JPH06103471A - Method and device for detecting moving object - Google Patents

Abstract

PURPOSE:To prevent brightness fluctuation due to sunshine fluctuation from being erroneously recognized as moving object intrusion by forming a fluctuation area picture for indicating the fluctuation state of brightness distribution and discriminating whether or tact a moving object is present within a visual field based on the fluctuation state of the picture element distribution. CONSTITUTION:The data of a fluctuation area picture memory 9 are compared with a threshold value supplied from a threshold value setting circuit 13 by each picture element and binarized picture data are stored in a binary picture memory 15. The fluctuation area picture and the binary picture are transferred to a comparator circuit 17 and arithmetic operation for subtracting the binary picture from the fluctuation area picture is performed for the each picture element. Then, a brightness fluctuation value towards picture element number distribution formation circuit 21 sums up the respective pixel data of a small fluctuation area picture memory 19 with brightness fluctuation values as parameters and sums up picture element number distribution data for the respective brightness fluctuation values. A discrimination arithmetic circuit 23 discriminates whether or not the moving object is present in the visual field based on the picture element distribution data and outputs the discriminated result to an output terminal 25.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention uses moving images (people, animals, vehicles, etc.) within a monitoring area using images taken by ITV or the like.
TECHNICAL FIELD The present invention relates to a moving body detection method and apparatus for determining and detecting whether or not there is an object, and particularly to a moving body detection method and apparatus suitable for outdoor use.

[0002]

2. Description of the Related Art An image captured by an ITV or the like in a monitoring area is monitored, and a moving object such as an illegal intruder or a vehicle is monitored based on the brightness change state of each pixel forming the image in the monitoring area (ITV field of view). Detection has been performed conventionally. For example, the brightness of each corresponding pixel of two images captured at a certain time interval is compared to extract the change state of the brightness distribution, and the change in the brightness distribution is extracted. It is determined whether or not there is a moving object.

As a typical example of such a detection method, an image in a monitoring area is picked up at a predetermined time interval, and a change area image showing a brightness change value of each corresponding pixel of two images during a certain time interval. And binarize each pixel of the change region image with a certain threshold value to obtain a binary image consisting only of pixels having a brightness change value equal to or more than the threshold value, and the total number of pixels forming the binary image, It is known to determine whether or not a moving body exists within the field of view based on the distribution shape, size, and the like.

[0004]

In the conventional moving object detection method, the luminance distributions of two images are compared on a pixel-by-pixel basis to extract the variation state of the luminance distribution, and the total number of pixels with a large variation amount,
The presence / absence of a moving object in the field of view is detected based on the distribution shape, dimensions, etc., but when the monitoring area is outdoors, a change in the brightness of each pixel in the field of view due to changes in the sunshine is as if a moving object had entered. In some cases, it caused a false detection.

Since the size and shape of the luminance change of each pixel in the visual field due to the change of the sunshine is uncertain, if attention is focused only on the pixel having a large amount of luminance change, whether the luminance change is due to the moving body or the sunshine change. Is difficult to identify correctly.

An object of the present invention is to compare the brightness of corresponding pixels of two images photographed at a certain time interval to form a change area image representing the change state of the brightness distribution, and to determine the change state of the pixel distribution. (EN) Provided are a moving body detection method and an apparatus therefor capable of discriminating between a luminance change due to a moving body entering and a luminance change due to a sunshine change, when it is determined whether or not a moving body exists in the field of view based on the above. .

[0007]

According to the present invention, the distribution state of the pixels whose value (luminance change value) is below a certain threshold value among the pixels forming the change area image as described above is This is based on the discovery of a new finding that there is a clear difference between the case and the case due to the change in sunshine.

