KR20220062920A - Stationary Livestock weight estimation system based on 3D images and Livestock weight estimation method using the same - Google Patents

Abstract

The present invention relates to a mounted type livestock weight estimation system based on a 3D image and a livestock weight estimation method using the same and, more specifically, to a system which is formed in a mounted type to be installed at the indoor space, and estimates the weight of livestock by using a livestock weight estimation application based on a 3D image. Provided is the mounted type livestock weight estimation system based on a 3D image, which comprises: a mounted type body unit to be installed in the indoor space; at least one 3D sensor installed at the mounted type body unit to film livestock; and an estimation terminal including a livestock weight estimation application to estimate the weight of livestock by using a livestock frame extracted by means of the 3D sensor. Furthermore, provided is the livestock weight estimation method using the mounted type livestock weight estimation system based on a 3D image and, more specifically, to the livestock weight estimation method which comprises: a filming step (a) in which livestock is filmed by means of a 3D sensor installed at the indoor space by the mounted type body unit to extract at least one livestock frame; and a weight estimation step (b) in which the terminal deduces an estimated weight by using the extracted livestock frame. Therefore, the weight of livestock can be periodically estimated and managed.

Description

Stationary Livestock weight estimation system based on 3D images and Livestock weight estimation method using the same

The present invention relates to a stationary livestock weight estimation system based on a 3D image and a livestock weight estimation method using the same. To a stationary livestock weight estimation system based on a 3D image that can periodically estimate and manage the weight of livestock by estimating the weight of livestock using the frame of the , and a livestock weight estimation method using the same.

In the case of the livestock industry, regular weight management is required for individual feeding of domesticated animals.

In particular, in the case of pig farms, the standard for shipping is very important, and it brings a very big difference to the income of the farm depending on the number of pigs that fit within the standard. Pigs are graded according to quantitative criteria according to body weight and fat thickness, and qualitative criteria according to fat distribution and meat color. Generally, pigs weighing 115 kg to 120 kg are called standard pigs.

It is very important to measure the weight accurately and select the pigs for shipment, because if the weight of a standard pig is satisfied, a higher grade can be obtained.

To this end, the need for periodic weight measurement or monitoring is required in the field.

Currently, the weight of pigs is measured by the chest measurement method and the pig hyeonggi.

The chest position measurement method is used to convert the weight by applying the value obtained by measuring the chest position of the money with a tape measure to the weight calculation formula.

In addition, the pig weighing machine directly measures the weight of pigs in an enclosed space after installing an accessory device on the scale that measures the pig's weight. There is a problem in that it is cumbersome to have to stand still for a certain period of time within the sentence, and in this process, it takes about 10 minutes or more based on one worker to measure the weight of one animal. There were breakdowns and difficulties in maintenance.

In addition, there is a shortage of manpower due to a decrease in the farm household population and an aging population, so countermeasures are needed.

Therefore, it is possible to measure the pig's weight simply and accurately to continuously manage the pig's weight and to reduce the labor force of the farmer, and there is a need for a technology for accurately predicting the weight of the pig at the time of shipment.

Meanwhile, a system or method for estimating the volume and weight of livestock through images by shooting livestock has recently been developed, but errors caused by obstruction factors (sunlight, movement of livestock, etc.) There was a problem that the accuracy was lowered.

In order to solve the above problems, the present invention is installed in a stationary type in a corridor through which livestock passes, photographing livestock with a 3D sensor, and estimating the weight of livestock using a plurality of frames obtained, thereby periodically measuring the weight of livestock An object of the present invention is to provide a stationary livestock weight estimation system based on a 3D image that can be estimated and managed, and a livestock weight estimation method using the same.

In order to solve the above problems, the stationary livestock weight estimation system based on a 3D image according to an embodiment of the present invention is formed in a stationary type that can be installed indoors, and a livestock weight estimation application based on a 3D image A system for estimating the weight of livestock by using, comprising: a stationary body that can be installed indoors; Based on a 3D image including a terminal including one or more 3D sensors installed in the stationary body part to photograph livestock and a livestock weight estimation application for estimating the weight of livestock using the livestock frame extracted through the 3D sensor A stationary livestock weight estimation system may be provided.

