and converts it into an electric signal. In the example of FIG. 1, the optical system 11 includes a lens system 13 having an angle of view (viewing angle) corresponding to a predetermined target monitoring area, and a spectrum (wavelength) of light entering the photoelectric conversion unit 12 from the lens system 13. And an optical filter 14 for limiting Further, the photoelectric conversion unit 12 includes a photoelectric conversion element having a predetermined number of pixels, such as a two-dimensional CC.
D is used.

The angle of view (viewing angle) of the lens system 13 is to be monitored.
Size of (flame and / or intruder, etc.) and photoelectric conversion element
It is set to an appropriate one based on the resolution (total number of pixels) of (CCD). Specifically, the wider the angle of the lens system 13 is, the larger the viewing angle is, and the wider the monitoring area can be covered. In this case, the photoelectric conversion element (C
(CD), the size of the monitoring area corresponding to one pixel also becomes large, and when the size of the target object is small, the information about the target object can be obtained from only one pixel of the photoelectric conversion element, and the amount of information about the target object is small. Will be significantly less. Therefore, the viewing angle of the lens system 13, that is, the size of the monitoring area corresponding to one pixel of the photoelectric conversion element, is the number of pixels required to sufficiently obtain information on the object even when the object size is small. (Preferably a plurality of pixels)
It is preferable that the object can be imaged (monitored) with.

For example, when the object to be detected is a flame and the target detection device is a flame detector, the standard for type approval of the flame detector according to the Fire Service Act is 33 × 3 for the fire test of the flame detector.
Using a fire tray with an area of 3 cm ² (33 cm square fire tray), normal heptane is put in this fire tray to ignite, and detection performance within 30 seconds is required. The combustion flame of normal heptane (hereinafter referred to as the flame of 3.3 cm square flame) on this flame has a width,
Since the heights are about 50 cm and about 1.5 m, respectively, the viewing angle of the lens system 13 (that is, the photoelectric conversion element 1
(The size of the monitoring area corresponding to the pixel) is the number of pixels that can effectively capture the fluctuations of this combustion flame from a position that is a predetermined distance away from this combustion flame, and the size of the flame that can be imaged (monitored). Good things.

As the photoelectric conversion element of the photoelectric conversion section 12, one having a sensitivity characteristic corresponding to the detection target (flame or intruder) can be selected and used. For example, when the object to be detected is a flame, an infrared CCD having a high sensitivity characteristic to light in the infrared region emitted from the flame, particularly light having a wavelength of about 4.3 microns, which is the resonance radiation of carbon dioxide, is used. Most preferred is a normal CC that is sensitive to light in the visible range.
It is also possible to use D (even a normal CCD has some sensitivity in the near infrared region). On the other hand, when the object to be detected is an intruder, it is preferable to use a normal CCD having sensitivity in the visible region.

When an infrared CCD is used as a photoelectric conversion element for detecting flames, the optical filter 14 of the optical system 11 cuts light other than the wavelength band near 4.3 μm. It is preferable to use a bandpass filter having a characteristic of transmitting light in a wavelength band around 3 microns. Further, when a normal CCD having sensitivity to light in the visible region is used as the photoelectric conversion element for detecting flame, the optical filter 14 includes a near-infrared low-pass filter (for example, a wavelength of 8500Å or less). Cut the light,
A visible light region may be cut by using a filter (transmitting light having a wavelength of 8500Å or more). That is, the optical filter 14 has a characteristic according to the spectral sensitivity characteristic of the photoelectric conversion element.

Further, the total number of pixels of the CCD is about 50 cm and about 1.
A lens system 1 from a position 5 m away from a flame of a size of 5 m
It is necessary for the image area corresponding to the flame of this size to have a resolution such that it covers a plurality of pixels when the image is picked up via 3. FIG. 2 shows a pixel configuration example of a two-dimensional CCD. In the example of FIG.
It has N and M pixel numbers (total pixel number N × M) in the x and y directions, respectively, and when a flame of a predetermined size is imaged as a target object at a predetermined distance, The corresponding image area (object image area) OBJ covers five pixels.

The photoelectric conversion unit 12 of the image pickup unit 1 picks up an image at a predetermined time interval and gives it to the image processing unit 2. The image data as shown in FIG. 2 captured at predetermined time intervals is sequentially captured, and predetermined image processing necessary for object detection (flame detection or intruder detection (for example, intruder detection)) is performed, and the predetermined image processing is performed. To get information about.

Specifically, the image processing unit 2 includes the photoelectric conversion unit 1
The image data from 2 (two-dimensional analog image data) is subjected to, for example, binarization processing, and has an A / D conversion function of converting the analog image data into binarized image data. Here, as the binarization threshold value a _th , a certain value between the highest luminance value and the lowest luminance value in one image data is generally used, but the image data obtained every predetermined time interval In the above, since the maximum brightness value and the minimum brightness value are not always the same value and generally change, it is preferable to change the binarization threshold value according to the change in the maximum brightness value and the minimum brightness value. As a result, it is possible to remove the effect of the brightness changing instantaneously at a certain point. Further, the image processing unit 2 performs feedback control on the photoelectric conversion unit 12 so that the image data of the highest brightness is not saturated in the A / D conversion process and a predetermined dynamic range is obtained, thereby performing automatic gain adjustment control of the image data. You may have the function to perform.

In any case, the image processing unit 2 has the image pickup unit 1
With respect to the analog image data a _x , _{y at} each pixel position (x, y) imaged at, for example, when a _x , _y ≧ a _th , the pixel value p _{x at} that pixel position (x, y), _{When y is set} to “1” (black pixel), and when a _x and _y <a _th , the pixel position
(x, y) pixel values p _x of the _y "0" can be carried out binarization process of the (white pixel). Further, in order to extract the contour of the object, the binarized image data may be subjected to a differentiation process. Specifically, the differentiation process on the binarized image data is performed by one pixel position (x, y) of the binarized image data.
, The pixel values p _x and _y are, for example, p _x and _y ≠
if p _{x-1, y-1} , p _x , _y ≠ p _{x-1, y} , p _x , _y ≠ p _{x-1, y + 1} , or if p _x , _y ≠ p _{x, y-1} Only by setting _px , _y = 1 (black pixel), and by setting _px , _y = 0 (white pixel) otherwise.

As described above, in the image processing unit 2, the image pickup unit 1
For images taken at predetermined time intervals in
A / D conversion processing (binarization processing) is performed, and target detection is performed based on the binarized image data obtained at predetermined time intervals.
Image processing required for (flame detection and intruder detection) is performed.

As the image processing necessary for detecting an object, first, a candidate of an object to be detected (flame and / or intruder (for example, intruder)) is detected as an object image from the binarized image data obtained at predetermined time intervals. It is necessary to perform a process of extracting as a region. Therefore, the image processing unit 2 compares, for example, the binarized image data at a certain time point with the binarized image data at the immediately preceding time point, and as a result of this comparison, the binarized image data before and after the time point When there is a change in the pixel value of a certain number of pixels in a certain cohesive image area (for example, an area where black pixels are connected) between data, the image area that has this change
The (connected area) is extracted as the object image area (the object image area is specified).

Specifically, for example, the binarized image data at time t ₀ is as shown in FIG. 3A, and the next 2 at time t ₁
When the binarized image data is as shown in FIG. 3 (b), the difference image data is as shown in FIG. 3 (c), and there is a change in the pixel values of the five pixels in the image area OBJ. Since it is recognized that the target object image area is present (because it is recognized that some object has occurred at time t ₁ ), this area OBJ can be specified as the object image area.

By the way, the present invention focuses on the fact that a flame or an intruder (for example, an intruder) has characteristics (information) different from factors other than the flame or the intruder, and the object specified as described above. Based on the pixel information of the image area OBJ, information about the object (feature information) is calculated, and whether the object is a predetermined object, that is, a detection target (flame or intruder) based on the information about the calculated object. I try to judge.

More specifically, when the detection target is a flame, the center-of-gravity mobility of the target image area OBJ and the main axis are used as information that well expresses the characteristics unique to a predetermined target (detection target). The rate of change and shape similarity can be calculated. Further, when the detection target is an intruder, the shape similarity rate between the object image area OBJ and the standard human body model (pattern) can be obtained.

Here, the center-of-gravity mobility, the spindle change rate, and the shape similarity rate of the object image area OBJ can be obtained as follows. That is, as described above, the predetermined time interval Δ
The object image area O from the binarized image data obtained every t
When BJ is specified, the moment of inertia M _pq of the following equation (Equation 1) is first considered as a characteristic expression of the object image area OBJ. In Expression 1, x and y are not the coordinate axes of the captured image having the numbers of N and M pixels as shown in FIG.
As shown in FIG. 4, when the object image area OBJ is specified from the captured image in FIG. 2, it is assumed that the object coordinate area is an orthogonal coordinate axis in contact with the object image area OBJ.

[0037]

[Equation 1]

In this equation of the moment of inertia M _pq , p
= Q = 0, M _pq , that is, M ₀₀ , represents the area as in the following equation (Equation 2).

[0039]

[Equation 2]

Further, in the equation of the moment of inertia M _pq of the equation 1, when p = 1, q = 0; p = 0, q = 1, M
_pq , that is, M ₁₀ and M ₀₁ is given by the following equation (Equation 3).

