JP2002218443A - Intruding object detecting method for automatically determining threshold for intruding object detection and intruding object monitor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an intruding object detecting method, an intruding object detection parameter setting method and an intruding object recognizing device which are highly reliable by making it possible to easily set an intruding object detection threshold even when the illumination and time period of a monitoring visual field area, a lens diaphragm, etc., are changed without needing skillfulness in setting work of the intruding object detection threshold. SOLUTION: This intruding object detecting method is to be provided with a differential processing step for calculating the difference of luminance value of each pixel between an input image inputted sequentially from an image pickup device and a reference background image, a binarization step for comparing the difference with a prescribed binarization threshold, a binarization threshold increasing step for increasing the binarization threshold, a detected pixel deciding step for deciding the reduction degree of pixels to be difference being equal to or larger than the binarization threshold by increasing the binarization threshold, and an intruding object detection threshold deciding step for deciding the intruding object detection threshold based on the decision results of the detected pixel deciding step so as to be able to detect an intruding object within the visual field of the image pickup device.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a monitoring apparatus using an image pickup apparatus, and more particularly to a method for detecting an intruding object in an image pickup field by a difference in luminance value between an input image from the image pickup apparatus and a reference background image for each pixel. The present invention relates to an intruding object detection method and an intruding object monitoring device that detects an intruding object detection threshold based on an area of a pixel that is equal to or larger than an intruding object detection threshold. The present invention relates to an intruding object detection method and an intruding object monitoring device which are determined as follows.

[0002]

2. Description of the Related Art In recent years, an intruding object detecting device using an image pickup device such as a camera as an image input means has not been conventionally used for manned monitoring by an observer, but automatically detects an intruding object in a monitoring field of view. In many cases, the type of the object is automatically confirmed, and a predetermined notification or alarm is automatically obtained. In order to realize such a system, first, processing for detecting a predetermined intruding object from an input image obtained by an image input unit such as a camera is required. As a method of realizing such processing, for example, an input image is compared with a reference background image (that is, an image in which an object to be detected is not captured), a difference is obtained for each pixel, and an area having a large difference is determined. There is a method of extracting as an object. This method is called a difference method and has been widely used conventionally.

The processing of the difference method will be described with reference to FIG.
FIG. 12 is a diagram for explaining the processing principle of object detection in the difference method. 1201 is an input image, 1202 is a reference background image, 1203 is a difference image, 1204 is a binarized image of the difference image 1203, 1205 is a subtractor, 1206 is a binarizer, and 1207 is a humanoid image of the input image 1201. Object area, 1208 is difference image
A difference region where a difference occurs in 1203, and 1209 is a binarized image
This is the binarized region extracted in 4.

In FIG. 12, a subtractor 1205 outputs an input image.
A difference between the luminance value of the reference background image 1202 and the luminance value of the reference background image 1202 is calculated for each pixel, and a difference image 1203 is output. Binarizer 1206
Is the luminance value (difference value) for each pixel for the difference image 1203
Is “0” when the pixel value of a pixel is less than a predetermined threshold value Th (difference value <Th), and “255” (the luminance value of one pixel) Is calculated with 8 bits) to obtain a binarized image 1204. Here, for example, the threshold value Th is set to “20”. As a result, a humanoid object 1207 shown in the input image 1201 is obtained.
Is calculated by the subtractor 1205 to calculate the area 1208 where the difference has occurred, and further by the binarizer 1206 to obtain the luminance value “255”.
The lump image 1209 is detected as an intruding object.

An example of an intruding object recognition method using this method will be described with reference to FIG. FIG. 13 is a flowchart showing the operation of the intruding object detection program for executing the intruding object detecting method. In the image input step 111, for example, a 320 pix width
, An input image 1201 having a height of 240 pix and 8 bits / pix is obtained, and the process proceeds to step 112. In the difference processing step 112, a difference for each pixel between the input image 1201 and the reference background image 1202 is obtained to obtain a difference image 1203, and the process proceeds to step 113. In the binarization processing step 113, the obtained difference image 1203 is converted to “255” for pixels that are equal to or larger than the intruding object detection threshold based on a predetermined binarization threshold, and for pixels that are smaller than the intruding object detection threshold. The binary image 1204 is acquired as "0", and the process proceeds to step 114.

In the intruding object detection processing step 114, for example, a cluster of pixels having a pixel value of "255" in the binary image 1204 is detected by the labeling method, and this is set as an intruding object, and the process proceeds to step 115. In the intruding object determination step 115, an intruding object detection processing step 114
If an intruding object is detected in step, the process proceeds to step 116, and if no intruding object is detected, the process returns to image input step 111. In the alarm / monitor display step 116, for example, the image output I / F (hereinafter, interface
The processing result is displayed on a monitor 1113 via an I / F 1110, or a warning lamp 1112 is turned on via an output I / F 1109, for example. Therefore, the intruding object detection method using the difference method compares the input image with the reference background image, obtains a difference for each pixel, and detects an area having a large difference as an object. As an object detection method to which the difference method is applied, for example, there is JP-A-79429 / 1995.

The above-described intruding object detection method detects an intruding object by comparing a difference between each pixel between an input image and a reference background image with a preset intruding object detection threshold value. If this intruding object detection threshold is set to a small value,
There is a possibility that a moving object other than the intruding object, such as noise (noise generated inside the image pickup apparatus or noise superimposed in the process of transmitting a video signal) other than the intruding object, or shaking trees, may be erroneously detected. On the other hand, if the intruding object detection threshold is set to a large value, it becomes impossible to detect pixels having a luminance value close to the reference background image in the pixels constituting the intruding object,
Oversight of intruding objects can occur. Therefore,
The detection performance of an intruding object largely depends on the intruding object detection threshold. However, it is necessary to set the threshold value for detecting an intruding object in accordance with the illuminance of the monitoring visual field, the time zone, the aperture of the lens, and the like, and the setting operation is complicated and requires skill.

[0008]

The above-mentioned prior art includes the following:
When detecting an intruding object using the difference method, it is important to set the threshold value of the intruding object detection threshold, but this setting work depends on the illuminance, time zone, lens aperture, etc. of the monitoring visual field area. It had to be performed every time it changed, which was complicated. In addition, an intruding object detection threshold that can remove noise other than an intruding object from an input image obtained from an imaging device, and an intruding object detection threshold by detecting a reference intruding object captured in an imaging field of view. Is calculated automatically,
Setting the threshold value for detecting an intruding object has a disadvantage that skill is required. An object of the present invention is to eliminate the above-mentioned disadvantages, does not require skill in setting the intruding object detection threshold value, even when the illuminance and time zone of the monitoring visual field area, the aperture of the lens, etc. are changed. It is an object of the present invention to provide a highly reliable intruding object detecting method and an intruding object recognizing device that can easily set an intruding object detecting threshold value.

