JPS62136990A - Abnormality monitoring device - Google Patents

Abstract

PURPOSE:To reduce a change in detection capacity due to a partial illuminating light quantity in a monitoring area by extracting only a he from a color picture signal obtained by a color picture image pickup means, and inputting it to an image processing means. CONSTITUTION:The hue is found by inputting three chrominance signal outputs from a color picture image pickup means 11 consisting of a color television camera, and is inputted to an abnormality monitoring device main body 5. On a picture memory 21, a hue image in a present monitoring area fetched in every moment from a picture input means 1 is stored, and it is subtracted from a luminance data on a reference picture element memory 22 at a difference absolute value circuit 23, then being made into an absolute value, and is binary-coded at a binarization circuit 24 with an appropriate threshold value, and an image consisting only of a picture element in which a luminance change between a present image and a reference image more than a prescribed threshold value is present can be obtained. And when an abnormality is detected at an abnormality decision means 3, the detection of the abnormality is outputted from an output means 4. In this way, even when nonuniformity in the illuminating light quantity within the monitoring area is present, a stable detection capacity can be obtained over the whole picture plane.

Description

[Detailed Description of the Invention] (Technical Field) The present invention relates to an abnormality monitoring device that uses hue values as image data to have the same detection ability in bright areas and dark areas. It is suitable for monitoring the occurrence of an abnormality in a monitoring area including a part.

(Background Art) Generally, current abnormality monitoring devices for intruder detection, crime prevention, and the like employ a method of detecting changes in brightness within a monitoring area using a black and white television camera. Figure 4(a)
(b) is a diagram for explaining the operation of the conventional example, and shows an input image captured by the conventional abnormality monitoring device. FIG. 4(a) is an example of an image showing a person in front of a building, and sunlight is shining from the right front. Furthermore, FIG. 4(b) shows a person hiding behind a building. This figure 4(a)
As can be seen by comparing (b), there is a large difference in detection ability between the detection object in the bright area of the monitoring area ((a) in the same figure) and the case in the dark area ((b) in the same figure). The problem is that there are differences.

In particular, as an image processing method in such a system, the brightness difference between the input image and the reference image is determined for each pixel,
Generally, the number of pixels whose brightness difference exceeds a predetermined threshold is counted, and an abnormality is determined based on the size of this counted value. However, in dark areas, the contrast is low and the difference from the reference image becomes small, making it difficult to detect objects. The image processing exemplified above is a type of binarization processing, but even when using other methods such as gradation processing such as differentiation, the differential value also depends on the contrast, so the detection ability in dark areas may be affected. There is a similar problem of inferiority compared to the department.

(Object of the Invention) The present invention has been made to solve the above-mentioned problems, and its purpose is to reduce changes in detection ability due to differences in local illumination light intensity in a monitoring area. The goal is to provide an abnormality monitoring device. .

(Disclosure of the Invention) In the abnormality monitoring device according to the present invention, as shown in FIG. tpi1 and FIG. An image processing means 2 that compares the obtained image with a reference image to obtain information necessary for abnormality determination, an abnormality determination means 3 that determines abnormality based on the information obtained by the image processing means rX2, and outputs the determination result. In the abnormality monitoring device, the image input means 1 includes a color image capturing means 11 such as a color television camera, and a color image signal obtained by the color image capturing means 11, in which the image input means 1 extracts only the hue. It includes a hue extraction means 12 for inputting to the image processing means 2.

In the present invention, only the hue is extracted as image data, so whether the detected object is in a bright area or a dark area, as illustrated in FIGS. It is possible to exhibit similar detection ability, and the change in detection ability due to differences in the amount of illumination light in the monitoring area is reduced.

Preferred embodiments of the present invention will be described below with reference to the accompanying drawings. FIG. 1 is a block diagram showing a schematic configuration of an abnormality monitoring device according to an embodiment of the present invention.

Color image capturing means 11-3 consisting of a color television camera
Book color signal output (R: Red, G: Green, B: B
lue) is input to the hue extraction means 12, and the hue is determined. Hue here means G/R, R/(R+G+B)
It is a numerical value representing the color itself, which does not depend on the amount of light, and can be expressed by a formula such as , or G/(R+G+B). The output of this hue extraction means 12 is input to the abnormality monitoring device main body 5,
Conventional processing is performed as described below.