[0041]

(Equation 3)

Therefore, as shown in the following equation (Equation 4), M ₁₀ /
Coordinates I _c and J _c obtained by M ₀₀ , M ₀₁ / M ₀₀ respectively represent the center of gravity G of the object image area OBJ in the x direction and the y direction. The coordinates I _c and J _c are standardized by M _00, that is, the area of M ₁₀ and M ₀₁ , respectively. Therefore, the coordinates I _c and J _c are invariable scales that are not affected by the size of the object image area OBJ.

[0043]

## EQU4 ## I _c = M ₁₀ / M ₀₀ J _c = M ₀₁ / M ₀₀

The moment of inertia M _f about the center of gravity G = (I _c , J _c ) as described above is given by the following equation (Equation 5).

[0045]

(Equation 5)

The straight line y = x passing through the center of gravity as described above.
The moment of inertia M _θ of P _{x, y} with respect to tan _θ is
It becomes like (Equation 6).

[0047]

(Equation 6)

Regarding Equations 5 and 6, x and y are
It is assumed that the coordinates are in the coordinate system when the center of gravity I _c , J _c is the origin.

In Equation 6, the angle that minimizes M _θ is θ
_{When 0} , y = xtan θ ₀ is the principal axis of inertia of P _{x, y} . From Equation 6, M _θ = M ₂₀ sin ² θ-2M ₁₁ sin θcos
Since θ + M ₀₂ cos ² θ holds, the following formula (Equation 7) is obtained by differentiating this by θ and setting it to 0 in order to minimize M _θ .

[0050]

[Equation 7] _{tan2θ 0 = 2M 11 / (M} 20 -M 02)

From this, the direction θ ₀ of the main axis of the object image area OBJ is given by the following equation (Equation 8).

[0052]

[Equation 8] θ ₀ = (1/2) tan ⁻¹ [2M ₁₁ / (M ₀₂ −M ₂₀ )]

FIG. 4 shows the center of gravity G of the object image area OBJ.
= (I _c , J _c ), the direction θ ₀ of the main axis of the object image region OBJ obtained as described above is shown.

As described above, the object image area OBJ
When the center of gravity G = (I _c , J _c ) and the direction θ _{0 of the} main axis are obtained, from these and the contour of the object image area OBJ extracted by the differential processing as described above, the present time (current screen)
The shape of the object in can be obtained. That is, the distance r from the center of gravity G = (I _c , J _c ) to the contour is calculated as a function of angle r
When plotted as (θ), a 2π periodic waveform peculiar to the object is drawn as shown in FIG. In FIG. 5, θ ₀ is the direction of the main axis.

As described above, since the distance function r (θ) characterizes the object image area OBJ, that is, the shape of the object, using the distance function r (θ),
It is possible to obtain the similarity rate of the shape of the object image area OBJ.

For example, when the target detection device of FIG. 1 is a flame detection device which detects a flame as a target object, it is difficult to preset a standard pattern (standard distance function) for the shape of the flame. In this case, the shape (distance function r ₁ ) of the object image area OBJ at the current time (current screen) with respect to the shape (distance function r ₂ (θ)) of the object image area OBJ at the previous time (previous screen) The similarity rate of (θ)) can be obtained as the shape similarity rate.

FIGS. 6A and 6B show examples of the object image area OBJ and the distance function r (θ) at the previous time point (previous screen) and the current time point (current screen), respectively. When obtaining these shape similarity rates, in order to eliminate the effect of changing the direction θ ₀ of the main axis between them, the reference point of the distance function r (θ) is set to the main axis direction θ ₀ at that time, respectively. To match. Then, for example, each distance function r (θ) is sampled by a predetermined angle Δθ (for example, 5 °) up to 360 °. When Δθ is 5 °, 72 samples r (θ _i ) (i = 1 to 72) are obtained. The distance function of the object image area OBJ at the present time (current screen) is r ₁ (θ _i )
When (i = 1 to 72) and the distance function of the object image area OBJ at the previous time point (previous screen) is r ₂ (θ _i ) (i = 1 to 72), these shape similarity rates f are , For example, given by

[0058]

[Equation 9]

Here, in order to eliminate the influence of the size and mobility of the object on the shape similarity f, r ₁ (θ _i ) and r ₂ (θ
It is necessary to standardize _i ). For example, the distance function is r
(θ) can be normalized to “1” at θ = θ ₀ (that is, r (θ ₀ ) = 1 can be set). As a result, r ₁ (θ _i = θ ₀ ) = 1 and r ₂ (θ _i = θ ₀ ) = 1 can be obtained, and the ratio of r ₁ (θ _i ) and r ₂ (θ _i ) is obtained. At this time, it is possible to eliminate the influence of the change in the size of the object and the mobility. Also, in this case, F has r ₂ (θ _i ) r
When it is smaller than ₁ (θ _i ), F (r ₂ (θ _i ) / r ₁ (θ _i ))
= R ₂ (θ _i ) / r ₁ (θ _i ), and when r ₂ (θ _i ) is larger than r ₁ (θ _i ), F (r ₂ (θ _i ) / r ₁ (θ _i )) = R ₁ (θ _i ) / r
_This is a function of ₂ (θ _i ). Therefore, the shape similarity f is 0.
It is in the range of ≦ f ≦ 1. Thus, the similarity rate (shape) between the distance function r ₁ (θ) of the object image area OBJ at the present time (current screen) and the distance function r ₂ (θ) of the object image area OBJ at the previous time (previous screen) The similarity rate f can be used as the information that well expresses the characteristic of the flame.

In the above example, r ₁ (θ _i ) and r ₂ (θ _i )
The shape similarity f was calculated by calculating the ratio of
For example, based on the difference between r ₁ (θ _i ) and r ₂ (θ _i ) (for example,
The shape similarity f can also be obtained based on the square of these differences. Also in this case, in order to eliminate the influence of the size and mobility of the object on the shape similarity f, r ₁ (θ _i ),
It is necessary to standardize r ₂ (θ _i ). That is, for example, by setting r ₁ (θ _i = θ ₀ ) = 1, r ₂ (θ _i = θ ₀ ) = 1, the difference between r ₁ (θ _i ) and r ₂ (θ _i ) is obtained. At this time, it is possible to eliminate the influence of the size and mobility of the object.

As described above, when the object to be detected is a flame, the information unique to the flame is well expressed as information.
The shape similarity rate of the object image area OBJ can be used, and whether or not the shape similarity rate of the object is equal to or larger than a predetermined threshold value can be reliably detected. You can

Further, for example, when the target detection apparatus of FIG. 1 is an intruder detection apparatus for detecting an intruder as an object, the shape of the intruder may be, for example, some standard human body models (some A standard human body shape pattern distance function r ₀ (θ)) is provided in advance, and some of these standard human body shape patterns (some distance function r ₀ (θ)) and the current (current screen) target It is possible to perform pattern matching with the shape (distance function r ₁ (θ)) of the object image area OBJ, and find the shape similarity having the largest value (similarity). At this time, matching with one standard pattern is performed by, for example, r ₁ (θ _i ) as in the case of flame detection.
And r ₀ (θ _i ), or
_This can be done based on the difference between ₁ (θ _i ) and r ₀ (θ _i ) (for example, based on the square of these differences). In addition, again
The distance function r of some standard human body shape patterns
₀ The (theta), for example, can be prepared such as the distance function r ₀ of the standard pattern of the human body standing front (theta), the distance of the standard pattern of the human standing side function r ₀ (theta).

As described above, the standard human body shape pattern (distance function r ₀ (θ)) and the shape of the object image area OBJ (distance function r ₁ (θ)) at the present time (current screen) are calculated. Even when the shape similarity is obtained by pattern matching, r ₀ (θ _i ) and r ₁ (θ _i ) are standardized in order to eliminate the influence on the shape similarity f due to the size and mobility of the object. Need to be converted. For example, the distance functions r ₀ (θ) and r ₁ (θ _i ) can be normalized to “1” at θ = θ ₀ (that is,
r ₁ (θ _i = θ ₀ ) = 1, r ₂ (θ _i = θ ₀ ) = 1). As a result, when pattern matching is performed between r ₀ (θ _i ) and r ₁ (θ _i ), it is possible to eliminate the influence of changes in the size of the object, mobility, and the like.

As described above, when the detection target is an intruder, the shape similarity rate of the object image area OBJ can be used as the information in which the unique features of the intruder are well expressed. It is possible to reliably detect whether or not the target object is an intruder by determining whether or not the shape similarity rate is equal to or more than a predetermined threshold value.

As described above, the shape similarity based on the distance function r (θ) from the center of gravity G = (I _c , J _c ) of the object image area OBJ to the contour is calculated as the object (flame or intruder). It can also be used as information in which unique features are well expressed.

When the object to be detected is a flame, the information unique to the flame is well expressed. In addition to the shape similarity of the object image area, the mobility of the center of gravity and the rate of change of the main axis are also included. Can also be used. Here, the mobility of the center of gravity and the rate of change of the main axis can be obtained as follows. That is, the center-of-gravity mobility g of the object image area OBJ is a plurality (n pieces) separated by a predetermined time interval Δt from the time t ₁ when the object is specified (including the time t ₁ for example). time t ₁ of, t _2, ... t n pieces each object as determined respectively on the basis of the binarized image data in the _n image region OBJ _1, OB
Center of gravity of J ₂ , ..., OBJ _n G (t ₁ ), G (t ₂ ), ..., G
The center of gravity G (t ₁ ), G (t ₂ ), with respect to the average value <G> of (t _n ),
, G (t _n ) variation (standard deviation value of variance) can be obtained as in the following equation (Equation 10).

