Dead chicken detection device and chicken farming system equipped with same

Abstract

To accurately and easily detect a dead hen in a poultry raising facility.SOLUTION: In detecting a dead hen 43 in a cage, the same place is imaged with an imaging device mounted on a feeding device every time feeding is done. In Fig. 3, there are six frames F1-F6. Presence or absence of the dead hen 43 is determined in each of the frames F1-F6, and the determination results are integrated and compared with a threshold. In Fig. 3(a), the dead hen 43 is determined in the frames F1, F2, F3, F4, and F6 five times in total, which is equal to or higher than a threshold of 5, so that it is determined that the dead hen 43 is present. The dead hen is not determined in the frame F5, but there is a possibility that the dead hen has failed to be determined. In Fig. 3 (b) in the meanwhile, the dead hen is sparsely determined in the frames F2 and F4, and the dead hen is not determined in the adjacent frames so that it is determined that the dead hen 43 is not present. The dead hen is determined less than the threshold of 5 times and there is a possibility of erroneous determination. In this manner, the dead hen 43 can be detected accurately and relatively quickly.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a device for detecting dead chickens by observing the inside of cages in a poultry farming facility, and a poultry farming system equipped with the same. [Background technology]

[0002] In recent years, chicken coops have become larger and feeding and other rearing tasks have been mechanized in order to improve egg production efficiency, i.e., to reduce the labor of producers, to be considerate of the surrounding environment, and to deal with chicken infectious diseases. However, even if the coop is isolated from the outside world to prevent infectious diseases, as the number of chickens raised increases and chickens have a short lifespan, a certain percentage of chickens will die. For example, in a large chicken coop that rears 100,000 chickens, 20 chickens may die a day, and in the summer, the number of dead chickens increases due to heat death caused by high temperatures.

[0003] These dead chickens not only decay themselves, but in some cases, they can block eggs laid by other chickens in the egg collection belt or at the back of the cage from rolling down the slope of the floor, which can cause a delay between laying and actually collecting the eggs. Also, with automated egg collection belts, if dead chickens get in the way, eggs cannot be collected. For this reason, dead chickens need to be removed as quickly as possible.

[0004] Meanwhile, in today's chicken coops, especially the large ones, rearing work has been automated, and chicken coops (chicken farming systems) have been realized where feeding, watering, egg collection, and manure disposal (replacement of floors) are all done without human intervention. Therefore, unlike in the old days when farmers raised chickens, there is no longer the opportunity to observe the chickens while feeding and collecting eggs, but dead chickens must be surveyed every day. However, with the aforementioned large scale, one chicken coop may have cages that are, for example, 100m long and 3m high, with 10 rows and two floors, and an inspection takes 1.5 to 2 hours, which is hard work.

[0005] Another problem is that the front of the cage has a continuous feed tray and egg tray running horizontally like a gutter, making it difficult to see inside the cage. Currently, a cage of a certain size often houses 10 or more chickens, and dead chickens are sometimes pushed along the slope of the floor by other chickens and discovered. For this reason, it often takes a certain amount of time for a dead chicken to be discovered. In particular, the top floor of the cage cannot be seen with the naked eye, so the keeper's intuition and experience are required, and there are many instances where something is overlooked.

[0006] In order to solve such problems, a dead chicken detection system has been proposed in Patent Document 1. Patent Document 1 uses a mobile camera vehicle to obtain visible and infrared images of the same location in a chicken coop, identifies pixels that match a specified registered chicken color (the color of dead chickens) from the visible image data, and identifies pixels with low temperatures from the infrared image data, and if a similar pixel is present near the matching pixel, i.e., if a mass is present, it is determined that a dead chicken is present. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Patent No. 6678898 Summary of the Invention [Problem to be solved by the invention]

[0008] In the above-mentioned conventional technology, dead chickens are detected relatively accurately even with a single image because the detection is based on two parameters, the chicken's color and body temperature. However, it takes a long time to determine whether a chicken has died or not, and it is not possible to detect chickens that have not yet died, even if they are already weak. Weak chickens not only do not lay eggs and waste feed, but they also get in the way of egg collection.

[0009] In addition, Tozai Industrial Trading Co., Ltd.'s dead chicken navigation system takes pictures of the inside of the cage early in the morning, and from the images, AI is used to determine that a dead chicken is one that does not move. However, even with this conventional technology, since it judges from a single image, it is difficult to make an accurate judgment if the image is taken in the early morning when the chickens are laying eggs, in the evening when they are resting, or when feeding activity is low.

[0010] An object of the present invention is to provide a dead chicken detection device that can accurately and quickly detect dead or weakened chickens, and a poultry farming system equipped with the same. [Means for solving the problem]

[0011] The dead chicken detection device of the present invention is a device for detecting dead chickens in cages containing chickens, wherein the cages are arranged in a plurality of rows at least horizontally, and the device comprises an imaging device that moves horizontally while taking successive images of the inside of the cages, a first determination means that analyzes the images taken by the imaging device and makes a provisional determination as to whether or not the chicken is a dead chicken, and a second determination means that accumulates the determination results of the first determination means for a predetermined number of times by matching the movement position standard of the imaging device, and makes a final determination that the chicken is an actual dead chicken if the result is above a predetermined threshold.

[0012] According to the above configuration, when detecting dead chickens in cages, in a large-scale chicken coop in which cages housing many chickens are lined up in a lateral (horizontal) direction (of course, in most cases they are also lined up in multiple layers in a vertical (vertical) direction), it is not practical to constantly observe each cage. Therefore, an imaging device is provided on a self-propelled cart, or preferably on a feeding device that drops feed while moving, and images of the inside of the cage are captured while moving laterally. Then, when analyzing the captured images to determine whether a chicken is dead, fine details such as movement cannot be determined if a determination is made from a single image, so the imaging device captures continuous images, and the first determination means provisionally determines whether or not the chicken is dead by, for example, performing image recognition on a frame-by-frame basis (for example, the belly is visible and the chicken is lying down).

