JP6874980B2 - Animal identification programs, animal identification devices, and animal capture systems - Google Patents

Description

The present invention relates to animal identification programs, animal identification devices, and animal capture systems.

In recent years, damage to crops and humans by wildlife living in the mountains has increased, and wildlife capture and extermination are being carried out as one of the countermeasures. For the capture of wildlife, an animal capture device that guides the wildlife into the cage and traps it in the cage is used.

The animal catching device puts food or the like that feeds the animal to be caught in the cage with the entrance of the animal in the cage open, and waits for the animal to enter the cage. Then, when the animal enters the cage, the entrance of the animal is blocked by a shutter or the like to confine the animal in the cage. At this time, the animal capture device detects whether or not the animal to be captured has entered the cage by various sensors installed in the cage. As one of the animal capture devices that detect animals by the sensor, a power-increasing infrared sensor and a photoelectric switch can be combined to reliably capture only solids of the desired size among the animals that have entered the cage. (See, for example, Patent Document 1). In this type of capture device, when an infrared sensor inserted into the cage's internal space through a through hole in the cage detects that an animal has entered the cage, a photoelectric switch detects the size of the animal.

Japanese Unexamined Patent Publication No. 2013-243965

However, when detecting an animal that has entered the cage with a sensor inserted in the cage, it is difficult to search the entire internal space of the cage with one sensor. For this reason, a blind spot occurs when the sensor detects an animal, and the detection of the animal to be captured that has entered the cage may fail. If the detection of the animal to be captured fails, the opportunity to capture the animal may be missed.

In one aspect, the present invention aims to reliably detect animals that have entered the cage.

One embodiment of the animal identification program causes a computer to perform the following seven processes. The first process is to capture an image of the entire space inside the cage that can capture animals through the face grid, which is captured by an imaging device installed outside the cage including the face grid. This is the process to acquire. The second process is a process of detecting an animal from the acquired image. The third process is a process of extracting the contour of the animal detected from the image. The fourth process can capture the position of the animal in the image based on the presence or absence of a surface grid in the area surrounded by the animal's contour in the image and the positional relationship between the animal's contour and the cage. It is a process of grasping whether or not it is a position. The fifth process is a process of counting the grid points of the surface grid included in the region surrounded by the outline of the animal in the image. The sixth process determines whether or not the animal in the captureable position is the animal to be captured, based on the number of grid points of the surface grid contained in the area surrounded by the outline of the animal. It is a process. The seventh process is a process of outputting a signal for activating a shutter that blocks the entrance of the animal in the cage when the position of the animal is a position where the animal can be captured and the animal is the animal to be captured. is there.

According to the above aspect, it is possible to reliably detect an animal that has entered the cage.

It is a perspective view which shows the structure of the animal capture apparatus which concerns on one Embodiment. It is a top view which shows the appearance of a cage. It is a front view which shows the appearance of a cage. It is a figure which shows the functional structure of the animal identification apparatus which concerns on one Embodiment. It is a flowchart explaining the process performed by the animal identification apparatus which concerns on one Embodiment. It is a figure explaining the method of grasping the position of an animal. It is a figure (No. 1) explaining the relationship between the size of an animal and the number of grid points. It is a figure (2) explaining the relationship between the size of an animal and the number of grid points. It is a figure (3) explaining the relationship between the size of an animal and the number of grid points. It is a figure which shows the modification of the functional structure of the animal identification apparatus. It is a figure which shows the system configuration of the animal capture system which applied the animal capture apparatus which concerns on a modification. It is a figure which shows the hardware configuration of a computer.

FIG. 1 is a perspective view showing a configuration of an animal capture device according to an embodiment.
As shown in FIG. 1, the animal capture device 1 according to the present embodiment includes a cage 2, an image pickup device 3, a support column 4, and an animal identification device 5.

The cage 2 is a room for confining the animal 10. The cage 2 includes a box portion 201, a shutter 202, and a lock mechanism 203.

The box portion 201 has, for example, a shape in which a surface grid in which metal rods are combined in a two-dimensional grid shape is attached to five of the six opening surfaces in a frame assembled in a rectangular parallelepiped shape. .. The remaining one of the six opening surfaces of the box portion 201 is open as an entrance for the animal 10.

The shutter 202 is a surface grid (plate-shaped member) attached to the box portion 201 so that the entrance and exit of the animal in the box portion 201 can be opened and closed. For example, the shutter 202 can move along a rail (not shown) provided in the box portion 201 between an open position that opens the entrance of the animal and a closed position that closes the entrance of the animal. It is attached to the box portion 201. The open position may be a position that does not prevent the animal 10 to be captured from moving back and forth between the internal space and the external space of the box portion 201. In the cage 2 of FIG. 1, the position above the entrance of the animal is the opening position of the shutter 202.

The lock mechanism 203 is a holding mechanism attached to the cage 2 to hold the shutter 202 in the open position. The lock mechanism 203 has a configuration capable of switching between a locked state that prevents the shutter 202 from moving in the opening / closing direction and an unlocked state that allows the shutter 202 to move in the opening / closing direction. When the shutter 202 is moved in the direction of the open position when the lock mechanism 203 is in the unlocked state, and a predetermined portion of the shutter 202 is moved to the open position side of the predetermined position in the opening / closing direction, the lock mechanism 203 is unlocked. It switches from the state to the locked state. As a result, the shutter 202 is held in the open position. On the other hand, when the lock mechanism 203 is in the locked state, for example, when a predetermined signal is input from the animal identification device 5, the lock mechanism 203 switches from the locked state to the unlocked state. As a result, the shutter 202 is in a state where it can be moved toward the closed position.

The lock mechanism 203 may have a configuration capable of holding the shutter 202 that has reached the closed position in the closed position.

The image pickup device 3 is used for imaging the cage 2. The image pickup apparatus 3 is installed at a position outside the cage 2 so that the entire cage 2 can be imaged. In the example shown in FIG. 1, the image pickup apparatus 3 is installed at a position above the cage 2 installed on the ground by using the support column 4 so as to give a bird's-eye view of the entire cage 2. The installation height of the image pickup device 3 may be appropriately determined based on the angle of view θ of the image pickup device 3 and the approximate dimensions of the cage 2.

The animal identification device 5 acquires an image of the cage 2 captured by the image pickup device 3, and identifies whether or not the animal 10 to be captured exists in the cage 2 at a captureable position based on the image. .. The animal identification device 5 is connected to the image pickup device 3 by the first signal cable 601 and acquires an image of the cage 2 captured by the image pickup device 3 through the first signal cable 601. Further, the animal identification device 5 is connected to the lock mechanism 203 by a second signal cable 602. When it is recognized that the animal 10 to be captured exists in the cage 2, the animal identification device 5 transmits a second signal cable 602 to a signal for unlocking the lock mechanism 203 (hereinafter referred to as “unlock signal”). To send.

When an animal is captured by the animal capture device 1 according to the present embodiment, the animal 10 to be captured waits for the animal 10 to be captured to enter the cage 2 while the shutter 202 of the cage 2 is held in the open position. Whether or not the animal 10 to be captured has entered the cage 2 is determined by the animal identification device 5 based on the image of the cage 2 captured by the image pickup device 3. At this time, the animal identification device 5 uses the surface grid of the cage 2 to determine whether or not the animal has entered the cage 2 and whether or not the entering animal is the animal 10 to be captured.

FIG. 2A is a plan view showing the appearance of the cage. FIG. 2B is a front view showing the appearance of the cage. The x-axis and y-axis in FIG. 2A correspond to the x-axis and y-axis of FIG. 1, respectively. Further, the y-axis and the z-axis of FIG. 2B correspond to the y-axis and the z-axis of FIG. 1, respectively.