[0067]

(Equation 10)

It should be noted that the center of gravity G is represented by x as in (I _c , J _c ).
Since it is composed of the coordinates and the y-coordinate, I _c is calculated by the equation (10), and independently of this, J _c
10 is performed, and the calculation result for I _{c and} the calculation result for J _c are combined, for example, to obtain the center-of-gravity mobility g.

The main axis change rate h of the object image area is
From the time point t ₁ when the target is specified (for example, at this time point t _1
( Including ₁ ), a plurality (n) separated by a predetermined time interval Δt.
Time t _1, t _2, ... n pieces each object as determined respectively on the basis of the binary image data at t _n image areas OBJ ₁ of the individual),
OBJ ₂ , ..., OBJ _n main axis directions θ ₀ (t ₁ ), θ
_{0 (t 2), ...,} θ 0 mean value of (t _n) <θ _0> direction of the main shaft with respect to _{θ 0 (t 1), θ} 0 (t 2), ..., θ variation of ₀ (t _n) ( The standard deviation value of variance) can be obtained as follows.

[0070]

[Equation 11]

Therefore, when the detection target is a flame, the image processing unit 2 of FIG. 1 specifies the object image area OBJ from the binarized image data obtained at every predetermined time interval Δt, The gravity center mobility and / or principal axis change rate and / or shape similarity rate can be obtained as information in which the unique characteristics of the flame are well expressed.

When the predetermined object is a flame,
In addition to the above-mentioned shape information (center of gravity mobility, main axis change rate, shape similarity rate), it is also possible to use predetermined temporal change characteristics as information that well expresses the unique characteristics of the flame. By also determining whether or not the object image area OBJ has a predetermined temporal change characteristic peculiar to the flame, it is possible to reliably detect whether or not the object is the flame.

As the above-mentioned temporal change characteristic, the inventor of the present application has a temporal fluctuation characteristic of the size (number of pixels; area) of the object image area and the size of the object image area (number of pixels;
Particular attention was paid to the regularity of the temporal variation of (area).

Therefore, when the detection target is a flame, the image processing unit 2 of FIG. 1 specifies the object image area OBJ from the binarized image data obtained at every predetermined time interval Δt, As the information in which the characteristic peculiar to the flame is well expressed, the temporal fluctuation characteristic of the size of the object image area OBJ and / or the regularity of the temporal fluctuation can be obtained. More specifically, the temporal fluctuation characteristic of the size (number of pixels) of the object image area OBJ is
It can be obtained as a dispersion ratio (standard deviation value of the variance) of the size (number of pixels) of J with respect to the temporal average value, and the regularity of temporal variation of the size (number of pixels) of the object image area OBJ. Can be obtained as an autocorrelation with respect to a temporal change in the size (number of pixels) of the object image area OBJ.

As described above, when the object to be detected is a flame, the image processing unit 2 obtains at least one of shape information, a dispersion ratio, and an autocorrelation, as the information that favorably expresses the characteristics unique to the flame. Processing can be performed. In this case, the time interval Δt of imaging needs to be appropriate (for example, a time interval of about 0.5 second to 2 seconds) so that the temporal fluctuation characteristics of the flame can be detected reliably. There is.

Specifically, the temporal fluctuation characteristic of the object image area, that is, the dispersion ratio (standard deviation value of the variance) d of the size (the number of pixels) of the object image area with respect to the temporal average is A plurality (n pieces) separated by a predetermined time interval Δt from the time point t ₁ at which the identification is performed (including the time point t ₁ for example).
Time t ₁ of, t _2, ... t n pieces each object as determined respectively on the basis of the binarized image data in the _n image region OBJ _1, O
BJ ₂ , ..., The number w (t ₁ ) of black pixels in OBJ _n , w
(t ₂ ), ..., W (t _n ) The average value <w> of the number of black pixels w (t ₁ ), w (t ₂ ), ..., w (t _n ) variation (standard deviation of variance) ) Can be obtained as the following equation.

[0077]

(Equation 12)

Further, the autocorrelation with respect to the time change of the size (the number of pixels) of the object image area is calculated from the number of black pixels in the object image area at a plurality of time points separated by a predetermined time interval Δt. It can be calculated as follows.

[0079]

(Equation 13)

As the autocorrelation cor (k) used in the judgment unit 3 for actually judging whether or not it is a flame, the autocorrelation function cor _m (k) is time-averaged with respect to the time parameter m. Is used. That is, the image processing unit 2 actually uses the autocorrelation value c given by the following equation.
Or (k) is given to the judgment unit 3.

[0081]

[Equation 14]

Here, m can be an arbitrary integer value, or m can be set to 0. When m is set to 0, the equation 14 is the time t _i
And the time (t _i + t _k ), which is a well-known autocorrelation function of the following equation.

[0083]

(Equation 15)

As described above, in the image processing section 2, the dispersion ratio (standard deviation value of dispersion) of the shape information of the object image area and the size (number of pixels) of the object image area with respect to the temporal average value.
d, when at least one of the autocorrelation cor (k) regarding the temporal change of the size (the number of pixels) of the object image area is obtained, the determination unit 3 determines, based on these processing results,
It is configured to determine whether or not the target image area is a predetermined target (flame).

The inventor of the present application, as an object (light source),
A flame, a rotating lamp, and an incandescent lamp of a 3.3 cm square fire tray were imaged from a predetermined imaging distance, and the temporal change in the number of black pixels in the object image area in the binarized image data of each of these objects was measured.

FIG. 7 shows the measurement result of the temporal change of the number of pixels (the number of black pixels) in the object image area corresponding to the flame in the binarized image data obtained by imaging the flame of the 3.3 cm square fire dish as the object. FIG. 8 is a diagram showing a change in the number of pixels (the number of black pixels) in the object image area corresponding to the rotating light in the binarized image data obtained by imaging the rotating light as the object. FIG. 9 is a diagram showing the results, and FIG. 9 shows the temporal change in the number of pixels (the number of black pixels) in the object image region corresponding to the incandescent light bulb in the binarized image data obtained by imaging the incandescent light bulb as the object. It is a figure which shows a measurement result.

Further, the inventor of the present application, based on the measurement result of the temporal change of the number of pixels (the number of black pixels) for each object in FIGS. 7, 8 and 9, the dispersion ratio d for each object is calculated. And the autocorrelation function cor _m (k) were obtained. In this measurement, the imaging time interval Δt was set to 1 second.

FIG. 10 is a diagram showing the dispersion ratio (temporal dispersion ratio) d of the flame, the rotating lamp, and the incandescent light bulb of the 3.3 cm square fire tray obtained as described above while changing the imaging distance. FIG.
At 0, the dispersion ratio d for the stove flame when the stove flame is imaged as the object is also shown.

From FIG. 10, when the object is a 3.3 cm square flame flame or a stove flame, the dispersion ratio d is approximately 0.3 to.
When the object is a rotating lamp, the dispersion rate d is in the range of approximately 0.9 to 1.2, and when the object is an incandescent light bulb, the dispersion rate d is 0.5. It turns out that it becomes almost 0. From this, the flame, the rotating lamp, and the incandescent lamp can be clearly identified based on the dispersion ratio d. Especially,
Since the dispersion ratio (temporal dispersion ratio) d does not change much even if the imaging distance changes, even if an image is taken from an arbitrary imaging distance, based on this dispersion ratio d, the object is a flame or a rotating lamp. It is possible to stably and easily discriminate between the incandescent lamp and the incandescent lamp. Incidentally, in the past, in order to detect the fluctuation of the flame, for example, the spectrum by the fast Fourier transform was obtained, and in this case, there was a problem that a complicated calculation was required. Rate d
Can easily obtain this without requiring a complicated operation such as a fast Fourier transform, and this temporal dispersion ratio d can be calculated from the flame, the rotating lamp and the incandescent lamp as described above. Since the stable and clear identification is possible, the dispersion rate d is particularly useful information in determining whether or not the flame is present.

FIG. 11 is a diagram showing the autocorrelation cor _m (k) of the rotating lamp obtained based on the measurement result of FIG. Note that FIG. 11 shows the autocorrelation cor _m (k) of the rotating lamp when the imaging distance is 1 m, 3 m, and 5 m, respectively.

FIG. 12 is a view showing the autocorrelation cor _m (k) of the flame of the 3.3 cm square fire tray, which is obtained based on the measurement result of FIG. Note that in FIG. 12, the imaging distance is 4 m, 6
autocorrelation cor of flame when m, 8m, 10m
_m (k) are shown respectively.

In FIGS. 11 and 12, m is set to "0".

Comparing FIG. 11 and FIG. 12, the autocorrelation cor _m (k) of the rotating lamp of FIG. 11 changes periodically with time, whereas the autocorrelation cor _m (k) of the rotating lamp of FIG. It can be seen that the autocorrelation cor _m (k) is almost constant in time. In the rotating lamp, the emission direction of light rotates at a constant rotation speed, and therefore, the amount of light received by the imaging unit 1 changes periodically with this rotation, and with this, the autocorrelation c
or _m (k) also changes periodically with time as shown in FIG. On the other hand, the amount of light emitted from the flame does not change periodically as in a rotating lamp, and the autocorrelation cor _m (k) is also shown in FIG.
It does not change cyclically like.

As described above, the autocorrelation makes it possible to clearly distinguish the flame having artificial periodicity such as a rotating lamp from the flame.

Thus, the dispersion ratio d and the autocorrelation cor
Is different for each object, that is, for a flame, a rotating lamp, and an incandescent lamp, and is useful information for determining whether or not a flame is present.