[0009]

SUMMARY OF THE INVENTION It is an object of the present invention to eliminate the above-mentioned disadvantages and to detect a binarized image when a binarization threshold for binarizing a difference image is increased. An object of the present invention is to provide a highly reliable intruding object detection device by determining an intruding object detection threshold based on a change in a pixel and accurately detecting an intruding object.

To achieve the above object, a method for setting an intruding object detection parameter according to the present invention is directed to a surveillance method for detecting an intruding object in a surveillance visual field by applying an image obtained from an imaging device to a difference method. A first difference image of a luminance value between a first input image from the imaging device and a reference background image stored in a storage device is generated, and the first difference image is generated using a predetermined binarization threshold. While performing the binarization processing, the binarization threshold is changed until the noise level of the binarized image is equal to or less than a predetermined value, and the noise level of the binarized image is reduced to a predetermined value or less. A threshold value for detecting an intruding object, wherein the threshold value for detecting an intruding object is determined based on the first binarizing threshold value. It is determined automatically.

Further, the method for setting an intruding object detection parameter according to the present invention is characterized in that the change of the binarization threshold is changed in an isometric, an isometric or a random manner. In the method for setting an intruding object detection parameter according to the present invention, the binarization threshold is increased. Also,
The method for setting an intruding object detection parameter according to the present invention is characterized in that the binarization threshold is reduced. In the method for setting an intruding object detection parameter according to the present invention, the first input image is an image having no intruding object.

Further, the method for setting an intruding object detection parameter according to the present invention further comprises a luminance value between the second input image including the invading human body from the imaging device and the reference background image stored in the storage device. The second difference image is generated, and the second difference image is binarized with a predetermined binarization threshold, and the size of the intruding object of the binarized image is equal to or smaller than a predetermined size. The binarization threshold is changed until becomes, and the binarization threshold at which the size of the intruding object of the binarized image is equal to or smaller than a predetermined size is set as a second binarization threshold, The method includes the first and second binarization thresholds, sets a third binarization threshold between the first and second binarization thresholds, and sets the third binarization threshold. The intruder is detected based on the value.

Further, in the method for setting an intruding object detection parameter according to the present invention, when the first and second threshold values are set, the change of the binarization threshold value is changed in an isometric, isometric or random manner. It is characterized by. In the method for setting an intruding object detection parameter according to the present invention, the binarization threshold is increased. In the method for setting an intruding object detection parameter according to the present invention, the binarization threshold is reduced. Further, the method for setting an intruding object detection parameter according to the present invention is characterized in that a predetermined size of the intruding object is represented by a circumscribed figure of the intruding object.

In the method for setting an intruding object detection parameter according to the present invention, first and third binarization thresholds respectively obtained from the first input image and the second input image are recorded. Executing the binarization process for a predetermined number of frames, recording the respective binarization thresholds, and selecting predetermined first and second binarization thresholds from the plurality of recorded binarization thresholds. Determine the value. Further, in the method for setting an intruding object detection parameter according to the present invention, the first binarization threshold value determines a maximum binarization threshold value, and
Is characterized in that the minimum binarization threshold value is determined. Further, in the intruding object detection parameter setting method according to the present invention, the binarization processing of the first difference image with a predetermined binarization threshold further includes providing a dead zone, and providing the dead zone in the provided dead zone. It is characterized in that no binarization processing is performed. Further, the intruding object detection parameter setting method of the present invention further obtains a difference between the first and second binarization thresholds, and a difference between the first and second binarization thresholds is equal to or less than a predetermined value. In the case of (1), there is a step of determining an abnormality.

Further, the intruding object monitoring device of the present invention is a first intruding object monitoring device for detecting an intruding object in a monitoring visual field from an image obtained from an imaging device by applying a difference method.
An imaging device that outputs an input image of the first input device, a first storage device that stores a reference background image, and a processing unit that generates a first difference image of a luminance value between the first input image and the reference background image. Performing a binarization process on the first difference image with a predetermined binarization threshold, and changing the binarization threshold until the noise component of the binarized image becomes a predetermined value or less; A first binarization processing unit that outputs a binarization threshold value at which a noise component of the binarized image is equal to or less than a predetermined value as a first binarization threshold value; A detection processing unit that detects an intruding object based on the binarization threshold.

Further, the imaging device of the intruding object monitoring device according to the present invention outputs a second input image including the intruding object,
The imaging device further includes the second input image and the first input image.
A processing unit for generating a second difference image of a luminance value with respect to the reference background image stored in the storage device, and performing a binarization process on the second difference image with a predetermined binarization threshold value ,
The binarization threshold is changed until the size of the intruding object of the binarized image is equal to or smaller than a predetermined size, and the size of the intruding object of the binarized image is equal to or smaller than a predetermined size. A second binarization processing unit for outputting a binarization threshold value as a second binarization threshold value;
A threshold setting unit for setting a third binarization threshold between the first and second binarization thresholds; The processing unit is for detecting an intruding object based on the second binarization threshold.

[0017]

Embodiments of the present invention will be described below with reference to the drawings. In the drawings, similar components are denoted by similar reference numerals. First, the principle of the present invention will be described with reference to FIG. FIG. 14 is a diagram illustrating a change in a binarized image for explaining a process of determining a binarized threshold. In FIG. 14, reference numerals 140 to 148 denote luminance values for each pixel of the same input image in which an intruding object (in this case, “person”) is captured from the imaging device and a reference background image in which no intruding object is captured. The binarized image generated by taking the difference of the binarization thresholds th is set to th = 5, 10,
The binarized image when increasing to 15, 20, 25, 30, 35, 40 is shown. Reference numeral 1400 denotes a noise image included in the binarized image 140, and reference numeral 1401 denotes an image of an intruding object. When the binarization threshold is increased from the initial value th = 5, the noise image gradually disappears, and at th = 25, the noise disappears. The binarization threshold at this time is defined as a first threshold Th1. When the binarization threshold is further increased, the size of the intruding object gradually decreases, and at th = 35, the intruding object is detected at the predetermined size. Shrink to less than. Let the binarization threshold at th = 35 be the second threshold Th2. Therefore, in order to completely remove noise and detect an intruding object without overlooking it, the intruding object detection threshold is set to the first threshold.
What is necessary is just to select a threshold value between Th1 and the second threshold value Th2. Although the first threshold value Th1 is a binarized threshold value at which noise completely disappears, it may be a threshold value at which a cluster of a predetermined number or more of pixels has disappeared, as described later. In the above description, the threshold value was increased from the initial value as the binarization threshold.
Needless to say, it can be reduced.