As the cage 2 for capturing animals, a cage having a size capable of accommodating the animal 10 to be captured is used. As shown in FIGS. 2A and 2B, the depth Ly1 in the cage 2 (in other words, the distance from the innermost position 201A of the box portion 201 to the shutter 202) is made longer than the body length A1 of the animal 10 to be captured. is there. More specifically, the depth Ly1 in the cage 2 is set so that the distance Ly2 from the innermost position 201A of the box portion 201 to the catchable line Lc is longer than the body length A1 of the animal 10 to be captured. The catchable line Lc is a line set to prevent the animal 10 that has entered the box portion 201 from going out of the cage 2 while the shutter 202 moves from the open position to the closed position. The catchable line Lc is set based on the agility of the animal 10 to be caught. An animal that has entered the box 201 tries to go out of the box 201 when it senses that the shutter 202 moves to the closed position due to, for example, a sound or the like. If the moving animal is agile, the animal may escape out of the box 201 before the shutter 202 reaches the closed position. Therefore, when the movement of the animal 10 to be captured is agile, the capture line Lc is set closer to the innermost position 201A of the box portion 201 than the shutter 202. In this case, the animal identification device 5 transmits an unlock signal to the lock mechanism 203 and closes the shutter 202 when the entire animal 10 that has entered the box portion 201 is located behind the capture line Lc. Move to. This deprives the animal 10 of the opportunity to escape from the cage 2 and makes it possible to capture the animal 10 more reliably. If the animal 10 to be captured is sluggish, the position of the shutter 202 may be set as the capture line Lc.

Further, the width Lx of the animal entrance 201B in the cage 2 is wider than the width A2 of the animal 10 so that the animal 10 to be captured can easily enter the box portion 201. Similarly, as shown in FIG. 2B, the height Lz of the animal entrance 201B in cage 2 (in other words, the distance from the ground 11 to the lower end of the shutter 202 held in the open position) is the target of capture. The height of an animal 10 is higher than A3.

Further, when the animals are confined in the cage 2 by the surface lattice, the cage 2 is an appropriate surface lattice in which the animal 10 to be captured is confined in a state where it is difficult to escape from the cage 2. That is, the thickness D of the metal rod 210 and the lattice pitches Px, Py, and Pz in the surface lattice of the cage 2 are selected based on the size and force of the animal 10 to be captured, respectively. For example, when the animal 10 to be captured is a ferocious animal such as a wild boar having a body length of 1 m or more, the surface lattice of the cage 2 has a metal rod thickness D of about 1 to several cm, and lattice pitches Px, Py, Each Pz is about a dozen cm. Further, for example, when the animal 10 to be captured is a small animal such as a mouse having a body length of about several cm to a dozen cm, the surface lattice of the cage 2 uses a thin metal wire having a thickness of about 1 mm instead of a metal rod. The lattice pitches Px, Py, and Pz are set to 1 to several cm, respectively.

The surface grids of the box portion 201 and the shutter 202 are not limited to the square grids as shown in FIGS. 2A and 2B, respectively, and may be square grids. For example, in the surface grid serving as the ceiling of the box portion 201 shown in FIG. 2A, the grid pitch Px in the width direction (x direction) and the grid pitch Py in the depth direction (y direction) may be different. Similarly, in the surface grid on the side surface of the box portion 201 shown in FIG. 2B, the grid pitch Py in the depth direction (y direction) and the grid pitch Pz in the height direction (z direction) may be different. Further, for example, the grid pitch Py in the depth direction in the surface grid serving as the ceiling of the box portion 201 may be different from the grid pitch Py in the depth direction in the surface grid serving as the side surface of the box portion 201.

In addition, each surface of the box portion 201 and the surface grid in the shutter 202 may have, for example, a diamond-shaped or hexagonal opening shape.

In the animal capture device 1 of the present embodiment, as described above, an image including the cage 2 is imaged by the image pickup device 3 installed above the cage 2 and at a position where the entire cage 2 can be imaged. The installation position of the image pickup device 3 is set based on the height and plane dimensions of the ceiling of the cage 2 (box portion 201) and the angle of view (imaging range) θ of the image pickup device 3. The image pickup device 3 may be installed at a position where the entire internal space from the innermost position 201A to the capture line Lc in the box portion 201 of the cage 2 can be imaged.

The image captured by the image pickup device 3 is transmitted to the animal identification device 5 through the first communication cable 601. The animal identification device 5 determines whether or not the animal 10 has entered the depth of the catchable line Lc in the cage 2 based on the image acquired from the image pickup device 3, and the invading animal 10 is the animal to be captured. Identify whether or not. When the animal 10 that has entered the cage 2 is the animal to be captured and the entire animal is located behind the capture line Lc, the animal identification device 5 uses the lock mechanism 203 through the second communication cable 602. Send an unlock signal to.

FIG. 3 is a diagram showing a functional configuration of the animal identification device according to the embodiment.
As shown in FIG. 3, the animal identification device 5 includes an image acquisition unit 510, an animal detection unit 520, an animal information extraction unit 530, a capture determination unit 540, and an output unit 550. In addition, the animal identification device 5 includes a storage unit 590 that stores various information including image data 591, grid information 592, and determination condition 593.

The image acquisition unit 510 acquires the image of the cage 2 captured by the image pickup device 3. The image data (image data 591) acquired by the image acquisition unit 510 is stored in the storage unit 590.

The animal detection unit 520 detects the animal shown in the image. For example, the animal detection unit 520 detects based on the difference (time change amount) between the image to be detected and the image captured before the image according to a known moving object detection method in the field of image processing. Detects the animals in the target image. The animal detection unit 520 may detect not only animals but also all moving objects in the image.

The animal information extraction unit 530 extracts animal information indicating the position, shape, and size of the detected animal based on the outline of the animal shown in the image and the surface grid of the cage 2. The animal information extraction unit 530 includes a contour extraction unit 531, a position grasping unit 532, and a grid point counting unit 533.

The contour extraction unit 531 extracts the contour of the animal from the image in which the animal is detected according to a known contour detection method in the field of image processing.

The position grasping unit 532 determines whether or not the existence position of the animal in the image is a captureable position. In the present embodiment, the position that is the internal space of the cage 2 (box part 201) and the whole animal exists behind the catchable line Lc is defined as the catchable position. That is, the position grasping unit 532 determines whether or not the existence position of the animal in the image is the internal space of the cage 2 (box part 201), and the box part 201 rather than the catchable line Lc for the entire animal. Determine if it exists in the back of. The position grasping unit 532 determines that the existence position of the animal is the internal space of the cage 2, for example, when the surface grid is reflected in the area surrounded by the outline of the animal in the image. Further, in the position grasping unit 532, for example, when the entire area surrounded by the outline of the animal in the image is on the innermost position 201A side of the cage 2 (box part 201) with respect to the capture line Lc, the position of the animal is located. Judge that it is a captureable position.

The grid point counting unit 533 counts the grid points included in the region surrounded by the outline of the animal among the grid points in the surface grid of the cage 2 (box portion 201) shown in the image.

The animal information extraction unit 530 counts the grid points in the grid point counting unit 533 when the existence position of the animal in the image is the internal space of the cage 2 and the position can be captured. When the grid points are counted, the animal information extraction unit 530 notifies the capture determination unit 540 of the animal information including the information indicating the contour of the animal and the information indicating the number of grid points in the area surrounded by the contour. To do.

The capture determination unit 540 determines whether or not to capture an animal based on the animal information extracted by the animal information extraction unit 530. Whether or not the capture determination unit 540 captures an animal based on, for example, whether or not the number of grid points and the distribution of the grid points contained in the area surrounded by the outline of the animal are within a predetermined range. Is determined. Whether or not the number of grid points and the distribution of grid points are within a predetermined range is determined by, for example, the determination condition 593 stored in the storage unit 590. The determination condition 593 includes, for example, information indicating the number of lattice points and the distribution of the lattice points, which are calculated in advance based on the lattice pitch of the surface lattice of the cage 2 and the size of the animal 10 to be captured. That is, the determination condition 593 includes information indicating the number of grid points and the distribution of grid points when the animal 10 to be captured is in the cage 2 (box portion 201) at a captureable position. The capture determination unit 540 notifies the output unit 550 of the determination result of whether or not to capture.

The output unit 550 outputs (transmits) an unlock signal to the lock mechanism 203 when the capture determination unit 540 determines that the animal is to be captured.