Here, the livestock weight estimation application may include a sensor photographing unit for extracting one or more livestock frames by photographing livestock by operating the 3D sensor, and a weight estimation unit for deriving an estimated weight using the extracted livestock frame.

In addition, the stationary body further includes a reader for recognizing livestock, wherein the sensor photographing unit operates the 3D sensor when the livestock biometric information is received from the reader to photograph the livestock and extract the livestock frame do it with

In addition, the weight estimation unit includes a conversion unit for converting the extracted livestock frame into three-dimensional coordinate data; It may include a preprocessor for preprocessing the converted 3D coordinate data to generate 3D livestock data, and a weight derivation unit for deriving an estimated weight from the 3D livestock data.

In addition, the pre-processing unit includes a factor extracting unit for extracting a factor from the three-dimensional coordinate data, the factors are head direction, floor angle, focal length, height, length 1, chest circumference, half circumference, half circumference, rear circumference, It may include one or more of an average body half circumference, a total body half circumference, and a number of cloud points.

(Here, length 1 is the distance from the front leg with the head removed to the tip of the buttocks, and length 2 is the distance between the front and hind legs.)

In addition, the weight derivation unit generates a candidate list by selecting one or more of the three-dimensional livestock data according to a factor, and determines the number of cases of condition satisfaction of the generated candidate list to derive the first weight of the three-dimensional livestock data a candidate list unit; It may include an algorithm derivation unit for deriving a second weight by applying a multiple regression formula to the three-dimensional livestock data, and a final derivation unit for deriving an estimated weight using the first weight and the second weight.

In addition, the candidate list unit selects one or more of the three-dimensional livestock data as candidates according to a factor to determine the number of cases of condition satisfaction of the list generation unit generating a candidate list and the generated candidate list, and in some cases, the 3 It may include a list processing unit for deriving the first weight of the dimensional livestock data.

In addition, the algorithm derivation unit is characterized in that it derives the second weight through Equation 1 below using the height, length 2, the average body half circumference, and the number of cloud points among the factors of the three-dimensional livestock data.

[Equation 1]

2nd weight = m ₁ + (h ₁ × height) + (2ㅣ ₁ × length 2) + (g ₁ × body half circumference average) + (p ₁ × number of cloud points in 3D livestock data)

(Where m ₁ is the weight constant, h ₁ is the height constant, 2ㅣ ₁ is the length 2 constant, g ₁ is the half-circumference average constant, and p ₁ is the cloud point constant of the 3D livestock data)

In addition, the livestock weight estimation application further includes a shipment determination unit that determines whether shipment is possible by comparing the derived estimated weight with the shipment possible weight, and when it is determined that shipment is possible in the shipment determination unit, a shipment mark on the livestock It may further include a marker unit.

Livestock weight estimation method using a stationary livestock weight estimation system based on a 3D image according to an embodiment of the present invention (a) extracts one or more livestock frames by photographing livestock through a 3D sensor installed indoors by a stationary body part It is possible to provide a livestock weight estimation method including a photographing step and (b) a weight estimation step in which the terminal derives an estimated weight using the extracted livestock frame.

In addition, before the photographing step, it may further include a livestock recognition step of recognizing the livestock.

In addition, after the weight estimation step, the method may further include a shipment determination step of determining whether shipment is possible by comparing the derived estimated weight with the shipment possible weight.

In addition, when it is determined that shipment is possible in the shipment determination step, the method may further include a shipment display step of marking the livestock for shipment through the marker unit.

As described above, the stationary livestock weight estimation system based on the 3D image according to the embodiment of the present invention and the livestock weight estimation method using the same are installed in a stationary type in the corridor through which the livestock passes, photographing the livestock with a 3D sensor, and obtaining By estimating the weight of the livestock using a plurality of frames, it is possible to estimate the weight of the livestock periodically and manage it easily.

In addition, by estimating the weight of livestock through the candidate list method and the multiple regression method using a plurality of frames obtained from the 3D sensor, the weight estimation accuracy and reliability may be excellent.

Therefore, there is no need for additional equipment to estimate the weight of livestock, and it is possible to reduce breeding costs through feed control through continuous weight management of livestock and to accurately predict the time of shipment, thereby increasing the profits of the farmer.

