JP2003196786A - Method and device for detecting moving object - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a moving object detecting method and a moving object detecting device capable of detecting a moving object (vehicle, etc.), with accuracy even at night or the like with a small quantity of light. <P>SOLUTION: A detection area is photographed in a first time interval, and a photographed image is obtained and stored. The photographed image is composed of a plurality of regions, and each of the regions has brightness data of the each region. A part where the area of a group of regions with brightness that is prescribed brightness or more in the photographed image is detected to be a moving object. In other words, a photographed binarized image (i) obtained by dividing each region of the photographed image (i) at a point of time (i) into two types of regions: one region has the prescribed brightness or more and the other region has brightness being less than the prescribed brightness is calculated. A moving object image (i) corresponding to the point of time (i) is calculated on the basis of the calculated, photographed and binarized image (i) and the photographed image (i). The moving object is detected on the basis of information of the calculated moving object image (i). <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a moving body detecting method and a moving body detecting device.

[0002]

2. Description of the Related Art A technique for detecting the behavior of a moving body (vehicle or the like) traveling on a road is required for the purpose of suppressing traffic accidents. For example, in Japanese Unexamined Patent Publication No. 10-105689, a preset detection area is photographed, and a background image (an image of a road when a moving body (vehicle, etc.) does not exist) and a current image (an image currently photographed) are taken. There has been proposed a moving body behavior detection device that detects a moving body (vehicle or the like) based on the difference between and.

[0003]

In the conventional method of detecting a moving body, the background is removed from the difference between the background image and the current image to extract only the moving body. However, in the conventional moving object detection method, when the amount of light at night is small, the difference in color or brightness (luminance) between the background image and the moving object image at night becomes small, making it difficult to distinguish the background from the moving object. Therefore, there is a possibility that the moving body cannot be detected accurately. It suffices to be able to provide illumination that illuminates the detection area, but it is necessary to install large-scale illumination that can illuminate a wide area, or to install multiple ordinary lights in a wide area. It is very difficult due to cost and space constraints. The present invention has been devised in view of such a point, and provides a moving body detection method and a moving body detection device capable of accurately detecting a moving body (vehicle or the like) even at night when the amount of light is small. The purpose is to

[0004]

A first invention of the present invention for solving the above-mentioned problems is a method for detecting a moving body as set forth in claim 1. The moving object detection method according to claim 1, wherein a moving object (vehicle or the like) is used without using a background image.
By detecting the light that emits light and the area irradiated by the light, and indirectly determining the moving body, the moving body (vehicle or the like) can be accurately detected even at night when the light amount is small. In addition, a group of areas with a predetermined brightness or higher (for example,
It is possible to remove a fine noise component by determining that a portion in which adjacent areas are continuously adjacent to each other without interruption and the area of which is equal to or higher than a predetermined luminance is a predetermined value or more is a moving body.

A second aspect of the present invention is a method for detecting a moving body as set forth in claim 2. In the moving object detection method according to claim 2, without using a background image,
An area having a predetermined brightness or higher is extracted from the captured image [i] to obtain a captured binary image [i], and the obtained captured binary image [i]
The moving object image [i] is calculated based on the captured image [i] and the captured image [i]. Therefore, the light emitted by the moving body (vehicle or the like) and the area irradiated by the light or the like are detected, and the moving body (vehicle or the like) can be easily and accurately detected even at night when the light amount is small. .

The third invention of the present invention is a method for detecting a moving object as described in claim 3. In the moving object detection method according to claim 3, without using a background image,
Captured image [i-n], captured image [i] and captured image [i +
[n] is used to detect the light emitted by the moving body (vehicle or the like) and the area illuminated by the light, and to detect the moving body, so that the moving body can be accurately measured even at night when the light amount is small. Vehicle) can be detected. Further, by using three captured images that are very close in time, it is possible to remove the background with almost no effect on changes in color or brightness (luminance). In addition, based on a difference binarized image that may include a region determined to be unchanged as a result of superimposing a change in luminance, and a captured binarized image in which a region having a predetermined luminance or higher is extracted. By obtaining the binarized image, the amount of information of the moving body in the binarized image is increased, and the moving body (vehicle or the like) can be detected more accurately even at night when the light amount is small. In addition, n is an integer of 1 or more, and for example, when an alarm or the like is generated according to the detected behavior of the moving body (vehicle or the like), a sampling interval (first predetermined time) necessary for generating the alarm or the like. (Spacing) is maintained, and at the same time, the optimum sampling interval for detecting a moving object (two times the first predetermined time interval when n = 2, three times the first predetermined time interval when n = 3, etc.) Can be set.

A fourth invention of the present invention is a method for detecting a moving object as described in claim 4. In the moving body detection method according to claim 4, the noise component can be effectively removed by appropriately changing the threshold value based on the luminance distribution of the region of the captured image, and the difference between the two captured images can be obtained. Based on this, it is possible to easily and appropriately obtain the differential binarized image.

A fifth aspect of the present invention is a method for detecting a moving body as set forth in claim 5. In the moving object detection method according to claim 5, for example, when the distance to the moving object is long, or when the speed of the moving object is slow, n
The value of is increased to increase the sampling interval for detecting a moving object. Further, when the distance to the moving body is short, or when the moving body has a high speed, the value of n is reduced to shorten the sampling interval for detecting the moving body. Alternatively, the value of n is set to an appropriate value according to the position and speed of the moving body. In this way, it is possible to set the optimum sampling interval for detecting the moving body depending on the situation.

A sixth aspect of the present invention is a method for detecting a moving body as set forth in claim 6. In the moving body detection method according to claim 6, when the moving body is detected, the first
By shortening the predetermined time interval and increasing the first predetermined time interval when a moving object is not detected, unnecessary operation can be suppressed and the life of the power supply or the like can be extended.

Further, a seventh invention of the present invention is a moving object detecting device as described in claim 7. By using the moving body detection device according to the seventh aspect, it is possible to realize a moving body detection device that can accurately detect a moving body (vehicle or the like) even at night when the amount of light is small.

An eighth invention of the present invention is a moving object detecting device as described in claim 8. If the moving body detection device according to claim 8 is used, the position and the moving direction of the detected moving body are obtained based on at least two moving body images, and the moving body (vehicle or the like) is located at a predetermined point (intersection or the like). When approaching, an alarm can be issued to alert people in the vicinity of the alarm device.

The ninth invention of the present invention is a moving object detecting apparatus as described in claim 9. If the moving body detection device according to claim 9 is used, by using an appropriate power source,
The moving body detection device can be operated. Further, when the solar cell is used, the energy cost for operating the moving body detection device can be reduced.