[0013] However, this provisional judgment may lead to a judgment that a chicken is dead even if it is resting after eating or has its belly up to lay eggs. Therefore, a second judgment means is provided to accumulate the provisional judgment results of the first judgment means a predetermined number of times (in the chronological order). At that time, since the imaging device is moving, the timing is adjusted so that the movement position reference, for example, the wall or the wire mesh part of the cage, is matched, and the provisional judgment results are accumulated. The accumulated value is compared with a predetermined threshold, and if it is equal to or exceeds the threshold, it is officially judged to be a dead chicken.

[0014] Therefore, dead chickens are not judged based on a single image taken by a moving image taking device, but based on repeated judgment results at the same location at different times, so at least the threshold number of movements (image taking) are required before a judgment can be made, which takes some time, but still allows accurate detection of dead chickens and weak chickens relatively quickly. Then, if an operator follows this judgment result and goes to the corresponding cage, he or she will be sure to find dead or weak chickens there, which improves the efficiency of the work of removing them, and there are no misses, earning the operator's trust.

[0015] In addition, in the dead chicken detection device of the present invention, the imaging device is provided on the feeding device or on a cart that follows the feeding device.

[0016] According to the above configuration, in a large-scale chicken coop in which cages housing many chickens are arranged in multiple tiers in the horizontal and vertical directions, an automatic feeding device is used that moves in front of each cage at a predetermined time along rails laid horizontally and throws feed into the feed trays (feeding trays) provided in each cage. Although the number of feeding times and time periods vary slightly depending on the chicken farmer, feeding is carried out, for example, five to six times during the day because the chickens are allowed to rest at night. Therefore, the imaging device is installed on this feeding device or a cart that follows it, for example, near the feed openings of each tier if the cages are stacked in multiple tiers, or on each tier on both sides if cages are provided on both sides.

[0017] And because chickens stand and move actively when eating, if you observe the chickens at this feeding time, especially by looking at the chicken's feet from a low viewpoint near the feeding tray, you can efficiently determine whether the chicken has died or not, and even its health condition, whether it is weak from summer fatigue, etc. Specifically, you can determine whether the chicken is healthy by looking at its belly or comb at the feeding time, or by the movement of its legs, which should move a little if it is standing.

[0018] In this way, by simply adjusting the timing of observing the chickens, dead chickens can be found relatively accurately and easily. Also, by observing at frequent feeding times, dead chickens can be found quickly. Furthermore, when an imaging device is provided in the feeding device, there is no need to provide a dedicated device as in Patent Document 1. On the other hand, when a feeding device has already been installed, a cart that follows the feeding device using the same walkway or rails and the imaging device is provided on the cart can be used to retrofit a dead chicken detection device that can observe chickens at feeding times.

[0019] Furthermore, in the dead chicken detection device of the present invention, the imaging device is characterized in that it observes the inside of the cage through the gap between a food receptacle (feeding tray) located relatively above and an egg receptacle located below.

[0020] According to the above configuration, the food receiver (feeding tray) is formed continuously in the horizontal direction like a gutter, which can hinder observation of the area around the chickens' feet from the low viewpoint. However, it is different from the egg receiver, which is also formed continuously in the horizontal direction like a gutter. By installing an imaging device so that it can look through the gap between the feed receiver and the egg receiver, it is possible to continue observing the area around the chickens' feet continuously and without obstruction between each cage, which is preferable.

[0021] In addition, in the dead chicken detection device of the present invention, the imaging device is provided in the feeding apparatus, and the feeding apparatus further includes a recording device for recording images captured by the imaging device, and the images captured by the recording device are transferred to the first judgment means at the starting point for replenishing feed to the feeding apparatus.

[0022] According to the above configuration, the feeding device travels back and forth in front of the cage, for example, 5 to 6 times a day, as described above, and it is necessary to replenish the feed at the base point for each travel. Therefore, the images captured by the imaging device are recorded in the recording device, and at the replenishment base point, the captured image data is collected and collected from the recording device to the first determination means by simple short-range wireless communication such as Wi-Fi (registered trademark). In this way, it is not necessary to lay wiring for detecting dead chickens in the feeding device or to install large-scale wireless communication equipment in a large (long) chicken coop, and the feeding device only requires the laying of conventional power lines and necessary control lines.

[0023] Furthermore, in the dead chicken detection device of the present invention, the first judgment means makes the provisional judgment by analyzing successive images from the imaging device and makes a binary judgment for each frame as to whether or not it is a dead chicken, and also makes a binary judgment as to whether or not it is passing through the moving position reference, and the second judgment means shifts the time axis of the binary judgment result as to whether or not it is a dead chicken and performs the accumulation for the predetermined number of times so that the moving position reference is consistent.

[0024] According to the above configuration, the first determination means provisionally determines whether or not the chicken is a dead chicken for each frame from the continuous images in a binary value, and determines whether or not the chicken has passed a moving position reference such as a wall or the wire mesh of a cage in that frame. Then, the second determination means, when accumulating the binary determination results as to whether or not the chicken is a dead chicken, adjusts the time axis of the binary determination results as to whether or not the chicken is a dead chicken so that the moving position reference is consistent.

[0025] Therefore, even if the travel speed of the feeding device, cart, etc. varies and the number of image frames between the movement position references (one cage) differs, the time difference can be adjusted and the binary provisional judgment results of whether or not a chicken is dead can be accurately accumulated in chronological order for a specified number of frames. The variation in the travel speed is caused by the wind direction and volume of the ventilation and cooling air, wheel slippage, or differences in drive voltage and load (amount of feed), etc. This makes it possible to accurately determine the result of the actual judgment of whether or not a chicken is dead.

[0026] Furthermore, in the dead chicken detection device of the present invention, the second judgment means is characterized in that it integrates the binary judgment result of whether or not the chicken is a dead chicken a predetermined number of times in accordance with a predetermined number of bits.