As described above, in the object detecting apparatus of FIG. 1, when the object to be detected is a flame (that is, when this object detecting apparatus is used for detecting a flame), the image processing unit 2 causes the image processing unit 2 to set a predetermined time interval Δt. When a flame candidate is specified as the object image area OBJ from the obtained binary image data, the gravity center mobility g of the object image area OBJ is calculated, and /
Alternatively, the main axis change rate h of the object image area is obtained, and / or the shape similarity f of the object image area is obtained, and / or the size (the number of pixels) of the object image area OBJ is temporally fluctuated. As a characteristic, a variance ratio (standard deviation value of variance) of the size (number of pixels) of the object image area OBJ with respect to the temporal average value is obtained, and / or the object image area OB
As the regularity of the temporal variation of the size of J (the number of pixels), the autocorrelation with respect to the temporal change of the size (the number of pixels) of the object image area OBJ is obtained, and at least one of them is selected. When one is determined, the determination unit 3 determines whether or not the object image area is a flame based on these processing results.

Therefore, in the judging section 3, the dispersion rate d, the autocorrelation cor, the center-of-gravity mobility g, the main axis change rate h, and the shape similarity rate f.
Whether or not the object is a flame can be determined based on at least one of the above. That is, it is possible to determine whether or not the flame is based on the dispersion ratio d, or it is possible to determine whether or not the flame is based on the autocorrelation cor, or the gravity center mobility g You can determine whether it is a flame based on, or
It is possible to determine whether or not the flame is based on the spindle change rate h, or it is possible to determine whether or not the flame is based on the shape similarity rate f. In combination, it is possible to determine whether or not it is a flame.

For example, the determination unit 3 is, in the image processing unit 2, for example, the dispersion ratio d, the autocorrelation cor, the gravity center mobility g,
When the main axis change rate h and the shape similarity rate f are obtained, the dispersion rate d, the autocorrelation cor, the center-of-gravity mobility g, the main axis change rate h, and the shape similarity rate f are used as parameters, and fuzzy theory is used.
It is possible to judge whether or not it is a flame.

Specifically, for example, for each parameter of the shape similarity rate f, the center-of-gravity mobility g, the principal axis change rate h, the dispersion rate d, and the autocorrelation cor, the membership function MEM (f ), MEM (g), MEM (h), M
EM (d) and MEM (cor) are set in advance, and the image processing unit 2
, Shape similarity f, center of gravity mobility g, spindle change rate h,
When the dispersion ratio d and the autocorrelation cor are obtained, the membership functions MEM (f), MEM (g), and M corresponding to each are calculated.
From EM (h), MEM (d), and MEM (cor), confidence factors o (f), o (g), o (h), o (d), and
o (cor) can be obtained, and these certainty factors o (f),
Finally, it is possible to detect whether or not it is a flame from o (g), o (h), o (d), o (cor) or by combining these certainty factors.

FIG. 13 shows the parameter (0
FIG. 14 is a diagram showing a setting example of a membership function MEM (f) expressing the certainty factor of flame for ˜1), and FIG. 14 shows, for parameters (0 to 1) of the gravity center mobility g,
Membership function MEM that expresses certainty that it is a flame
FIG. 15 is a diagram showing a setting example of (g), and FIG. 15 is a setting example of a membership function MEM (h) expressing a certainty factor of flame for the parameter (0 to 1) of the spindle change rate h. FIG.

FIG. 16 is a diagram showing a setting example of the membership function MEM (d) expressing the certainty factor of flame for the parameter (0 to 1) of the temporal dispersion ratio d, and FIG. 17 is a parameter (0 to 0) of the autocorrelation cor (k).
It is a figure which shows the example of setting of the membership function MEM (cor) expressing the certainty factor which is flame about 1). In addition,
For rotating lights, the dispersion ratio d may be greater than 1.0. For values above 1.0, this is converted to a parameter value of 1.0 and the membership function MEM (d )It was set.

As can be seen from FIGS. 13 to 17, each membership function MEM (f), MEM (g), MEM
(h), MEM (d), and MEM (cor) are shape similarity f,
Center-of-gravity mobility g, principal axis change rate h, dispersion rate d, autocorrelation co
When the probability that the parameter value of r is flame is the highest, a certainty factor (weighting) is given, and when the probability that it is a flame is the lowest, certainty factor (0) is given (weighting). And a membership function like this
It can be set by human judgment. Therefore, by using such a membership function, it is possible to make flame detection judgment close to human judgment. Further, the information of the shape similarity rate f, the center-of-gravity mobility g, the main axis change rate h, the dispersion rate d, and the autocorrelation cor are well suited as the parameters of the membership function of such a fuzzy theory. There is.

Now, for example, the object is a flame, and the dispersion rate d, the autocorrelation cor, the center-of-gravity mobility g, the main axis change rate h, the shape similarity rate f obtained by the image processing unit 2 are calculated.
Each parameter value of "0.3", "0.9"
When it is 5 ”,“ 0.9 ”,“ 0.8 ”,“ 0.7 ”,
From the membership functions of FIGS. 13 to 17, the certainty factors o (0.3), o (0.95), o (0.9),
o (0.8) and o (0.7) are "1.0" and "1."
It becomes 0 ”,“ 1.0 ”,“ 1.0 ”,“ 1.0 ”.

When the object is a rotating lamp, the rotating lamp does not appear in the image unless it is synchronized with the shutter speed of the image pickup unit. Therefore, the gravity center mobility g, the spindle change rate h, and the shape similarity rate f are measured. It is impossible. For example, the dispersion ratio d and the autocorrelation c of this object (rotating light) obtained by the image processing unit 2
or, the mobility of the center of gravity g, the main axis change rate h, and the shape similarity rate f are “1.0”, “0.5”, “measurable”, “measurable”, and “measurable”, respectively. At a certain time, from the membership functions of FIGS. 13 to 17, the certainty factors o (1.0), o (0.5), o (unmeasurable), o
(Measurement impossible) and o (Measurement impossible) are "0.0", "0.0",
"Measurement impossible", "Measurement impossible", "Measurement impossible".

Further, the object is an incandescent light bulb (general light source whose position is fixed), and the dispersion ratio d, the autocorrelation cor, and the center-of-gravity mobility g of the object obtained by the image processing unit 2 are
The parameter values of the spindle change rate h and the shape similarity rate f are "0.1", "1.0", "1.0", "1.0",
When it is “1.0”, the certainty factors o (0.1), o of each parameter value are calculated from the membership functions of FIGS. 13 to 17.
(1.0), o (1.0), o (1.0), o (1.0) are "0.
It becomes 0 ”,“ 0.0 ”,“ 0.0 ”,“ 0.0 ”,“ 0.0 ”.

Further, the object is an artificial light flicker, and the dispersion rate d, the autocorrelation cor, the center-of-gravity mobility g, the main axis change rate h, and the shape similarity rate of the object obtained by the image processing unit 2 are calculated. Each parameter value of f is "0.
4 ”,“ 0.8 ”,“ 0.5 ”,“ 0.2 ”,“ 0.5 ”, the certainty factor o (0 of each parameter value is calculated from the membership functions of FIGS. 13 to 17. .4), o (0.8), o
(0.5), o (0.2), and o (0.5) are "1.0" and "1."
It becomes 0 ”,“ 0.0 ”,“ 0.0 ”,“ 0.5 ”.

In this way, when the certainty factors o (d), o (cor), o (g), o (h), and o (f) for each parameter value are obtained, the decision unit 3 determines, for example, Average value of each confidence (o
(d) + o (cor) + o (g) + o (h) + o (f)) / 5 is obtained, and when the average value is equal to or greater than a predetermined threshold value, for example, “0.8”, it is determined that the flame is present. When it is "0.8" or less, it can be judged that it is not a flame.

In the above example, the object is a flame, and the certainty factors o (0.3), o (0.95), o (0.9) of the respective parameter values.
9), o (0.8), o (0.7) are "1.0", "1.
In case of 0 ”,“ 1.0 ”,“ 1.0 ”,“ 1.0 ”,
Since this average value is "1.0" and is "0.8" or more, it can be determined that the object is a flame.

Further, the object is a revolving light, and the certainty factors o (1.0) and o (0.5) of the respective parameter values are "0.0",
In the case of "0.0", "measuring impossible", "measuring impossible", and "measuring impossible", this average value cannot be measured, so it can be determined that the object is not a flame.

Also, the object is an incandescent light bulb, and the certainty factors o (0.1), o (1.0), o (1.0),
o (1.0) is "0.0", "0.0", "0.0",
When it is "0.0" or "0.0", this average value is "0.0".
Since it is "0" and is "0.8" or less, it can be determined that the object is not a flame.

Also, the object is an artificial light flicker, and the certainty factors o (0.4) and o (0.
8), o (0.5), o (0.2), o (0.5) are "1.
When it becomes 0 ”,“ 1.0 ”,“ 0.0 ”,“ 0.0 ”,“ 0.5 ”, this average value becomes“ 0.5 ”, which is less than“ 0.8 ”. It can be judged that the object is not a flame.

As described above, according to the object detecting device of the present invention, when the object detecting device is used for flame detection, by using the object imaged image data having a large amount of information, the unique characteristics of the flame generated during a fire etc. (Characteristics that can be clearly distinguished from the factors of (1)) is determined, and whether or not the object is a flame is determined based on this information, so the reliability of the determination as to whether or not it is a flame. Can be significantly improved.

Therefore, the object detecting device of the present invention can be used as a flame detecting device and applied to a fire alarm device.