The tenth invention of the present invention is the tenth aspect.
The vehicle approach warning device as described in 1. If the vehicle approach warning device according to claim 10 is used, it is determined whether or not the moving body is a vehicle based on the size of the detected moving body, and the determined vehicle is based on at least two moving body images. When the vehicle is approaching a predetermined point (intersection or the like) by determining the position and the moving direction of the vehicle, it is possible to suppress a traffic accident by issuing an alarm from an alarm device.

The eleventh invention of the present invention is the eleventh invention.
The vehicle approach warning device as described in 1. If the vehicle approach warning device according to the eleventh aspect is used, the vehicle approach warning device can be operated by using an appropriate power source. Further, when the solar cell is used, the energy cost for operating the vehicle approach warning device can be reduced.

[0015]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 shows a schematic configuration diagram of an embodiment of a moving body detection apparatus to which the moving body detection method of the present invention is applied. In FIG. 1, the moving body C shows an alley β with poor visibility.
It shows an example of trying to cross the highway α from (is trying to go straight). In this example, there is an obstacle γ on the left side of the moving body C, and the main road α on the left side cannot be seen in the view from the moving body C. In the normal case, the driver of the mobile unit C slowly moves to the intersection and checks the traffic conditions on the left and right (of the main road α). Then, after traveling on the main road α and confirming that there is no moving body (vehicle or the like) coming toward the intersection, the vehicle crosses the main road α. However, in the case of dim light such as at dusk, the driver of the mobile body C may overlook the existence of the mobile body A traveling on the main road α and coming toward the intersection, which may lead to a traffic accident.

The image pickup apparatus 1 has a first predetermined time interval,
An image of the detection area (including the moving body A in FIG. 1) is captured. The processing device 2 stores the captured image in the storage device 3 at the first predetermined time interval, and processes the captured image stored in the storage device 3 according to the program to detect the moving body. Then, when the processing device 2 detects the moving body A traveling on the main road α and coming toward the intersection,
An alarm operation signal is sent to the alarm device 4. When the alarm device 4 receives the alarm operation signal from the processing device 2, the alarm device 4 generates an alarm by voice or light (various methods of alarm can be used). The driver of the moving body C can determine that another moving body (in this case, the moving body A) is approaching the intersection because the warning is issued from the warning device 4. As a result, the main road α can be safely crossed. The image capturing device 1, the processing device 2, the storage device 3, and the alarm device 4 may be separate devices, respectively.
It may be a device in which some of them are integrated (in the example of FIG. 1, the processing device 2 and the storage device 3 are integrated). The processing device 2 and the alarm device 4 may be connected by a wireless line or a wired line. Further, the installation place can be variously changed. As a power supply for driving each device, an AC power supply may be used, a solar cell may be used, or both an AC power supply and a solar cell may be provided and switched as needed. . Various power sources can be used as the power source. In the case where a solar cell is provided, for example, a battery panel is provided on the upper portion of the image capturing device 1 or the like.

[Principle of detection of moving body (in daytime with a large amount of light (day mode)]] Next, referring to FIG. 2, a method of detecting a moving body in a case of daytime with a large amount of light (day mode) will be described. The detection principle will be described. In all the images used in this embodiment, the brightness (luminance) is represented by a digital value (for example, 0 to 0).
It is represented by the number 255, "0" is the darkest, "255"
The individual pixels converted to the brightest value are arranged in an orderly manner (eg, vertical direction: 480 pixels, horizontal direction: 640 pixels)
It is a digital image that has been configured. In addition, in each drawing, solid lines, dotted lines, one-dot chain lines, two-dot chain lines, etc. are appropriately used for the arrows connecting the respective images in order to clarify the flow of processing. First, the image capturing apparatus 1 captures an image of the detection area at a first predetermined time interval (for example, 1/8 second interval), and the processing apparatus 2 stores the captured image in the storage device 3. In the example of FIG. 2, the captured image [i-1], captured image [i], and captured image [i + 1] are obtained and stored in the storage device 3 at times [i-1], [i], and [i + 1]. ing. At time [i], the processing device 2 obtains the captured image [i] and stores it in the storage device 3, and further, based on the difference between the captured image [i-1] and the captured image [i]. The binarized difference binarized image [i-1, i] is obtained and stored in the storage device 3. In this example, the differential binarized image shows the moving body in black and the background excluding the moving body in white (black and white 2).
Is represented by a value). Since the time [i-1] and the time [i] are very close to each other, there is almost no change in the brightness of the background or the like due to changes in the weather or the like, and the background can be appropriately removed. Further, when the first predetermined time interval is short or when the speed of the moving body is slow, the difference is calculated for the portion where the moving body is superposed and the difference in brightness (luminance) is small in the difference binarized image. Will be removed. For this reason, in FIG. 2, a part of the overlapped portion is removed, and it is white like the background (hereinafter, this state is referred to as a hollow state). The details of how to obtain the difference binarized image will be described later.

At time [i + 1], the processing device 2
Obtains the captured image [i + 1], stores it in the storage device 3, and obtains a binarized difference image [i, i + 1] based on the difference between the captured image [i] and the captured image [i + 1]. , In the storage device 3. Then, the difference binarized image [i-1,
i] and the binary difference image [i, i + 1],
Find the mask image [i]. Here, the mask image is 2
The mask image represented by the value and obtained at time [i + 1] is not the mask image corresponding to time [i + 1],
It is a mask image [i] corresponding to time [i]. In addition,
Details of how to obtain the mask image will be described later. Then, the moving body image [i] is obtained based on the obtained mask image [i] and the captured image [i] corresponding to the time [i]. The moving object image [i] is obtained by extracting only the black portion of the mask image [i] from the captured image [i]. In the moving body image, the background other than the moving body is removed from the captured image, and only the moving body exists. Details of how to obtain the moving body image will be described later. In this example, the moving image [i] corresponding to the captured image [i] captured at the time [i] is extracted at the time [i + 1] instead of the time [i]. The interval of [i + 1] is short (in this embodiment,
Since it is 1/8 second), it has almost no influence on the detection of a moving body and the generation of an alarm.

[First Embodiment (Detecting Moving Object Using Difference in Photographed Image)] In the first embodiment, movement is performed using the difference in photographed image as in the case of the “day mode”. Find the body image. However, since the moving object image is obtained by a method different from the “day mode”, the details will be described below.

[Principle of detection of moving body (in the case of night time when the light amount is small (night mode)]] With reference to FIG. 3, the moving body detecting method of the present invention in the case of night time (night mode) where the light amount is small. The detection principle of is explained. Hereinafter, differences from FIG. 2 will be described. At time [i-1], the processing device 2 obtains the captured image [i-1] and stores it in the storage device 3. Furthermore, each area (each pixel) of the captured image [i-1] has a predetermined brightness or higher (for example, brightness "220" or higher).
And a binarized image obtained by classifying into two types of regions of less than a predetermined brightness (regions of a predetermined brightness or higher are expressed in black, and regions of a predetermined brightness or lower are expressed in white). i-
1] is required. In this case, the light of the moving body A and the area illuminated by the light, the area illuminated by the light of the moving body B, the streetlight and the area in the vicinity of the streetlight are extracted as areas having a predetermined brightness or higher.