In order to achieve the above object, the present invention provides a step of capturing an image in a monitoring area at a predetermined time interval and a change representing a brightness change value of each pixel of two images during a certain time interval. Forming an area image; obtaining a luminance change value vs. pixel number distribution for all pixels having a luminance change value smaller than a predetermined threshold; and performing the monitoring based on the state of the luminance change value vs. pixel number distribution. And a step of determining whether or not a moving body exists in the area.

Further, according to the present invention, whether a moving object exists in the monitoring area based on the total number of pixels of which the luminance change value is the second threshold value or more and the distribution shape thereof among the pixels forming the changed area image. A logical product of a step of determining whether or not there is a moving body presence determination in the monitoring area based on the state of the luminance change value vs. pixel number distribution and a moving body presence determination based on a pixel having a luminance change value of a second threshold value or more. Therefore, the method further comprises the step of generating an output signal of the presence of the moving body.

The present invention further includes a camera means for picking up images in the surveillance area at predetermined time intervals, and a first image taken at a certain time and a second image taken at a different time. And a means for forming a change area image representing the change value of the brightness of each pixel, and the brightness change value of each pixel of the change area image is compared with a predetermined second threshold value, and the brightness change value is equal to or more than the second threshold value. Is the maximum value, and the second
When it is less than the threshold value, it is converted to 0 to form a binary image, and the binary image is subtracted from the change area image for each pixel, and when the difference is positive, it is left as it is, and when the difference is negative. When 0
Based on the state of the brightness change value vs. pixel number distribution, a comparison and conversion means for obtaining a slight change image by converting into, a means for forming a brightness change value vs. pixel number distribution for each pixel of the small change image, And a means for determining whether or not a moving object exists in the monitoring area.

Further, according to the present invention, a pixel having a brightness change value equal to or larger than a predetermined threshold value of the change area image, or the total number of pixels of the binary image and at least one of the distribution shape and the size thereof is included in the monitoring area. A means for determining whether or not a moving body exists, and a moving body presence determination in the monitoring area based on the state of the luminance change value vs. pixel number distribution and a moving body presence determination based on the state of pixels of a binary image. And a means for generating an output signal indicating the presence of a moving body according to a logical product.

[0012]

The image in the monitoring area is imaged at a predetermined time interval, for example, by an ITV camera, and each pixel between the first image captured at a certain time and the second image captured at a different time from this A change area image representing a brightness change value (difference or ratio of brightness) is formed, and a brightness change value vs. pixel number distribution is formed for all pixels having a brightness change value smaller than a predetermined threshold value. Based on the state of the pixel number distribution, it is determined whether or not a moving body exists in the monitoring area.

For example, in the luminance change value vs. pixel number distribution, when the variation in the pixel number distribution is large, the luminance change value 0
Has a peak value of the number of pixels in the vicinity of, and the number of pixels of other luminance values is significantly small, or the number of pixels on the side of a luminance value smaller than this in the vicinity of the threshold value itself, the total number thereof.
When at least one of the average values is small, it is determined that the moving body exists in the monitoring area.

For a small change area image including pixels whose brightness change value is smaller than a predetermined threshold value, the brightness value of each pixel of the change area image is compared with the threshold value, and the data of pixels having a value equal to or more than the threshold value is deselected.
Data is set to 0, or the luminance value of each pixel of the change area image is compared with the second threshold value, and the pixel having a value equal to or greater than the second threshold value is set to the maximum value (for example, 255), while the second value is set to the second value.
Pixels that have a value less than the threshold have a minimum value (eg,
0), a binary image is formed, the binary image is subtracted from the change area image for each pixel, and when the difference is positive, it is unchanged, and when the difference is negative, it is converted to 0. To be

Further, if necessary, the moving object is detected by the conventional method based on the total number of pixels of the binary image or the pixels having a value equal to or larger than the threshold value in the change area image, the distribution state, etc. It is also possible to generate the determination output signal according to the logical product of the determination result and the determination result of the moving body detection based on the luminance change value of the small change area image versus the pixel number distribution.