When the animal 10 is captured by the animal capture device 1, first, a cage 2, a support 4, an imaging device 3, and an animal identification device 5 are installed at a place where the animal 10 to be captured appears. At this time, for example, lattice information 592 including information indicating the lattice pitch of the surface lattice and the position of the lattice points reflected in the image captured by the image pickup device 3 in the cage 2 to be used is created, and the storage unit 590 of the animal identification device 5 is used. Remember. Further, for example, the determination condition 593 is created based on the lattice pitch in the cage 2 and the size of the animal 10 to be captured, and is stored in the storage unit 590 of the animal identification device 5.

After that, the shutter 202 of the cage 2 is held in the open position, and for example, a feeding bait or the like for guidance is arranged in the vicinity of the innermost position of the cage 2 (box portion 201). After preparing for capturing the animal 10 in this way, in the animal capture device 1 of the present embodiment, for example, the animal identification device 5 performs the process according to the flowchart of FIG. 4 for a predetermined time until the capture of the animal 10 is completed. Do it at intervals.

FIG. 4 is a flowchart illustrating a process performed by the animal identification device according to the embodiment.
First, the animal identification device 5 acquires an image captured by the image pickup device 3 (step S1), and performs a process of detecting the animal 10 from the image (step S2). The image acquisition unit 510 acquires the image in step S1. The animal detection unit 520 performs the detection process in step S2. The animal detection unit 520 determines whether or not an animal is shown in the image according to a known moving object detection method in the field of image processing, and detects the animal in the image.

Next, the animal identification device 5 determines whether or not the animal 10 has been detected from the image (step S3). The process of step S3 is performed by, for example, the animal detection unit 520. If no animal is detected (step S3; NO), the animal detection unit 520 determines that the processing after step S4 on the image acquired in step S1 is skipped (not executed). As a result, the animal identification device 5 ends the processing for the image acquired in step S1 and goes into a standby state until the start timing of the next step S1 arrives.

On the other hand, when an animal is detected (step S3; YES), the animal detection unit 520 causes the animal information extraction unit 530 to execute the process of extracting the animal information (steps S4 to S8).

The animal information extraction unit 530 first extracts the contour of the animal 10 from the image to be processed (step S4). The process of step S4 is performed by the contour extraction unit 531. The contour extraction unit 531 extracts the contour of the animal 10 in the image according to a known contour extraction method in the field of image processing.

Next, the animal information extraction unit 530 grasps the position of the animal based on the contour of the extracted animal (step S5). The process of step S5 is performed by the position grasping unit 532. The position grasping unit 532 first determines whether or not the surface grid of the cage 2 is reflected in the area surrounded by the outline of the animal in the image. When the surface grid is not shown, the position grasping unit 532 grasps that the existence position of the animal is outside the cage 2. On the other hand, when the surface grid is shown, the position grasping unit 532 grasps that the existence position of the animal is the internal space of the cage 2 (box 201). Further, when the surface grid is shown, the position grasping unit 532 grasps whether or not the existence position of the animal is a captureable position based on the positional relationship between the outline of the animal and the cage 2. In the present embodiment, for example, whether or not the animal is in a catchable position is determined based on whether or not the entire region surrounded by the outline of the animal is located behind the box portion 201 with respect to the catchable line Lc. judge. When the entire region exists on the back side of the box portion 201 from the catchable line Lc, the position grasping unit 532 grasps that the existence position of the animal 10 is behind the catchable line Lc.

After step S5, the animal information extraction unit 530 again determines whether or not the animal is in the cage 2 based on the grasped position of the animal 10 (step S6). The determination in step S6 is performed again by, for example, the position grasping unit 532. When the existence position of the animal is outside the cage 2 (step S6; NO), the position grasping unit 532 determines that the processing after step S7 on the image acquired in step S1 is skipped (not executed). As a result, the animal identification device 5 ends the processing for the image acquired in step S1 and goes into a standby state until the start timing of the next step S1 arrives.

On the other hand, when the animal 10 is in the cage 2 (step S6; YES), the animal information extraction unit 530 then determines whether or not the animal is behind the catchable line (step S7). The determination in step S7 is performed again by, for example, the position grasping unit 532. In the present embodiment, as described above, when the entire area surrounded by the outline of the animal is located behind the catchable line Lc, the position of the animal is behind the catchable line Lc. (The animal is farther than the catchable line). That is, when the catchable line Lc passes through the area surrounded by the outline of the animal 10 or is deeper than the area surrounded by the outline of the animal, the position grasping unit 532 determines the existence position of the animal 10. It is understood that the position is not deeper than the catchable line Lc. When the existence position of the animal 10 is not a position deeper than the capture line Lc (step S7; NO), the position grasping unit 532 skips the processing after step S8 on the image acquired in step S1 (does not execute). ). As a result, the animal identification device 5 ends the processing for the image acquired in step S1 and goes into a standby state until the start timing of the next step S1 arrives.

Further, when the animal 10 is behind the catchable line Lc (step S7; YES), the animal information extraction unit 530 then counts the grid points of the region surrounded by the contour (step S8). The process of step S8 is performed by the grid point counting unit 533. The grid point counting unit 533 of the face grid included in the region surrounded by the outline of the animal 10 in the image, for example, based on the information indicating the position of the grid points in the face grid in the image included in the grid information 592. Count the grid points.

After completing the process of step S8, the animal identification device 5 then determines whether or not the number and distribution of the grid points are within the predetermined ranges (step S9). The determination in step S9 is performed by the capture determination unit 540. The capture determination unit 540 determines whether or not the number of grid points counted in step S8 is within the range indicating the number of grid points in the case of an animal to be captured, which is set in the determination condition 593. Further, the capture determination unit 540 is an animal to be captured in which the distribution of the lattice points based on the contour of the animal extracted in step S4 and the number of lattice points counted in step S8 is set in the determination condition 593. It is determined whether or not it is within the range indicating the distribution of the grid points in the case. When either one or both of the number of grid points and the distribution of grid points is not within the predetermined range (step S9; NO), the capture determination unit 540 indicates that the animal 10 detected from the image is not the animal to be captured. Recognize that. In this case, the capture determination unit 540 determines that the process of step S10 is skipped (not executed). As a result, the animal identification device 5 ends the processing for the image acquired in step S1 and goes into a standby state until the start timing of the next step S1 arrives.

On the other hand, when the number and distribution of the lattice points are within the predetermined ranges, the capture determination unit 540 indicates that the animal 10 detected from the image is the animal to be captured and the existence position is a position where the capture is possible. Recognize that. Therefore, when the number and distribution of the lattice points are within the predetermined ranges (step S9; YES), the animal identification device 5 then outputs an unlock signal to the lock mechanism 203 of the cage 2 (step S9; YES). S10). The output unit 540 performs the process of step S10. As a result, the animal identification device 5 ends the processing for the image acquired in step S1 and goes into a standby state until the start timing of the next step S1 arrives.

When the output unit 540 outputs the unlock signal, the lock mechanism 203 changes from the locked state to the unlocked state. Therefore, the shutter 202 held in the open position moves (falls) to the closed position, and the entrance of the animal in the box portion 201 is blocked. This completes the capture of the animal 10.

As described above, the animal identification device 5 according to the present embodiment performs a process (step S6) of grasping the position of the animal when the animal 10 is detected from the image. The contents of the process of step S6 will be described with reference to FIG.

FIG. 5 is a diagram illustrating a method of grasping the position of an animal.
FIG. 5 shows an example of an image 12 captured by the image pickup device 3 when the animal 10 enters the internal space of the cage 2 (box portion 201). The position on the image is specified by a discrete value in pixel units. For example, when the image 12 is a U × V pixel rectangle, the position of each pixel is perpendicular to the number of pixels from the origin in the horizontal direction (u direction), with the pixel in the upper left corner as the origin (0,0). It is represented by the number of pixels from the origin in the direction (v direction).

When the image pickup device 3 is installed above the cage 2, for example, the depth direction in the cage 2 is the u direction of the image 12, and the entrance of the animal is to the left of the innermost position 201A of the box 201. To install. In this case, the innermost position 201A of the cage 2 (box 201) and the position of the captureable line Lc on the image 12 can be specified by the value (number of pixels) in the u direction, respectively.

