Denseness estimation device, denseness estimation method, and program

Abstract

To provide a density degree estimation device, density degree estimation method and program which can quickly estimate the correct density degree of animals by estimating the density degree of animals on the basis of an image in an animal rearing house.SOLUTION: A density degree estimation device 1 comprises: an image data processing unit 212-1 which generates an image for estimation from an in-house image being an image of animals reared in an animal rearing house; and a density degree estimation unit 212-2 which estimates a density degree of animals based on the image for estimation. The density degree estimation unit 212-2 estimates the density degree of animals by performing kernel density estimation on the basis of the image for estimation.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a congestion estimation device, a congestion estimation method, and a program. [Background technology]

[0002] Conventionally, methods for controlling the rearing environment for efficiently growing livestock such as chickens have been developed. For example, Patent Document 1 discloses a chicken coop ventilation system that controls the ventilation of the chicken coop, the operation of a heat exchanger, etc., based on measurements from an outside air thermometer that measures the air temperature outside the chicken coop, an inside thermometer that measures the air temperature inside the chicken coop, etc., as a method for controlling the temperature inside the chicken coop. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-10010 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the control method of Patent Document 1, in order to control the rearing environment for chickens, the air temperature is measured with a thermometer or the like. In addition, carbon dioxide is measured and ventilation control is performed to realize a more suitable rearing environment.

[0005] However, when livestock such as chickens are raised in a breeding house, the animals may crowd together in an area where the air temperature, floor (ground) temperature, etc. are comfortable, which may worsen the rearing environment, causing an increase in carbon dioxide concentration, etc. In this way, the density of animals in a breeding house affects the rearing environment of the animals and, ultimately, the growth rate of the animals, but it is difficult to accurately estimate the animal density in real time using measurements with a thermometer, a carbon dioxide concentration measuring device, etc.

[0006] The present invention has been made in consideration of the above-mentioned circumstances, and aims to provide a density estimation device, a density estimation method, and a program that can instantly and accurately estimate animal density by estimating the density of animals based on images inside animal enclosures. [Means for solving the problem]

[0007] In order to achieve the above object, a congestion estimation device according to a first aspect of the present invention comprises: an image data processing unit that generates an estimation image from an inside image, which is an image of an animal kept in the animal house; a density estimation unit that estimates the density of the animals based on the estimation image, The density estimation unit estimates the density of the animals by performing kernel density estimation based on the estimation image.

[0008] A storage unit that stores the estimation result of the animal density. A display unit that displays the estimation result, The congestion estimation unit is calculating a feature amount for evaluating the density from the density calculated by performing the kernel density estimation; storing the estimation result based on the feature amount in the storage unit and displaying it on the display unit; This may also be the case.

[0009] The image data processing unit further comprises: generating the binarized estimation image based on the house image, and detecting pixels in which the animal is photographed from the estimation image; The density estimation unit performs the kernel density estimation based on coordinate information of the detected pixels. This may also be the case.

[0010] Also, the kernel function of the kernel density estimation is a normal distribution. This may also be the case.

[0011] Also, a camera for capturing images of the inside of the building; A camera control unit that controls the camera, The camera control unit captures the interior image at a predetermined time interval. This may also be the case.

[0012] Moreover, the congestion estimation unit calculating an average value of the density of each pixel calculated from the estimation image as the feature amount at the estimation time; This may also be the case.

[0013] In addition, in a congestion estimation method according to a second aspect of the present invention, An estimation image is generated from an inside image, which is an image of an animal kept in the animal house; The density of the animals is estimated by performing kernel density estimation based on the estimation image.

[0014] Moreover, the program according to the third aspect of the present invention comprises: Computer, an image data processing unit that generates an estimation image from an inside image, which is an image of an animal kept in the animal house; a density estimation unit that estimates the density of the animals by performing kernel density estimation based on the estimation image; Function as. Effect of the Invention

[0015] According to the population density estimation device, population density estimation method, and program of the present invention, the animal density is estimated by kernel density estimation based on images of the inside of the animal enclosure, making it possible to estimate the animal density accurately in an instant. [Brief description of the drawings]