FIG. 18 is a diagram showing an example of the construction of a fire alarm device to which the object detecting device of the present invention is applied. Referring to FIG. 18, in the fire alarm device, in the target detection device shown in FIG. 1, the image capturing unit 1 is set so as to properly capture an image of flame as a detection target, and the output from the determination unit 3 is set. ，
That is, when the determination result of the determination unit 3 is flame, it is further provided with an alarm output unit 4 that determines a real fire and outputs a fire alarm (abnormality alarm).

FIG. 19 is a flow chart for explaining the processing operation of the fire alarm device of FIG. In this fire alarm device, prior to actually operating it, for example, a membership function for each parameter (mobility of center of gravity, rate of change of main axis, shape similarity rate, dispersion rate, autocorrelation) is shown in, for example, FIGS. The determination is made as shown in 17 and this is set in the determination unit 3 in advance (step S1).

After performing such initial setting, the object is imaged by the image pickup unit 1, and the image processing unit 2
When this object is detected as the object image area, the image processing unit 2 thereafter, based on the pixel information of this object image area, the center-of-gravity mobility, the main axis change rate, the shape similarity rate, the dispersion rate, and the self rate. Each piece of correlation information (each parameter value) is determined as described above (step S2).

When each piece of information (each parameter value) is determined by the image processing section 2, the judging section 3 uses a membership function corresponding to each piece of information (each parameter value). , Confidence that the object is a flame
(Fuzzy value) is calculated (step S3). Then, based on the certainty factor obtained for each parameter value (for example, by checking whether or not the average value of each certainty factor is greater than a predetermined threshold value (for example, "0.8")), the object is a flame. If it is determined that the object is a flame, a signal for causing an alarm output is output to the alarm output unit 4 (step S5). Thereby, the alarm output unit 4 can output an alarm only when the determination unit 3 determines that the flame is present.

As described above, in the fire alarm device of FIG.
Information that allows the flame detection device to express the unique features of a flame that occur during a fire (features that can be clearly distinguished from other non-fire alarm factors) by using the imaged image data of an object that has a large amount of information. Since it is possible to determine whether or not the object is a flame based on this information, it is possible to significantly improve the reliability of the fire determination. In other words,
In a conventional fire alarm device (self-fire alarm system) that uses an ultraviolet or infrared sensor (sensor), etc., a false alarm may be output due to various non-fire alarm factors.
The fire alarm system of FIG. 18 can very effectively prevent the occurrence of false alarms due to non-fire alarm factors.

Further, the object detecting device of the present invention can be used as an intruder detecting device (for example, an intruder detecting device) and applied to a crime prevention system (crime alarm device).

FIG. 20 is a diagram showing a structural example of a crime prevention alarm device to which the object detecting device of the present invention is applied. Referring to FIG. 20, in the security alarm device, in the target detection device shown in FIG. 1, the image capturing unit 1 is set to capture an image of an intruder (for example, an intruder) as a detection target, and the determination unit An alarm output unit 4 for outputting an alarm (abnormality alarm) when the output from the unit 3, that is, the determination result of the determination unit 3 is an intruder is further provided.

FIG. 21 is a flow chart for explaining the processing operation of the security alarm system of FIG. In this security alarm device, for example, some standard human body shape patterns have a distance function r before being actually operated.
₀ (θ) is set in advance (step S11).

After performing such initial setting, the object is imaged by the image pickup unit 1, and the image processing unit 2
When this target object is detected as the target object image area, the image processing unit 2 then uses the distance function as described above as the shape information of the target object image area based on the pixel information of the target object image area. Determine r ₁ (θ) (step S1
2). That is, in the image processing unit 2, the object image area O
Distance function r ₁ (θ _i ) from the center of gravity to the contour of BJ
Is calculated as described above. And this distance function r
₁ (θ _i ) and some standard prepared human body shape pattern distance functions r ₀ (θ _i ) are pattern-matched,
Among them, the one having the largest value (similarity rate) is obtained as the shape similarity rate (degree of coincidence of the object pattern with the standard human body shape pattern) (step S13).

In this manner, when the image processing unit 2 determines the shape similarity rate, the determination unit 3 determines whether the shape similarity rate is larger than a predetermined threshold value (for example, "0.8"). By checking, it is determined whether the object is an intruder (step S14). As a result, when it is determined that the object is not an intruder, the process ends. On the other hand, when it is determined in step S14 that the object is an intruder, a signal for outputting an alarm is output to the alarm output unit 4 (step S15). Thereby, the alarm output unit 4 can output an alarm only when the determination unit 3 determines that the intruder is an intruder.

As described above, in the crime prevention alarm device of FIG.
In the intruder detection device, by using the imaged image data of the object with a large amount of information, the information unique to the intruder (feature that can be clearly distinguished from other factors than the intruder) is displayed. Since it is possible to determine and determine whether or not the object is an intruder based on this information, the reliability of the intruder determination can be significantly improved.

In the above example, the detection target is an intruder.
In the case of (for example, an intruder), the shape similarity rate based on the distance function r ₁ (θ) from the center of gravity of the object image area to the contour is used as the information in which the unique features of the intruder are well expressed. , The information unique to the intruder is well expressed, together with the shape similarity based on the distance function r ₁ (θ),
Alternatively, circularity can be used instead.

Specifically, the circularity e of the object image area OBJ in the binarized image data at a certain time is the number of pixels forming the entire object image area OBJ (the area of the object image area OBJ is (Corresponding) u and this object image area O
The number of pixels forming the outline of BJ (corresponding to the length of the outline of the object image area OBJ) v is obtained by the following equation.

[0127]

[Equation 16] e = (4π · u) / v ²

Here, the number of pixels (area) u constituting the entire object image area OBJ is the object image when each pixel of the object image area OBJ is represented as a black pixel in the binarized image data. It can be obtained by counting the number of black pixels forming the entire area OBJ. The number of pixels (contour length) v forming the contour of the object image area OBJ is, for example, further differentiated with respect to the binarized image data, and in this differentiated image data, a black pixel corresponding to the object. Can be obtained by counting the number of

For example, the binarized image data at one time point is as shown in FIG.
When the object image area is OBJ in (a), the number of pixels (area) u forming the entire object image area can be obtained as “5”, which is the total number of black pixels in the object image area OBJ.

Further, when the differential processing is applied to the binary image data of FIG. 22A (that is, one pixel position (x, y) of the binary image data of FIG. 22A is focused on. and when,
If the pixel values p _x , _y are, for example, p _x , _y ≠ p _{x-1, y-1} , p _x ,
_{y ≠ p x-1, y} , p x, y ≠ p x-1, y + 1 or p _{x,, y} ≠ p
_x, only in the case of _y-1, p _x, and _y = 1 (black pixel), p _x otherwise, when subjected to the treatment and _y = 0 (white pixel)),
The differential image data as shown in FIG.
In the differential image data of (b), the number of pixels forming the contour of the object (contour length) v is the total number of black pixels of the portion corresponding to the object image area OBJ of FIG. You can ask.

If the object image area OBJ has a circular shape, and the radius is assumed to be r, the number u of pixels forming the entire object image area is proportional to “πr ² ”, and The number v of pixels forming the contour of the image area is “2π
Since the circularity e is proportional to r ", the circularity e is" 1.0 ". In other words, the circularity e of the object image area is" 1 "when the shape of the object image area is close to a circle. The closer to 0.0 "and the more complicated the shape, the closer to" 0.0 ". When the object is an intruder, the circularity e is, for example, 0.4 to
If it is about 0.6, the circularity e is, for example, 0.4 to
Whether or not the object is an intruder can be determined depending on whether or not it is within the range of 0.6.

As described above, the circularity of the object image area OBJ is only the binary image data at a certain time point, for example, the binary image data at the time point t ₁ when the object image area OBJ is specified. The circularity e can be obtained based on the above, but in order to further increase the reliability, a predetermined time interval Δt from the time point t ₁ when the object image area is specified (including the time point t ₁ for example). time t ₁ of the plurality of (n) that are separated by, t _2, ... t n-number of objects respectively obtained based on the binary image data in the _n image region OBJ _1, OBJ _2,
The average value <e> of the circularity e (t ₁ ), e (t ₂ ), ..., E (t _n ) of OBJ _n can be calculated by the following equation.

[0133]

[Equation 17]

In this way, the information unique to the intruder is satisfactorily expressed, together with the shape similarity f.
Alternatively, the circularity e (<e>) can be used instead.

Furthermore, in addition to the shape information (f, e) as described above, or instead of the shape information (f, e) as described above, the information unique to the intruder is well expressed. It is also possible to use the size S of the object, the moving speed mv, or the like. Here, the size S of the object can be obtained as the total number of pixels of the object image area OBJ, and the moving speed mv of the object is the object image area at a certain time point and the previous time point. It can be determined by comparing with the object image area. When the size S of the target object and the moving speed mv are obtained, it is determined whether the target object is an intruder depending on whether the size S of the target object is appropriate as the size of the human body. Can be determined, and the moving speed mv of the object
Whether or not the object is an intruder can be determined by whether or not is appropriate as the moving speed of the human.

As described above, in the target detection apparatus of FIG. 1, when the detection target is an intruder (for example, an intruder) (that is, when this target detection apparatus is used for intruder detection),
The image processing unit 2 determines a candidate for an intruder from the binarized image data obtained at each predetermined time interval Δt as the object image area OBJ.
The shape similarity f of the object image area OBJ, and / or the object image area O
The circularity e of BJ can be obtained, and / or the size S of the object image area OBJ can be obtained, and / or the moving speed mv of the object image area OBJ can be obtained, and at least one of these can be obtained. When determined, the determination unit 3 determines that the object image area is an intruder based on these processing results.
It can be determined whether (for example, an intruder).