[0016]

1 is a block diagram showing a first embodiment of the present invention. The image in the monitoring area is captured by ITV1, and the image signal has multiple gradations (for example, 0 to 2) at each scheduled time interval.
55 (256 gradations) as an image or image signal of brightness (n
Xm) This time is stored in the image memory 3 in the form of pixels. The image signal M _i−1 stored in the image memory 3 this time is transferred to the previous image memory 5 by the time when the next image signal M _i is taken into the image memory 3 this time. The image signals M _i-1 and M _i of the two image memories 3 and 5 are supplied to the subtraction circuit 7 for each pixel and subtracted between the data of the same pixel to obtain the absolute value of the difference, that is, the luminance change amount. To be The subtraction result, that is, the change area image representing the brightness change (absolute value) data of each pixel during one imaging time interval is stored in the change area image memory 9.

FIGS. 2 and 3 (a) schematically show an example of the storage data of the change area image memory when there is no sunshine change and there is a moving body, and when there is no moving body and there is sunshine change. Shows. In these figures, the number is 1
It is the amount of change in luminance of the pixel region during the imaging time interval, and the amount of change in luminance of the pixel region in which no numerical value is entered is 0.
Suppose that The luminance value of each pixel of the original image captured by ITV1 is represented by 256 gradations of 0 to 255.

Since the contour of the moving body is generally clear, the (contour) of the moving body in the image can be seen as shown in FIG.
Although there is a large change in brightness in the part, almost no change in brightness is observed in other parts, and should ideally be 0. However, in reality, a luminance change of 2 to 3 or less (in the case of 256 gradations) is often recognized due to factors such as a shift in the start position when the signal from the camera is A / D converted, a quantization error, and the occurrence of jitter. .

On the other hand, in the case of sunshine change, as shown in FIG. 3 (a), the shape and size of the area of large brightness change are indefinite, and the contour is blurred due to irregularity, but the brightness is large to some extent on the screen. Change. The present invention is intended to experimentally confirm the characteristics of such a brightness change, and skillfully utilize the characteristics to discriminate and extract a moving object.

The data in the variable area image memory 9 is supplied to a binarization circuit 11, where it is compared for each pixel with a threshold value (a method for determining it will be described later) supplied from a threshold value setting circuit 13. In the binarization of this embodiment, when the luminance value of the target pixel is larger than the threshold value, the luminance value of the pixel is set to the maximum value (that is, 255), and when it is less than the threshold value, it is set to the minimum value (that is, 0). . The binarized image data is stored in the binary image memory 15.

2 (b) of FIGS. 2 and 3 shows (a) of each figure.
It is an example of a binarized image obtained by binarizing the with a threshold value (= 20). In FIG. 2B, it can be seen that the pixel region of the portion corresponding to the moving body is extracted, but in FIG.
However, since there is a pixel area with a large change in brightness, when trying to determine a moving object using only these binarized images as in the conventional case, the total number of pixels of both pixels, the shape of the distribution, the size, etc. are similar. If there is, it may cause a misjudgment.

The changed area image and the binary image are respectively transferred to the comparison circuit 17, and the calculation for subtracting the binary image from the changed area image is performed for each pixel. In this case, if the difference value is positive, it is stored as it is in the corresponding pixel of the small change region image area memory 19, but if the difference value is negative, 0 is stored in the corresponding pixel. Each of (c) of FIGS. 2 and 3 is an example of a small change region image obtained for a case where a moving body exists and a case where there is a change in sunshine.

The luminance change value vs. pixel number distribution forming circuit 21
Each pixel data in the small change area image area memory 19 is totaled using the brightness change value as a parameter, and the pixel number distribution data for each brightness change value is totaled. Based on the pixel number distribution data, the determination calculation circuit 23 determines whether or not there is a moving object in the field of view according to the criteria described later, and outputs the determination result to the output terminal 25. Further, the pixel number counting / determining circuit 29 analyzes the binary image in the memory 15 according to the conventional method, and determines whether or not there is a moving object in the visual field based on the total number of pixels, the distribution shape, and the size. , A determination result is generated at the output terminal 31.