In addition, there is no hassle of inducing livestock to stagnate for a certain period of time in order to estimate the weight, so it is possible to solve the problems caused by the shortage of manpower in the farmhouse, the aging of the manpower, and the enlargement of the scale.

In addition, as it can be applied not only to pigs, but also to various livestock such as chickens and cattle, its utility is expected to expand.

1 is an exemplary diagram illustrating a state in which a stationary livestock weight estimation system based on a 3D image according to an embodiment of the present invention is installed.
2 is an exemplary diagram illustrating a state of photographing livestock through a stationary livestock weight estimation system based on a 3D image according to an embodiment of the present invention.
3 (a) and (b) are exemplary pictures showing the cattle frame extracted through the livestock photography of FIG.
4 is a block diagram showing the configuration of the terminal of FIG.
5 is a block diagram showing the configuration of the weight estimation unit of FIG.
6 is an exemplary view showing a factor.
7 is a block diagram showing the configuration of the weight derivation unit of FIG.
8 is a flowchart schematically illustrating a livestock weight estimation method using a stationary type livestock weight estimation system based on a 3D image according to an embodiment of the present invention.
9 is a flowchart sequentially illustrating steps S3 of FIG. 8;
10 is a flowchart sequentially illustrating steps S32 of FIG. 9;
11 is a flowchart sequentially illustrating steps S320 of FIG. 10;
12 is a flowchart illustrating a step S3201 when the first, second, and third candidate lists satisfy a condition;
13 is a flowchart illustrating a process in which step S32012a of FIG. 12 is performed.
14 is a flowchart illustrating a process in which step S32016a of FIG. 12 is performed;
15 is a flowchart illustrating a process in which steps S3201 to S32010b are performed when the first and second candidate lists satisfy conditions;
16 is a flowchart illustrating a step S3201 when the second and third candidate lists satisfy a condition;
17 is a flowchart illustrating a process in which step S32013c of FIG. 16 is performed.
18 is a flowchart illustrating a process in which steps S3201 to S32010d are performed when the first and third candidate lists satisfy conditions;
19 is a flowchart illustrating a process in which steps S3201 to S32010e are performed when only the third candidate list satisfies a condition;
20 is a flowchart illustrating a process of performing steps S3201 to S32010f when there is no conditional satisfaction candidate list.

Hereinafter, the description of the present invention with reference to the drawings is not limited to specific embodiments, and various modifications may be made and various embodiments may be provided. In addition, it should be understood that the contents described below include all transformations, equivalents, and substitutes included in the spirit and scope of the present invention.

In the following description, terms such as 1st, 2nd, etc. are terms used to describe various components, meanings are not limited thereto, and are used only for the purpose of distinguishing one component from other components.

Like reference numbers used throughout this specification refer to like elements.

As used herein, the singular expression includes the plural expression unless the context clearly dictates otherwise. In addition, terms such as "comprises", "comprises" or "have" described below are intended to designate the existence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification. It should be construed as not precluding the possibility of addition or existence of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

In addition, in the description with reference to the accompanying drawings, the same components are given the same reference numerals regardless of the reference numerals, and the overlapping description thereof will be omitted. In describing the present invention, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted.

In the present invention, the livestock weight estimation application is preferably provided in a mobile communication terminal including a smart phone communicating through a wireless communication network, but may also be provided in a computer environment communicating through a wired communication network. Hereinafter, the description will be focused on the mobile communication terminal.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings 1 to 20.

1 is an exemplary diagram illustrating a state in which a stationary livestock weight estimation system based on a 3D image according to an embodiment of the present invention is installed, and FIG. 2 is a stationary livestock weight based on a 3D image according to an embodiment of the present invention. It is an exemplary view showing a state of photographing livestock through the estimation system, FIGS. 3 (a) and (b) are exemplary photographs showing a livestock frame extracted through the livestock photographing of FIG. 2, FIG. 4 is FIG. 1 is a block diagram showing the configuration of the terminal of , FIG. 5 is a block diagram showing the configuration of the weight estimator of FIG. 4 , FIG. 6 is an exemplary diagram showing a factor, and FIG. 7 is a block showing the configuration of the weight derivation part of FIG. 5 It is also

A stationary livestock weight estimation system based on a 3D image according to an embodiment of the present invention (hereinafter referred to as a 'stationary livestock weight estimation system') is installed in a passageway through which livestock passes indoors, and easily measures the weight of livestock Therefore, it is intended to manage the weight and time of shipment of livestock.