Next, an embodiment of an intruding object monitoring apparatus according to the present invention will be described. FIG. 11 is a block diagram showing the configuration of the intruding object monitoring device of the present invention. 1101 is a television camera (hereinafter referred to as TV camera), 1102 is an input device, 1103
Is an image input interface 1104 is an input interface, 1105 is an image memory, 1106 is a work memory, and 1107 is a CPU (Central P
1108 is a program memory, 1109 is an output I / F, 1110 is an image output I / F, 1112 is a warning light, 1113 is a monitor, and 1111 is a data bus.

In FIG. 11, a TV camera 1101 is connected to an image input I / F 1103, and an input device 1102 is connected to an input I / F.
The warning light 1112 is connected to the output I / F 1109, and the monitor 1113 is connected to the image output I / F 1110. In addition, image input I / F1103, input I / F1104,
Image memory 1105, work memory 1106, CPU 1107, program memory 1108, output I / F 1109 and image output I
/ F 1110 is coupled to data bus 1111.

In FIG. 11, a TV camera 1101 picks up an image in the field of view including the monitoring target area. TV camera
1101 converts the captured video into an electrical video signal (for example, N
TSC video signal) and convert the converted video signal to image input
Give to I / F 1103. The image input I / F 1103 converts the input video signal into image data in a format (for example, 320 pix width, 240 pix height, 8 bit / pix) that is handled by the intruding object monitoring device, and transmits the data via the data bus 1111. Image memory
Give to 1105. The image memory 1105 stores the sent image data. The input device 1102 detects at least one input operation of a specific operation such as a voice or a gesture of a human or an auxiliary animal, an input by an external input device such as a button, a keyboard, a mouse, etc., and detects an operation signal (for example, RS-232C).
Then, the converted operation signal is supplied to the input I / F 1104.

The input I / F 1104 is a format for handling the input operation signal by the intruding object monitoring device (for example, operations of up, down, left, right, and button press are “1”, “2”, respectively).
), "3", "4", "5") and give the converted operation data to the work memory 1106 via the data bus 1111. As the format, for example, RS-232C is used. Work memory may be used
1106 stores the input operation data. CPU 1107
Analyzes the image stored in the image memory 1105 in the work memory 1106 according to the program stored in the program memory 1108. As a result of the above analysis, TV
Information such as whether an intruding object has entered the imaging field of view of the camera 1101 is obtained.

The CPU 1107 supplies a video signal to the monitor 1112 via the image output I / F 1110, and displays, for example, a processing result image. At the same time, the CPU 1107 outputs the output I / F
A control signal for turning on the warning light 1112 via 1109 is given to the warning light 1112. The warning light 1112 is turned on by the input control signal. The image output I / F 1110 converts the video signal from the CPU 1107 into a format (for example, an NTSC video signal) that can be used by the monitoring monitor 1113, and
Send to 3. The monitor 1113 displays, for example, an intruding object detection result image.

FIG. 2 is an example of a flowchart showing the operation of the first embodiment of the present invention. This flowchart is executed by using, for example, the intruding object monitoring device of FIG. 11 described above. In this embodiment, a first intruding object detection threshold determining step 101 and a second intruding object detecting threshold determining step are performed before the image input step 111 of the intruding object detection flowchart according to the prior art shown in FIG. 103 and an intruding object detection threshold value selection step 201 are added.

In FIG. 2, in a first intruding object detection threshold value determining step 101, a threshold value for binarizing a difference image is detected as a binarized image when the binarization threshold is increased. This is a step of determining an intruding object detection threshold based on a noise level having a luminance value of 255 ”(hereinafter, this is referred to as the number of pixel clusters). The first intruding object detection threshold value determining step 101 will be described with reference to FIG.

FIG. 4 is an example of a flowchart for explaining the operation of the first intruding object detection threshold value determining step 101 in FIG. The reference background image 1202 is stored in the image memory 1105 in advance. In FIG. 4, in the image selection step 401, an image in which there is no intruding object to be detected in the monitoring visual field is selected. This process
For example, while watching the image captured by the TV camera 1101 on the screen of the monitor 1113, the observer determines whether or not there is an intruding object to be detected in the monitoring visual field, and uses the input device 1102 to intrude. The object monitoring device is notified that there is no intruding object to be detected, and it is determined that an appropriate image has been selected by the notification.
Move to 02. Next, in the image input step 402,
As in the image input step 111, for example, width 320 pix
Get an input image, 240 pix high, 8 bit / pix.
In the difference processing step 403, similarly to the difference processing step 112, a difference for each pixel between the input image 1201 and the reference background image 1202 is obtained, and a difference image 1203 is obtained (see FIG. 12). In the binarization threshold value initialization step 404, the binarization threshold value Th is initialized to, for example, Th = 1.

In the binarization processing and display step 405,
The difference image 1203 obtained in the difference processing step 403 is binarized based on the binarization threshold Th set at that time, and the pixel value in the difference image 1203 is changed to the binarization threshold T.
h is set to “255” and the binarization threshold Th
Pixels that are less than “0” are set to “0” and a binarized image 1204 is acquired. Also, the binarization threshold and the acquired binarized image at this time are displayed on the screen of the monitor 1113. Next, in the object detection processing step 406, a cluster of pixels having a pixel value “255” (referred to as a detected object) in the binarized image 1204 is detected, and the number thereof is counted. For example, in this processing, a cluster of pixels is a predetermined area (for example, 10 pixels).
The number of clusters of pixels described above may be counted.

In the number-of-detected-objects determination step 407, if the number of clusters of pixels detected in the object detection processing step 406 is 0, the flow branches to a first intruding object detection threshold value determination and display step 408. If the value is 1 or more, the flow branches to the binarization threshold value increasing step 409. First intruding object detection threshold determination and display step
In 408, the value of the binarization threshold Th used in the binarization processing step 405 is determined as the first intruding object detection threshold Th1, and the first threshold candidate mark is set as described later.
806a is displayed on the monitor 1113, and the first intruding object detection threshold value determining step 101 of FIG. 2 is ended, and the process proceeds to the second intruding object detection threshold value determining step 103. In addition, in the binarization threshold increasing step 409, the binarization threshold is increased by one, and the process proceeds to the binarization processing step 405.