2 (d) and 3 (d) are the same as FIG. 2 (c).
It is an example of a pixel number distribution curve for each brightness value obtained from.
Note that these distribution curves are the data of each of the above-mentioned (c).
The graph is not an exact graph of the data, but an average graph obtained in an experiment conducted by the present inventor.

As is clear from the comparison of (d) in FIGS. 2 and 3, in the case of FIG. 2 in which a moving body exists, an extremely large peak appears at a brightness value of 0, and the number of other brightness values is large. However, if there is no moving object and there is only a change in sunshine as shown in FIG.
The pixel distribution does not appear, and the pixel distribution is seen over the entire range of the luminance value below the threshold value, so that a clear determination can be made.

Therefore, a judgment reference value which is somewhat larger than 10 is set, and a data exceeding the judgment reference value is set.
If the number of data is absent or less than the predetermined value, it can be determined that there is a moving body, and if the number of data exceeding the judgment reference value is more than the predetermined value, it can be determined that there is no moving body. In this way, even if the total number of pixels of the binarized image and the distribution shape are similar to those determined to have a moving object, the presence of the moving object can be accurately determined based on the comparison of the small change region images. Can be judged and extracted.

Further, the variation of the brightness value of the small change image is discriminated using the standard deviation as an index, and when the variation is small, it is determined that there is a moving body, and when the variation is large, it is determined that there is a change in sunshine and no moving body. You can In addition, the number of pixels exhibiting a brightness change value near the threshold value, its average value, the total number thereof, etc. are compared with the determination reference value, and when the determination reference value is larger, it can be determined that there is a moving object.

The threshold value used for the above-described binarized image formation is a fixed value obtained by an experiment in advance and the brightness value of the variable area image to be binarized, as in the prior art. There is a case where it is calculated and determined each time based on the pixel number distribution for each.

The fixed threshold value is obtained by binarizing the actual image to be processed with various threshold values in consideration of the situation of the installation location of the ITV camera 1, the characteristics of the image processing apparatus, and the like. It is determined experimentally in advance by taking into consideration the discrimination by, the quality of extraction, the amount of noise, and the like. The advantage in this case is that the calculation processing time can be shortened, and it is the best method when the luminance change of the image to be detected is limited to a range that can be estimated in advance by experiments. However, there is a drawback in that the determination accuracy decreases when the actual change in luminance exceeds the range that is initially estimated.

As the threshold value calculation method, two methods, a mode method and a discriminant analysis method, have been conventionally adopted. In the mode method, the distribution curve of the brightness value vs. the number of pixels obtained for each pixel of the image to be binarized is 2 as shown in FIG.
In the case of having one peak, the minimum value K1 between the two peaks.
Is a threshold value.

In the discriminant analysis method, when the distribution curve of the brightness value vs. the number of pixels obtained for each pixel of the image to be binarized is divided into two groups G1 and G2 with a certain brightness value K2, The value K2 is set as a threshold value so that the variation of the brightness value in each group is small and the variation between the groups is large. In this case, it is convenient to use the intra-class variance as the index for the intra-group variation and the inter-class variance as the index for the inter-group variation.

If the threshold value is determined by calculation, it is not necessary to carry out an experiment in advance, and a threshold value corresponding to the large change in the luminance of the image can be obtained. Therefore, an advantage of always obtaining an appropriate discrimination accuracy can be expected. On the other hand, since the threshold value is determined regardless of the brightness of the detection target, if the brightness of the part other than the detection target in the binarization target image changes, the determination accuracy tends to decrease, and the program becomes long and the calculation time becomes long. Has the drawback of being long. However, if the threshold value is corrected to a more appropriate threshold value by automatic learning, the above drawbacks can be improved.