When the animal 10 enters the internal space of the box portion 201, there is a surface grid that serves as the ceiling of the box portion 201 between the animal 10 and the imaging device 3. Therefore, when the animal 10 is present in the internal space of the box portion 201, the contour 13 of the animal 10 extracted from the image 12 is in a state of being divided by the metal rod 210 of the surface lattice as shown in FIG. Detected. When the contour 13 of the animal 10 is divided into a plurality of partial contours 1301, 1302, 1303, ... In this way, the contour extraction unit 531 complements the missing portion by, for example, the metal rod 210 of the surface lattice. A series of contours 13 is extracted. Further, in the position grasping unit 533, the presence position of the animal 10 is the internal space of the box portion 201 because the surface grid (metal rod 210) of the box portion 201 passes through the region surrounded by the contour 13 of the animal. To grasp. In addition, the position grasping unit 533 sets the existing position of the animal 10 inside the box portion 201 based on the information indicating that, for example, when the contour extraction unit 531 extracts the contour 13 and the portion missing by the surface grid is complemented. It may be grasped as a space.

When it is recognized that the animal 10 exists in the internal space of the box portion 201, the position grasping unit 303 of the animal identification device 5 determines whether or not the existence position of the animal 10 is a captureable position. The position grasping unit 303 includes the entire region surrounded by the contour 13 of the animal in the region on the image 12 which becomes the internal space of the cage 2 when the entrance of the animal is blocked by the shutter 202. In this case, it is determined that the animal is in the catchable position.

Further, the determination as to whether or not the existence position of the animal 10 that has entered the internal space of the box portion 201 is a captureable depth position is determined by the innermost part of the contour 13 extracted by the contour extraction unit 531. This can be done based on the positional relationship between the point Q farthest from the position 201A and the catchable line Lc. For example, as shown in FIG. 5, the position in the u direction of the pixel corresponding to the point Q farthest from the innermost position 201A of the box portion 201 in the contour 13 of the animal is the box portion 201 rather than the position of the captureable line Lc. It is assumed that the innermost position is 201A side. In this case, the distance Ly3 from the innermost position 201A of the box portion 201 to the point Q of the contour 13 is shorter than the distance from the innermost position 201A of the box portion 201 to the catchable line Lc. Therefore, the number of pixels in the u direction from the innermost position 201A of the box portion 201 to the point Q of the contour 13 is smaller than the number of pixels in the u direction from the innermost position 201A of the box portion 201 to the captureable line Lc.

As shown in FIG. 5, the position of each pixel is represented with the upper left corner of the image 12 as the origin, and when the innermost position of the box portion 201 exists to the right of the captureable line Lc, the point Q and the capture The existence position of the animal 10 may be determined based on the value in the u direction with respect to the possible line Lc.

Further, as described above, the position of the captureable line Lc may coincide with the position of the shutter 202. In this case, the position grasping unit 533 determines whether or not the entire area surrounded by the outline of the animal is included in the area on the image 12 which becomes the internal space of the cage 2 when the entrance of the animal is blocked by the shutter 202. Based on, it is determined whether or not the existence position of the animal 10 is a captureable position.

In this way, by grasping the existence position of the animal based on the contour 13 of the animal extracted from the image 12 including the entire cage 2, the blind spot with respect to the existence position of the animal 10 disappears. This makes it possible to correctly determine whether or not the animal 10 that has entered the cage 2 (box portion 201) can be captured.

Further, in the animal identification device 5 of the present embodiment, the capture determination unit 540 determines whether or not the animal 10 that has entered the captureable position is an animal to be captured (step S9). The capture determination unit 540 uses the grid points of the surface grid of the cage 2 (box portion 201) selected based on the size and force of the animal 10 to be captured, and captures the animals that have entered the capture position. Determine if it is the target animal. Therefore, in the animal identification device 5 of the present embodiment, the grid point counting unit 533 performs a process (step S8) of counting the grid points of the surface grid of the box portion 201 existing in the region surrounded by the outline of the animal. Do.

FIG. 6A is a diagram (No. 1) for explaining the relationship between the size of the animal and the number of grid points. FIG. 6B is a diagram (No. 2) for explaining the relationship between the size of the animal and the number of grid points. FIG. 6C is a diagram (No. 3) for explaining the relationship between the size of the animal and the number of grid points. Note that FIGS. 6A to 6C schematically show the surface grid 250 that serves as the ceiling in the box portion 201 of the cage 2 and the contours of the animals that have entered the cage 2.

FIG. 6A shows the relationship between the existence position of the animal and the number of grid points in the internal space of the cage 2 (box portion 201) as the first relationship between the size of the animal and the number of grid points.

The contours 13A and 13B of the two animals in FIG. 6A have the same shape and dimensions, but differ only in their positions in the cage 2. When an animal is present in the area surrounded by the upper contour 13A of the two contours 13A and 13B, the two metal rods 210 extending in the depth direction and the eight metals extending in the width direction in the surface grid 250 are present. The rod 210 passes through the area surrounded by the contour 13A. On the other hand, when an animal exists in the area surrounded by the lower contour 13B of the two contours 13A and 13B, three metal rods 210 extending in the depth direction and nine extending in the width direction in the surface grid 250. The metal rod 210 and the metal rod 210 of the above pass through the region surrounded by the contour 13B. In this way, the number of metal rods 210 of the surface grid 250 passing through the region surrounded by the outline of the animal changes depending on the position where the animal exists, and therefore the number of grid points included in the region surrounded by the contour of the animal. Will be a different value depending on the location of the animal. In the example of FIG. 6A, the number of grid points R in the region surrounded by the upper contour 13A of the two contours is 16, while the grid in the region surrounded by the lower contour 13B is The number of points R is 23. In FIG. 6A, among the grid points of the surface grid 250, the grid points R in the region surrounded by the contours 13A and 13B are represented by black circles. Therefore, for example, by setting that the number of lattice points in the area surrounded by the contour is 15 or more, it is possible to determine that the animal corresponding to the contour is the animal to be captured. It will be possible.

FIG. 6B shows the relationship between the size of the animal and the number of grid points in the internal space of the cage 2 (box portion 201) as the second relationship between the size of the animal and the number of grid points.

The contours 13A and 13C of the two animals in FIG. 6B show the contours of two animals of the same species but different sizes. For example, the upper contour 13A is the contour of the parent (adult), and the lower contour 13C is the contour of the child (juvenile). Even for animals of the same species, if the size is different, the number of metal rods 210 of the surface grid 250 passing through the contoured area is different, so the number of grid points in the contoured area is different. Makes a difference. In the example of FIG. 6B, the number of grid points R in the region surrounded by the upper contour 13A is 16, while the number of grid points R in the region surrounded by the lower contour 13C is 10. Is.

Among the animals 10 to be captured, for example, only parents (adults) that have grown to a certain size or larger may be targeted for capture. Even in such a case, whether or not the animal to be captured is an animal to be captured by determining whether or not the animal is to be captured based on the number of grid points in the area surrounded by the contour. It becomes possible to easily determine whether or not. For example, in the example of FIG. 6B, the juvenile can be excluded from the capture target by setting the number of lattice points in the region surrounded by the contour to be 12 or more as a determination condition. Therefore, for example, when a vermin is targeted for capture, it is possible to selectively capture a large solid (adult) that causes greater damage.

FIG. 6C shows the relationship between the species of the animal that entered the internal space of the cage 2 (box part 201) and the number of grid points as the third relationship between the size of the animal and the number of grid points.

The contours 13D and 13E of the two animals in FIG. 6C are the contours of two animals of different species. For example, the upper contour 13D is the contour of a quadrupedal animal to be captured, and the lower contour 13E is the contour of a snake.

It is also possible for an animal of a species different from the animal to be captured to enter the cage 2. Therefore, if it is determined whether or not an animal is a capture target only by the number of grid points R in the area surrounded by the outline of the animal, it is possible that an animal (species) that is not a capture target is erroneously determined as a capture target. There is sex. For example, in FIG. 6C, the number of grid points R in the region surrounded by the upper contour 13D is 10. Therefore, when an animal corresponding to the upper contour 13D is targeted for capture, for example, it is a condition for determining the capture target that the number of grid points R in the region surrounded by the contour is 10 or more. In this case, since the number of grid points in the region surrounded by the lower contour 13E in FIG. 6C is 11, it is determined that the animal (snake) corresponding to the lower contour 13E is the target of capture. In order to prevent such erroneous determination, in the present embodiment, in addition to the number of grid points R in the region surrounded by the contour of the animal, the distribution of the grid points R or the shape of the contour is taken into consideration in the cage 2. Determine if the invading animal is the target of capture.