Therefore, the determination unit 3 determines whether the object is an intruder (for example, an intruder) based on at least one of the shape similarity f, the circularity e, the size S, and the moving speed mv. You can judge. That is, it is possible to determine whether or not it is an intruder (intruder) based on the shape similarity f, or it is determined whether or not it is an intruder (intruder) based on the circularity e. It is also possible to determine whether it is an intruder (intruder) based on the size S, or whether it is an intruder (intruder) based on the moving speed mv. You can judge
Furthermore, it is also possible to determine whether or not it is an intruder (intruder) by appropriately combining these.

For example, when the image processing unit 2 obtains the shape similarity f, the circularity e, the size S, and the moving speed mv, the determining unit 3 determines the shape similarity f, the circularity e, and the size. It is also possible to judge whether or not it is an intruder (intruder) by using fuzzy theory with S and moving speed mv as parameters.

Specifically, for example, for each parameter of shape similarity f, circularity e, size S, and moving speed mv,
Membership functions MEM (f), MEM (e), MEM (S), MEM (m) expressing the certainty factor of an intruder (intruder)
v) is set in advance, and when the shape similarity f, the circularity e, the size S, and the moving speed mv are obtained by the image processing unit 2, the membership functions MEM (f) and M corresponding to each are obtained.
From EM (e), MEM (S), and MEM (mv),
It is possible to obtain the certainty factors o (f), o (e), o (S), and o (mv) that are flames, and these certainty factors o (f), o (e), o
It is also possible to finally detect whether it is an intruder (intruder) from (S), o (mv) or by combining these certainty factors.

As described above, when the target detection device of FIG. 1 is used as an intruder detection device, it can be reliably determined whether or not it is an intruder (intruder).

In each of the above configuration examples, the analog image data from the image pickup section 1 (photoelectric conversion section 12) is binarized as A / D conversion processing in the image processing section 2 to obtain the analog image data. Is converted into binarized image data, and the necessary processing for flame detection and intruder detection is performed. However, in the image processing unit 2, the analog image data from the image pickup unit 1 (photoelectric conversion unit 12) is processed. It is also possible to perform multi-value processing as the A / D conversion processing, convert the analog image data into multi-value digital image data, and then perform the same processing required for flame detection and intruder detection as described above.

Further, in each of the above configuration examples, there is one object, and one object image area (connected area) from the picked-up image.
Although the case where the OBJ is specified has been described, the present invention can be similarly applied to the case where there are a plurality of objects and a plurality of object image areas (a plurality of connected areas) are included in the captured image. In this case, it is possible to reliably determine whether or not each target object is a predetermined detection target (flame or intruder) by performing the above-described processing for each of the plurality of target object image areas.

For example, two object image areas from the captured image
(Two connected areas) When OBJ ₁ and OBJ ₂ are specified,
The image processing unit 2 has two object image areas OBJ ₁ and OB.
Labeling processing can be performed in which pixels in J ₂ are labeled with label numbers. For example, each pixel in the object image area OBJ ₁ is given the same label number “1”, and each pixel in the object image area OBJ ₂ is given the same label number “2”. Then, the same image processing as described above is performed for each pixel area having the same label number, and the determination processing can be performed based on the image processing result.

That is, in the above example, the predetermined image processing is performed on the object image area OBJ ₁ marked with "1" as the label number, the first image processing result is obtained, and the label number is "1". Predetermined image processing is performed on the object image area OBJ _{2 with} 2 ″
Of the image processing result of the first image processing result, it is determined whether the object with the label number “1” is a predetermined object based on the first image processing result, and based on the second image processing result. It is possible to determine whether or not the object with the label number “2” is the predetermined object.

In the above description, the alarm output unit 4 is provided in the object detection device of FIG. 1 and the alarm output unit 4 outputs an alarm when it is determined that the object is a flame or an intruding object. Instead of such an alarm output from the alarm output unit 4, or together with such an alarm output, the determination result from the determination unit 3 can be transmitted to the outside of the target detection device. For example, as shown by the broken line in FIG. 1, this target detection device is connected to the receiver 100 via a predetermined transmission line, and this target detection device is connected to the receiver 1
When calling from 00 (for example, when an address is polled), the determination result from the determination unit 3 of the target detection device is returned to the receiver 100, and the receiver 100 side performs alarm processing and the like. Is also possible.

In the above description, the target detection device of FIG. 1 is configured as a flame detection device for detecting a flame or an intruder detection device for detecting an intruder. It is also possible to equip the detection device with the functions of both a flame detection device and an intruder detection device. That is,
As described above, whether the target is a flame or an intruder, the image processing unit 2 of the target detection apparatus of FIG. In addition, since the determination unit 3 basically has a similar determination processing function for these, the target detection device of FIG.
When both the flame detection function and the intruder detection function are provided, at least the image processing unit 2 and the determination unit 3 can be used for both flame detection and intruder detection. Specifically, the image processing unit 2 and the determination unit 3 are
When it is composed of one processor and RAM, ROM, etc.,
This one processor unit can be provided with image processing and judgment processing functions for both flame detection and intruder detection. For example, an image processing program and a judgment processing program for flame detection are stored in a RAM or a ROM, and an image processing program and a judgment processing program for intruder detection are stored therein. The flame detection process can be performed by the image processing program and the determination processing program, and the intruder detection process can be performed by the image processing program and the determination processing program for intruder detection.

Further, the image pickup unit 1 can also be configured to be used for both flame detection and intruder detection. That is, as the photoelectric conversion unit 12 of the image pickup unit 1,
Only one sensor (eg, a normal visible light CCD (CCD sensitive to the visible region)) can be used to detect both flame and intruder.

However, the visible light range is used when monitoring an intruder, while the near infrared range is used when monitoring a flame, for example, the wavelength of light used for flame detection and intruder detection. Because the areas are different,
When both flame detection and intruder detection are performed using only one sensor (for example, a normal visible light CCD), when intruder detection is performed, the visible light is allowed to pass through and the light is allowed to enter the sensor. At the time of flame detection, it is desirable to perform switching control so that the visible region is cut and the light cut in the visible region enters the sensor.

When detecting an intruder, the visible light is allowed to pass therethrough to enter the sensor. On the other hand, when the flame is detected, the visible area is cut and the light cut in the visible area is allowed to enter. Such switching control and switching control as to whether the image processing unit 2 or the determination unit 3 is to perform flame detection or intruder detection can be realized as the switching control means by the above-mentioned processor unit, for example.

FIG. 23 is a diagram showing an example of the structure of an object detecting device provided with such a switching control means 7. By providing such a switching control means 7, FIG.
The function of detecting both a flame and an intruder (function as an intruder / flame detecting device) can be provided in various forms with only one target detection device.

For example, the switching control means 7 of the object detecting apparatus of FIG. 23, for example, causes the image pickup unit 1 to initially have a function as an intruder sensor, and causes the object detecting apparatus to perform intruder monitoring so that the object is When it is detected, the judgment unit 3 judges whether or not this object is an intruder, and the judgment unit 3
When it is determined that the user is not an intruder, the imaging unit 1
The function of the image pickup unit 1 is switched so as to have a function as a flame sensor, and after switching so as to have a function as a flame sensor, the target detection device is caused to perform flame monitoring, and the determination unit 3
The switching control can be performed so as to determine whether or not the flame is present.

FIG. 24 is a flow chart for explaining the processing operation of the object detecting apparatus of FIG. Referring to FIG. 24, the switching control unit 7 initially sets the photoelectric conversion unit 12 (one sensor) of the image pickup unit 1 to allow visible light to enter as it is. In this state, for example, the brightness adjustment is performed to adjust the brightness. After the adjustment or the like is performed, the target detection device is caused to start the intruder monitoring processing operation (step S21).

As a result, in the image processing section 2, the image pickup section 1
For example, as described above, based on the image processing result for intruder detection from the image processing unit 2, the determination unit 3 performs the image processing for intruder detection described above on the object imaged in Depending on the method, it is determined whether or not the user is an intruder (step S22). The process of determining whether or not the user is an intruder starts, for example, when the difference between the current image data and the previous image data is extracted (the connected component of the difference pixel is extracted by a predetermined threshold or more).

If it is determined that the user is an intruder in the determination processing of step S22, for example, an intruder alarm is sounded.
(Step S26). On the other hand, if it is determined in the determination process of step S22 that the user is not an intruder, the difference between the current image data and the previous image data (difference data) is further extracted, and it is determined whether or not the difference data exists. (Step S23). As a result, if there is difference data, the process returns to step S21 again, and it is determined again whether or not the user is an intruder.

In this way, when the intruder determination processing is performed, it is determined in step S22 that the user is not an intruder, and when it is determined in step S23 that there is no difference data, the switching control unit 7 picks up an image. The state of the image pickup unit 1 is switched so that the photoelectric conversion unit 12 (one sensor) of the unit 1 enters the light that cuts the visible region. In this state, for example, the brightness adjustment is performed, and the brightness adjustment is performed. After
The target detection device is caused to perform the flame monitoring processing operation (step S24).

As a result, in the image processing section 2, the image pickup section 1
For example, the image processing for flame detection as described above is performed on the object imaged in (1), and the determination unit 3 uses the image processing result for flame detection from the image processing unit 2 in the manner described above. Then, it is determined whether or not it is a flame (step S25). As a result, when it is determined that the flame is present, for example, a fire alarm is sounded (step S26).