[0027] According to the above configuration, the first determination means does not determine whether a chicken is dead based on a single image capture result of the moving image capture device, but instead uses the result as a provisional determination result, and the second determination means accumulates the provisional determination results to make a final determination. The timing is adjusted so that the movement position reference of the image capture device, for example, a wall or a wire mesh part of a cage, coincides with the provisional determination results. During the accumulation, for example, if the binary determination result of whether or not a chicken is dead by the first determination means is less than a predetermined number of bits (frames) between the movement position references, i.e., for one cage, the second determination means inserts dummy bits (frames) and deletes bits (frames) if it is more than a predetermined number of bits (frames). Alternatively, without determining a predetermined number of bits (frames) for one cage, dummy bits (frames) are inserted according to the data with the largest number of bits (frames).

[0028] This makes it possible to compensate for variations in the moving speed (number of frames) of the imaging device when adjusting the timing and accumulating the determination results.

[0029] Furthermore, in the dead chicken detection device of the present invention, the second judgment means uses the result of the accumulation as reference data, creates data shifted one frame before and after, and compares the result of adding these three data together with the predetermined threshold value.

[0030] According to the above configuration, even if a dead chicken happens to be missed at the same timing and this is reflected in the accumulation result (count value), by adding data shifted forward or backward in timing and comparing it with the threshold value, such missed detection can be compensated for and an accurate judgment can be made.

[0031] Furthermore, the poultry farming system of the present invention is characterized by including the above-mentioned dead chicken detection device.

[0032] According to the above configuration, a poultry farming system can be realized that can easily and quickly identify weak chickens from dead chickens. Effect of the Invention

[0033] As described above, the dead chicken detection device and poultry farming system of the present invention equipped with it capture images of the inside of a cage while moving the imaging device laterally and analyzes the captured images. In determining whether a chicken is dead, the first determination means makes a provisional determination as to whether or not it is a dead chicken based on the state of the chicken in each successive image, such as whether its belly is visible and it is lying down, and the second determination means adjusts the timing so that the movement position reference of the successive images, for example the wall or the wire mesh of the cage, coincides, adds up the provisional determination results and compares them with a predetermined threshold value to make an actual determination of whether a chicken is dead.

[0034] Therefore, although it takes some time to make a judgment, since the judgment is made based on the repeated judgment results at the same location and at different times, it is possible to accurately detect everything from dead chickens to weak chickens. [Brief description of the drawings]

[0035] [Figure 1]1 is a block diagram of a poultry farming system equipped with a dead chicken detection device according to one embodiment of the present invention. FIG. [Diagram 2] FIG. 1 is a cross-sectional view of a portion of a chicken coop according to one embodiment of the present invention. [Diagram 3] FIG. 2 is a diagram for explaining an image of determining whether a dead chicken is present using the dead chicken detection device of FIG. 1, and is a diagram showing frame accumulation. [Figure 4] FIG. 4 is a diagram for explaining an image of frame timing adjustment in the frame accumulation in FIG. 3. [Diagram 5] FIG. 2 is a functional block diagram for explaining a determination method using the dead chicken detection device of FIG. 1. [Figure 6] FIG. 13 is a diagram showing the provisional determination of dead chickens. [Figure 7] FIG. 13 is a diagram showing how the center position of the cage wall is determined. [Figure 8] FIG. 8 is a diagram showing how frame timing is adjusted based on the determination results of FIG. 7. [Figure 9] FIG. 9 is a diagram for explaining a method for determining the presence or absence of dead chickens by integrating data timed in FIG. 8. [Figure 10] FIG. 10 is a diagram for explaining a method for determining whether or not there are actual dead chickens by processing the data in FIG. 9. [Figure 11] 11 is a diagram showing a data string as an example of the determination result of FIG. 10. FIG. [Figure 12] FIG. 13 is a diagram showing the search results for parameters for determining the presence or absence of dead chickens. [Figure 13] In FIG. 12, a diagram showing preferred parameters is shown. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0036] FIG. 1 is a block diagram of a poultry farming system equipped with a dead chicken detection device according to an embodiment of the present invention. FIG. 1(a) is a front view of a chicken coop 1, and FIG. 1(b) is a side view. The dead chicken detection device of this embodiment is generally used to monitor the health of many chickens, particularly dead chickens, raised in one or more chicken coops 1 from an office 11, and to share the information on mobile terminals 12 carried by breeders, etc. Note that the chickens raised are not limited to egg-laying females, and may be meat chickens or chickens in the growth stage up to adulthood. In addition, in this specification, a description of normal breeding other than the detection of dead chickens and unhealthy (weakened) chickens will be omitted.

[0037] FIG. 2 is a cross-sectional view of a part of a chicken coop 1 according to an embodiment of the present invention. In the chicken coop 1, multiple rows of cage chicken coops (only two rows (mountains) are shown in FIG. 1 for the sake of simplicity) 2 are formed in parallel with each other, for example, over 100 m in the width (depth in FIG. 1) direction. In each cage chicken coop 2, multiple (four in FIG. 1) tiers of cages 3 are stacked, and each cage 3 is divided into a predetermined length in the width direction by a wall 31 such as a wire mesh. Each cage 3 is divided into two in the depth (left and right in FIG. 1) direction, so that each cage chicken coop 2 can be accessed from the front and back. Each cage 3 houses, for example, ten or more chickens 41-43 (hereinafter, collectively referred to as reference number 4) in each of the two tiers. In one chicken coop 1, the cage chicken coops 2 as shown in FIG. 1 may be two stories high.

[0038] In front of the cages 3 arranged in the horizontal direction, a feed tray (feeding tray) 51 is installed at the top and an egg tray 52 is installed at the bottom, like a gutter. A water supply pipe 53 is installed in the horizontal direction at the back (center) of the cages 3 arranged back to back. A water supply port is installed in each cage 3 arranged back to back. The water supply port is, for example, a nipple-type waterer. When the chickens 4 push up the nipple-shaped protrusion 54 with their beaks, a valve opens and chicken drinking water flows down. The floor of the cages 3 is made of a coarse mesh plate 55, so that the droppings of the chickens 4 pass through the mesh plate 55 and fall onto the droppings removal belt 56 below. The droppings removal belt 56 is moved (circulated) at regular intervals to scrape off the droppings and dry them. The net plate 55 slopes downward from the rear (center) side of the back-to-back cages 3, allowing laid eggs to roll and making it easy to push out dead chickens.