At time [i], the photographed binarized image [i] is obtained in the same manner as at time [i-1], and the difference binarized image [i-1, i] is calculated. Difference 2
The binarized image [i-1, i] is in a hollow state, as in FIG. In addition, at night when the amount of light is small, the difference in brightness between the background and the moving body itself is small, and thus the moving body itself is likely to be almost removed. However, the light and the area illuminated by the light (high-luminance area) appear as a difference. In addition, unlike FIG. 2, the area illuminated by the light has a higher uniformity of brightness (smaller difference in brightness value) than the area of the moving body itself, and thus a hollow area is present over a wide range. Is likely to be. Therefore, the difference binarized image [i-1, i]
, The photographed binary image [i-1] and the photographed binary image [i]
Is added using a logical sum or the like to obtain a binarized image [i-1, i].

At time [i + 1], the photographed binarized image [i + 1] is obtained in the same manner as at time [i],
Similarly, the difference binarized image [i, i + 1] is obtained, and the binarized image [i, i + 1] is obtained. Then, the mask image [i] is obtained from the logical product of the binarized image [i-1, i] and the binarized image [i, i + 1]. Difference 2 as in FIG.
The binarized image [i-1, i] and the difference binarized image [i, i +
When the logical product with 1] is obtained, since a part of the hollow area is large, only a small amount of information remains as shown in the logical product image [i] in FIG. Is difficult. However, by increasing the amount of information by obtaining the logical sum of the captured binary image, the mask image [i] having the amount of information that can accurately detect the moving object.
Can be obtained.

Then, the moving body image [i] is obtained based on the obtained mask image [i] and the photographed image [i] corresponding to the time [i]. The moving object image [i] is obtained by extracting only the black portion of the mask image [i] from the captured image [i]. In the moving body image, the background other than the moving body is removed from the captured image, and only the moving body exists. However, in this case, not the moving body (vehicle or the like) but the area illuminated by the light or the like emitted by the moving body (the vehicle or the like) and the street light which is not moving but has a predetermined brightness or higher are detected. (Hereinafter, these are referred to as high-luminance bodies). A method of removing a noise component such as a street light that is not a moving object will be described later.
It should be noted that the determination of daytime etc. with a large amount of light (day mode) and nighttime etc. with a small amount of light (night mode) can be made, for example, in the daytime (daytime) when the brightness distribution of the captured image is close to that of FIG. Mode) and the brightness distribution of the captured image is shown in FIG.
If it is close to (B), it is determined to be night (night mode). In this case, various approximation methods are possible. In addition, the following embodiments will describe a moving object detection method in the night mode (when the amount of light is small, such as at night) according to the present invention.

[Principle of Detection of Moving Object (Continuous Shooting and Continuous Processing in Night Mode)] FIG. 4 continuously executes the processing of FIG. 3 described above at a first predetermined time interval. It shows the situation. Although the photographed binary image and the difference binary image are omitted in FIG. 4, FIG.
The binarized image is obtained in the same manner as. For example, at time [i], the captured image [i] is obtained and stored, and 2 is calculated based on the difference between the captured image [i-1] and the captured image [i].
The binarized difference binarized image [i-1, i] is obtained and stored, and the photographed binarized image [i] obtained by extracting the region of the photographed image [i] having a predetermined brightness or higher is obtained and stored. And the difference 2
For the binarized image [i-1, i], the captured binarized image [i-1]
And the captured binarized image [i] are added using a logical sum or the like to obtain and store the binarized image [i-1, i]. Then, the binarized image [i-2, i-1] and the binarized image [i-1, i]
The moving object image [i-1] can be obtained by obtaining the mask image [i-1] from the logical product of and and extracting the black portion of the mask image [i-1] from the captured image [i-1]. . Similarly, the moving body image [i] can be obtained at time [i + 1], and the moving body image [i + 1] can be obtained at time [i + 2]. Then, the moving body image [i-1], moving body image [i], moving body image [i
−1], the moving direction and moving speed of the moving body (high-luminance body), the distance to the moving body (high-luminance body), or the like can be obtained. The distance to the moving object (high brightness object) can be estimated by the position of the moving object (high brightness object) in each moving object image (in this embodiment, the moving object (high brightness object) is on the ground. To move). The method of obtaining the moving direction, moving speed, position, etc. of the moving body (high brightness body) will be described later.

[How to obtain difference binary image] Next, referring to FIG.
A method for obtaining a difference binarized image from the difference between two captured images will be described using. FIG. 5 illustrates
The captured image is divided into 8 × 8 blocks (X, Y). Also, in this example, each block (X, Y) is 4 ×
A total of 16 pixels of 4 are arranged in an orderly manner, and each pixel has a measured value based on the brightness (luminance). For example, each pixel measures the brightness (luminance). As shown in FIG. 5, the block (6,
5) and the block (6, 6), and the value of each pixel of the block (6, 5) and the block (6, 6) of the captured image [i] is the amount of brightness (luminance) detected by each pixel. (The portion indicated by the dotted line indicates the outer shape portion of the moving body (in this case, the area illuminated by the light or the like) for reference). In addition, a portion where the color is changed in each block shows a difference in luminance as a reference.

Here, in order to obtain the difference between the photographed image [i-1] and the photographed image [i], the digital amount of each pixel of the photographed image [i] corresponds to the photographed image [i-1]. Subtract the digital amount of pixels. Then, the absolute value of the obtained difference is calculated. For example, the block (6,
The digital amount (120) at the upper right of the block (6, 6) of the captured image [i-1] is subtracted from the digital amount (50) of the pixel at the upper right of 6). Then, the absolute value of the difference is calculated for each pixel (“70” in this case), and the calculated value is stored in the corresponding pixel portion. Next, set the absolute value of the difference to 2
Quantify. For example, the absolute value of the difference is greater than or equal to a threshold value (for example,
Pixel portions which are "60" or more) are set to "1", and pixel portions whose absolute difference is less than the threshold value (for example, less than "60") are set to "0". This makes it possible to obtain a difference binarized image having only the binary values of “1” and “0” from the difference between the two captured images. For example, if the pixel portion of "0" is set to white and the pixel portion of "1" is set to black, the difference binarized image [i-1, i] shown in FIG.
Is obtained. According to this method, it is possible to remove the background other than the moving object with high accuracy because the difference is between the two captured images at a very short time interval. However, since the pixels with a small difference in brightness (luminance) are regarded as the background and are removed, the brightness (luminance) of the moving body (high-luminance body) is almost uniform, and the moving speed of the moving body (high-luminance body) is high. When the shooting speed is low or the shooting interval (first predetermined time interval) is short, in the captured image [i-1] and the captured image [i], the same moving body (high brightness body) is overlapped (see FIG. 5). In the "moving object superimposed pixel" therein, there is a case where the moving object (high brightness object) is removed as a background even though the moving object (high brightness object) exists.
As for this coping method, as described above, the difference 2
This can be dealt with by using a logical sum of the binarized image and the photographed binarized image or the like to obtain the binarized image in which the portion in the hollow state is corrected.