In the above description, the image selection step
In 401, an image in which there is no intruding object to be detected in the monitoring visual field area is selected.For example, an image in which one or more intruding objects exist may be selected. In step 407, when the number of detected objects detected in the object detection processing step 406 is the number of intruding objects appearing in the selected video, the first intruding object detection threshold value determining and displaying step is performed.
Branch to 408. Also, in a binarization threshold initialization step 404, the binarization threshold Th is set to Th.
= 1, but the value to be initialized may be set freely according to the condition of the monitoring visual field area. Further, in the binarization threshold increase step 409, the binarization threshold is increased by one, but it is obvious that the threshold may be other than one. , Or may be increased in a random manner.

Next, in a second intruding object detection threshold value determination step 103, "255" is detected in the binarized image when the binarization threshold for binarizing the difference image is increased.
This is a step of determining an intruding object detection threshold value based on a change in the size of a cluster of pixels having a luminance value of. The second intruding object detection threshold value determination step 103 will be described with reference to FIG.

FIG. 5 is an example of a flowchart for explaining the operation of the second intruding object detection threshold value determining step 103 in FIG. FIG. 5 shows the image selection step of FIG.
Instead of 401, a binarization threshold value initialization step 404, a detection object number determination step 407, a first intrusion object detection threshold value determination and display step 408, and a binarization threshold increase step 409, Image selection step 501
Using a binarization threshold initialization step 504, a detected object size determination step 507, a second intruding object detection threshold determination and display step 508, and a binarization threshold increase step 509 It is. The other steps are the same as those in FIG.

In FIG. 5, in an image selection step 501, an image in which a reference intruding object serving as a reference for determining an intruding object detection threshold value is selected in the monitoring visual field is selected. The reference intruding object is a person when the intruding object monitoring device is used for monitoring an intruder, and a vehicle when the intruding object monitoring device is used for monitoring a vehicle. In this process, for example, in the same manner as in the case of FIG. 4, the observer determines whether or not the video includes the reference intruding object in the monitoring visual field, and uses the input device 1102 to enter the intruding object monitoring device. It is assumed that an object is shown and an appropriate image is selected by the notification. Subsequently, the processing of the image input step 402 and the difference processing step 403 is performed, and the process proceeds to step 504.

In a binarization threshold value initializing step 504, the binarization threshold value is initialized to, for example, a first intruding object detection threshold value Th1, followed by a binarization processing and display step 405 and an object detection. The processing of the processing step 406 is performed, and the process proceeds to step 507.

Subsequently, a detection object size determination step 507
Then, it is determined whether the size of the circumscribed rectangle of the largest detected object is equal to or smaller than a predetermined value. Here, the predetermined value is a size regarded as an intruding object to be detected. For example, a 1/2 type CCD (element size: width dx = 6.5 mm, height dy)
= 4.6 mm), f = 25 mm lens, distance from camera to surveillance area L = 50 m, input image size: width X0 =
When monitoring with 320 pix and height Y0 = 240 pix, the intruding object to be detected is width w0 = 1 m and height h0 = 1.
Assuming 5 m, the following equation (1) is obtained.

(Equation 1) The size of the circumscribed rectangle of the sensing object (width w, height h) is w
When ≤ W0 and h ≤ H0, it is determined to be less than a predetermined value.

In the detection object size determination step 507,
If the size of the circumscribed rectangle of the largest detected object is smaller than a predetermined value, the process branches to the second intruding object detection threshold value determination and display step 508, and if the size is larger than the predetermined value, the binary threshold value is set. Branch to increment step 509.

In the second intruding object detection threshold value determination and display step 508, a value obtained by subtracting 1 from the binary threshold value Th used in the binary processing step 405 (the binary threshold value)
A threshold value immediately before Th, that is, a binary threshold value obtained by reducing the increment in the binary threshold value increasing step 509) is determined as a second intruding object detection threshold value Th2. As will be described later, a second threshold candidate mark 807a representing the determined second intruding object detection threshold is monitored by the monitor 111.
3 Displayed above (FIG. 8), and the second intruding object threshold value determining step 103 in FIG. Further, in the binarization threshold value increasing step 509, the binarization threshold value is increased by 1, and the process proceeds to the binarization processing step 405. In the above description, the step width of the increase of the binarization threshold is set to 1, but is not limited to this, and may be set to 2 or more.
As described above, the step width may be increased in an equal manner, may be increased in an equal ratio, or may be increased in a random manner.

Subsequently, in FIG. 2, in an intruding object detection threshold value selecting step 201, the values are obtained in a first intruding object detection threshold value determining step 101 and a second intruding object detection threshold value determining step 103. The threshold between the first intruding object detection threshold Th1 and the second intruding object detection threshold Th2 is defined as the intruding object detection threshold. That is, the intruding object detection threshold Th is determined as follows. Th1 ≦ Th ≦ Th2 Equation (2) This processing is performed, for example, using the input device 1102 by the observer using either the first intruding object detection threshold Th1 or the second intruding object detection threshold Th2. This is done by selecting Incidentally, the intruding object detection threshold value determination step 103
Determining at least one threshold value Th3 (for example, the average value of Th1 and Th2) between the first intruding object detection threshold Th1 and the second intruding object detection threshold Th2 before In step 201, any one of the intruding object detection thresholds Th1, Th2, and Th3 may be selected.

Here, the first intruding object detection threshold value Th1
The relationship between the threshold value Th2 and the second intruding object detection threshold Th2 will be described with reference to FIG. FIG. 10 shows a difference level 1002 of noise detected by the difference method (noise generated inside the image pickup apparatus or noise superimposed in a process of transmitting a video signal).
And a level 1001 of the difference between the intruding object and the intruding object (the moving object other than the intruding object will be described later).

As shown in FIG. 10, in a first intruding object detection threshold value determining step 101, a first intruding object detection threshold value T is determined using an image in which an intruding object to be detected is not captured.
Since h1 was determined (or using an image with one or more intruding objects), the noise difference level 1002 was
Becomes smaller than the intruding object detection threshold value 1004 (Th1), and in the second intruding object detection threshold value determination step 102, the binarization threshold of the limit for detecting the reference intruding object is detected by the second intruding object detection. Since the threshold value Th2 is determined, the difference level 1001 of the intruding object is set to the second intruding object detection threshold 1
006 (Th2). That is, by selecting any one of the first intruding object detection threshold Th1 and the second intruding object detection threshold Th2 as the intruding object detection threshold, erroneous detection of noise is prevented, and An intruding object detection threshold value that can detect an intruding object can be set.