FIG. 2 is a block diagram showing an example of the internal configuration of the abnormality monitoring device main body 5. The image processing means 2 includes an input image memory 21 and a reference image memory 22. As shown in FIG. Reference image memory 2
2 stores image data in which images of the monitoring area when there is no abnormality are taken in as reference images at regular update intervals. The input image memory 21 stores hue images of the current monitoring area that are taken in from the image input means 1 every moment. The absolute difference circuit 23 subtracts the luminance data of both image memories 21 and 22 between pixels to convert it into an absolute value. The binarization circuit 24 binarizes the output of the absolute difference circuit 23 using an appropriate threshold value. As a result, an image consisting only of pixels whose brightness has changed by a predetermined threshold value or more between the current image and the reference image is obtained. The abnormality determination means 3 receives the binarized signal obtained by the binarization circuit 24 and detects an abnormality from this signal. For abnormality detection, for example, a method can be used in which the signals obtained from the binarization circuit 24 are counted, and if the count exceeds a certain value, it is determined that an abnormality has occurred. Further, as a method for more advanced abnormality determination, a method having an inference function based on artificial intelligence can also be used. The output means 4 outputs a message to that effect when an abnormality is detected, and outputs a message to that effect on a monitor television,
Various types of printers, alarm lamps, alarm buzzers, etc. can be employed.

In the present invention, a hue signal is used as the image signal input to the main body 5 of the abnormality monitoring device, instead of an image signal from a black and white television camera. The calculation in the hue extraction unit p'i12 may be performed in analog or digital form, but ultimately it is input to the input image memory 21 of the image processing means 2 as a digital signal. An example of image input of the monitoring area using this hue signal is shown in Fig. 3(a).
Shown in (b). The scenes shown in Figures 3(a) and (b) are
This corresponds to the case shown in FIG. 4(,)(b). Since it is a hue-only image, there is no effect of the shadow of the building, and parts of the building that have the same hue have the same value. The contrast of the detected object is also constant even under conditions where uneven illumination exists. In this way, it is possible to make the detection capability of the abnormality monitoring device substantially uniform over the entire monitoring area. Strictly speaking, the hue under direct sunlight and the hue in the shade where there is no direct sunlight and only receives scattered light from the surroundings are slightly different, but there is still a difference in brightness of more than an order of magnitude under the same conditions. The detection ability can be sufficiently stabilized compared to those using general black and white images.

(Effects of the Invention) In the present invention, as described above, since abnormality monitoring is performed using image data consisting only of hue, for example, areas of a building that are exposed to direct sunlight and areas that are in the shade, etc. Another advantage is that even if there is unevenness in the amount of illumination within the monitoring area, stable detection ability can be obtained over the entire screen.

In addition, as stated in the description of the examples, the present invention
This is particularly suitable when using a configuration in which the reference image is updated in the image processing means.

That is, according to the present invention, since the input image is stable even if the amount of illumination light changes, the frequency of updating the reference image can be reduced.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing a schematic configuration of an abnormality monitoring device according to an embodiment of the present invention, FIG. 2 is a block diagram showing a schematic configuration of an abnormality monitoring device main body in the same embodiment, and FIG.
FIGS. 4A and 4B are explanatory diagrams for explaining the operating state of the same embodiment as described above, and FIGS. 4A and 4B are explanatory diagrams for explaining the operating state of the conventional example. 1 is an image input means, 2 is an image processing means, 3 is an abnormality determination means, 4 is an output means, 11 is a color image capturing means, and 12 is a hue extraction means. First drawing image input means 1 FIG. 2 Image processing means 2 FIG. 3 (G)

Claims (1)

[Claims] (1) an image input means that images a monitoring area and quantizes an image signal; an image processing means that compares the image obtained by the image input means with a reference image and obtains information necessary for abnormality determination;
In an abnormality monitoring device including an abnormality determination means for determining an abnormality based on information obtained by the image processing means and an output means for outputting the determination result, the image input means may be a color image capturing means such as a color television camera. 1. An abnormality monitoring device comprising: a hue extracting means for extracting only hue from a color image signal obtained by a color image capturing means and inputting the extracted hue to an image processing means.