[How to obtain mask image] Next, two 2
A method of obtaining the mask image from the logical product of the binarized images will be described. In the binarized image, each pixel is either “0” or “1”. For each pixel, a logical product with the corresponding pixel is obtained. For example, in the "day mode", the result of obtaining the logical product of the difference binarized image [i-1, i] and the difference binarized image [i, i + 1] shown in FIG. 2, for example, "0" When the pixel portion of is set to white and the pixel portion of "1" is set to black, the mask image [i] shown in FIG. 2 is obtained. Further, for example, in the “night mode”, as a result of obtaining the logical product of the binarized image [i−1, i] and the binarized image [i, i + 1] shown in FIG. 3, for example, “0” When the pixel portion of is set to white and the pixel portion of "1" is set to black, the mask image [i] shown in FIG. 3 is obtained.

[How to obtain moving body image] Next, a method of obtaining a moving body image from a photographed image and a mask image will be described. As described above, in the mask image, each pixel portion is either "0" or "1". For example,
2 or 3, the pixel portion of the photographed image [i] corresponding to the portion where the pixel of the mask image [i] is "0" (in this case, the white portion in the mask image [i]) is "0". (In this case, it is white). In addition, the pixels of the captured image [i] corresponding to the portion where the pixels of the mask image [i] are “1” (in this case, the black portion in the mask image [i]) retain the digital amount as they are. in this way,
The moving body image [i] can be obtained.

[Setting of First Predetermined Time Interval (1) (When Mobile Object is at Low Speed)] In the present embodiment, it is not assumed that the mobile object is at an extremely low speed. This is because in the case of extremely low speed, it is not necessary to detect as a moving body (high brightness body) and issue an alarm. For example, it is only necessary to be able to detect a moving body (high-luminance body) that moves at a speed of about 15 km / h or more. The first predetermined time interval is influenced by the speed of the vehicle on the road in the detection area and the like, but is preferably ¼ second or more. In addition,
The setting of this value may be changed for each road in the detection area.

[Setting of first predetermined time interval (2) (when moving body is at high speed)] FIG. 6 shows that the moving speed of the moving body (high-luminance body) is high, or the shooting interval (first predetermined time). Time interval)
Shows a case where there is a moving object (high brightness object) and the number of captured images is small. For example, as shown in FIG. 6, when the moving body (high-luminance body) exists only in the captured image [i], the moving body image [i-1] and the moving body image [i +
1] has no moving body (high-luminance body), and the moving body exists only in the moving body image [i]. (In the example of FIG. 6, although the moving body images [i-1] and [i + 1] include the high-intensity body (street light) that is not moving, the high-intensity body (vehicle that is actually moving) (vehicle Etc.) is not included.) In this case, even if the moving body images [i-1], [i], and [i + 1] are used,
The moving direction and moving speed of the moving body (high brightness body) cannot be obtained. Therefore, the first predetermined time interval is set so that the number of captured images in which the moving body (high-luminance body) to be detected is large. The first predetermined time interval is influenced by the speed of the vehicle on the road in the detection area and the like, but is preferably ⅛ second or less. The setting of this value may be changed for each road in the detection area.

[Optimization of Time Interval for Detecting Low-speed or High-speed Moving Object] From the above description, in order to accurately detect a low-speed moving object (high-luminance object) using the difference between the captured images. It is preferable to set the first predetermined time interval to 1/4 second or more. To accurately detect a high-speed moving object (high brightness object) in each captured image, the first predetermined time interval is set to 1 / second. It is preferably set to 8 seconds or less. A method for solving this will be described with reference to FIG. For example, as shown in FIG. 7, each captured image is captured every ⅛ second. However,
The binarized image is not taken once, but n times (n is
(An integer of 2 or more) Obtained from past captured images. Similarly, the mask image and the moving body image are also obtained from images n times past. FIG. 7 shows an example in which “n = 2” is set (photographed images are photographed every 1/8 second). For example, at time [i + 1], the captured image [i + 1] is obtained and stored, and the difference between the captured image [i-1] (twice past) and the captured image [i + 1] (currently captured) is calculated. The binarized difference binary image [i−1, i + 1] is obtained and stored, and the difference binarized image [i−1, i + 1] and the captured image 2 are stored.
The logical sum of the binarized image [i-1] and the photographed binarized image [i + 1] is obtained, and the binarized image [i-1, i + 1] is obtained and stored. Next, the obtained binarized image [i-1, i + 1]
Then, the mask image [i-1] is obtained from the logical product of the two-time past binarized image [i-3, i-1]. Then, the moving body image [i-1] can be obtained from the obtained mask image [i-1] and captured image [i-1]. In other words, in this case, the moving body image is obtained based on the difference between the photographed images every 1/4 second. In this case, time [i-1]
The moving body image [i-1] corresponding to the captured image [i-1] captured in the above is not the time [i-1] but the time [i + 1].
However, since the interval between the time [i-1] and the time [i + 1] is short (in this case, 1/4 second), it hardly affects the occurrence of an alarm.

At time [i + 2], a photographed image [i + 2] is obtained and stored, and the difference between the photographed image [i] (twice past) and the photographed image [i + 2] (currently photographed) is obtained. Difference binarized image [i, i + 2] based on
Is calculated and stored, and the difference binarized image [i, i + 2]
And the binarized image [i] and the binarized image [i + 2] are ORed to obtain and store the binarized image [i, i + 2]. Next, the obtained binarized image [i, i + 2] and 2
The mask image [i] is obtained from the logical product of the binary image [i-2, i] of the past times. Then, the moving object image [i] can be obtained from the obtained mask image [i] and captured image [i]. Since the process of obtaining the moving body image is executed for each shooting, the time interval between the time [i + 1] and the time [i + 2] is 1/8 second. Therefore, the moving body image [i-1],
[I] and [i + 1] represent moving objects existing in the captured image every 1/8 second.