Returning to FIG. 2, in the image input step 111 following the step 201, the TV camera 1101
An input image having a width of 320 pix, a height of 240 pix, and 8 bits / pix is obtained, and the process proceeds to step 112. Difference processing step 112
Then, a difference image between the input image and the reference background image is obtained by obtaining the difference between the luminance values for each pixel, and the process proceeds to step 113. In the binarization processing step 113, the obtained difference image is determined based on the intruding object detection threshold value selected in step 201 as “255” for pixels that are equal to or larger than the intruding object detection threshold value, and The pixel is set to "0" to obtain a binary image, and the process proceeds to step 114 '. In the intruding object detection processing step 114 ', for example, a cluster of pixels having the pixel value "255" is detected in the binary image by a well-known labeling method, and the process proceeds to step 115'. In the intruding object determination step 115 ', the intruding object detection processing step 11
If the size of the circumscribed figure of the intruding object detected in 4 'is, for example, the circumscribed rectangle is equal to or larger than a predetermined size, it is determined that the intruding object has been detected, and the process proceeds to step 116. If the size of the circumscribed rectangle of the intruding object is smaller than the predetermined size, it is determined that the intruding object has not been detected, and the process returns to the image input step 111. Note that the predetermined size is calculated by the above-described equation (1). In the alarm / monitor display step 116, for example, the processing result is displayed on the monitor 1113 via the image output I / F 1110, and a warning or the like is turned on via the output I / F 1109, for example. Therefore, according to the present embodiment, the first intruding object detection threshold Th1 and the second intruding object detection threshold Th2 are determined from the input image obtained by the imaging device,
By selecting any one of them, the threshold value for detecting an intruding object can be easily set, and an intruding object in the visual field of the imaging device can be detected.

FIG. 3 is an example of a flowchart showing the processing operation of the second embodiment of the present invention. In the second embodiment, at least one candidate of a first intruding object detection threshold and a second candidate of a second intruding object detection threshold are recorded, and the first intruding object detection is performed based on each candidate. The threshold value and the second intruding object detection threshold value are determined. FIG. 3 is a flow chart shown in FIG. 2 in which a first intruding object detection threshold recording step 102, a second intruding object detection threshold recording step 104, a predetermined frame end determination step 105, And a second intruding object detection threshold value selecting step 107 are added. The other steps are the same as those in the flowchart shown in FIG.

In FIG. 3, as described with reference to FIG. 2, the process of the first intruding object detection threshold value determining step 101 is performed, and the process proceeds to step 102. In a first intruding object detection threshold recording step 102, the first intruding object detection threshold Th1 obtained in the first intruding object detection threshold determining step 101 is changed to a first intruding object detection threshold. It is recorded in the work memory 1106 as a candidate.

Next, also in step 103, as described with reference to FIG. 2, the process of the second intruding object detection threshold value determining step 103 is performed, and the process proceeds to step 104. In the second intruding object detection threshold recording step 104, the second intruding object detection threshold Th2 obtained in the second intruding object detection threshold determining step 103 is changed to the second intruding object detection threshold. It is recorded in the work memory 1106 as a candidate.

Subsequently, predetermined frame end determination step 1
In step 05, it is determined whether or not a predetermined number of intruder detection thresholds have been obtained for a predetermined number of frames. If a predetermined number of frames (for example, 5) have been obtained, the first intruder detection threshold is determined. The flow branches to the selection step 106, and if not obtained, the flow branches to the first intruding object detection threshold recording step 101.

First intruding object detection threshold selection step
At 106, the largest value among the first intruder detection threshold candidates recorded in the work memory 1106 is selected as the first intruder detection threshold. In the second intruding object detection threshold selection step 107, the work memory 1106
Is selected as the second intruding object detection threshold value among the second intruding object detection threshold candidates recorded in. Therefore, according to the present embodiment, since the largest value among the obtained candidates for the first intruding object detection threshold value is used as the first intruding object detection threshold value, noise can be reliably removed. (The highest noise difference level can be removed), and the smallest value among the obtained candidates for the second intruding object detection threshold value is set as the second intruding object detection threshold value. Therefore, the intruding object can be reliably detected (the lowest difference level of the intruding object can also be detected), and the reliability of the intruding object recognition device can be improved. In this embodiment, a plurality of candidates are prepared for only one of the first and second intruding object detection thresholds, and for the other, as in FIG. It may be modified so as to be determined.

FIGS. 6 and 7 are an example of a flowchart showing a third embodiment of the present invention. This third embodiment is:
Providing a dead zone at the time of determining the first intruding object detection threshold,
At the time of determining the second intruding object detection threshold value, the region where the intruding object exists is designated, and, for example, the processing shown in the flowchart of FIG. Is performed according to the flowchart of FIG. 6, and a second intruding object detection threshold value determining step is performed.
The processing of step 103 is performed according to the flowchart of FIG. FIG. 6 is a flowchart shown in FIG. 4, in which a dead zone setting step is performed between step 401 and step 402.
601 is added, and another binarization processing step 602 is used in place of the binarization processing step 405. FIG.
Is the flowchart shown in FIG.
Between step and step 403
701 is added, and another detection object size determination step 702 is used in place of the detection object size determination step 507.

In FIG. 6, as described with reference to FIG. 4, the process of the image selection step 401 is performed, and the process proceeds to step 601. In the dead zone setting step 601, a moving object other than an intruding object to be detected, such as a sway of trees, is set as a dead zone so that the noise difference level is detected more accurately. This will be described with reference to FIG. Figure 9 shows the input image 9
01 is an example in which a tree 903 and grass 904a, 904b, 904c are shown.

At this point, the observer operates the input device 1102 to move the position indicating mark 908 reflected on the monitor 1113.
Specify 906. The designated area becomes a dead zone, and pixels in the dead zone are not used for determining the first intruding object detection threshold. Next, the processing operation from step 402 to step 404 is performed, and the process proceeds to step 602.

In the binarization processing step 602, the pixel whose difference value is equal to or larger than the binarization threshold and which is not a dead zone is set to "255",
A binarized image in which the rest is "0" is created. A moving object other than an intruding object to be detected, such as a tree sway, has a difference level larger than the noise difference level, as shown in FIG. Therefore, by setting the dead zone, a more accurate noise difference level can be detected.