[0039] In the large-scale cage poultry house 2 configured as described above, dead chickens such as those indicated by reference number 43 in the cage 3 and weak chickens such as those indicated by reference number 42 can generally be detected accurately and quickly by increasing the frequency of observing the inside of the cage 3. However, in a large-scale cage poultry house 2 in which the cages 3 housing a large number of chickens 4 are arranged in multiple stages in the horizontal direction and the vertical direction, it is not practical to observe each cage 3 all the time. It is therefore important to note that in the dead chicken monitoring device of this embodiment, an imaging device 7 is provided on the feeding device 6 that drops feed while moving, and the inside of the cage 3 is photographed in succession while moving in the horizontal direction. Then, the dead chickens 43 and weak chickens 42 are judged from the photographed images by a judgment means 111 provided in the office 11, as will be described in detail later. The imaging device 7 is not limited to the feeding device 6, but may be provided on a cart that follows it.

[0040] The feeding devices 6 are provided in each row (mountain) of the cage chicken house 2, and are controlled by a control device (not shown) to move on their own at a predetermined time to feed the feed receptacles (feeding trays) 51 of the cages 3 in each row (tier). For this purpose, rails 61 are laid on the upper front surface of each of the cages 3, which are lined up in large numbers in the horizontal direction, and wheels 62 run on the rails 61 to move a frame 63. The frame 63 is provided with feeding openings 64 corresponding to the feed receptacles (feeding trays) 51 of the cages 3 in each row (tier), and an imaging device 7 is installed near each feeding opening 64.

[0041] Specifically, when the imaging device 7 captures successive images while moving in front of the cage 3, the food receptacle (feeding tray) 51 and the egg receptacle 52 are formed continuously in the lateral (horizontal) direction like a gutter, as described above, and therefore in this embodiment, the imaging device 7 observes the inside of the cage 3 through the gap between the food receptacle (feeding tray) 51, which is positioned relatively higher, and the egg receptacle 52, which is positioned relatively lower.

[0042] 2, rails 61 are laid on the top and frame 63 runs while suspended from rails 61, making it easy to clean floor 10 of poultry house 1, but rails 61 may also be laid on floor 10. Frame 63 may also be stabilized by connecting opposing rows (mountains) to each other, and anti-sway rails and wheels or sliding plates that come into contact with the rails may be provided on the top and bottom of frame 63.

[0043] The imaging device 7 is realized by a digital video camera or the like, and each captured image is recorded in a common recording device 71 mounted on the feeding device 6 together with the camera's identification information and date and time information. Then, while the feeding device 6 is returning to the home position (base point) as shown in FIG. 1(b), the recording device 71 transmits the captured image data together to a router 102 installed near the home position by a short-range simple wireless communication 103 such as Wi-Fi (registered trademark). The captured image data received by the router 102 is further transmitted to a server 112 in the office 11 via a communication line 104 in the poultry farming facility and stored there. The home position is set, for example, at a location where a feed refilling machine 101 equipped with a feed tank and a hopper is installed. Although the number of feeding times and the time periods vary slightly depending on the poultry farmer, the chickens are allowed to rest at night, so the feeding device 6 leaves this home position and travels back and forth in front of the cages 3 at predetermined times, for example, 5 to 6 times during the day, and feed is replenished at the home position on each return (round trip).

[0044] The captured images in the server 112 are appropriately read out to the personal computer 111 for analysis, which is the first judgment means. Then, the image is recognized by artificial intelligence (AI) for each frame, and it is provisionally judged whether it is a healthy chicken 41 or a dead chicken 43. A dead chicken 43 is judged, for example, if it is lying down with its belly visible or its comb is on the floor. However, in this provisional judgment, the chicken that seems to be weak, as indicated by reference numeral 42, may be resting after eating or laying eggs, that is, healthy. Therefore, as the second judgment means, the personal computer 111 accumulates the provisional judgment results for a predetermined number of frames (in the chronological order), compares them with a predetermined threshold, and judges the chicken 43 to be a dead chicken if it is equal to or greater than the threshold.

[0045] It should be noted that since the imaging device 7 is moving, the personal computer 111 as the second judging means, when making the main judgment, adjusts the timing so that the wall 31 matches the moving position reference in the captured image, and accumulates the provisional judgment results. If the main judgment result indicates a dead chicken 43 or a weak chicken 42, it is displayed on the screen of the personal computer 111 together with the cage number, and the same information is shared with the mobile terminal 12 carried by the keeper via a public wireless communication line 113 such as a mobile phone line.

[0046] 3 and 4 illustrate an image of determining a dead chicken. FIG. 3(a) and FIG. 3(b) show the result of determining a dead chicken by the image recognition of the artificial intelligence (AI) in images taken at different times at the same position by the same imaging device on different dates or different imaging devices. In the example of FIG. 3, the number of accumulated frames n is set to 6 and the determination threshold t is set to 5 in determining a dead chicken. FIG. 3(a) and (b) show the six frames F1, F2, . . . , F6 arranged in three columns and two rows. In FIG. 3(a) and (b), a feed tray (feeding tray) 51 is shown at the top and an egg tray 52 is shown at the bottom, but the angle of view of the imaging device 7 may be adjusted to cut these out. In this embodiment, the image recognition of the artificial intelligence (AI) excludes these parts in advance, so that the angle of view can be expanded even when a general-purpose imaging device 7 is used.

[0047] In Fig. 3(a), a dead chicken 43 is detected five times in frames F1, F2, F3, F4, and F6, and although it was not detected in frame F5, it is possible that the detection was missed, so it is determined that a dead chicken 43 is present because the threshold value t is exceeded. On the other hand, in Fig. 3(b), it is detected sparsely in frames F2 and F4, and it is not detected in the previous and following frames either, so it is determined that the threshold value t is exceeded, so there is a possibility of a misdetection, and it is determined that a dead chicken 43 is not present.