That is, a photographed image is obtained by photographing at the first predetermined time interval and stored, and the photographed image [i] at the time [i] and the photographed image n times past the photographed image [i] are displayed. i-n] (n is an integer greater than or equal to 1) and a captured image [i + n] of the captured image [i] n times in the future, the captured image [i-n] and the captured image [i] are obtained. Difference binarized image [i−n, i] binarized based on the difference between the captured image [i] and captured image [i + n] i, i + n], and the captured image [i−n], captured image [i], and captured image [i +
n], the respective regions are classified into two types of regions, that is, a region having a brightness equal to or higher than a predetermined brightness and a region having a brightness lower than the predetermined brightness, a captured binary image [i-n], a captured binary image [i], and The captured binary image [i + n] is obtained, and the obtained difference binary image [i-
[n, i], the photographed binary image [i-n], and the photographed binary image [i], and the calculated difference binary image [i] , I + n], the captured binary image [i], and the captured binary image [i + n], and the obtained binary image [i-
[n, i] and the binarized image [i, i + n], the mask image [i] corresponding to the time point [i] is obtained, and based on the obtained mask image [i] and the captured image [i]. Then, the moving body image [i] corresponding to the time point [i] is obtained, and the moving body is detected based on the obtained information of the moving body image [i]. In this example, the first predetermined time interval is 1/8 second and n =
Since it is 2, the moving object is extracted every 1/8 second based on the difference every 1/4 second. This makes it possible to accurately detect low-speed and high-speed moving bodies.

[How to obtain moving direction and moving speed of moving body] Next, referring to FIG. 8, a method for obtaining the moving direction and moving speed of the moving body (high brightness body) based on the obtained moving body image. Will be described. For example, as shown in FIG. 8, the obtained moving body image is divided into 8 × 8 blocks (X, Y). Also, in this example, each block (X, Y) is 4 ×
A total of 16 pixels of 4 are arranged in an orderly manner, and each pixel has a measured value based on the brightness (luminance). By using the matching between the blocks, each block (X [i], Y in which a moving body (high brightness body) exists
[I]) destination block (X [i + 1], Y [i +
1]) is detected, and the moving direction and moving distance (motion vector) of the block are obtained. The moving speed can be calculated from the moving distance in a predetermined time.

Referring to FIG. 8, the motion vector plane [i-1, i] is calculated from the moving body image [i-1] and the moving body image [i].
A method of obtaining a (motion vector of a moving body (high-luminance body) from time [i-1] to time [i]) will be described. For example, the digital amount contained in each pixel in the block (6, 5) of the moving body image [i-1] has the value shown in FIG. Further, the digital amount contained in each pixel in the block (7, 5) of the moving body image [i] has the value shown in FIG. (The part indicated by the dotted line shows the outer shape of the moving body (high brightness body) as a reference, and the part in which the color in the block is changed is shown as a part of the moving body (high brightness body). .) In this case, the blocks (6, 5) of the moving body image [i-1] and the blocks (7, 5) of the moving body image [i].
Are determined to match, and the motion vector plane [i-1,
On i], the vector going from block (6, 5) to block (7, 5) is obtained. Similarly, the "(block) motion vector" in each block is calculated,
“(Block) motion vector” with similar direction and similar distance
Are averaged to obtain a “(moving body) motion vector”.
Then, the moving direction and the moving distance of the moving body (high brightness body) can be obtained from the “(moving body) motion vector”. Further, the moving speed of the moving body (high brightness body) can be obtained from the moving distance in a predetermined time. Note that, as a method of obtaining matching between blocks, there is (1) the sum of absolute values of difference gradation values of pixels in the block of the related art,
(2) Absolute value of the difference between the average gradation values of the pixels in the block,
(3) absolute value of difference in standard deviation of tone values of pixels in block, (4) cross-correlation coefficient of tone values of pixels in block,
(5) There are various methods such as the degree of coincidence of the gradation value of the pixel in the block by the Fourier coefficient. In the present embodiment, (1)
The sum of absolute values of the difference gradation values of the pixels in the block was used,
Other methods may be used.

[Shooting timing (first predetermined time interval), n value (“n (n is an integer greater than or equal to 1)” when obtaining the difference between the image n times past and n times future)) Change] In the above description, the first predetermined time interval is "1/8".
It was explained with the example that it is fixed to "second" and n is fixed to "2".
It can be changed according to the situation. [Change of First Predetermined Time Interval] For example, when the moving body image is obtained and there is no moving body (high brightness body) in the moving body image, the first predetermined time interval is increased. (For example, 1 second). When the distance to the moving body (high brightness body) based on the position of the moving body (high brightness body) in the moving body image is large (the moving body is far), the first predetermined time interval is lengthened. Good. Further, when the moving speed of the moving body (high brightness body) obtained from the moving distance in the predetermined time is small, the first predetermined time interval may be lengthened. In the opposite case, the first predetermined time interval may be shortened. This makes it possible to set an optimum sampling interval for detecting a moving body (high-luminance body). In addition, when the first predetermined time interval is changed, the calculation of the moving speed is also changed along with the change of the first predetermined time interval.

[Change of n Value] Further, for example, when the moving body image is obtained, the distance to the moving body (high brightness body) is determined based on the position of the moving body (high brightness body) in the moving body image. When it is large (the moving body is far), the n value may be increased (for example, n = 8). Alternatively, when the moving speed of the moving body (high brightness body) obtained from the moving distance in a predetermined time is small, the n value may be increased. In the opposite case, the n value may be reduced. Alternatively, the value of n may be set appropriately according to the position and speed of the moving body (high brightness body). This makes it possible to set an optimum sampling interval for detecting a moving body (high-luminance body). Note that n
When the value is changed, the calculation of the moving speed is also changed with the change of the n value.

[Removal of High-Brightness Object (Fixed High-Brightness Object) that Has Not Moved] Next, referring to FIG. 9, it is detected as a moving object (high-brightness object) such as a street lamp that has not moved. A method of removing an object (in this description, referred to as a fixed high-intensity body) will be described. In FIG. 9, the n value is set to “1” in order to easily understand the method of removing the fixed high-intensity body. In the present invention, a moving body (high brightness body) such as a vehicle approaching a predetermined point (for example, the intersection shown in FIG. 1) is detected,
Fixed bright objects should not be detected as moving objects as they will generate an alarm. However, since each photographed image photographed at the first predetermined time interval has “brightness above a predetermined level”, it is extracted as a moving body (high-luminance body) in the moving body image. For example, as shown in FIG. 9, when a fixed high-intensity body (a streetlight in this example) is present in a captured image, there is "brightness above a predetermined level" in each captured image. Therefore, the fixed high-intensity body also exists in each binarized image, each mask image, and each moving body image. When the fixed high-intensity body exists in the moving body image, the moving direction and the moving distance of the block in which the fixed high-intensity body exists are detected by the "(block) motion vector" shown in FIG. (Actually, the fixed high-intensity body does not move, so "(block) motion vector"
None is detected, but this is not preferable because the processing load of the processing device 2 increases. ) Therefore, before obtaining the "(block) motion vector", "(block) motion vector"
Distinguish between blocks that should be obtained and blocks that should not be obtained.