As can be seen from the above description, according to the present invention, the moving object detection is based on the number of pixels and the distribution state of the binarized image which is conventionally composed of pixels having a large luminance change during one imaging time interval. Contrary to what was done, the moving object is detected based on the number of pixels and the distribution state in the small change area image consisting of pixels with little change in brightness during one imaging time interval, and the brightness due to sunshine change is thereby obtained. It is intended to prevent misjudging a change as an invasion of a moving body. Further, by using the logical product of the judgment result by the new method and device according to the present invention and the judgment result by the conventional method, the intrusion judgment of the moving body can be made more accurately.

FIG. 5 is a block diagram of an essential part showing a second embodiment of the present invention. The change area image memory 9 to the small change area image memory 19 shown in FIG. 1 or the change area image memory 9 is compared. Conversion circuit 17, small change area image memory 19
Is replaced with. As is clear from the comparison with FIG. 1, this embodiment is a simplified means for obtaining the luminance value-pixel number distribution from the change area image.

The comparison circuit 17A includes a changing area image memory 9
The data (luminance value) of each pixel is compared with a threshold value (the value may be the same as or different from that set by the threshold setting circuit 13) supplied from the threshold setting circuit 13A. When the data of each pixel is larger than the threshold value, it is ignored and discarded, and when the data is small, the data is supplied to the luminance change value / pixel number distribution forming circuit 21. The brightness change value vs. pixel number distribution forming circuit 21 classifies the received data for each brightness value and accumulates the data to create the brightness value vs. pixel number distribution data or graph it. Subsequent determinations are made in the same way as in the first embodiment.

According to the second embodiment, there is an advantage that the configuration and the procedure are greatly simplified. Of course, in this case as well,
Naturally, the logical product with the determination result by the conventional method can be used.

In the above description, the change area image is the difference in the brightness value for each pixel of two temporally consecutive single images, but instead of at least one of the single images, a plurality of images including the single image are used. You may use the average value for every pixel of a continuous image.

[0038]

According to the present invention, the brightness of each corresponding pixel of two images captured at a certain time interval is compared with each other to form a change area image representing the change state of the brightness distribution, and the field of view is changed based on the change state of the pixel distribution. When determining whether or not there is a moving object inside, it is possible to distinguish between a change in brightness due to intrusion of a moving object and a change in brightness due to change in sunshine, and to prevent a change in brightness due to change in sunshine as intrusion of a moving object.

[Brief description of drawings]

FIG. 1 is a block diagram showing a first embodiment of the present invention.

FIG. 2 is a diagram showing an example of a change area image, a binarized image, a small change area image, and a luminance value vs. pixel number distribution when a moving object is present in the monitoring field of view.

FIG. 3 is a diagram similar to FIG. 2 in the case where there is no moving body within the monitoring field of view and there is a change in sunshine.

FIG. 4 is a diagram showing an example of a luminance value-pixel number distribution for explaining a method of obtaining a threshold value by calculation.

FIG. 5 is a block diagram showing a main part of a second embodiment of the present invention.

[Explanation of symbols]

1 ... ITV 3 ... Current image memory 5 ... Previous image memory 7 ... Subtraction circuit 9 ... Change area image memory 11 ... Binarization circuit 13
... threshold value setting circuit 15 ... binary image memory 17 ... comparison conversion circuit 17
A ... Comparison circuit 19 ... Slight change image memory 21 ... Luminance change value vs. pixel number distribution forming circuit 23 ... Judgment arithmetic circuit

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Ryoichi Matsunaga Ryoichi Matsunaga 2-82 Watanabe-dori, Chuo-ku, Fukuoka City, Fukuoka Prefecture Kyushu Electric Power Co., Inc. (72) Kazutoshi Ono Otoburi Village, Tosuri Village, Kanzaki-gun, Saga Prefecture Character Higashiyama 5006-26 Nishim Electronics Industrial Co., Ltd. RD Center- (72) Inventor Yoshihiro Ishida Large-sized Omagari Higashiyama 5006-26 Nishim Electronic Industry Co., Ltd. RD Center, Kanzaki-gun, Saga Prefecture