[0048] Meanwhile, Fig. 4 is a diagram for explaining a method of adjusting the timing for the accumulation. Fig. 4(a) is an image captured at different times at the same position by the same imaging device 7, similar to Figs. 3(a) and (b). Similarly to Figs. 3(a) and (b), frames F1, F2, ..., F6 are shown in three rows and two columns. However, while Fig. 3 shows an image near the center of the cage 3, Fig. 4 shows an image near the wall 31, which serves as the reference for the movement position.

[0049] To be precise, Fig. 4(a) shows images captured at different times at what appears to be the same location. In the example of Fig. 4(a), wall 31 appears somewhere in images (frames) F1-F6. However, there is variation in the position of wall 31 in images (frames) F1-F6. This variation is often due to a difference in the speed of feeding device 6, since imaging device 7 is mounted on feeding device 6 and moves, and more specifically, due to the direction and volume of airflow for ventilation and cooling, slippage of wheels 62 against rails 61, fluctuations in driving voltage, the loading status of food, etc.

[0050] 4(a) simply accumulating frames F1-F6 will result in misalignment of chickens 41-43 within frames F1-F6, making it difficult to find dead chicken 43 or weak chicken 42. Therefore, when making a main judgment by accumulating frames F1-F6 as shown in FIGS. 3(a) and 3(b), personal computer 111, serving as the second judgment means, adjusts the timing so that the wire mesh portion of wall 31, serving as a reference for moving position in the captured images, coincides, and accumulates the provisional judgment results.

[0051] FIG. 4(b) shows the results of adjusting the timing of each image (frame) F1 to F6 in FIG. 4(a). In the following description, it is assumed that the imaging device 7 moves from right to left toward the screen. FIG. 4 shows an image in which the wall 31 is in the center of the image, that is, the image is just between the cages 3. In FIG. 4(a) and FIG. 4(b), the wall 31 is originally in the center of the image in frames F1 and F2, that is, there is no timing deviation, so no adjustment is required. In frames F3, F4, and F5, FIG. 4(a) shows that the wall 31 is on the left side of the screen, that is, the imaging device 7 is too slow and the wall 31 has not reached the center position of the image, and FIG. 4(b) shows that the timing is adjusted to be faster. Conversely, in frame F6, FIG. 4(a) shows that the wall 31 is on the right side of the screen, that is, the imaging device 7 is too fast and the wall 31 has passed the center of the image, and FIG. 4(b) shows that the timing is adjusted to be slower.

[0052] 5 is a functional block diagram for explaining the above-mentioned processing method in the personal computer 111 serving as the first and second determination means. Each imaging device 7 captures moving images P1, P2, ..., Pn (hereinafter, collectively referred to as P) for each round trip of the feeding apparatus 6. n is the number of accumulated frames, and for example, for one day, there are six feedings, so n=12. Then, as described above, for each image (frame) F1, F2, ..., Fn (hereinafter collectively referred to as F) of each video P, artificial intelligence (AI) recognizes the image and creates a string of consecutive binary data H1, H2, ..., Hn (hereinafter collectively referred to as H) that determines whether or not a dead chicken 43 is present in the image (frame) F, and also creates a string of consecutive binary data W1, W2, ..., Wn (hereinafter collectively referred to as W) that determines whether or not a wall 31 is present.

[0053] FIG. 6 is a diagram for explaining a method for creating the binary data H, W. As shown in FIG. 3, the moving image P is a succession of images of a given range at a given time in front of the cage 3. When this is expanded into a continuous screen for easy understanding, it becomes as shown in FIG. 6(a). Each image (frame) F is cut out from the given range, for example, as shown in FIG. 6(b). There are two images (frames) cut out in FIG. 6(b), and they are designated by the reference characters Fx and Fy. When a binary determination is made from these images (frames) Fx, Fy as shown in FIG. 6(c), the column of data W of the wall 31 becomes as shown in FIG. 6(d), and the column of data H of the dead chicken 43 becomes as shown in FIG. 6(e).

[0054] In accumulating the data H of the dead chicken 43 shown in FIG. 6(e) n times, it is necessary to specify the exact position of which cage and which position the data is from. Therefore, a position specifying process is performed to specify the actual center point of the wall 31 from the data W, which is the binary judgment result of the wall 31 shown in FIG. 6(d), and a data string indicating the judgment result of the center point is obtained as a moving position reference. FIG. 7 shows a method for determining the center point of the wall 31. Here, for example, the data H is 25 frames, i.e., 25 bits of data, and the wall data W is 15 frames, i.e., 15 bits of data, per cage 3, but in FIG. 7, the number of bits is reduced to simplify the drawing. The 25 frames of the data H are the number of frames in which the wall 31 is not reflected at all, and the 15 frames of the data W are the number of frames in which the wall 31 is reflected at least partially.

[0055] FIG. 7(a) is a string of data on the wall, similar to FIG. 6(d). In each image (frame) F, "1" indicates that a wall has been detected, and "0" indicates that a wall has not been detected. FIG. 7(b) is the actual center point of the wall 31. FIG. 7(c) is a graph showing the determination result of FIG. 7(a) as a broken line. In FIG. 7(c), when a wall 31 is detected (when the binary data becomes "1"), the counter starts counting, and when the count value cnt, which is the number of consecutive counts of frames in which the wall 31 is detected, reaches or exceeds the threshold value t, this section is determined to be a wall 31.

[0056] However, since the wall data W is 15 bits, even if the wall actually continues, if even one of the 15 bits is missed in the count (wall recognition), it may not be recognized as a wall even if the remaining data is correct, and two cages may be erroneously determined as one cage. Therefore, a counter that does not detect the wall 31 is provided, and when the wall 31 is no longer detected (when the binary data changes to "0"), the counter starts counting, and if the count value cnt' is less than a threshold value s, for example 1, the wall 31 is determined to continue (the count value cnt continues to be added), and if it is 2 or more, the wall 31 is determined to have ended (the count value cnt is stopped to be added). In FIG. 7(c), the center position of the count value cnt thus obtained is determined to be the center position of the wall in FIG. 7(b), as shown in FIG. 7(d).