[0016] [Figure 1] 1 is a block diagram showing a configuration of a congestion estimation device according to an embodiment of the present invention. [Diagram 2] 1 is a flowchart showing a flow of congestion estimation according to an embodiment. [Diagram 3] 1A and 1B are diagrams showing examples of images related to density estimation, in which (A) is a building interior image Ih, (B) is a grayscale image Ig, and (C) is an estimation image Ib. [Figure 4] 1A and 1B are conceptual diagrams showing a method for calculating density, in which (A) is an example of an estimation image Ib, (B) is an example of coordinate information φ stored in a storage unit, and (C) is an example of density S at each pixel. [Diagram 5] 13 is an example of an image Ih of the inside of a building at a specific time in winter. [Figure 6] (A) is an example of a distribution map of the density S corresponding to each pixel of the building interior image Ih, and (B) is a histogram showing the frequency of each density in (A). [Figure 7] 6 is a graph showing the change over time in feature amount F, which indicates the degree of crowding, estimated from the building interior image Ih of FIG. 5. [Figure 8] 8 shows data from Figure 7 at times when the density was low, where (A) is the building interior image Ih, (B) is the estimation image Ib, (C) is the density S at each coordinate, and (D) is a histogram of the density. [Figure 9] 8 shows data for times when the density in FIG. 7 was high, where (A) is the building interior image Ih, (B) is the estimation image Ib, (C) is the density S at each coordinate, and (D) is a histogram of the density. [Figure 10] 11 is a graph showing an example of a change over time in a feature amount F that indicates a density in summer. [Figure 11] 11 shows data for times when the density in FIG. 10 was high, where (A) is the building interior image Ih, (B) is the estimation image Ib, (C) is the density S at each coordinate, and (D) is a histogram of the density. [Figure 12] 11 shows data from Figure 10 at times when the density was low, where (A) is the building interior image Ih, (B) is the estimation image Ib, (C) is the density S at each coordinate, and (D) is a histogram of the density. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] Hereinafter, a population density estimation device 1 according to an embodiment of the present invention will be described with reference to the drawings. In this embodiment, a population density estimation device 1 that estimates the population density of chickens raised in a breeding house will be described as an example.

[0018] As shown in the block diagram of FIG. 1, the congestion estimation device 1 includes a camera 10 and a control unit 20.

[0019] The camera 10 is a camera that captures an image of a target area in a breeding house for estimating the density of chickens. The camera 10 captures an image I h The data is transmitted to the control unit 20. The type, resolution, and other characteristics of the camera 10 are not particularly limited, but it is preferable that the camera 10 has a resolution sufficient to enable animals in the target area to be individually recognized.

[0020] The control unit 20 is, for example, a computer device, and includes a control unit 21, a storage unit 22, a display unit 23, and an input unit 24, as shown in FIG.

[0021] The control unit 21 is composed of a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), a crystal oscillator, etc., and controls the operation of the camera 10. The control unit 21 also converts the building interior image I captured by the camera 10 into h The control unit 21 loads various operation programs and data stored in the ROM, storage unit 22, etc. of the control unit 21 into the RAM and operates the CPU, thereby realizing each function of the control unit 21 shown in Fig. 1. In this way, the control unit 21 operates as a camera control unit 211 and an estimation unit 212.

[0022] The camera control unit 211 controls the camera 10 connected to the control unit 20 to capture an image of the target area and generate an image of the inside of the building I. h Get the.

[0023] The estimation unit 212 includes an image data processing unit 212-1 and a density estimation unit 212-2. The image data processing unit 212-1 processes the acquired building interior image I h Based on this, image processing is performed to estimate the chicken density in the target area. b Generate the estimation image I b is an image for extracting basic data used to calculate the density. b Here is a picture of the building I h The image data processing unit 212-1 also generates a binary image based on the estimation image I b The coordinate data of the pixels where chickens are present is extracted from the data and used as basic data for calculating the density.

[0024] The density estimation unit 212-2 estimates the estimation image I generated by the image data processing unit 212-1. b Based on this, kernel density estimation is performed and the feature value F is extracted to estimate the density. The detailed estimation procedure will be described later.

[0025] The storage unit 22 is a non-volatile memory such as a hard disk or a flash memory, and stores the interior image I h The system stores an algorithm for estimating chicken density from the data, information about the estimated density, etc.

[0026] The display unit 23 is a display device provided in the control unit 20, which is a computer device, and is, for example, a liquid crystal monitor. The display unit 23 displays the inside image I captured by the camera 10. h , and information about the congestion level estimated by the estimation unit 212 are displayed.