Claims (22)

[Claims] 1. A method of capturing an image in a monitoring area at a predetermined time interval, a step of forming a change area image representing a brightness change value of each corresponding pixel of two images in a certain time interval, and a brightness. Obtaining a luminance change value vs. pixel number distribution for all pixels whose change values are less than a predetermined threshold,
A method of detecting a moving body, comprising the step of determining whether or not a moving body exists in the monitoring area based on the state of the brightness change value vs. pixel number distribution. 2. The step of obtaining the luminance change value vs. pixel number distribution compares the luminance change value of each pixel of the change area image with a predetermined threshold value, and the pixel having the luminance change value equal to or higher than the threshold value is set to 0. On the other hand, the method for detecting a moving object according to claim 1, further comprising assigning a value as it is to a pixel having a brightness change value smaller than a threshold value and counting the number of pixels having the same brightness change value. 3. The step of obtaining a luminance change value vs. pixel number distribution compares the luminance change value of each pixel of the change area image with a predetermined second threshold value, and a pixel having a luminance value equal to or higher than the second threshold value. Is converted to the maximum value, while pixels having a brightness value smaller than the threshold value are converted to 0 to form a binary image, and the change area image data is
The data of the binary image is subtracted from the data, and at that time, the pixels with a positive difference are unchanged, and the pixels with a negative difference are converted to 0 to form a small change region image, and the obtained small change image is obtained. The moving object detection method according to claim 1, further comprising counting the number of pixels having the same brightness change value in the area image. 4. The method for detecting a moving object according to claim 1, wherein at least one of the two images is an average value of a plurality of images captured continuously. 5. The moving object detection method according to claim 1, wherein the brightness change value is a difference between brightness values of pixels of the two images. 6. The moving object detection method according to claim 1, wherein the brightness change value is a ratio of brightness values of pixels of the two images. 7. In the luminance change value-pixel number distribution,
It is determined that a moving object exists in the monitoring area when the pixel has a peak value of the number of pixels at the position where the brightness change value is 0 and the number of pixels indicating the brightness value near 0 is within a predetermined reference range. The moving object detection method according to any one of claims 1 to 6, wherein 8. In the luminance change value vs. pixel number distribution,
Claims characterized in that when a predetermined number or more of pixels are distributed in most of the brightness value range from the brightness change value 0 to the threshold value, it is determined that no moving body exists in the monitoring area. Item 7. The moving body detection method according to any one of Items 1 to 6. 9. In the luminance change value vs. pixel number distribution,
3. The moving object is determined to be present in the monitoring area when the number of pixels indicating the luminance value excluding the vicinity of the luminance change value 0 is smaller than a predetermined determination reference value.
The moving body detection method according to any one of 1 to 6. 10. The method according to claim 1, wherein when the standard deviation in the luminance change value vs. pixel number distribution is within a predetermined determination reference range, it is determined that a moving object exists in the monitoring area. 7. The moving body detection method according to any one of 6. 11. In the distribution of the luminance change value vs. the number of pixels, the number of pixels that present a luminance value in the vicinity of the side smaller than the threshold value, and at least one of the total number and the average value thereof are predetermined. The moving object detection method according to claim 1, wherein when the value is smaller than the reference value, it is determined that a moving object exists in the monitoring area. 12. Among the pixels forming the change area image,