For example, when a quadruped animal corresponding to the upper contour 13D in FIG. 6C is the target of capture, the distribution of grid points in the area surrounded by the contour (in the depth direction) based on the body length and width of the quadruped animal. It is possible to estimate the relationship between the number of pieces and the number of pieces in the width direction). Therefore, for example, by setting an upper limit for the dimension of the contour in the depth direction or the number of grid points in the depth direction, it is possible to prevent an animal that is not the target of capture from being erroneously determined to be the target of capture. It becomes. In the example of FIG. 6C, the dimension in the depth direction of the contour is 8 times or less of the grid pitch, or the number of grid points in the depth direction in the area surrounded by the contour is 7 or less. The animal (snake) corresponding to the contour 13E can be excluded from the capture target.

Note that FIGS. 6A to 6C show examples of the contours 13A and 13D of the animals to be captured, in which the animals corresponding to the contours face each other in the depth direction of the cage 2 (box portion 201). However, the orientation of the animals that have entered the cage 2 varies. Therefore, when counting the grid points included in the area surrounded by the contour of the animal, for example, as shown in FIGS. 6A to 6C, the animal corresponding to the contour is in the depth direction of the cage 2 (box portion 201). The grid points may be counted by rotating the contour so as to face the direction.

As described above, in the animal capture device 1 according to the present embodiment, the animal 10 to be captured enters the cage 2 based on the image 12 of the cage 2 captured by the image pickup device 3 installed outside the cage 2. Determine if it has been done. At this time, the image pickup device 3 is installed at a position where the entire space set as the space in which the animal to be captured can be captured in the internal space of the cage 2 can be imaged, and the internal space in the cage 2 and the image pickup device 3 are installed. The portion existing between and is referred to as a surface grid 250. Further, in the animal capture device 1 according to the present embodiment, the position of the animal in the image is based on the relationship between the contour 13 of the animal extracted from the image and the grid points of the surface grid 250 of the cage 2 on the image 12. Determines whether or not is inside the cage 2. As a result, there is no blind spot (that is, an undetectable range) when detecting an animal that has entered the cage 2, so that the animal capture device 1 according to the present embodiment has an accuracy of detecting an animal that has entered the cage 2. It will be very expensive. In addition, since it is possible to detect an animal that has entered the cage 2 without installing various sensors in the cage 2, even if an animal with strong alertness is the target of capture, the animal can be placed in the cage 2. It becomes easier to guide. Further, the cost can be reduced as compared with the case where the presence position and size of the animal are detected by the combination of a plurality of sensors such as the combination of the power raising type infrared sensor and the photoelectric switch.

Further, the surface grid 250 of the cage 2 in the animal catching device 1 has a grid pitch according to the size and force of the captured animal. Therefore, it is possible to easily grasp the size and shape of the animal in the image 12 based on the number and distribution of the lattice points in the region surrounded by the contour 13 extracted from the image 12. Therefore, according to the animal capture device 1 of the present embodiment, it is possible to prevent an animal that is not the capture target from being mistakenly determined to be the capture target and the shutter 202 of the cage 2 to be closed, resulting in failure to capture the animal to be captured. Is possible.

The animal capture device 1 in FIG. 1 is only an example of the animal capture device according to the present embodiment. The animal capture device according to the present embodiment can be appropriately changed as long as it does not deviate from the gist of the present embodiment. For example, the cage 2 may be able to capture an image capable of grasping the entire internal space in which the animal 10 in the box portion 201 can be captured by the imaging device 3 installed outside the cage 2. Therefore, the cage 2 may have a surface grid as a portion of the six surfaces surrounding the invading animal 10 that exists between the internal space of the cage 2 (box portion 201) and the imaging device 3. Further, the image pickup device 3 may be installed not only above the cage 2 but also at a position facing the side surface of the box portion 201. In this case, for example, among the side surfaces of the box portion 201, the side surface existing between the internal space of the box portion 201 and the image pickup device 3 is used as a surface grid, and is farther than the internal space of the box portion 201 when viewed from the image pickup device 3. Cover the side surface with a flat plate. By doing so, it becomes possible to determine whether or not the existence position of the animal is the internal space of the cage 2.

Further, the method of closing the entrance of the animal in the cage 2 (box part 201) with the shutter 202 can be appropriately changed. For example, the shutter 202 moves to the open position when the pressing load is received from the external space side of the box portion 201, and is held in the closed position when the pressing load is received from the internal space side. It may be attached to 201.

Further, the image pickup device 3 and the animal identification device 5 are not limited to the first communication cable 601 and may be connected by wireless communication according to a predetermined wireless communication standard. Similarly, the animal identification device 5 and the lock mechanism 203 are not limited to the second communication cable 602, and may be connected by wireless communication according to a predetermined wireless communication standard.

Further, the flowchart of FIG. 4 is only an example of the processing performed by the animal identification device 5. The process performed by the animal identification device 5 according to the present embodiment can be appropriately changed without departing from the gist of the present embodiment. For example, a plurality of animals may be captured by adding the number of animals to be captured in the cage 2 to the condition for outputting the unlock signal to the lock mechanism 203. Further, the determination of whether or not the animal that has entered the cage 2 is the target of capture depends on whether or not the number of grid points included in the area surrounded by the outline of the animal in the image is equal to or more than a predetermined number. You may judge. In addition, when determining whether or not the animal is a capture target based on the number of grid points contained in the area surrounded by the outline of the animal, the lower limit value and the upper limit value of the number of grid points to be captured are set. You may.

In addition, the animal identification device 5 according to the present embodiment may be configured to transmit, for example, an image or information on whether or not an animal has been captured to a monitoring device installed at a remote location.

FIG. 7 is a diagram showing a modified example of the functional configuration of the animal identification device.
As shown in FIG. 7, the animal identification device 5 according to the modified example includes an image acquisition unit 510, an animal detection unit 520, an animal information extraction unit 530, a capture determination unit 540, an output unit 550, and a storage unit 560. And. The image acquisition unit 510, the animal detection unit 520, the animal information extraction unit 530, and the capture determination unit 540 in the animal identification device 5 of FIG. 7 each have the same functions as the animal identification device 5 of FIG. Further, the storage unit 590 in the animal identification device 5 of FIG. 7 stores various data including image data 591, grid information 592, and determination condition 593 (see FIG. 3).

Further, the output unit 550 in the animal identification device 5 according to the modified example includes a first output unit 551 and a second output unit 552. When the animal identification device 5 determines that the animal in the cage 2 is the target of capture and the existence position of the animal is a captureable position, the first output unit 551 attaches the lock mechanism 203 of the cage 2 to the cage 2. On the other hand, the unlock signal is output (transmitted). On the other hand, the second output unit 552 outputs (transmits) to the monitoring device 15 the image of the cage 2 acquired by the image acquisition unit 510 and the information indicating that the unlock signal has been transmitted to the lock mechanism 203. .. The second output unit 552, for example, performs wireless communication with the nearest repeater 16 in accordance with a predetermined wireless communication standard, and transmits an image or the like to the monitoring device 15 via the repeater 16.

In this way, by transmitting the image of the cage 2 and the information indicating that the unlock signal has been transmitted from the animal identification device 5 to the monitoring device 15, the capture status of the animal 10 by the animal capture device 1 is monitored at a remote location. It becomes possible to do. For example, whether or not the animal was successfully captured in a remote place by transmitting the image of the cage 2 following the information indicating that the unlock signal was transmitted from the animal identification device 5 to the monitoring device 15. , It becomes possible to confirm whether or not the captured animal is an animal to be captured. As a result, when the animal is successfully captured or when the animal is unsuccessful, it is possible to promptly take an appropriate response. For example, when the animal capture device 1 is installed in the mountains, by checking the capture status with the monitoring device 15, it is possible to save the trouble of regularly visiting the installation location to confirm whether or not the animal has been captured. It will be possible.

Further, the animal capture device 1 provided with the animal identification device 5 according to the modified example can be applied to, for example, an animal capture system for the purpose of exterminating harmful animals.