A method of distinguishing between a block for which a "(block) motion vector" should be obtained and a block for which it should not be obtained will be described with reference to FIG. FIG. 9 corresponds to FIG.
In the same manner as the above, the obtained moving body image is divided into 8 × 8 blocks (X,
Y). Then, an addition map is obtained from the moving body image divided into blocks. In the addition map, for example, “+” is added to a block in which a moving body (high-luminance body) exists.
"2" is allocated, and "-1" is allocated to a block in which no moving body (high brightness body) exists. It should be noted that the colored portion in the addition map indicates the region in which the moving body (high-luminance body) exists as a reference. For example, in the addition map [i] obtained from the moving body image [i], blocks (1, 2), (2, 1) to (2, 2), (2, 4) to
(2,5), (3,3) to (3,6), (4,3) to
(4,4), (5,4) to (5,6), (6,4) to
Since (6, 6), (7, 4) to (7, 6) have moving bodies (high brightness bodies), "+2 (first predetermined value)" is assigned to the block and other blocks ( "-1 (second predetermined value)" is assigned to a block in which no moving body exists. Then, the cumulative value (judgment value) of each block is stored in the cumulative map. It should be noted that the colored portion in the cumulative map is shown by reference to the area determined to be the fixed high-intensity body.

Here, whether the block for which the "(block) motion vector" should be obtained or the block for which it should not be obtained,
Two methods for distinguishing between will be described. [First Method] In the first method, in each block obtained by dividing a moving body image, a moving body (high brightness body) is provided for each block.
Is a method of determining the duration of time that exists. In the first method, the addition map and the cumulative map may be omitted. However, a duration map (not shown) for storing the duration in which the moving body (high-luminance body) was present for each block
Need. A block whose duration is equal to or longer than the second predetermined time is excluded from the determination of the moving body (high brightness body).
In the example of FIG. 9, the block (1, 2) and the block (2,
The moving body (high-luminance body) continuously exists in each block of 1) and the block (2, 2). In each of these blocks, if a moving object (high brightness object) continuously exists for a second predetermined time (for example, 5 seconds) or more, the block (1, 2)
The block (2, 1) and the block (2, 2) are determined as the blocks for which the “(block) motion vector” should not be obtained. A block other than the block in which the moving body (high-luminance body) exists is a block for which the “(block) motion vector” should be obtained. In the first method, when the moving body (high-luminance body) no longer exists, the determination exclusion of the moving body (high-luminance body) is restored (returning to the determination of the moving body).

[Second Method] In the second method, the first predetermined value is added when a moving body (high-luminance body) exists in each block obtained by dividing the moving body image, and the moving body exists. If not, the second predetermined value is subtracted and the cumulative value (judgment value) is obtained. When the cumulative value (judgment value) becomes equal to or larger than the third predetermined value, the block is excluded from the judgment of the moving body. In the example of FIG. 9, the cumulative value (judgment value) of each block is stored in the cumulative map. For example, when the addition value (“+2” or “−1”) of each block of the addition map [i] is added to the accumulation value (judgment value) of each block of the accumulation map [i−1], the accumulation map [i ] Is obtained. In this cumulative map, the cumulative value (judgment value) is the third
A block having a predetermined value of 50 or more (for example, 50) or more is excluded from the determination of the moving body. In addition, the return from the judgment exclusion of the moving object (returning to the judgment of the moving object) is provided with a hysteresis as shown in the “graph for each block” in FIG. It is shown that the object is judged to be a high-luminance body), and the judgment is returned to 30 or less).

The cumulative value (judgment value) in the cumulative map
It is preferable to set appropriate upper and lower limit values (for example, upper limit value: 100, lower limit value: 0). (FIG. 9 shows the lower limit:
In this example, 0 is set. ) By appropriately setting the first predetermined value, the second predetermined value, and the third predetermined value using the second method, the fixed high-intensity body that is blinking, and the vibrating (the wind) Fixed high-intensity objects can be appropriately excluded from the determination of moving objects. The block excluded from the determination of the moving body is determined as the block for which the “(block) motion vector” should not be obtained. In addition, blocks other than the block in which the moving body exists are blocks for which the “(block) motion vector” should be obtained. In addition, in both the first method and the second method, the first to third predetermined values can be changed according to the situation. For example, when there are many areas where the fixed high-intensity body exists (in the evening or in the case of a lot of diffused reflection such as in rainy weather), the first predetermined value may be decreased or the third predetermined value may be increased to increase the fixed high brightness. It is also possible to reduce the body determination area.

[Removal of Other Noise Components] Next, referring to FIG. 10, a method of removing other noise components (such as diffuse reflection in the vicinity of the boundary of a region having a predetermined luminance or higher or in the evening or in rainy weather) will be described. In FIG. 10, it becomes gradually darker in the evening (time [i-2]), becomes darker gradually at night (time [i-1] and [i]) (time [i +]).
1]) and the morning (time [i + 2]). Therefore, in FIG. 10, the time [i-2] is in the "day mode", the time [i-1] and the time [i] are in the "night mode", and the time [i +
1] and time [i + 2], it is the “day mode”. The switching method between the “day mode” and the “night mode” is determined by, for example, the brightness distribution of the captured image shown in FIG.
When the brightness distribution of the photographed image is close to that in FIG. 11B, it is determined to be nighttime (night mode).

Note that, in FIG. 10, the n value is set to "1" in order to easily understand the method of removing other noise components. Similar to the removal of the fixed high-intensity body, other noise components should not be detected as a moving body (high-intensity body). However, since each photographed image photographed at the first predetermined time interval has "brightness equal to or higher than a predetermined value", it is extracted as a moving body (high-luminance body) in the moving body image. For example, in FIG.
As shown in 0, when other noise components (near the boundary of a region with a predetermined brightness or more, in the evening, diffuse reflection in the rain, etc.) exist in the captured image, the other noise components are
It also exists in a photographed binary image (not shown), a differential binary image (partly not shown), a binary image, a mask image, and a moving object image.

For example, at the time [i-1], the "day mode" is switched to the "night mode". At this point in time, the time [i-2] is in the "day mode", so as shown in FIG.
2] and the binarized image [i-3, i-2] do not exist.
Therefore, the binarized image [i-2, i-1] is, for example, the difference binarized image [i-2, i-1] and the captured binarized image [i.
-1] and the mask image [i-2] is
For example, it is obtained from the logical product of the difference binary image [i-3, i-2] and the binary image [i-2, i-1]. Further, when the differential binarized image [i−2, i−1] is obtained, the threshold value for binary determination is switched between “day mode” and “night mode”. For example, the threshold is set to about "30" in the "day mode" and increased to about "60" in the "night mode". "Night mode" is better
This is because the difference between light and dark is large, and unless the threshold value is raised, a lot of noise occurs in the difference binary image.