Selecting a luminance change value that is equal to or greater than a second threshold value, and determining whether or not a moving object exists in the monitoring area based on the total number of selected pixels and the distribution shape thereof. An output signal indicating the presence of a moving body is output according to a logical product of a moving body presence determination in the monitoring area based on the state of the luminance change value vs. pixel number distribution and a moving body presence determination based on a pixel having a luminance change value of a second threshold value or more. The moving object detection method according to claim 1, further comprising a step of generating. 13. A binary image is obtained by assigning a maximum luminance value to selected pixels and assigning 0 to pixels that are not selected in the step of selecting those whose luminance change value is greater than or equal to a second threshold value. The moving body detection method according to claim 12, wherein the moving body detection method is performed. 14. Each pixel between a camera means for picking up an image in the monitoring area at a predetermined time interval and a first image picked up at a certain time and a second image picked up at a different time. Means for forming a change area image representing the brightness change value of the pixel, comparing the brightness change value of each pixel with a predetermined threshold value, discarding the brightness change value larger than the predetermined threshold value, and changing the brightness change value smaller than the predetermined reference value to Comparing means for outputting as it is, means for obtaining a luminance change value vs. pixel number distribution for all pixels having a luminance change value smaller than a predetermined threshold value based on the output of the comparing means, and the luminance change value vs. pixel number distribution And a means for determining whether or not a moving body exists in the monitoring area based on the state of 1. 15. Among the pixels forming the change area image,
Means for selecting a luminance change value equal to or greater than a second threshold value;
Means for determining whether or not a moving object exists in the monitoring area based on the total number of selected pixels and its distribution shape, and movement within the monitoring area based on the state of the luminance change value vs. pixel number distribution. The means for generating an output signal of the presence of a moving object according to a logical product of the determination of the presence of the moving object and the determination of the presence of the moving object based on a pixel having a brightness change value equal to or more than a second threshold value. Mobile object detection device. 16. Pixels between a camera means for picking up an image in the monitoring area at a predetermined time interval and a first image taken at a certain time and a second image taken at a different time. Means for forming a change area image representing the change value of the brightness of the change area image and the change value of the brightness of each pixel of the change area image are compared with a predetermined second threshold value, and the change value of the brightness is the second value.
Pixels above a threshold value are converted to maximum values, and pixels above the second threshold value are converted to 0 to form a binary image, and a binary image is subtracted from the change area image for each pixel, When the difference is positive, it is left as it is, and when the difference is negative, it is converted to 0 to obtain a small change image, and a comparison conversion means for obtaining a small change image, and a luminance change value vs. pixel number distribution is formed for each pixel of the small change image. A moving body detecting apparatus comprising: a means and a means for determining whether or not a moving body exists in the monitoring area based on the state of the luminance change value vs. pixel number distribution. 17. A means for determining whether or not a moving object exists in the monitoring area based on the total number of pixels of a binary image and its distribution shape, and based on a state of the brightness change value vs. pixel number distribution. And a means for generating an output signal indicating the presence of a moving body according to a logical product of the determination of the presence of a moving body in the monitoring area and the determination of the presence of a moving body based on the total number of pixels of a binary image and its distribution shape. The moving body detection device according to claim 16. 18. The means for determining whether or not a moving object exists in the monitoring area based on the state of the luminance change value vs. pixel number distribution, the luminance change obtained based on the output of the comparing means. The value-to-pixel number distribution state is compared and contrasted with a standard brightness change value-to-pixel number distribution state prepared in advance, and when the deviation is within a predetermined value, it is determined that a moving object exists in the monitoring area. The moving body detection device according to any one of claims 14 to 17. 19. The moving body according to claim 14, wherein the image picked up by the camera means is stored in the image memory as multi-grayscale data for each pixel. Detection device. 20. The change area image is a difference between a brightness value of each pixel of the first image and a brightness value of each pixel of the second image. The moving body detection device described. 21. The change area image is a ratio of a luminance value for each pixel of the first image and a luminance value for each pixel of the second image, according to any one of claims 14 to 17. The moving body detection device described. 22. The brightness value of each pixel of at least one of the first and second images is an average brightness value for each pixel of at least one image captured continuously. The moving body detection apparatus according to any one of 1 to 17.