FIG. 8 is a diagram showing a system configuration of an animal capture system to which the animal capture device according to the modified example is applied.

As shown in FIG. 8, the animal capture system 17 includes a plurality of animal capture devices 1, a repeater 16, a monitoring device 15, and a notification device 18.

Each of the plurality of animal capture devices 1 is installed at a predetermined position in the extermination target area 19. The animal identification device 5 in each of the plurality of animal capture devices 1 has the functional configuration shown in FIG. 7, and the image of the cage 2 acquired from the image pickup device 3 and the information indicating that the unlock signal has been transmitted can be obtained. It is transmitted to the monitoring device 15 via the repeater 16. The repeater 16 and the monitoring device 15 are connected via a communication network 20 such as the Internet.

Further, the alarm 18 in the animal capture system 17 is a device that notifies the person who collects the animals captured by the animal capture device 1 installed in the extermination target area 19 of the animal capture device 1 that has captured the animals. The alarm 18 performs wireless communication with the repeater 16 according to, for example, a predetermined wireless communication standard. When the repeater 16 or the monitoring device 15 acquires information indicating that the unlock signal has been transmitted from the animal identification device 5, information including the installation location of the animal capture device 1 including the animal identification device 5 that has transmitted the information. Is transmitted to the alarm 18. The alarm 18 is not limited to a dedicated device for notifying that an animal has been captured, and may be, for example, a smartphone or a computer having a communication function.

In the animal capture system 17 of FIG. 8, among the plurality of animal capture devices 1 installed in the extermination target area 19, the installation position of the animal capture device 1 in which the shutter 202 of the cage 2 is moved to the closed position and the capture of animals. It is possible to know from the alarm 18 whether or not the success is achieved. Therefore, it is possible to efficiently collect the captured animals and return the shutter 202 to the open position.

The system configuration of the animal capture system 17 is not limited to the configuration shown in FIG. 8, and can be changed as appropriate.

The animal identification device 5 according to the above embodiment can be realized by a computer and a program executed by the computer. Hereinafter, the animal identification device 5 realized by a computer and a program will be described with reference to FIG.

FIG. 9 is a diagram showing a hardware configuration of a computer.
As shown in FIG. 9, the computer 25 communicates with the processor 2501, the main storage device 2502, the auxiliary storage device 2503, the input device 2504, the output device 2505, the input / output interface 2506, and the medium drive device 2507. It includes a control device 2508. These elements 2501 to 2508 in the computer 25 are connected to each other by a bus 2510, and data can be exchanged between the elements.

The processor 2501 is a Central Processing Unit (CPU), a Micro Processing Unit (MPU), or the like. The processor 2501 controls the overall operation of the computer 25 by executing various programs including the operating system. Further, the processor 2501 executes, for example, an animal capture program including processing according to the flowchart of FIG.

The main memory 2502 includes a Read Only Memory (ROM) and a Random Access Memory (RAM) (not shown). In the ROM of the main storage device 2502, for example, a predetermined basic control program read by the processor 2501 when the computer 25 is started is recorded in advance. On the other hand, the RAM of the main storage device 2502 is used by the processor 2501 as a work storage area as needed when executing various programs. The RAM of the main storage device 2502 can be used for storing, for example, grid information 592, determination condition 593, and the outline of an animal extracted from an image.

The auxiliary storage device 2503 is a storage device having a larger capacity than the RAM of the main storage device 2502, and includes, for example, a Hard Disk Drive (HDD) and a non-volatile memory (Solid State Drive (SSD) such as a flash memory. ) Etc. The auxiliary storage device 2503 can be used for storing various programs, various data, and the like executed by the processor 2501. Auxiliary storage device 2503 can be used, for example, to store an animal capture program that includes processing according to the flowchart of FIG. Further, the auxiliary storage device 2503 can be used for storing, for example, image data 591, grid information 592, determination condition 593, and animal contours extracted from the image.

The input device 2504 is, for example, a keyboard device, a touch panel device, or the like. When the user of the computer 25 performs a predetermined operation on the input device 2504, the input device 2504 transmits the input information associated with the operation content to the processor 2501. The input device 2504 can be used, for example, for inputting an execution start command of an animal capture program, inputting and editing grid information 592 and determination information 593, and the like.

The output device 2505 is, for example, a display device such as a liquid crystal display device or a printing device such as a printer. The output device 2505 can be used for displaying and printing the operating status of the computer 25, the grid information 592, the determination information 593, and the like.

The input / output interface 2506 connects the computer 25 and other electronic devices. The input / output interface 2506 includes, for example, a Universal Serial Bus (USB) standard connector. The input / output interface 2506 can be used, for example, for connecting the computer 25 and the image pickup device 3 by the first communication cable 601 and connecting the computer 25 and the lock mechanism 203 by the second communication cable 602.

The medium drive device 2507 reads out the programs and data recorded in the portable storage medium 26, and writes the data stored in the auxiliary storage device 2503 to the portable storage medium 26. As the medium drive device 2507, for example, a memory card reader / writer corresponding to one or a plurality of types of standards can be used. When a memory card reader / writer is used as the medium drive device 2507, the portable storage medium 26 is a memory card (flash memory) of a standard supported by the memory card reader / writer, for example, a Secure Digital (SD) standard. ) Etc. are available. Further, as the portable recording medium 26, for example, a flash memory provided with a USB standard connector or the like can be used. Further, when the computer 25 is equipped with an optical disk drive that can be used as the medium drive device 2507, various optical disks that can be recognized by the optical disk drive can be used as the portable recording medium 26. Optical discs that can be used as the portable recording medium 26 include, for example, Compact Disc (CD), Digital Versatile Disc (DVD), Blu-ray Disc (registered trademark), and the like. The portable recording medium 26 can be used, for example, to store an animal capture program that includes processing according to the flowchart of FIG. Further, the portable recording medium 26 can be used for storing, for example, image data 591, grid information 592, determination condition 593, and animal contours extracted from the image.

The communication control device 2508 is a device that connects the computer 25 to a network such as the Internet and controls various communications between the computer 25 and other communication devices via the network. The communication control device 2508 performs wireless communication with, for example, a repeater 16 connected to the communication network 20, and is another communication device connected to the communication network 20 via the repeater 16 and the communication network 20. Communicate with.

When the user of the computer 25 inputs an execution start command of the animal capture program to the computer 25 using the input device 2504, the processor 2501 stores the animal capture program in a non-temporary recording medium such as the auxiliary storage device 2503. Is read and executed. While executing the animal capture program, the computer 25 performs processing according to the flowchart of FIG. 4, for example, according to a predetermined schedule. While executing the process according to the flowchart of FIG. 4, the processor 2501 serves as an image acquisition unit 510, an animal detection unit 520, an animal information storage unit 530, a capture determination unit 540, and an output unit 550 in the animal identification device 5. It works (it works). Further, while the processing according to the flowchart of FIG. 4 is being executed, the RAM of the main storage device 2502, the auxiliary storage device 2503, and the like are used for image data 591, lattice information 592, determination condition 593, and animals extracted from the image. It functions as a storage unit 590 that stores contours and the like.

The computer 25 operated as the animal identification device 5 does not need to include all the elements 2501 to 2508 shown in FIG. 9, and some elements may be omitted depending on the application and conditions. For example, in the computer 25, the medium driving device 2507 may be omitted. Further, when the animal capture device 1 is used alone, the communication control device 2508 can be omitted.