Next, in FIG. 7, as described with reference to FIG. 5, the processing of the video selection step 501 and the image input step 402 is performed, and the flow advances to step 701. In the reference intruding object area setting step 701, the area (circumscribed rectangle) of the reference intruding object is specified. This will be described with reference to FIG. In FIG. 9, a reference intruding object 902 is shown in an input image 901, and a monitor operates the input device 1102 to display a monitor 1.
By moving the position indication mark 908 shown in 113, the area 907 of the reference intruding object is designated by, for example, a rectangle. It is obvious that the area of the reference intruding object is not limited to the circumscribed rectangle, but any circumscribed figure can be used. Next, the processing operation from step 403 to step 406 is performed, and the process proceeds to step 702.

In the detected object size determination step 702,
When the size of the detected object detected in the reference intruding object area 907 specified in the reference intruding object area setting step 701 becomes smaller than a predetermined ratio of the reference intruding object area 907,
The flow branches to a second intruding object detection threshold value determination step 508, and if the ratio is equal to or more than a predetermined ratio, the flow branches to a binarization threshold increase step 509. Here, the predetermined ratio is, for example,
0.3. That is, if the size of the reference intruding object is 30% or more, it can be detected as an intruding object. Therefore, according to the present embodiment, the first intrusion object detection threshold can be obtained by accurately detecting the difference level of the noise superimposed on the input image. Further, according to the present embodiment, the second intruding object detection threshold value can be obtained without calculating the size of the intruding object as in the first embodiment, and the reliability of the intruding object recognition device can be improved. It can be improved.

Further, in this embodiment, a unique effect is obtained by designating the area of the intruding object and determining the second intruding object detection threshold value in that area. To explain this, in the difference method, if there is a pixel whose luminance of the intruding object is close to that of the reference background image, the pixel is determined to be “0” by the binarization processing, and in some cases, the intruding object is divided into a plurality of pieces. May be observed. In this case, the size of the circumscribed figure of the detected object is apparently small, and the second intruding object detection threshold determined in the first embodiment is smaller than the optimum value.
In the present embodiment, an area where an intruding object exists is specified in a reference intruding object area setting step 701, and an object detected in that area in a detected object size determining step 702 (becomes "255" by binarization processing). It is determined whether or not the number of pixels (a group of pixels) is equal to or greater than a predetermined ratio in the designated area. Since the determination is made based on the ratio of pixels that become “255” in the binarized image, the determined second intruding object detection threshold value indicates that the intruding object is equal to or more than a certain value, regardless of whether the image is divided and observed. It can be assured that detection is performed with pixels having the ratio of.

FIG. 1 is an example of a flowchart showing a fourth embodiment of the present invention. In the fourth embodiment, the width (difference value) between the first intruding object detection threshold value Th1 and the second intruding object detection threshold value Th2 is determined, and the obtained intruding object detection threshold value is determined as the intruding object detection threshold value. It is determined whether or not it is suitable for the detection processing. FIG. 1 is a flow chart shown in FIG. 3, in which after a second intruding object detection threshold value selecting step 107, a first and second intruding object detection threshold value difference determining step 108 and a third intruding object detection step are performed. The detection threshold value determination step 109 is added, and another intrusion object detection threshold value selection step 110 is used instead of the intrusion object detection threshold value selection step 201.

The first and second intruding object detection threshold value difference determining step 108 is obtained by the first intruding object detection threshold value selecting step 106 and the second intruding object detection threshold value selecting step 107. The difference between the obtained first intruding object detection threshold Th1 and the second intruding object detection threshold Th2 is obtained, and if the difference is less than a predetermined value (for example, 5), the first intruding object detection is performed. The process branches to a threshold value determining step 101, and if it is equal to or more than a predetermined value, the process branches to a third intruding object detection threshold value determining step 109. In the above embodiment, the first and second intruding object detection threshold value difference determination steps
At 108, if the difference between the first intruding object detection threshold Th1 and the second intruding object detection threshold Th2 is less than a predetermined value, the process branches to the first intruding object detection threshold determination step 101. In the first and second intruding object detection threshold value difference determining step 108, if the process does not branch to the third intruding object detection threshold value determining step 109 even if it is repeated several times, for example, an alarm / monitor It is also possible to branch to the display step 116 so as to notify the observer of the abnormality.

Third Intruding Object Detection Threshold Determination Step
At 109, at least one third intruding object detection threshold Th3 that is greater than the first intruding object detection threshold Th1 and less than the second intruding object detection threshold Th2 is determined. This is, for example, the third intruding object detection threshold
If one Th3 is determined, the average of the first intruding object detection threshold Th1 and the second intruding object detection threshold Th2 may be used.

Next, an intruding object detection threshold value selecting step
In 110, one of the first intruding object detection threshold Th1, the second intruding object detection threshold Th2, and the third intruding object detection threshold Th3 is set as the intruding object detection threshold. This process will be described with reference to FIG. 10. For example, the observer uses the input device 1102 to
This is performed by selecting one of Th1 and the second intruding object detection threshold Th2 and the third intruding object detection threshold Th3. Therefore, according to the present embodiment, even when the intensity of the wind changes and the amount of the apparent movement of the moving object 1103 other than the intruding object to be detected such as the swaying of the tree in the input image changes, the first The observer operates the input device 1102 to easily select an appropriate intruding object detection threshold from among the intruding object detection threshold, the second intruding object detection threshold, and the third intruding object detection threshold. Can be set to

FIG. 8 shows an embodiment of a screen displayed on the monitor 1113 of the present invention. FIG. 8 shows how the binarized image changes with respect to the binarization threshold.
Of the intrusion object detection threshold candidate and the second intrusion object detection threshold candidate are indicated on the screen, and a binary image 801 (reference intrusion object 802, noise 803) is displayed on the screen.
a, 803b, 803c), binarization threshold level gauge 804
, An identification symbol (binary threshold mark) 805 indicating the position on the binary threshold level gauge 804 of the current binary threshold, a mark of a candidate for the first intruding object detection threshold
806a, 806b, 806c and candidate marks 807a, 807b, 807c of the second intruding object detection threshold are displayed.