Referring to FIG. 1 , the stationary livestock weight estimation system may include a stationary body unit 1 , 3D sensors 2a and 2b , a terminal 3 , a reader 4 , and a marker unit 5 .

The stationary body part 1 may be installed in a stationary manner indoors, and may include an attachment part formed to be attached to an indoor wall surface, etc., and a frame part in which the 3D sensors 2a, 2b, etc. are installed. It may be implemented in the form shown in FIG. 1, but is not limited thereto, and may be formed in various forms.

One or more 3D sensors 2a and 2b may be installed in the stationary body part 1 to secure a three-dimensional livestock frame by photographing livestock. In this case, the 3D sensors 2a and 2b may be provided with various sensors capable of capturing a 3D image, such as a lidar, and a color depth sensor is preferable, but is not limited thereto.

In addition, when the 3D sensors 2a and 2b are installed in the stationary body part 1, as shown in FIG. 2, two 3D sensors 2a, 2b are installed in the upper center of the livestock, one in the vertical direction. and the other one is installed on one side of the upper side of the livestock to be photographed in a diagonal direction, but this is only an example of the present invention, so it is not limited thereto, and the two 3D sensors (2a, 2b) are installed on the upper side of the livestock It can be installed in various ways, such as being installed to shoot in a diagonal direction from the other side.

When the 3D sensors 2a and 2b are installed as shown in FIG. 2, a livestock frame as shown in FIG. 3 can be secured.

These 3D sensors 2a and 2b may be operated by the sensor photographing unit 32 .

The terminal 3 may be a mobile terminal of a user such as a breeder of a farmhouse or a manager, and may be easily applied to a PC tablet in addition to a mobile terminal.

As described above, the terminal 1 is implemented as a mobile terminal to facilitate installation, mobility, and convenience, so that an administrator can easily measure the weight of livestock.

In addition, the terminal 3 may be installed in the stationary body portion 1, but is implemented to be detachable and can be used in various ways as needed.

The livestock weight estimation application 30 is capable of estimating the weight of livestock using the livestock frame extracted through the 3D sensors 2a and 2b, and refers to a general application based on Android and iOS, but the terminal 3 or Depending on the wired/wireless service type, it may be provided as a general application or a web service-based application. As a method of providing, it can be downloaded and installed by accessing the server through the terminal 3 or by downloading it through an online application market (eg, Android market, Apple store, online market of a telecommunication company, etc.).

Referring to FIG. 4 , the livestock weight estimation application 30 may include a data storage unit 31 , a sensor photographing unit 32 , a weight estimation unit 33 , a shipment determination unit 34 , and a management unit 35 . there is.

The data storage unit 31 may store livestock standard data generated by using previously collected livestock data, and may store livestock biometric information and estimated weight data input from a user. In addition, it is possible to store a standard value of the available weight for shipment, and the like.

Here, the livestock standard data is data standardized by month or weight by analyzing livestock data collected in advance by measuring livestock at livestock farms, taking 3D images, and may include 3D livestock data by month or weight, The pre-collected livestock data may include livestock biometric information, three-dimensional model data, and weight.

In addition, livestock biometric information is biometric information of livestock to be weighed, and may include one or more of livestock classification number, species, sex, and number of months, and it is preferable to include all of them.

The sensor photographing unit 32 operates the 3D sensors 2a and 2b to photograph livestock to extract one or more livestock frames.

First, the sensor photographing unit 32 executes the livestock weight estimation application when the livestock is recognized from the reader 4 and the livestock biometric information is received, and the 3D sensors 2a and 2b detect the livestock. When livestock is detected, the 3D sensors 2a and 2b may be initialized to photograph the livestock. In addition, one or more livestock frames can be extracted by capturing when shooting is in progress.