Regarding the above-described embodiment, the following additional notes will be further disclosed.
(Appendix 1)
An image that can grasp the entire space in which animals can be captured in the internal space of the cage is acquired through the surface grid, which is imaged by an imaging device installed outside the cage including the surface grid.
An animal was detected from the acquired image,
The contour of the animal detected from the image is extracted.
Based on the presence or absence of the surface grid in the area surrounded by the contour of the animal in the image and the position of the contour of the animal farthest from the innermost position of the cage, the animal in the image. Know if the position is a captureable position and
The grid points of the surface grid included in the region surrounded by the contour of the animal in the image are counted.
Based on the number of grid points of the surface grid included in the area surrounded by the contour of the animal, it is determined whether or not the animal at the catchable position is the animal to be captured.
When the position of the animal is a catchable position and the animal is the animal to be captured, a signal for activating a shutter that closes the entrance of the animal in the cage is output.
An animal identification program characterized by having a computer perform processing.
(Appendix 2)
In the process of determining whether or not the animal is the target of capture, when the number of grid points of the surface grid included in the region surrounded by the contour of the animal is equal to or greater than the threshold value, the captureable position Determining that the animal in the area is the animal to be captured,
The animal identification program according to Appendix 1, wherein the animal identification program is characterized in that.
(Appendix 3)
In the process of determining whether or not the animal is the target of capture, the capture is possible when the number of lattice points of the surface lattice included in the region surrounded by the contour of the animal is within a predetermined range. It is determined that the animal in the above position is the animal to be captured.
The animal identification program according to Appendix 1, wherein the animal identification program is characterized in that.
(Appendix 4)
In the process of determining whether or not the animal is the target of capture, the number of grid points of the surface lattice included in the region surrounded by the contour of the animal is equal to or more than the threshold value and is based on the contour of the animal. When the distribution of the grid points is within a predetermined range, it is determined that the animal at the catchable position is the animal to be caught.
The animal identification program according to Appendix 1, wherein the animal identification program is characterized in that.
(Appendix 5)
The process of grasping whether or not the position of the animal is a captureable position is performed in the area on the image that becomes the internal space of the cage when the entrance of the animal is blocked by the shutter. A process of determining that the animal is in the captureable position when the entire contoured area is included.
The animal identification program according to Appendix 1, wherein the animal identification program is characterized in that.
(Appendix 6)
In the process of grasping whether or not the position of the animal is a captureable position, the entire area surrounded by the outline of the animal is the position of the shutter on the image and the innermost position in the internal space of the cage. Includes a process of determining that the animal is in the catchable position when it is included in the innermost position side of the catchable line set between and.
The animal identification program according to Appendix 1, wherein the animal identification program is characterized in that.
(Appendix 7)
The process to be executed by the computer further includes a process of outputting information indicating that a signal for operating the shutter has been output to an external device.
The animal identification program according to Appendix 1, wherein the animal identification program is characterized in that.
(Appendix 8)
The process to be executed by the computer further outputs information indicating that a signal for operating the shutter is output to the external device, and then outputs an image of the cage acquired from the imaging device to the external device. Including processing,
The animal identification program according to Appendix 7, wherein the animal identification program is characterized by the above.
(Appendix 9)
Image acquisition that acquires an image that can grasp the entire space in which animals can be captured in the internal space of the cage 2 through the surface grid, which is imaged by an imaging device installed outside the cage including the surface grid. Department and
An animal detection unit that detects animals from the acquired image,
A contour extraction unit that extracts the contour of the animal detected from the image, and
Based on the presence or absence of the surface grid in the region surrounded by the contour of the animal in the image and the positional relationship between the contour of the animal and the cage, it is determined whether or not the animal is in a position where it can be captured. And the position grasping part to grasp
A grid point counting unit that counts the grid points of the surface grid included in the area surrounded by the contour of the animal in the image,
A capture determination unit that determines whether or not an animal at a captureable position is an animal to be captured based on the number of grid points of the surface grid included in the area surrounded by the contour of the animal. ,
When the animal in the captureable position is the animal to be captured, an output unit that outputs a signal for operating a shutter that closes the entrance of the animal in the cage, and an output unit.
An animal identification device comprising.
(Appendix 10)
In the capture determination unit, when the number of grid points of the surface grid included in the area surrounded by the contour of the animal is equal to or greater than the threshold value, the animal at the captureable position is the animal to be captured. Judge as there,
The animal identification device according to Appendix 9, wherein the animal identification device is characterized by the above.
(Appendix 11)
In the capture determination unit, the number of grid points of the surface grid included in the region surrounded by the contour of the animal is equal to or more than the threshold value, and the distribution of the grid points based on the contour of the animal is within a predetermined range. If, it is determined that the animal in the captureable position is the animal to be captured.
The animal identification device according to Appendix 9, wherein the animal identification device is characterized by the above.
(Appendix 12)
The position grasping unit is said to be the case where the entire region surrounded by the outline of the animal is included in the region on the image that becomes the internal space of the cage when the entrance of the animal is blocked by the shutter. Determining that the animal is in the capture position,
The animal identification device according to Appendix 9, wherein the animal identification device is characterized by the above.
(Appendix 13)
In the position grasping unit, the entire region surrounded by the outline of the animal is the innermost part of the capture line set between the position of the shutter on the image and the innermost position in the internal space of the cage. When it is included on the position side, it is determined that the animal is in the catchable position.
The animal identification device according to Appendix 9, wherein the animal identification device is characterized by the above.
(Appendix 14)
The output unit further outputs information indicating that a signal for operating the shutter has been output to an external device.
The animal identification device according to Appendix 9, wherein the animal identification device is characterized by the above.
(Appendix 15)
The output unit outputs the image of the cage acquired from the imaging device to the external device, following the information indicating that the signal for operating the shutter has been output.
The animal identification device according to Appendix 14, wherein the animal identification device is characterized by the above.
(Appendix 16)
An imaging device that captures an image of a cage including a surface grid, an image that is installed outside the cage and can grasp the entire space in which animals can be captured in the internal space of the cage via the surface grid, and the imaging device. An animal capture device provided with an animal identification device that identifies whether or not an animal to be captured has entered the cage based on the image captured in step 3, and a monitoring device that monitors the inside of the cage of the animal capture device. Including and
The animal identification device is
An image acquisition unit that acquires an image of the cage from the image pickup device, and
An animal detection unit that detects animals from the acquired image,
A contour extraction unit that extracts the contour of the animal detected from the image, and
Based on the presence or absence of the surface grid in the region surrounded by the contour of the animal in the image and the positional relationship between the contour of the animal and the cage, it is determined whether or not the animal is in a position where it can be captured. And the position grasping part to grasp
A grid point counting unit that counts the grid points of the surface grid included in the area surrounded by the contour of the animal in the image,
A capture determination unit that determines whether or not an animal at a captureable position is an animal to be captured based on the number of grid points of the surface grid included in the area surrounded by the contour of the animal. ,
When the animal in the captureable position is the animal to be captured, the first output unit that outputs a signal for operating the shutter that closes the entrance of the animal in the cage to the cage, and the first output unit.
A second output unit that outputs information indicating that a signal for operating the shutter has been output to the monitoring device, and a second output unit.
An animal capture system characterized by being equipped with.
(Appendix 17)
The second output unit outputs the image of the cage acquired from the imaging device to the monitoring device, following the information indicating that the signal for operating the shutter has been output.
The animal capture system according to Appendix 16, wherein the animal capture system is characterized in that.
(Appendix 18)
The animal capture system includes a plurality of said animal capture devices and an alarm.
The monitoring device transmits information indicating the animal catching device that outputs a signal for operating the shutter to the alarm.
The animal capture system according to Appendix 16, wherein the animal capture system is characterized in that.

1 Animal capture device 2 Cage 201 Box section 202 Shutter 203 Lock mechanism 250 Surface grid 3 Imaging device 4 Strut 5 Animal identification device 510 Image acquisition section 520 Animal detection section 530 Animal information extraction section 531 Contour extraction section 532 Position grasping section 533 Lattice point Counting unit 540 Capture judgment unit 550 Output unit 590 Storage unit 591 Image data 592 Lattice information 593 Judgment condition 10 Animal 12 Image 13, 13A to 13E Animal contour 15 Monitoring device 16 Repeater 17 Animal capture system 18 Alarm 19 Extermination target area 25 Computer 2501 Processor 2502 Main memory 2503 Auxiliary storage 2504 Input device 2505 Output device 2506 Input / output interface 2507 Media drive device 2508 Communication control device 2510 Bus 26 Portable recording medium

Claims (9)