[0027] The input unit 24 is an input device for inputting parameters related to shooting such as the angle of view of the camera 10, the time interval for calculating the density, instructions to start and end the density estimation, etc. The input unit 24 is a keyboard, a touch panel, a mouse, etc. provided in the control unit 20.

[0028] The control unit 20 also communicates with the camera 10 via a communication interface (communication I / F). Specifically, the camera control unit 211 transmits control information to the camera 10 and transmits the captured interior image I h The control unit 21 also causes the memory unit 22 to store information such as the estimated chicken density, the estimated time of the density, etc.

[0029] Hereinafter, the congestion estimation method according to the present embodiment will be specifically described with reference to the flowchart of FIG.

[0030] When crowding estimation is started by inputting an estimation start input to the input unit 24, the camera control unit 211 of the control unit 20 controls the camera 10 to capture an image of a target area in the breeding house at a predetermined estimation time, and generates an inside-house image I h (Step S11). FIG. 3(A) shows the captured image I h This is an example.

[0031] In this embodiment, a single camera 10 is used to capture an image of a predetermined area in the animal house. However, this is not limited to this. A plurality of cameras 10 may be used to capture an image of the inside of the animal house of a target area corresponding to each camera 10. h This allows the density of animals in a wider area of ​​the enclosure to be estimated. The same target area may also be photographed from different directions by multiple cameras 10, allowing for estimation with fewer errors.

[0032] The camera control unit 211 controls the building image I captured by the camera 10. h The data is stored in the storage unit 22 and transmitted to the image data processing unit 212-1 (step S12). h The image I may be a color image or a grayscale image. h is a color image.

[0033] The image data processing unit 212-1 generates the building image I based on the data received in step S12.h Convert it to grayscale and get grayscale image I g The method of grayscaling is not particularly limited, and any known method such as a method of averaging RGB or a method using gamma correction can be used.

[0034] The image data processing unit 212-1 converts the grayscale image I generated in step S13 into g is binarized and the estimation image I b (Step S14). The threshold value for the binarization process is set in advance to a value between the brightness of the chicken area in the image to be processed and the brightness of the floor of the breeding house, which is the background. As a result, as shown in the example of FIG. 3(C), an estimation image I is generated, which is a binary image in which the chicken area is white and the background area other than the chicken is black. b That is, through the binarization process, pixels in which a chicken is photographed are detected as white pixels.

[0035] The image data processing unit 212-1 generates an estimation image I b Among them, the coordinate information φ=[φ1, φ2]=[x, y] of the white pixel is stored in the storage unit 22 (step S15).

[0036] Next, the density estimation unit 212-2 calculates the density S based on the coordinate information φ of the white pixels stored in the storage unit 22 (step S16). The density estimation unit 212-2 also calculates a feature amount F from the calculated density S, and displays and stores it as an estimation result of the chicken density (step S17). Specifically, the density estimation unit 212-2 calculates the density S using kernel density estimation. In this embodiment, kernel density estimation is performed using a kernel function of normal distribution to calculate the density S(φ(k),φ), as shown in the following formula.

[0037]

number

[0038] 4(A) to (C) are examples of calculating density S for an image of 3×3 pixels. FIG. 4(A) is a diagram showing the distribution of white pixels and black pixels, and FIG. 4(B) is a diagram showing coordinate information φ stored in storage unit 22. Note that in this example, for the purpose of explanation, symbols such as circles and stars are attached to each pixel. The parameters of the above formula in this example are as follows: k=1,2,...,9 N=4 (number of white pixel data) φ(k): Coordinate information of the kth pixel φ: Coordinate information of all white pixels stored in the memory unit 22 φ1(k): x-coordinate of the kth pixel φ2(k): y coordinate of the kth pixel h1: Bandwidth on the x-axis h2: Bandwidth on the y-axis

[0039] Fig. 4(C) is a diagram showing the density S of each pixel calculated for Fig. 4(A). As shown in Fig. 4(C), since φ(5) (pixel indicated by a star in the figure) is located in the center of all the white pixels, it can be seen that the density S(φ(5), φ) of φ(5) is high.

[0040] Here, the bandwidth h i is a parameter that can be set by any method, and can be determined by a known method such as a method using standard deviation. In this embodiment, the bandwidth h is set by the user based on the distribution of the calculated density S, and is appropriately selected so that the density of animals in the target area can be easily determined. More specifically, the user sets the bandwidth h (= h1) for the x-axis and the bandwidth h (= h2) for the y-axis while checking the distribution of the calculated density S.