On the other hand, if it is determined in step S25 that the flame is not the flame, the switching control means 7 again captures an image so that the photoelectric conversion section 12 (one sensor) of the image capturing section 1 receives visible light as it is. The state of the unit 1 is switched, and, for example, the brightness is adjusted in this state, and after the brightness is adjusted, the target detection device starts the intruder monitoring processing operation (step S21).

In this way, with one object detection device having a simple structure, it is possible to perform flame monitoring (flame detection) while performing intruder monitoring (intruder detection).

In the above example, the flame monitoring is performed while the intruder monitoring is performed, but conversely, the intruder monitoring can be performed while performing the flame monitoring.
That is, in this case, the switching control means 7, for example,
Initially, the image pickup unit 1 is made to have a function as a flame sensor, the target detection device is made to perform flame monitoring, and when the target object is detected, the determination unit 3 determines whether or not the target object is a flame. When the determination unit 3 determines that the flame is not the flame, the function of the image pickup unit 1 is switched so that the image pickup unit 1 has a function as an intruder sensor, and the target detection device is caused to monitor the intruder. Switching control is performed in the section 3 so as to determine whether or not the user is an intruder.

Further, in the above example, either the intruder or the flame is set as a normal monitoring target, and the flame (or the intruder) is monitored while the intruder (or the flame) is monitored (normal monitoring). However, it is also possible to perform monitoring control (switching control) with the intruder and the flame as equal monitoring targets. That is, in the target detection device of FIG. 23, the switching control unit 7 alternately switches the image capturing unit 1 to the function as the intruder sensor and the function as the flame sensor, for example, and in synchronization with this, the image processing unit. 2, judgment unit 3
It is also possible to perform switching control such that the processing of (1) is switched to the intruder processing and the flame processing alternately.

In this case, for example, at one time point t ₁ , the image pickup section 1 is switched to the function as the intruder sensor.
(The photoelectric conversion unit 12 (one sensor) is switched to a state in which visible light is allowed to enter as it is), the image processing unit 2, the determination unit 3
Then, image processing for intruder detection is performed on the image captured in this state, and based on the result of the image processing,
Intruder determination processing is performed, and at the next time point t ₂ , the image pickup unit 1 is switched to the function as a flame sensor (photoelectric conversion unit 1
2 (a single sensor) is switched to a state in which visible light is cut off.) The image processing unit 2 and the determination unit 3 perform image processing for flame detection on the image captured in this state. , The flame determination process is performed based on the result of the image processing, and at the next time t ₃ , the imaging unit 1 is switched to the function as the intruder sensor (the photoelectric conversion unit 12 (one sensor)). The visible light is switched on as it is), and the image processing unit 2 and the determination unit 3 perform image processing for intruder detection on the image captured in this state, and based on the result of the image processing. In this way, the intruder can be monitored and the flame can be monitored alternately, such as inspecting the intruder.

In addition, the object detecting device of FIG.
In the normal state, it may be controlled to function as a flame detection device, and in the monitoring state, the flame may be controlled to function as an intruder / flame detection device that detects both an intruder.

In each of the above examples, the switching control means 7
Automatically switches between intruder monitoring and flame monitoring, but you can manually switch between intruder monitoring and flame monitoring.
It is also possible to configure the switching control (for example, by a manual switch).

In this case, when the operator sets, for example, a manual switch on the intruder monitoring side, the target detection device in FIG. 23 functions as an intruder detection device. That is, the image pickup unit 1 is switched to a function as an intruder sensor (switched to a state where visible light is allowed to enter the photoelectric conversion unit 12 (one sensor) as it is), and in the image processing unit 2 and the determination unit 3,
Image processing for intruder detection is performed on the image captured in this state, and intruder determination processing is performed based on the result of the image processing.

When the operator sets, for example, a manual switch to the flame monitoring side, the object detecting device in FIG. 23 functions as a flame detecting device. That is, the imaging unit 1 is switched to a function as a flame sensor (switched to a state in which visible light cut light enters the photoelectric conversion unit 12 (one sensor)), and in the image processing unit 2 and the determination unit 3, Image processing for flame detection is performed on the image captured in this state, and flame determination processing is performed based on the result of the image processing.

As described above, depending on the configuration of the switching control means 7, it is possible to perform various types of monitoring control on different objects, ie, an intruder and a flame, with a single object detection device. That is, the function of detecting both the flame and the intruder (function as the intruder / flame detecting device) can be provided in various forms by using only one target detection device of FIG.

In the switching control means 7, the image pickup unit 1
A mechanical shutter, for example, can be used to switch between the function as an intruder sensor and the function as a flame sensor.

FIG. 25 is a diagram showing a structural example of a mechanical shutter. In the example of FIG. 25, the mechanical shutter 10
1 is installed in front of the lens system 13 of the image pickup unit 1, and a visible light cut filter is inserted / removed on / from the optical path of the object monitoring area according to a control signal from the shutter control line 102.
It has a mechanism to close (open or close). 26A shows a state where the visible light cut filter 103 is closed (closed), and FIG. 26B shows a state where the visible light cut filter 103 is opened (open). ing.

When using such a mechanical shutter 101, the switching control means 7 causes the mechanical shutter 101 to function when the image pickup section 1 functions as an intruder sensor.
Is controlled so as to be in an open state as shown in FIG. 26B, and when the imaging unit 1 is made to function as a flame sensor, the mechanical shutter 101 is controlled so as to be in a closed state as shown in FIG. 26A. To do.

Also, in the object detecting apparatus of FIG. 23,
An alarm output unit 4 may be provided as in the case of the target detection device of FIG. 1. In this case, an intruder alarm and a flame alarm may be output according to the intruder monitoring state and the flame monitoring state. it can.

As described above, the object detecting apparatus of FIG. 23 has a simple structure, but has a function of monitoring and detecting both an intruder and a flame by itself. So, if you use this target detection device,
It is not necessary to separately arrange the intruder detection device and the flame detection device, wiring can be reduced, and installation space and cost can be reduced.

Further, in the above description, the alarm output unit 4 is provided in the object detection device of FIG. 23, and when it is determined that the object is a flame or an intruding object, the alarm output unit 4 outputs an alarm. Instead of such an alarm output from the alarm output unit 4, or together with such an alarm output, the determination result from the determination unit 3 can be transmitted to the outside of the target detection device. For example, as shown by a broken line in FIG. 23, this target detection device is connected to the receiver 100 via a predetermined transmission line, and when the target detection device is called from the receiver 100 (for example, address polling is performed). It is also possible to return the determination result from the determination unit 3 of the target detection device to the receiver 100 so that the receiver 100 side performs alarm processing and the like.

In this case, as in the object detecting device of FIG. 23, if the single device has a function of monitoring and detecting both an intruder and a flame, the object monitoring device using this object detecting device will be described. For the system, only one system (receiver) is required, and for the intruder sensor function and the flame sensor function,
In this one receiver, since only one address is required (only one address (polling address) is required for the target detection device in FIG. 23), both intruder monitoring and flame monitoring are performed. Even when performing, it is possible to avoid complication of management.

In other words, when the intruder detection device and the flame detection device are separately arranged,
Even if the intruder detection device and the flame detection device are monitored by one receiver, separate addresses (for example, polling addresses) need to be attached to the intruder detection device and the flame detection device, respectively. However, there is a problem that the management becomes complicated, but in the target detection device of FIG. 23, when this is connected to the receiver and both intruder monitoring and flame monitoring are performed, only one receiver is required. ,Also,
Since it suffices to attach only one address, management and the like can be performed extremely easily.

Further, in the configuration example of FIG. 23, the switching control means 7 is provided in the target detection device, but the target detection device is connected to the receiver 100 via a predetermined transmission line to provide a target monitoring system. When configured (when the target detection device is called from the receiver 100 (for example, when address polling is performed), the determination result from the determination unit 3 of the target detection device is returned to the receiver 100. , In the case where the receiver 100 is adapted to perform alarm processing and the like), instead of providing the switching control means 100 in the target detection device, it is provided in the receiver 100 as shown in FIG. It is also possible to switch the target detection device to the intruder detection device state or the flame detection device state by a switching control command from the receiver 100.

Further, in the configuration examples of FIGS. 23 and 27,
The image processing unit 2 and the determination unit 3 of the target detection device can perform the image processing and determination processing for intruder detection and the image processing and determination processing for flame detection in the manner described above. The configuration example of FIG. 27 is not limited to the above method as long as the image processing unit 2 and the determination unit 3 can be used for both intruder detection and flame detection.
Image processing and determination processing for arbitrary intruder detection and image processing and determination processing for arbitrary flame detection can be performed.

Further, in the above-mentioned example, when the image processing and the determination processing are performed by one processor unit, the image processing and the determination processing (program) for intruder detection, the image processing and the determination processing (program) for flame detection. ) To RAM
However, the image processing and judgment processing (program) for intruder detection and the image processing and judgment processing (program) for flame detection can be held in any manner. For example, image processing and judgment processing (program) for intruder detection, image processing and judgment processing (program) for flame detection are provided on a floppy disk or C
It is recorded in a portable storage medium such as a D-ROM in advance, this recording medium is attached to the target detection device when the target detection device is activated, and image processing for intruder detection recorded in this recording medium is performed. Also, the judgment processing (program), the image processing for flame detection and the judgment processing (program) can be loaded into the RAM or the like and used.

[0178]

As described above, according to the inventions of claims 1 to 3, claim 10, and claim 11,
Unique features of intruders (features that can be clearly distinguished from other factors) by using captured image data of a large amount of information
Is determined and whether or not the object is an intruder is determined based on this information, so that the reliability of the determination as to whether or not the object is an intruder can be significantly improved.