The example shown in FIG. 10 shows a state in which noise is mixed in a moving image or the like at time [i], time [i + 1], and time [i + 2]. When other noise components are present in the moving body image, the moving direction and moving distance of the block in which the other noise components are present are detected by the “(block) motion vector” shown in FIG. Therefore, before obtaining the moving image,
Remove other noise components.

Here, two methods for removing other noise components before obtaining the moving body image will be described. [First Method] In the first method,
This is a method in which an isolated minute moving body (high-luminance body) is regarded as noise. As described above, the images used in this embodiment are all digital images in which individual pixels for measuring brightness (luminance) are arranged in an orderly manner. In addition, the moving image [i] has a pixel portion of the captured image [i] corresponding to a portion of the mask image [i] where the pixel is “0” (in this case, a white portion in the mask image [i]). The moving object image [i] can be obtained by setting it to "0" (in this case, white). From this, in the moving body image, it can be determined that the moving body is an isolated moving body (high-luminance body) by determining that the pixel is surrounded by "0". Further, the determination as to a minute moving body (high-luminance body) is performed by counting the number of pixels forming an isolated moving body (high-luminance body), and determining that the number of pixels is a predetermined number (for example, 6) or less. Just make a decision. By the above method, an isolated minute moving object (other noise component) can be removed from the moving object image.

[Second Method] In the second method, in the process of obtaining the binary difference image, the threshold value for judging the binary value of "1" or "0" from the absolute value of the difference is appropriately changed. However, this is a method of removing other noise components from the differential binary image. The threshold value is the total area (the number of pixels of “1”, etc.) of the area (pixels) in which the absolute value of the difference in the difference binary image is equal to or more than the threshold value, and the total area of the binarized image (all the constituent pixels (Number of etc.) and the ratio. Even if the threshold is changed according to the ratio of the total area of the regions (pixels) in which the absolute value of the difference in the difference binarized image is equal to or greater than the threshold to the total area of the regions (pixels) less than the threshold. Good. Various methods are possible for changing the threshold value based on the area of the region (pixel) in which the absolute value of the difference in the difference binarized image is equal to or larger than the threshold value.

For example, in FIG. 10, time [i-1]
In the difference binarized image [i-2, i-1] in, the threshold value is "60". In this example, the difference binarized image [i-
Since the noise component remains in [2, i-1], the noise component remains in the binarized image [i-2, i-1]. For example, the ratio of the total area of the regions (pixels) in which the absolute value of the difference in the difference binarized image is equal to or more than the threshold to the total area is the first
When the ratio becomes equal to or more than a predetermined ratio, the threshold value is increased to “70” and is used in the next process of obtaining the difference binarized image. Also,
On the contrary, for example, the ratio of the total area of the regions (pixels) in which the absolute value of the difference in the difference binarized image is equal to or more than the threshold value to the entire area is less than the second predetermined ratio (first predetermined ratio> When it reaches the second predetermined ratio), the threshold value is reduced to “60” and is used in the next process for obtaining the difference binarized image. in this way,
It is possible to reduce the noise amount by changing the threshold value according to the amount of the high brightness area.

[Second Embodiment (A Moving Object is Detected Only from Luminance Information Without Using Difference)] Next, a second embodiment in the "night mode" will be described with reference to FIG. To do. In the second embodiment, the detection area is set to the first
The images are taken at predetermined time intervals, and the taken images are obtained and stored. In addition, the captured image is composed of multiple areas,
Each area has brightness data for each area, and is a cluster of areas having a predetermined brightness or higher in a captured image (for example, a portion where adjacent areas are continuously higher than the predetermined brightness without interruption).
A portion having an area equal to or larger than a predetermined value is detected as a moving body. For example, at time [i], the processing device 2 obtains the captured image [i] and stores the captured image [i] in the storage device 3, and the captured image [i] has a predetermined brightness or higher (for example, the brightness “220”).
The above area) is set to “1 (black)”, and the area less than the predetermined brightness is set to “0 (white)” to obtain the photographed binary image [i]. Then, from the photographed image [i], the photograph 2
The moving body image [i] is obtained by extracting only the "1 (black)" portion of the binarized image [i]. Then, a region (lump portion) that is an isolated portion and has a predetermined area or more (for example, the number of pixels “100” or more) is determined as a moving body. The noise component, the removal of the fixed high-intensity body, and the processing method of “motion vector” are the same, and the description thereof will be omitted. As described above, in the second embodiment, the moving body image can be obtained more easily than in the first embodiment.

In this case, the moving body image [i] corresponding to the photographed image [i] photographed at the time [i] is extracted at the time [i]. In addition, when switching from the “day mode” to the “night mode” and when switching from the “night mode” to the “day mode”, the presence / absence of the differential binarized image, the moving object in the moving object image ( Since the case of the moving body itself and the case of the high-luminance body are different, for example, the detection of the motion vector is not executed only at the time of switching.

[Application to Vehicle Approach Warning Device] When the moving body (high brightness body) obtained in the “night mode” is larger than a predetermined size (area) by the above moving body detection method, The moving body (high brightness body) is recognized as a vehicle. Then, the "(moving body) motion vector" of the recognized vehicle is obtained based on at least two moving body images, and an alarm is issued from the alarm device based on the direction, speed, and position of the "(moving body) motion vector". generate. For example, in the motion vector plane [i-1, i] in FIG.
The “(moving body) motion vector” is a predetermined point (for example, an intersection, and in this case, the motion vector plane [i−1,
If it is moving toward (approaching) the bottom edge of i], an alarm is issued. Alternatively, the size of the “(moving object) motion vector” that is (approaching) toward the predetermined point (in this case, the lower end of the motion vector plane [i-1, i]) is the predetermined size. If it is larger than that (when the speed is high), an alarm is generated. Alternatively, the position of the “(moving object) motion vector” heading (approaching) in the direction of the predetermined point (in this case, the lower end of the motion vector plane [i-1, i]) becomes the predetermined position. When arrived (for example, block (5, 1) to block (8, 8)
If either position is reached), an alarm is generated.

The moving body detection method and the moving body detection apparatus of the present invention are not limited to the processing or the configuration described in the present embodiment, and various modifications can be made without departing from the scope of the present invention.
It can be added and deleted. For example, the configuration of the moving body detection device is not limited to that shown in FIG. 1, and various configurations are possible. The present invention is not limited to the detection of a moving body (vehicle) traveling on a road, but can be applied to the detection of various moving bodies. Although the present embodiment has been described using the luminance information,
It is also possible to use color information. (It is also possible to distinguish a similar group of color information as a moving body.)
Further, the method for determining whether to switch between the “day mode” and the “night mode” and the processing method at the time of switching described in the present embodiment are not limited to the description of the present embodiment, and various methods are possible. The numerical values used in the description of the present embodiment are examples, and the present invention is not limited to these numerical values. The images, graphs, etc. shown in the present embodiment are examples, and the present invention is not limited to these images, graphs, etc. Further, the above (≧), the following (≦), the greater (>), the less than (<) and the like may or may not include an equal sign.