[0057] However, the determination result of Fig. 7(d) may also vary in the number of images (frames) between the walls 31 if there is variation in the travel speed of the imaging device 7. As described above, this variation in travel speed is caused by the wind direction and volume of the ventilation and cooling air, wheel slippage, or differences in drive voltage and load (amount of food), etc. Therefore, in this embodiment, the number of bits is matched over the n number of integration times of the images (frames) for the determination result of the center position of the wall shown in Fig. 7(d).

[0058] Specifically, an example of a data string extracted from the determination results of FIG. 7(d) for the videos P1, P2, and Pn is shown in FIG. 8(a). In FIG. 8(a), the room (cage) 1 has the same width, and the position of the wall between the room (cage) 1 and the room (cage) 2 is the same between the videos P1, P2, and Pn. In contrast, there is a difference in the width of the room (cage) 2, and the position of the wall between the room (cage) 3 is the earliest in the video P1 and the latest in the video P2, with the video Pn being between them. Then, in this embodiment, as shown in FIG. 8(b), dummy data d is inserted into the data string up to the length of the latest video P2. Specifically, with the video P2 as a reference, dummy data d is inserted for two frames into the video P1 and for one frame into the video Pn. By doing so, the timing at which the wall 31 between the rooms (cages) appears can be matched between the videos P1, P2, and Pn. The data string of the wall center positions after timing adjustment created in this manner is indicated by the reference characters w1, w2, . . . , wn in FIG. 5 (hereinafter, they will be referred to collectively by the reference character w).

[0059] In the above example, to match the number of bits between videos P1, P2, and Pn, a dummy bit (frame) d is inserted to match the data with the largest number of bits (frames) (P2 in Figure 8(a)) without determining a specific number of bits (frames) for one cage. However, it is also possible to determine a specific number of bits (frames) for one cage (25+15=40 in the above explanation), and insert the dummy bit (frame) d if it is less than that, and delete the bit (frame) if it is more.

[0060] Then, when accumulating images (frames) n times for the row of data H of dead chicken 43 shown in Fig. 6(e), timing adjustment is performed for the row of data w at the center position of this wall 31. That is, dummy data d in the data w is similarly inserted into the corresponding data H of dead chicken 43 to adjust the bit length, and the data of wall 31 is also superimposed. In this way, data h1, h2,...,hn (hereinafter, collectively referred to as h) of dead chicken 43 after position alignment is created.

[0061] Thereafter, the data h of the dead chicken 43 after position alignment is accumulated (added in the chronological order) for n frames. An image of this accumulation is shown in FIG. 9. FIG. 9(a) shows an example of adding four frames with n=4, and to simplify the drawing, only the central position of the 15 bits of data for the wall 31 is shown, with the rest being set to "0" data. Similarly, the data within the room (cage) is also shown with a reduced amount. Simply accumulating the data h for the four frames in FIG. 9(a) results in the added data h0 shown in FIG. 9(b). The change in FIG. 9(b) is shown in graph form as shown in FIG. 9(c).

[0062] As is clear from the graph, if the threshold value t for determining that a chicken is dead is 2, then there should be a block, i.e. the period during which the integrated value exceeds 2 should be continuous to a certain extent, but there is a dip where the integrated value falls below the threshold during the period indicated by reference character B in Fig. 9(c). The integrated value in Fig. 9(b) is also "0", because the data h for the provisional determination of a dead chicken 43 in each frame in Fig. 9(a) contains a non-detected "0" indicated by reference character E1 due to a false detection at the same timing.

[0063] Even if such a false positive occurs, based on FIG. 7 described above, in the first, third, and fourth frames during the counting of the count value cnt, the count value cnt' is only "1." In other words, the dead chicken 43 is determined based on the preceding and following count values ​​cnt. In contrast, in frame 2, based on FIG. 7 described above, during the counting of the count value cnt indicated by reference character E2, the count value cnt' counts four "0"s, and the dead chicken 43 is not detected. The "1" indicated by reference character E3 is outside the cluster of "1s," and is simply a false positive.

[0064] The false detection indicated by reference symbol E1 in Fig. 9(a) happens to occur at the same timing across the four frames to be accumulated. However, in the example of Fig. 9, the non-detection "0" occurs only for one frame timing, so the added data h0 shown in Fig. 9(b) becomes "0" only for one frame period B, and according to Fig. 7 described above, the count value cnt' becomes only 1, so no detection error occurs. However, if the non-detection "0" occurs over two frame timings, and the threshold value for the count value cnt' remains at 1, it will be erroneously determined (overlooked) that there is no dead chicken 43.

[0065] Here, as described above, the thresholds for the count values ​​cnt and cnt' may be appropriately set based on the size of the mass of dead chickens 43 relative to the number of images (frames) of the inside of the cage 3, which is 25, and the number of images (frames) of the wall 31, which is 15, per cage. The image capture device 7 has a lower frame rate than a normal moving image capture device (video camera), and one image (frame) is, for example, 0.1 seconds. However, if the thresholds for the count values ​​cnt and cnt' are set to be strict, the detection accuracy of dead chickens 43 and weak chickens 42 increases, but it takes a long time to reach a judgment, and it takes a long time to judge a particularly weak chicken 42, even though it is almost certain that the chickens are dead when they are judged. On the other hand, if the thresholds are relaxed, the judgment is quick, but there is a problem that the number of erroneous judgments increases.