[0041] Figure 5 shows images of the inside of a building taken at a specific time from 1:00 to 14:00 on a certain day in winter. hFIG. 6A shows an example of a building image I at a certain time calculated by the congestion estimation method according to the present embodiment. h 6(B) is a histogram showing the frequency of each density.

[0042] In this embodiment, the density estimation unit 212-2 calculates the average value of the density S of each pixel, and sets the calculated average value as the feature amount F representing the density of chickens at that time.

[0043] In this embodiment, in order to simplify the calculation process for calculating the feature amount F, h From the densities S corresponding to all the pixels, the densities S corresponding to half of the pixels are extracted and the average value is calculated. This makes it possible to calculate the feature amount F with a smaller calculation load. In this embodiment, the average value of the densities S is used as the feature amount F, but this is not limited to this, and the median, standard deviation, a combination of these with the average value, etc. may also be used.

[0044] Figure 7 shows the inside of the building in Figure 5. h 5 is a graph showing the time course of feature F, which represents the density of chickens, estimated from the image I in Fig. 5. h 7, it can be seen that the density of chickens in a breeding house can be appropriately estimated by the density estimation method according to the present embodiment.

[0045] More detailed estimation data is shown in Fig. 8(A)-(D) and Fig. 9(A)-(D). Fig. 8(A)-(D) shows images of the inside of the building at a time when the building was less crowded (2 o'clock). h (Fig. 8(A)) The estimation image I b (B) of Fig. 8, (C) of Fig. 8, and (D) of Fig. 8. The density S of each coordinate is shown, and the histogram of density S is shown. Figs. 9(A) to 9(D) show the image I of the building at the time of highest density (11:00). h (Fig. 9(A)), Estimation image I b (Figure 9(B)), the density S of each coordinate (Figure 9(C)), and a histogram of the density S (Figure 9(D)).

[0046] From Figures 8(A)-(D) and Figures 9(A)-(D), we can see that the times when chicken density is low, i.e., when chickens are sparse and a lot of ground is visible, and the times when chicken density is high, i.e., when chickens are densely packed within the target area and little ground is visible, can be appropriately estimated.

[0047] The above-mentioned Fig. 7, Fig. 8(A)-(D), and Fig. 9(A)-(D) are examples of data for one day in winter (December). On the other hand, Figs. 10-12 show examples of data for one day in summer (July). Fig. 10 is a graph showing the change in the feature amount F that represents the density. Figs. 11(A)-(D) show images I of the inside of a building at a time (3 o'clock) when the density is high. h (Fig. 11(A)), Estimation image I b (B) of FIG. 11, (C) of FIG. 11, and (D) of FIG. 11. The density S of each coordinate is shown, and the histogram of density S is shown. Also, (A) to (D) of FIG. 12 show the image I of the inside of the building at the time of low density (12 o'clock). h (Fig. 12(A)), Estimation image I b 12(B)), the density S of each coordinate (FIG. 12(C)), and a histogram of the density S (FIG. 12(D)). It can be seen from FIGS. 10 to 12 that the density estimation method according to the present embodiment can appropriately estimate times when chicken density is low and times when chicken density is high.

[0048] Returning to the flowchart of FIG. 2, the control unit 21 stores data such as the density S calculated by the density estimation unit 212-2 and the feature F as an estimation result in the memory unit 22 and displays the data on the display unit 23 (step S18).

[0049] The control unit 21 repeats the above-described congestion estimation until the congestion estimation is terminated due to an input of an estimation end to the input unit 24, the end of a preset estimation period, etc. (NO in step S19). The control unit 21 terminates the process when a termination condition is satisfied, such as an input of an estimation end to the input unit 24, the end of a preset estimation period, etc. (YES in step S19).

[0050] As described above, in the crowding estimation device 1 according to the present embodiment, the inside image I h Since the animal density is estimated by kernel density estimation based on the above, it is possible to estimate the animal density in real time. h Since the density is estimated based on this, it is possible to estimate the animal density more accurately compared to methods that estimate the animal density by placing measuring devices such as thermometers and carbon dioxide concentration meters in the animal enclosures.