Captured by the installed image pickup apparatus outside the cage including the surface grid, it acquires an image that can grasp the internal empty HazamaAkira of the cage through the surface grid,
An animal was detected from the acquired image,
The contour of the animal detected from the image is extracted.
Based on the presence or absence of the surface grid in the region surrounded by the contour of the animal in the image and the positional relationship between the contour of the animal and the cage, the region surrounded by the contour of the animal in the image. Grasp whether or not the whole is included in the area that will be the internal space of the cage,
The grid points of the surface grid included in the region surrounded by the contour of the animal in the image are counted.
Based on whether the number of grid points of the surface grating included in the area enclosed by the contour of the animal is greater than or equal to the threshold value, before kidou product is determined whether the animal capture target ,
The entire area surrounded by the outline of the animal is included in the area that becomes the internal space of the cage , and the number of lattice points of the surface lattice included in the area surrounded by the outline of the animal is equal to or greater than the threshold value. In some cases, it outputs a signal that activates a shutter that blocks the entrance of the animal in the cage.
An animal identification program characterized by having a computer perform processing. In the process of determining whether or not the animal is the target of capture, the number of grid points of the surface lattice included in the region surrounded by the contour of the animal is equal to or more than the threshold value and is based on the contour of the animal. If the distribution of the lattice points is within a predetermined range, it determines that the pre kidou product is an animal of the capture target,
The animal identification program according to claim 1. An image that can grasp the entire internal space of the cage through the surface grid, which is imaged by an imaging device installed outside the cage including the surface grid, is acquired.
An animal was detected from the acquired image,
The contour of the animal detected from the image is extracted.
The presence or absence of the surface grid in the area surrounded by the contour of the animal in the image and the movement.
Based on the positional relationship between the contour of the object and the cage, the entire area surrounded by the contour of the animal is the position of the shutter that blocks the entrance of the animal on the image and the maximum in the internal space of the cage. Grasp whether or not it is included in the innermost position side of the captureable line set between the inner position and
The grid points of the surface grid included in the region surrounded by the contour of the animal in the image are counted.
It is determined whether or not the number of lattice points of the surface lattice included in the region surrounded by the contour of the animal is equal to or greater than the threshold value.
The entire area surrounded by the outline of the animal is included on the innermost position side of the catchable line set between the position of the shutter on the image and the innermost position in the internal space of the cage. Moreover, when the number of lattice points of the surface lattice included in the area surrounded by the contour of the animal is equal to or more than the threshold value, a signal for activating the shutter that closes the entrance of the animal in the cage is output.
An animal identification program characterized by having a computer perform processing. The process to be executed by the computer further includes a process of outputting information indicating that a signal for operating the shutter has been output to an external device.
The animal identification program according to any one of claims 1 to 3. Captured by the installed image pickup apparatus outside the cage including the surface grid, an image acquisition unit that acquires an image that can grasp the internal empty HazamaAkira of the cage through the surface grid,
An animal detection unit that detects animals from the acquired image,
A contour extraction unit that extracts the contour of the animal detected from the image, and
Based on the presence or absence of the surface grid in the region surrounded by the contour of the animal in the image and the positional relationship between the contour of the animal and the cage, the entire region surrounded by the contour of the animal is the cage. a position detector detecting by determining whether Luke not included in the internal space and a region of,
A grid point counting unit that counts the grid points of the surface grid included in the area surrounded by the contour of the animal in the image,
Based on whether the number of grid points of the surface grating included in the area enclosed by the contour of the animal is greater than or equal to the threshold value, before kidou product is determined whether the animal capture target Capture judgment unit and
Included in the region where the entire region surrounded by the contour of said animal is the internal space of the cage, and the number of grid points of the surface grating included in the area enclosed by the contour of the animal is above the threshold In some cases, an output unit that outputs a signal that activates a shutter that closes the entrance of the animal in the cage, and
An animal identification device comprising. In the capture determination unit, the number of grid points of the surface grid included in the region surrounded by the contour of the animal is equal to or more than the threshold value, and the distribution of the grid points based on the contour of the animal is within a predetermined range. If it determines that the pre kidou product is an animal of the capture target,
The animal identification device according to claim 5. An image acquisition unit that acquires an image that can grasp the entire internal space of the cage through the surface grid, which is imaged by an imaging device installed outside the cage including the surface grid.
An animal detection unit that detects animals from the acquired image,
A contour extraction unit that extracts the contour of the animal detected from the image, and
Based on the presence or absence of the surface grid in the region surrounded by the contour of the animal in the image and the positional relationship between the contour of the animal and the cage, the entire region surrounded by the contour of the animal is described as described above. Whether or not it is included in the innermost position side of the catchable line set between the position of the shutter that blocks the entrance of the animal on the image and the innermost position in the internal space of the cage.
The position grasping unit that judges and grasps
A grid point counting unit that counts the grid points of the surface grid included in the area surrounded by the contour of the animal in the image,
A capture determination unit that determines whether or not the number of grid points of the surface grid included in the region surrounded by the contour of the animal is equal to or greater than a threshold value.
The entire area surrounded by the outline of the animal is included on the innermost position side of the catchable line set between the position of the shutter on the image and the innermost position in the internal space of the cage. Moreover, when the number of grid points of the surface lattice included in the area surrounded by the contour of the animal is equal to or greater than the threshold value, an output for outputting a signal for operating the shutter that closes the entrance of the animal in the cage. Department and
An animal identification device comprising. A cage including the surface grid, an imaging device for capturing an image that can grasp the internal empty HazamaAkira of the cage through the surface grid is disposed on the outside of the cage, based on the image captured by the imaging equipment Including an animal capture device provided with an animal identification device for identifying whether or not an animal to be captured has entered the cage, and a monitoring device for monitoring the inside of the cage of the animal capture device.
The animal identification device is
An image acquisition unit that acquires an image of the cage from the image pickup device, and
An animal detection unit that detects animals from the acquired image,
A contour extraction unit that extracts the contour of the animal detected from the image, and
Based on the presence or absence of the surface grid in the region surrounded by the contour of the animal in the image and the positional relationship between the contour of the animal and the cage, the entire region surrounded by the contour of the animal is the cage. a position detector detecting by determining whether Luke not included in the internal space and a region of,
A grid point counting unit that counts the grid points of the surface grid included in the area surrounded by the contour of the animal in the image,
A capture determination unit that determines whether or not the number of grid points of the surface grid included in the region surrounded by the contour of the animal is equal to or greater than a threshold value.
It included in the region where the entire region enclosed by the contour of the front kidou product becomes an internal space of the cage, and the number is the threshold of the lattice points of the surface grating included in the area enclosed by the contour of the animal In the above cases, the first output unit that outputs a signal for operating the shutter that closes the entrance of the animal in the cage to the cage, and
A second output unit that outputs information indicating that a signal for operating the shutter has been output to the monitoring device, and a second output unit.
An animal capture system characterized by being equipped with. A cage including a surface grid, an imaging device installed outside the cage and capturing an image capable of grasping the entire internal space of the cage through the surface grid, and the cage based on the image captured by the imaging device. It includes an animal capture device provided with an animal identification device for identifying whether or not an animal to be captured has entered the inside, and a monitoring device for monitoring the inside of the cage of the animal capture device.
The animal identification device is
An image acquisition unit that acquires an image of the cage from the image pickup device, and
An animal detection unit that detects animals from the acquired image,
A contour extraction unit that extracts the contour of the animal detected from the image, and
Based on the presence or absence of the surface grid in the region surrounded by the contour of the animal in the image and the positional relationship between the contour of the animal and the cage, the entire region surrounded by the contour of the animal is described as described above. It is determined whether or not the animal is included in the innermost position side of the catchable line set between the position of the shutter that blocks the entrance of the animal on the image and the innermost position in the internal space of the cage. The position grasping part to grasp and the
A grid point counting unit that counts the grid points of the surface grid included in the area surrounded by the contour of the animal in the image,
A capture determination unit that determines whether or not the number of grid points of the surface grid included in the region surrounded by the contour of the animal is equal to or greater than a threshold value.
The entire area surrounded by the outline of the animal is included on the innermost position side of the catchable line set between the position of the shutter on the image and the innermost position in the internal space of the cage. Moreover, when the number of grid points of the surface lattice included in the area surrounded by the contour of the animal is equal to or greater than the threshold value, a signal for activating the shutter that closes the entrance of the animal in the cage is sent to the cage. The first output unit to output and
A second output unit that outputs information indicating that a signal for operating the shutter has been output to the monitoring device, and a second output unit.
An animal capture system characterized by being equipped with.

Images