In FIG. 8, the intruding object monitoring apparatus operates, for example, the processing operation of the flowchart of FIG. 4 is started, and first, when the binarization threshold is determined in the binarization threshold initialization step 404, the monitor is started. At 1113, a binarization threshold mark is displayed at the position of the binarization threshold value, and a binarized image acquired with the binarization threshold is displayed. Similarly, every time the processing of steps 405 to 409 is repeated, the binarization threshold mark is updated and displayed on the monitor 1113 at the position of the binarization threshold value, and the binarization threshold value is obtained. The binarized image thus updated is displayed. When the first binarization threshold candidate is determined, the candidate mark 806a is further displayed. Similarly, for example, when the processing operation of the flowchart in FIG. 5 is performed, and as a result, when the second binarization threshold candidate is determined, the candidate mark 807a is further displayed. Then, when the third binarization threshold value is determined by the third intruding object detection threshold value determination step 109 in the flowchart of FIG. 1, the candidate mark (not shown) is further displayed. . An intruder detection threshold is set by the monitor using the input device 1102 to select a binarization threshold deemed appropriate from among them, and the mark (not shown) monitor 1113 is set. Will be displayed. Note that these marks (not shown) may be provided in any form along the level gauge.
In this way, the binarization threshold mark 805 changes according to the set binarization threshold, and accordingly, the binarization image 8
01 also changes.

Each time a processing operation (for example, FIG. 1) is executed (for example, about three times), each time a candidate for an intruding object detection threshold is obtained, the candidate is displayed next to the binarization threshold level gauge 804. Candidate marks 806a, 806b at positions corresponding to the values
, 806c, 807a, 807b, 807c and a third binarization threshold mark candidate are displayed in a superimposed manner. By displaying on the monitoring monitor screen in this way, it is possible to know how the binarized image 801 can be obtained based on the intruding object detection threshold being set.

In the above embodiment, when determining the threshold value for detecting an intruding object, the binarization threshold value is changed in a direction to increase from the initial value. However, it is apparent that the binarization threshold may be changed in a direction to decrease from the initial value (maximum value). In that case, the first, second,
In each of the third and fourth embodiments, the second intruding object detection threshold value is determined first, and then the first intruding object detection threshold value is determined.

In determining the second threshold value for detecting an intruding object, for example, in step 505 in FIG. 5, it is determined whether the size of the circumscribed rectangle of the largest detected object is equal to or larger than a predetermined value. If the value is equal to or greater than the predetermined value, step 5
The process branches to 08, and the binarization threshold Th used in the binarization processing step 405 is determined as the second intruding object detection threshold Th2. On the other hand, in step 508, if the size of the circumscribed rectangle of the largest detected object is smaller than the predetermined value, the process branches to step 509, and subtracts 1 from the binarization threshold Th,
The processing moves to the binarization processing step 405.

In determining the first intruding object detection threshold value, for example, in step 407 of FIG.
In step 204, the number of clusters of pixels having a pixel value of "255" is counted. If the number is not 0, the flow branches to step 408 and the binarization threshold T used in the binarization processing step 405 is used.
The value obtained by subtracting 1 from h is the first intruding object detection threshold Th1
To be determined. On the other hand, if the number of clusters of pixels having the pixel value “255” counted in step 407 is 0, the binarization threshold Th is decremented by 1 in step 409, and the process proceeds to the binarization processing step 405. Binarization threshold Th
In the direction of decreasing the threshold value from the initial value to determine the intruding object detection threshold value, it is apparent to those skilled in the art from the description in the above specification that the details of each of the above embodiments are modified. Therefore, further description is omitted.

[0062]

Therefore, an intruding object detection threshold value capable of removing noise other than an intruding object from an input image obtained from an imaging device and a reference intruding object detected in an imaging field of view are detected. The detection threshold is automatically calculated, and the intrusion detection threshold can be easily set by selecting one of the detection thresholds. No skill is required, and even when the illuminance, time zone, lens aperture, etc. of the monitoring visual field change, the threshold value for intruding object detection can be easily set, and the application range of the intruding object recognition device can be greatly expanded. .

[Brief description of the drawings]

FIG. 1 is a flowchart showing a processing operation according to an embodiment of the present invention.

FIG. 2 is a flowchart illustrating a processing operation according to an embodiment of the present invention.

FIG. 3 is a flowchart illustrating a processing operation according to an embodiment of the present invention.

FIG. 4 is a flowchart illustrating a processing operation according to an embodiment of the present invention.

FIG. 5 is a flowchart illustrating a processing operation according to an embodiment of the present invention.

FIG. 6 is a flowchart illustrating a processing operation according to an embodiment of the present invention.

FIG. 7 is a flowchart showing a processing operation according to an embodiment of the present invention.

FIG. 8 is a diagram showing a screen display according to an embodiment of the present invention.

FIG. 9 is a diagram showing a method for setting a dead zone and a reference intruding object region according to the present invention.

FIG. 10 is a diagram illustrating a difference level of a moving object other than an intruding object, noise, and an intruding object to be detected.

FIG. 11 is a block diagram showing a configuration of an embodiment of an intruding object monitoring device according to the present invention.

FIG. 12 is a block diagram illustrating the principle of detecting an intruding object in the difference method.

FIG. 13 is a flowchart showing a conventional intruding object detection operation.

FIG. 14 is a diagram for explaining an operation principle of determining an intruding object threshold according to the present invention.

[Explanation of symbols]

101: first intruding object detection threshold value determining step, 10
2: First intruding object detection threshold recording step, 103:
Determining a second intruding object detection threshold value; 104: recording a second intruding object detection threshold value; 105: determining the end of a predetermined number of frames; 106: selecting a first intruding object detection threshold value; : Second intruding object detection threshold value selecting step; 108: first and second intruding object detection threshold value difference determining step; 109: third intruding object detection threshold value determining step; 110: intruding object detection Threshold selection step, 111: Image input step, 11
2: difference processing step, 113: binarization processing step,
114: intruding object detection step, 115: intruding object determination step, 116: alarm / monitor display step, 201: intruding object detection threshold selection step, 401: video selection step, 402: image input step, 403: difference processing step 404: Binarization threshold value initialization step, 405:
Binarization step, 406: object detection processing step, 40
7: Detection object number determination step, 408: First intrusion object detection threshold determination step, 409: Binarization threshold increase step, 501: Video selection step, 507: Detection object size determination step, 508: No. 2, an intruding object detection threshold determination step, 509: binarization threshold increasing step, 601: dead zone setting step, 602: binarization step, 701: reference intruding object area setting step, 702: detection object size judgment Step, 804: binarization threshold level gauge, 805: binarization threshold mark, 806a, 8
06b, 806c: candidate mark of first intruding object detection threshold, 807a, 807b, 807c: candidate mark of second intruding object detection threshold, 1101: TV camera, 1102: input device,
1103: Image input I / F, 1104: Input I / F, 1105: Image memory, 1106: Work memory, 1107: CPU, 110
8: Program memory, 1109: Output I / F, 1110: Image output I / F, 111: Data bus, 1112: Warning light, 111
3: Monitoring monitor, 1201: Input image, 1202: Reference background moving image, 1203: Difference image, 1204: Binary image, 120
5: Differentiator, 1206: Binarizer.