Particularly, in the inventions according to claims 2 and 11, the membership function is set in advance with the information that is the characteristic of the intruder being well expressed as a parameter.
When the information that expresses the unique features of the intruder is satisfactorily expressed, the certainty factor that the object is the intruder is obtained from the membership function using the determined information as a parameter value, and the obtained certainty factor is obtained. Since it is determined whether or not the object is an intruder based on the above, it is possible to make a more reliable intruder detection determination that is similar to a human determination.

In the inventions according to claims 4 to 8, the object image area is extracted from the image pickup means and the image taken by the image pickup means, and the object image area is extracted based on the pixel information of the object image area. An object detection device comprising image processing means for indexing information on an object, and means for determining whether or not the object is a flame based on information on the object indexed by the image processing means, It is configured to be able to detect both flames and intruders, and switches the state of the imaging means depending on whether the detection target is a flame or an intruder, and
A switching control means for controlling the processing functions of the image processing means and the determination means is provided, and the target detection device is caused to function as a flame detection device by the switching control of the switching control device, or an intruder Since it is designed to function as a detection device, it is possible to monitor (detect) both a flame and an intruder with a single target detection device, despite the simple and compact configuration.

In particular, in the invention described in claim 8, since a CCD having sensitivity to light in the visible region is used as the image pickup means, a low cost product can be provided.

According to the twelfth aspect of the invention, the object detecting device according to any one of the first to ninth aspects is connected to the receiver via a predetermined transmission line, Since the target detection device sends the target detection result to the receiver when called from the receiver, the receiver side should perform alarm processing etc. based on the target detection result from the target detection device. You can

According to the thirteenth aspect of the present invention, when the target detection device has both the intruder detection function and the flame detection function, the state of the target detection device is intruded by the switching control command from the receiver. Switching control can be performed to either the person detection device or the flame detection device.

[Brief description of drawings]

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

FIG. 2 is a diagram showing a pixel configuration example of a two-dimensional CCD.

FIG. 3 is a diagram for explaining a process of identifying a target image area from a captured image.

FIG. 4 is the center of gravity G of the object image area OBJ, the direction θ of the main axis.
It is a figure for demonstrating ₀ and the distance function r ((theta)).

FIG. 5 is a diagram showing an example of a distance function r (θ) of an object image area OBJ.

FIG. 6 is a diagram for explaining a shape similarity f of an object image area OBJ.

FIG. 7 is the number of pixels in the object image area corresponding to the flame in the binarized image data obtained by capturing the flame of the 3.3 cm square fire tray.
It is a figure which shows the measurement result of the time change of (black pixel number).

FIG. 8 is the number of pixels in the object image area corresponding to the rotating light in the binarized image data obtained by imaging the rotating light as the object.
It is a figure which shows the measurement result of the time change of (black pixel number).

FIG. 9 is a diagram showing measurement results of temporal changes in the number of pixels (the number of black pixels) in the object image region corresponding to the incandescent light bulb in the binarized image data obtained by imaging the incandescent light bulb as the object.

FIG. 10 is a diagram showing a measurement result of a temporal dispersion rate.

FIG. 11 is a diagram showing the autocorrelation of a rotating lamp obtained based on the measurement results of FIG.

FIG. 12 is 3.3 cm obtained based on the measurement result of FIG.
It is a figure which shows the autocorrelation of the flame of Kakuhisara.

FIG. 13 is a diagram showing an example of setting a membership function that expresses the certainty factor of flame for the parameter of the shape similarity ratio f.

FIG. 14 is a diagram showing a setting example of a membership function expressing a certainty factor of flame for a parameter of the center-of-gravity mobility g.

FIG. 15 is a diagram showing a setting example of a membership function expressing the certainty factor of flame for the parameter of the spindle change rate h.

FIG. 16 is a diagram showing a setting example of a membership function that expresses a certainty factor that is flame for the parameter of the temporal dispersion ratio d.

FIG. 17 shows parameters of autocorrelation cor (k),
It is a figure which shows the example of setting of the membership function expressing the certainty factor which is a flame.

FIG. 18 is a diagram showing a configuration example of a fire alarm device to which the target detection device of the present invention is applied.

19 is a flowchart showing an example of processing operation of the fire alarm device of FIG.

FIG. 20 is a diagram showing a configuration example of a crime prevention alarm device to which the object detection device of the present invention is applied.

FIG. 21 is a flow chart showing an example of processing operation of the security alarm device of FIG. 20.

FIG. 22 is a diagram for explaining the process of determining the circularity of an object.

FIG. 23 is a diagram showing another configuration example of the object detection device according to the present invention.

FIG. 24 is a flowchart for explaining the processing operation of the target detection device of FIG. 23.

FIG. 25 is a diagram showing a configuration example of a mechanical shutter.

FIG. 26 is a diagram for explaining the operation of the mechanical shutter in FIG. 25.

FIG. 27 is a diagram showing a configuration example of a target monitoring system according to the present invention.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Imaging part 2 Image processing part 3 Judgment part 4 Alarm output part 7 Switching control means 11 Optical system 12 Photoelectric conversion part 13 Lens system 14 Optical filter 100 Receiver 101 Mechanical shutter

Claims (13)

[Claims] 1. An image processing means, an image processing means for extracting an object image area from an image taken by the image capturing means, and calculating information on the object based on pixel information of the object image area, and image processing. Based on the information on the object indexed by the means, a determination means for determining whether the object is an intruder, the image processing means,
As the information, at least one of the shape similarity rate of the object image area, the circularity of the object image area, the size of the object image area, and the moving speed of the object image area is calculated,
The determination means includes a shape similarity rate of the object image area determined by the image processing means, a circularity of the object image area,
An object detection apparatus, which determines whether or not an object is an intruder based on at least one of the size of the object image area and the moving speed of the object image area. 2. The object detection device according to claim 1,
The determination means includes a shape similarity rate of the object image area,
A membership function that has shape similarity, circularity, size, and moving speed as parameters corresponding to the circularity of the object image area, the size of the object image area, and the moving speed of the object image area, respectively. The determination means is set in advance, and each of the shape similarity of the target image area, the circularity of the target image area, the size of the target image area, and the moving speed of the target image area is set by the image processing means. When the parameter value is calculated, the certainty factor for each calculated parameter value is obtained by the membership function corresponding to each, and the object is an intruder based on the certainty factor obtained for each parameter value. An object detection device characterized by determining whether or not 3. The object detection device according to claim 1, wherein
The object detecting device, wherein one CCD having sensitivity to light in the visible region is used as the imaging means. 4. Image pickup means, image processing means for extracting an object image area from an image picked up by the image pickup means, and calculating information on the object based on pixel information of the object image area, and image processing. A target detection device having a determination means for determining whether or not the target object is a predetermined target object based on the information on the target object indexed by the means, which has a flame detection function and an intruder detection function. And a control for switching the processing function of the imaging means, the image processing means, and the determination means to the flame detection function or the intruder detection function, depending on whether the detection target is a flame or an intruder. A switching control unit for performing the switching is further provided, and the target detection device is controlled by the switching control of the switching control unit.
A target detection device which is made to function as a flame detection device or as an intruder detection device. 5. The object detection device according to claim 4,
The switching control means performs flame monitoring (or intruder monitoring) while performing intruder monitoring (or flame monitoring),
A target detection device, characterized in that the state of the target detection device is switched and controlled. 6. The object detection device according to claim 4,
The object detection device, wherein the switching control means is configured to perform switching control with the intruder and the flame being monitored as equal targets. 7. The object detection device according to claim 4,
The switching control means causes the target detection device to function as, for example, a flame detection device in a normal state, and functions as an intruder / flame detection device that detects both a flame and an intruder in a monitoring state. The target detection device is characterized in that switching control is performed. 8. The object detection device according to claim 4, wherein the switching control unit is configured to be capable of manually switching control between intruder monitoring and flame monitoring. Object detection device characterized by. 9. The object detection device according to claim 4,
One CCD having sensitivity to light in the visible region is used as the image pickup unit, and the switching control unit allows light in the visible region to enter the CCD as it is in the intruder monitoring state.
On the other hand, in the flame monitoring state, the object detection device is characterized in that the light incident on the CCD is controlled so that the visible light cut light is incident on the CCD. 10. A feature of deciding whether or not an object is an intruding object based on image information obtained by picking up image data of the object, which is capable of satisfactorily expressing characteristics unique to the intruding object. Target detection method. 11. The object detection method according to claim 10, wherein a membership function is set in advance with information that is a parameter expressing characteristics unique to an intruder in a good condition,
When the information that well expresses the unique features of the intruder is determined, the certainty factor that the object is the intruder is obtained from the membership function with the determined information as a parameter value. An object detection method characterized by determining whether or not an object is an intruder based on a certainty factor. 12. The target detection device according to claim 1, wherein the target detection device is connected to a receiver via a predetermined transmission path, and the target detection device is called from the receiver. The target monitoring system is characterized in that the target detection result is transmitted to a receiver when the target monitoring system is turned on. 13. A target monitoring system in which a target detection device for detecting a predetermined target is connected to a receiver via a predetermined transmission path, wherein the target detection device has a flame detection function and intruder detection. The receiver is provided with a switching control means for controlling whether the target detection device functions as a flame detection device or an intruder detection device. According to a switching control command from the switching control means of the receiver, the target detection device is caused to function as a flame detection device or an intruder detection device. Target monitoring system.