[0051] In this embodiment, an image I of the inside of the breeding house is taken. h However, this is not limited to the above. For example, the building image I h The density may be estimated after performing distortion correction, trimming, and other processing on the image. This allows for more accurate estimation of the density. In this case, an image correction process may be inserted between steps S12 and S13 in the flowchart of FIG. 2, and the corrected image may be used to perform grayscale conversion and subsequent processing.

[0052] In addition, in this embodiment, the density of chickens raised in a chicken coop is estimated, but the present invention is not limited to this, and the density of other animals such as pigs, rabbits, ducks, etc. may be estimated. In this case, it is preferable to adjust the background color by painting the inside of the coop, for example, so that the difference in brightness between the image data of the animals and the background such as the ground of the coop is large.

[0053] Although the camera 10 and the control unit 20 according to the present embodiment are directly connected, this is not limiting. For example, the camera 10 and the control unit 20 may be connected via a network. This allows the density of animals in a breeding house to be estimated from a remote location, so that even if there are multiple breeding houses or a large breeding house, the information can be collected in one place and the environment in which the animals are raised can be easily evaluated.

[0054] In this embodiment, the crowding estimation device 1 includes a camera 10, and an image Ih However, the present invention is not limited to this. For example, the density is estimated based on the past building image I stored in the memory unit 22. h The density may be estimated based on the building image I h The necessary data can be read from the data base, and the density of animals can be estimated and used to evaluate the relationship between the animal's rearing environment and its growth rate.

[0055] The animal density estimation method according to the above embodiment can be realized by using a normal computer system. For example, a computer program for executing the density estimation according to the above embodiment can be stored in a computer-readable recording medium such as a USB memory or a DVD-ROM and distributed, and the computer program can be installed in a computer to cause the computer to function as the control unit 20 of the density estimation device 1 that executes the above density estimation. [Industrial Applicability]

[0056] The present invention is suitable for a rearing environment evaluation system that estimates the density of animals raised in a breeding house to evaluate the rearing environment, and is particularly suitable for a rearing environment evaluation system that estimates the density of chickens in a chicken house where a large number of animals are raised. [Explanation of symbols]

[0057] REFERENCE SIGNS LIST 1 Denseness estimation device, 10 Camera, 20 Control unit, 21 Control unit, 211 Camera control unit, 212 Estimation unit, 212-1 Image data processing unit, 212-2 Denseness estimation unit, 22 Storage unit, 23 Display unit, 24 Input unit

Claims

1. an image data processing unit that generates an estimation image from an inside image, which is an image of an animal kept in the animal house; a density estimation unit that estimates the density of the animals based on the estimation image, The image data processing unit includes: generating the binarized estimation image based on the house image, and detecting pixels in which the animal is photographed from the estimation image; The congestion estimation unit is calculating a density of the animals at each pixel by performing kernel density estimation for each pixel of the estimation image based on coordinate information of the pixel detected by the image data processing unit; estimating the density of animals by averaging the density of animals for each pixel and calculating a feature amount for evaluating the density of animals in the estimation image; A congestion estimation device comprising:

2. A storage unit that stores the estimation result of the animal density; A display unit that displays the estimation result, The congestion estimation unit is storing the estimation result based on the feature amount in the storage unit and displaying it on the display unit; The congestion estimation device according to claim 1 .

3. the kernel function of the kernel density estimation is a normal distribution; 3. The congestion estimation device according to claim 1 or 2.

4. A camera for capturing images of the interior of the building; A camera control unit that controls the camera, The camera control unit captures the interior image at a predetermined time interval. The congestion estimation device according to any one of claims 1 to 3.

5. A binarized estimation image is generated based on an interior image, which is an image of an animal kept in the animal house; Detecting pixels in which the animal is photographed from the estimation image; calculating a density of the animal at each pixel by performing kernel density estimation for each pixel of the estimation image based on coordinate information of the detected pixel; estimating the density of animals by averaging the density of animals for each pixel and calculating a feature amount for evaluating the density of animals in the estimation image; A method for estimating congestion, comprising:

6. Computer, an image data processing unit that generates a binarized estimation image based on an interior image, which is an image of an animal kept in a breeding house, and detects pixels in which the animal is photographed from the estimation image; a density estimation unit that estimates the animal density by calculating the animal density of each pixel by performing kernel density estimation for each pixel of the estimation image based on coordinate information of the pixel detected by the image data processing unit, and averaging the animal densities of each pixel to calculate a feature amount for evaluating the animal density in the estimation image; A program that functions as a

Images