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI theme coat ゛ (reference) G08B 25/00 510 G08B 25/00 510M F term (reference) 5B057 AA19 BA02 CA08 CA12 CA16 CE12 DA06 DC32 5C054 AA02 AA04 FC05 FF06 HA18 5C084 AA02 AA07 AA13 BB04 BB31 CC17 DD11 EE01 EE02 FF27 GG43 GG52 GG56 GG57 GG78 HH10 HH12 HH13 5C087 AA02 AA03 AA23 AA24 AA25 BB03 BB32. GA08 JA11

Claims (16)

[Claims] 1. A monitoring method for detecting an intruding object in a monitoring visual field by applying a difference method to an image obtained from an imaging device, wherein the first input image from the imaging device and a storage device are stored in a storage device. A first difference image having a luminance value with respect to a reference background image is generated, the first difference image is binarized with a predetermined binarization threshold, and a noise level of the binarized image is set to a predetermined value. The above-mentioned binarization threshold is changed until the value becomes equal to or less than
A binarization threshold at which the noise level of the binarized image is equal to or less than a predetermined value is set as a first binarization threshold, and an intruding object is detected based on the first binarization threshold. An intruding object detection method for automatically determining a threshold value for detecting an intruding object. 2. The method for detecting an intruding object according to claim 1, wherein the threshold value for detecting the intruding object is automatically determined.
An intruding object detection method for automatically determining a threshold value for detecting an intruding object, characterized in that a change in the binarization threshold value is changed in an equal, equal or random manner. 3. An intruding object detection method for automatically determining a threshold value for detecting an intruding object according to claim 2, wherein said binarized threshold value is increased. An intruding object detection method that automatically determines the threshold value. 4. The intruding object detection method according to claim 2, wherein the threshold value for detecting the intruding object is automatically determined.
An intruding object detection method for automatically determining a threshold value for detecting an intruding object, wherein the threshold value is reduced. 5. An intruding object detection method according to claim 1, wherein a threshold value for intruding object detection is automatically determined.
The intruding object detection method for automatically determining a threshold value for detecting an intruding object, wherein the first input image is an image having no intruding object. 6. The method for detecting an intruding object according to claim 1, wherein the threshold value for detecting the intruding object is automatically determined.
Further, a second difference image of a luminance value between a second input image including the invading human body from the imaging device and the reference background image stored in the storage device is generated, and the second difference image is generated. At a predetermined binarization threshold, and changing the binarization threshold until the size of the intruding object of the binarized image is equal to or smaller than a predetermined size, A binarization threshold at which the size of the intruding object of the binarized image is equal to or smaller than a predetermined size as a second binarization threshold, including the first and second binarization thresholds, A third threshold value is set between the first and second threshold values, and an intruder is detected based on the third threshold value. An intruding object detection method that automatically determines a threshold for object detection. 7. The method for detecting an intruding object according to claim 6, wherein the threshold value for detecting the intruding object is automatically determined.
When setting the first and second thresholds, the threshold for intruding object detection is characterized in that the change of the binarization threshold is changed in an isometric, isometric, or random manner. The intruding object detection method decided on. 8. An intruding object detection method according to claim 7, wherein a threshold value for automatically detecting an intruding object is determined.
An intruding object detection method for automatically determining a threshold value for detecting an intruding object, wherein the threshold value is increased. 9. The method for detecting an intruding object according to claim 7, wherein the threshold value for detecting the intruding object is automatically determined.
An intruding object detection method for automatically determining a threshold value for detecting an intruding object, wherein the threshold value is reduced. 10. The intruding object detection method according to claim 6, wherein a predetermined size of the intruding object is represented by a circumscribed figure of the intruding object. An intruding object detection method for automatically determining a threshold value for detecting a moving intruding object. 11. The intruding object detection method according to claim 6, wherein a threshold value for automatically detecting an intruding object is further obtained from the first input image and the second input image, respectively. First and third binarization thresholds are respectively recorded, the binarization process is executed for a predetermined number of frames, each binarization threshold is recorded, and the plurality of recorded binarization thresholds are recorded. A method for automatically determining a threshold value for detecting an intruding object, wherein the first and second binarizing threshold values are determined from the following. 12. The method for automatically determining a threshold value for detecting an intruding object according to claim 11, wherein the first threshold value is determined by the first threshold value. Automatically determining a threshold value for detecting an intruding object, wherein the second binary threshold value is determined as a minimum binary threshold value. Intrusion object detection method to be determined. 13. The intruding object detection method for automatically determining a threshold value for detecting an intruding object according to claim 6, wherein the first difference image is binarized by a predetermined binarization threshold value. The processing further includes automatically setting a threshold value for detecting an intruding object, wherein a dead zone is provided and no binarization process is performed in the provided dead zone. 14. The intruding object detection method for automatically determining a threshold value for detecting an intruding object according to claim 6, further comprising obtaining a difference between the first and second binarization threshold values. When the difference between the first and second binarization thresholds is equal to or less than a predetermined value, it is determined that the threshold is abnormal. Detection method. 15. An intruding object monitoring apparatus for detecting an intruding object in a monitoring field of view from an image obtained from an imaging apparatus by applying a difference method, wherein the imaging apparatus outputs a first input image and a reference background image is stored. A first storage device, a processing unit for generating a first difference image of a luminance value between the first input image and the reference background image, and a predetermined threshold for binarizing the first difference image The binarization process is performed, and the binarization threshold is changed until the noise component of the binarized image is equal to or less than a predetermined value, and the noise component of the binarized image is equal to or less than a predetermined value. A first binarizing threshold value to be output as a first binarizing threshold value
And a detection processing unit for detecting an intruding object based on the output first binarization threshold value. 16. The intruding object monitoring device according to claim 15, wherein the imaging device outputs a second input image including the intruding object, and the imaging device further outputs the second input image and the second input image. 1
A processing unit for generating a second difference image of a luminance value with respect to the reference background image stored in the storage device, and performing a binarization process on the second difference image with a predetermined binarization threshold value Changing the binarization threshold until the size of the intruding object of the binarized image is equal to or smaller than a predetermined size,
A second binarization processing unit that outputs, as a second binarization threshold, a binarization threshold at which the size of the intruding object of the binarized image is equal to or smaller than a predetermined size; A threshold setting unit that includes a first and second binarization threshold, and sets a third binarization threshold between the first and second binarization thresholds. The intrusion object monitoring device, wherein the detection processing unit detects an intrusion object based on the second binarization threshold.