[0066] Therefore, in this embodiment, the above-mentioned added data h0, which is simply accumulated by adjusting the reference position of the determination data H of the dead chicken 43, is processed as follows. FIG. 10 is a diagram for explaining the data processing method. First, the added data h0 shown in FIG. 9(b) is shown in FIG. 10(a) and is used as the reference data. As described above, the reference position (timing) of this reference data is also adjusted based on the center position of the wall as shown in FIG. 8. In this embodiment, data is created by shifting this reference data forward or backward by one image (field). The rear-shifted data is shown in FIG. 10(b), and the front-shifted data is shown in FIG. 10(c). Then, these three frames of data are added. The addition result is shown in FIG. 10(d).

[0067] The change in the data in Fig. 10(d) is shown in a graph similar to Fig. 9(c) as Fig. 9(e). In contrast, the added data h0 shown in Fig. 9(b) and Fig. 10(a) is shown in Fig. 10(f). Comparing the graph in Fig. 10(f) with the graph in Fig. 10(e), it can be seen that the dip in the count value due to missed detection is compensated for and becomes equal to or greater than the threshold value t. The median value of the count value cnt between the threshold value t and above is determined as the location of dead chickens 43 or weak chickens 42. The column of data K of the determination result combining the center position of the wall with the location of the dead chickens 43 or weak chickens 42 is as shown in Fig. 10(g).

[0068] Then, the screen of the personal computer 111 or mobile terminal 12 displays the cage number in which the dead chicken 43 or the weak chicken 42 is located. Therefore, the actual display data K', as shown in Figure 11, is data K in which the room (cage) number is counted each time a wall 31 is passed (determined), and the display data K' indicates in which room (cage) and where the dead chicken 43 or the weak chicken 42 is located. In Figure 11, it is near the wall between room (cage) 2 and room (cage) 3.

[0069] It should be noted that adding the shift data shown in Figures 10(b) and (c) to the reference data shown in Figure 10(a) may result in a decrease in the accuracy of judgment, such as the resolution. However, within one frame, which in this embodiment is about 0.1 seconds, the impact of such a decrease in accuracy is small, and the compensation effect of the above-mentioned dip is far greater.

[0070] FIG. 12 shows the results of searching for optimal parameters for the count value cnt of the number of consecutive frames and the threshold value t for determining whether or not there are dead chickens 43 or weak chickens 42. The experiment was conducted on data for five days with four rows (mountains) of cages 2. The number of accumulated frames n was set to 6. That is, the chickens passed in front of the cages 3 12 times during six feedings per day, but only the outward journey was imaged. The correct determination of the presence of dead chickens 43 or weak chickens 42 was made by manually observing the images captured by the imaging device 7 and actually removing them. The count value cnt was changed from 1, i.e., when it exceeded the threshold value t even for a moment, to 16, i.e., when it exceeded the threshold value t in a frame equivalent to the width of the actual wall 31. The maximum value of the threshold value t was set to a maximum of 18, because the accumulated value may be tripled due to n=6 and the shift addition in FIG. 10. For the score in Figure 12, f1-score, which is the harmonic mean of precision and recall, was used.

[0071] From Figure 12, as shown in Figure 13, when the count value cnt of the number of consecutive frames is 10, that is, about 2 / 3 of the 15 frames in which the wall 31 may be seen, and the threshold value t is 8, that is, after about three judgments, the score is 90 or more. More specifically, the precision rate is 100% or more and the recall rate is 90%. These parameters may be determined according to the actual setup of the chicken coop 1, the breeding environment, and the like.

[0072] As described above, in the dead chicken detection device of this embodiment and the poultry farming system using it, to detect dead chickens 43 inside cages 3, a large number of cages 3 lined up in a cross (horizontal) direction are continuously photographed by a moving imaging device 7, and the dead chickens 43 are identified by analysis using AI or the like. The judgment result from a single image is treated as a provisional judgment result, and a predetermined number n of times (in the chronological order) are accumulated with the timing adjusted so that the wire mesh parts of the cages etc. match, and a final judgment is made that the chicken is an actual dead chicken if it is above a threshold value t.

[0073] Therefore, dead chickens 43 are judged from the repeated judgment results at the same location but at different times, so that at least the number of movements (image capture) equal to the threshold t is required before a judgment can be made, and although it takes some time, it is still possible to accurately detect dead chickens 43 through to weak chickens 42 relatively quickly. Then, if an operator follows this judgment result and goes to the corresponding cage, he or she will be sure to find dead chickens 43 or weak chickens 42 there, which improves the efficiency of the work of removing them, and also eliminates false starts, thereby earning the operator's trust.

[0074] Furthermore, in the dead chicken detection device of this embodiment, a large chicken coop 1 is made up of cages 3 housing a large number of chickens 4 lined up in multiple tiers in the horizontal and vertical directions, and a feeding device 6 is provided which automatically feeds the chickens by moving in front of each cage 3 sequentially at predetermined times along rails 61 laid horizontally and dropping feed into feed receptacles (feeding trays) 51 provided in each cage 3, and an imaging device 7 is installed near the feeding opening 64 of each tier of this feeding device 6.

[0075] On the other hand, since the chickens 4 stand and move actively when eating, by observing the chickens at this feeding time, particularly by looking at the chickens' feet from a low viewpoint near the feed tray 51, it is possible to efficiently determine whether the chickens 43 are dead or not, and even the health condition of the chickens 42, whether they are weak from summer fatigue or the like. Specifically, it is possible to determine whether the chickens 43 are dead or not, and whether they are weak chickens 42, due to summer fatigue, by looking at the abdomen or the comb 431 at the feeding time, or by the movement of the legs 411, which should move a little if they are standing. In this way, by simply adjusting the timing of observing the chickens 4, it is possible to find dead chickens 43 and weak chickens 42 relatively accurately and easily. Also, by observing the chickens at frequent feeding times, it is possible to quickly find dead chickens and weak chickens 42.

[0076] Furthermore, since feed receiver (feeding tray) 51 is formed continuously in the horizontal direction like a gutter, this presents an obstacle when observing the area around the feet 411 of the chickens 4 from the low viewpoint. However, it is different from egg receiver 52 which is also formed continuously in the horizontal direction like a gutter. Therefore, in the dead chicken detection device of this embodiment, imaging device 7 is installed so as to look through the gap between these two, which makes it possible to continue observing the area around the feet 411 of the chickens 4 continuously and without obstacles between each cage 3, which is preferable.