[0054]

As described above, the moving object detecting method according to any one of claims 1 to 6, the moving object detecting device according to any one of claims 7 to 9 or the vehicle approach warning device according to any one of claims 10 to 11 is provided. If used, a moving object (vehicle or the like) can be accurately detected even at night when the amount of light is small.

[Brief description of drawings]

FIG. 1 is a schematic configuration diagram of an embodiment of a moving body detection device of the present invention.

FIG. 2 is a diagram illustrating a detection principle of a moving object detection method in the case of daytime or the like (day mode) where the light amount is large.

FIG. 3 is a diagram for explaining the detection principle of the moving body detection method in the case of nighttime when the amount of light is small (night mode) according to the present invention.

FIG. 4 is a diagram showing how the process of FIG. 3 is continuously executed at first predetermined time intervals.

FIG. 5 is a diagram illustrating a method of obtaining a difference binarized image from a difference between two captured images.

FIG. 6 is a diagram showing an example in which there are few captured images in which a moving body exists.

FIG. 7 is a diagram illustrating a method of accurately detecting a low-speed moving body and a high-speed moving body with high accuracy.

FIG. 8 is a diagram illustrating a method of obtaining a moving direction and a moving speed of a moving body based on the obtained moving body image.

FIG. 9 is a diagram illustrating a method of removing an object (fixed high-intensity body) that is not moving but is detected as a moving body (high-intensity body).

FIG. 10 is a diagram illustrating another method of removing a noise component.

FIG. 11 is a diagram showing an example of a luminance distribution.

FIG. 12 is a diagram for explaining a second embodiment of the present invention in the case of nighttime or the like (night mode) where the amount of light is small.

[Explanation of symbols]

1 Imaging device 2 processing equipment 3 storage devices 4 Alarm device

─────────────────────────────────────────────────── ─── Continuation of front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) G06T 7/60 G06T 7/60 150J G08G 1/056 G08G 1/056 // B60R 21/00 628 B60R 21 / 00 628B F term (reference) 5B057 AA16 BA29 BA30 CA08 CE12 DA07 DB09 DC04 DC22 5H180 BB09 BB15 CC04 DD02 GG09 5L096 AA06 BA04 DA03 FA59 FA69 GA08 GA19 GA51 HA04

Claims (11)

[Claims] 1. A detection region is photographed at a first predetermined time interval, a photographed image is obtained and stored, and the photographed image is composed of a plurality of regions, and each region has luminance data for each region. A moving body detection method, which detects a portion in which a lumped area of a region having a predetermined luminance or more in a captured image is a predetermined value or more as a moving body. 2. The moving object detection method according to claim 1, wherein each region of the photographed image [i] at time [i] has two types of regions, a region having a predetermined brightness or more and a region having a predetermined brightness or less. The photographed binary image [i] classified into the above is obtained, and the moving body image [i] corresponding to the time point [i] is obtained based on the obtained photographed binary image [i] and the photographed image [i]. ,
A moving body detection method for detecting a moving body based on the obtained information of the moving body image [i]. 3. A detection area is photographed at a first predetermined time interval, a photographed image is obtained and stored, and the photographed image is composed of a plurality of areas, and each area has luminance data for each area. , The captured image [i] at time [i] and the captured image [i]
For the captured image [i] (n is an integer greater than or equal to 1) and the captured image [i + n] n times in the future for the captured image [i], the captured image [i -N] based on the difference between the captured image [i] and the binarized image [i-n, i] based on the difference between the captured image [i] and the captured image [i + n] The binarized difference binary image [i, i + n] is obtained, and the captured image [i-n], the captured image [i], and the captured image [i
+ N], each region is classified into two types of regions, that is, a region having a luminance equal to or higher than a predetermined luminance and a region having a luminance lower than the predetermined luminance, a photographed binarized image [i-n], a photographed binarized image [i], and A photographed binarized image [i + n] is obtained, and 2 based on the obtained difference binarized image [i-n, i], photographed binarized image [i-n], and photographed binarized image [i]. The binarized image [i-n, i] and the calculated difference binarized image [i, i
+ N] and the captured binary image [i] and the captured binary image [i +
n] and the binarized image [i, i + n], and the binarized image [i−n, i] and the binarized image [i, i]
+ N], the mask image [i] corresponding to the time point [i] is obtained, and the moving body image corresponding to the time point [i] is obtained based on the obtained mask image [i] and the captured image [i]. A moving body detection method of obtaining [i] and detecting the moving body based on the obtained information of the moving body image [i]. 4. The moving object detection method according to claim 3, wherein when a difference binarized image is obtained, an area in which an absolute value of a difference between brightness data of corresponding areas of two captured images is equal to or more than a threshold value. Then, the difference binarized image is obtained by classifying into two types of regions that are less than the threshold value, and the threshold value is changed based on the brightness distribution of the region of the captured image,
Moving object detection method. 5. The moving body detection method according to claim 3, wherein the value of n is changed based on at least one of the detected position and speed of the moving body. 6. The moving body detection method according to claim 1, wherein when the moving body is detected, the first predetermined time interval is shortened,
A method of detecting a moving body, wherein the first predetermined time interval is lengthened when the moving body is not detected. 7. An imaging device, a processing device, and a storage device, wherein the imaging device captures an image of the detection region at a first predetermined time interval, and the processing device captures an image at a first predetermined time interval. A moving body detection device that stores the captured image in a storage device and detects the moving body using the moving body detection method according to any one of claims 1 to 6. 8. An imaging device, a processing device, a storage device, and an alarm device are provided, the imaging device captures an image of the detection region at a first predetermined time interval, and the processing device has a first predetermined time interval. Then, the captured image is stored in the storage device, the moving body is detected by using the moving body detection method according to claim 2, and the moving body is detected based on at least two moving body images. A moving body detection device which obtains an alarm from a warning device when a moving body is approaching a predetermined point by obtaining a position and a moving direction. 9. The moving body detection device according to claim 7, further comprising at least one of an AC power supply and a solar cell as a power supply. 10. An imaging device, a processing device, a storage device, and an alarm device, wherein the imaging device captures an image of the detection region at a first predetermined time interval, and the processing device has a first predetermined time interval. Then, the captured image is stored in a storage device, the moving body is detected by using the moving body detecting method according to claim 2, and the moving body is detected based on the size of the detected moving body. Is a vehicle, and based on at least two moving body images,
A vehicle approach warning device that obtains the determined position and moving direction of a vehicle and issues an alarm from an alarm device when the vehicle is approaching a predetermined point. 11. The vehicle approach warning device according to claim 10, comprising at least one of an AC power supply and a solar battery as a power supply.