[0077] Here, it is not necessary to find dead chickens 43 and weak chickens 42 in real time, and the actual removal work is performed about once a day, so it is sufficient if there are no oversights. In other words, it is desirable to detect dead chickens 43 quickly, but a detection delay of about the above time does not cause a big problem. Therefore, the image captured by the imaging device 7 is recorded in the recording device 71, and when the feeding device 6 returns to the home position and replenishes feed from the replenishment device 101, the captured image data is collected and collected from the recording device 71 by the wireless communication 103 to the determination means 111, and analysis is performed each time, or after a day's worth of data to be accumulated is collected. In this way, it is not necessary to lay wiring for detecting dead chickens 43 in the feeding device 6, and the feeding device 6 only needs to have a conventional power line and necessary control lines laid around it. In addition, the wireless communication 103 can be a simple short-range wireless communication such as Wi-Fi (registered trademark), and there is no need to install large-scale wireless communication equipment so that radio waves can reach every corner of the large (long) chicken coop 1.

[0078] In this embodiment, the recording device 71 is not provided for each imaging device 7, and in the example of FIG. 1, it is shared by four devices mounted on the same feeding device 6. In recent years, even general-purpose (cheap) imaging devices have improved in image quality, and there is no problem with AI judgment even in a composite screen. As a result, the judgment time per screen can be shortened, and the capacity of the recording device 71 can also be reduced.

[0079] Furthermore, in the dead chicken detection device of this embodiment, when the results of the provisional judgment are accumulated multiple n times to make an actual judgment, a binary judgment is made for each frame as to whether or not it is a dead chicken 43, and similarly, a binary judgment is made as to whether or not it is passing through wall 31, which serves as the movement position reference, and the accumulation is performed by shifting the time axis of the provisional judgment results so that the movement position references match, that is, by adjusting the timing between frames. Therefore, even if the running speed of feeding device 6 varies and the number of image capture frames between the movement position references (one cage) differs, the time difference can be adjusted and the binary provisional judgment results as to whether or not it is a dead chicken 43 can be accurately accumulated in chronological order for a predetermined number of frames n.

[0080] Furthermore, when adjusting the timing and accumulating the provisional judgment results, a dummy bit (frame) d is inserted between the movement position references, i.e., in one cage, in accordance with the data with the largest number of bits (frames), so that the variation in the movement speed (number of frames) of the imaging device 7 can be compensated for.

[0081] Furthermore, for the result of the accumulation (count value), data shifted one frame forward and backward is created using the result of the accumulation (count value) as the reference data, and these three data are added together and compared with the threshold value t. Therefore, even if a dead chicken happens to be missed at the same timing and this is reflected in the result of the accumulation (count value), the missed detection can be compensated for by the data before and after, making it possible to make an accurate judgment.

[0082] In the above explanation, the cage number is obtained from the counting result of the wall 31, but the cage number may also be obtained by reading the numbers or barcode displayed on each cage 3 using the imaging device 7 itself or a separate reader, or it may be obtained as traveling position data from the control device of the feeding device 6 together with information on the level of the cage 3 that the imaging device 7 corresponds to. [Explanation of symbols]

[0083] 1. Chicken Coop 10 Floor surface 101 Feed refill machine 102 Router 103 Wireless Communications 104 Communication Line 11 Office 111 Judgment means 112 Server 113 Public wireless communication lines 12 Mobile devices 2. Cage Poultry House 3 Cage 4. Chicken 41 Healthy Chickens 411 Feet 42 Weak Chicken 43 Dead chicken 431 Cockscomb 51 Feeding tray 52 Egg Receiver 53 Water supply pipe 55 Mesh Board 56 Defecation belt 6 Feeding device 61 Rail 62 wheels 64 Feeding port 7. Imaging device 71 Recording Devices

Claims

1. A device for detecting dead chickens in a cage housing chickens, A plurality of the cages are arranged at least in the horizontal direction, and an imaging device is configured to capture continuous images of the inside of the cage while moving in the horizontal direction; A first determination means for analyzing an image captured by the imaging device and provisionally determining whether or not the image is a dead chicken; and a second determination means for accumulating the determination results of the first determination means for a predetermined number of times by matching a moving position reference of the imaging device, and determining that the chicken is actually dead when the result is equal to or greater than a predetermined threshold value; The first determination means performs the provisional determination by analyzing continuous images of the imaging device, and performs a binary determination for each frame as to whether or not the chicken is a dead chicken, and also performs a binary determination as to whether or not the chicken is passing through the moving position reference; The second judgment means is a dead chicken detection device characterized in that it shifts the time axis of the result of the binary judgment of whether or not the chicken is a dead chicken and performs the accumulation for the predetermined number of times so that the moving position standard is consistent.

2. 2. The dead chicken detection device according to claim 1, wherein the imaging device is provided on a feeding device or a cart that follows the feeding device.

3. 2. The dead chicken detection device according to claim 1, wherein the imaging device observes the inside of the cage through a gap between a food tray arranged relatively above and an egg tray arranged relatively below.

4. 3. The dead chicken detection device according to claim 2, wherein the imaging device is provided in the feeding apparatus, the feeding apparatus further comprises a recording device for recording images captured by the imaging device, and the images captured by the recording device are transferred to the first determination means at a starting point for replenishing feed to the feeding apparatus.

5. 2. The dead chicken detection device according to claim 1, wherein the second determination means performs integration of the binary determination result of whether or not the chicken is a dead chicken a predetermined number of times in accordance with a predetermined number of bits.

6. 6. The dead chicken detection device according to claim 5, wherein the second determination means creates data shifted one frame before and after the result of the accumulation as reference data, and compares the result of adding up these three data with the predetermined threshold value.

7. A poultry farming system comprising a dead chicken detection device described in any one of claims 1 to 3.

Images