However, the present invention is not limited thereto, and as the livestock weight estimation application is executed, the 3D sensors 2a and 2b may be operated to detect the livestock, and when the livestock is detected, the 3D sensors 2a and 2b may be initialized to photograph the livestock can make it In addition, since the photographing button is activated on the screen of the terminal 3, it may be implemented in various ways, such as capturing the photographing button according to the user's pressing of the photographing button.

It is preferable that the capture consists of continuous capture so that a large number of livestock frames can be extracted, and the continuous capture can be performed according to the value of the number of consecutive captures. The continuous capture count value may be 10 to 12, but is not limited thereto.

The livestock frame obtained here may include two-dimensional information and depth information.

In this way, by extracting the livestock frame through the capture, it is possible to minimize the performance degradation.

On the other hand, the sensor photographing unit 32 may stop the operation when the livestock is not detected and allow it to proceed again. This can prevent capture even when the livestock passes the 3D sensors 2a and 2b.

The weight estimation unit 33 may derive an estimated weight using one or more extracted livestock frames.

Referring to FIG. 5 , the weight estimation unit 33 may include a conversion unit 330 , a pre-processing unit 331 , and a weight derivation unit 332 .

After arranging the livestock frames, the conversion unit 330 may extract points and convert them into 3D coordinate data. Such three-dimensional coordinate data may be stored in the data storage unit 31 .

Here, the three-dimensional coordinate data may be data about the shape of the right or left side (half-shape of the livestock) based on the isometric axis of the livestock, rather than realizing all the shapes of the livestock.

The pre-processing unit 331 may pre-process the converted 3D coordinate data to generate 3D livestock data. For this purpose, it may include a validation unit, a noise removal unit, and a factor extraction unit.

The validation unit determines the validity of the three-dimensional coordinate data, and since it is possible to obtain a livestock frame that is not suitable for use due to obstruction factors (sunlight, movement of livestock, etc.), the validity is checked by checking the number of extracted points. can judge

Validity can be determined depending on whether the number of extracted points is greater than or equal to a set number of points, and when the number of points is less than the number of points, the three-dimensional coordinate data is dropped so that it is not used to derive the estimated weight.

The noise removal unit removes noise from the 3D coordinate data, and since objects other than livestock (land, building frames, etc.) can also be photographed, the extracted points that correspond to objects other than livestock can be removed

The factor extractor may extract a factor from the 3D coordinate data to generate 3D livestock data. In this case, the 3D livestock data may include 3D coordinate data and a factor.

In this case, the factors are head direction, floor angle, focal length, height, length 1 (length01), chest circumference (girth_first), middle circumference (girth_mid), rear circumference (girth_end), average half circumference of the body, It may be one or more of the total body half circumference and the number of cloud points, but is not limited thereto, and various factors such as bending or not may be extracted.

As shown in FIG. 6 , length 1 is the distance from the front leg with the head removed to the tip of the buttocks, and length 2 is the distance between the front legs and hind legs.

The weight derivation unit 332 may derive the estimated weight from the three-dimensional livestock data.

Here, when there are two or more three-dimensional livestock data, the weight derivation unit 332 repeats the estimated weight derivation process according to the number of three-dimensional livestock data to obtain an estimated weight according to each three-dimensional livestock data, Estimated weight data corresponding to the number can be obtained. That is, the estimated weight is obtained for each three-dimensional livestock data.

The estimated weight data may include the derived estimated weight and three-dimensional livestock data, but is not limited thereto, and may further include other information.

Referring to FIG. 7 , the weight deriving unit 332 may include a candidate list unit 3320 , an algorithm deriving unit 3321 , and a final deriving unit 3322 .

The candidate list unit 3320 selects one or more three-dimensional livestock data according to a factor to generate a candidate list, and determines the number of cases of condition satisfaction of the generated candidate list to derive the first weight of the three-dimensional livestock data. can

To this end, the candidate list unit 3320 may include a list generator and a list processor.

The list generator may generate a candidate list by selecting one or more three-dimensional livestock data as candidates according to a factor.

Specifically, the list generator compares one or more three-dimensional livestock data through a factor based on the livestock standard data, and selects candidate 1, candidate 2, and candidate 3 as candidates 1, 2, and 2 when they belong to the standard livestock data. The final first, second, and third candidate lists may be generated by adding them to the three candidate lists.

In this case, when the 3D livestock data is selected as a candidate, a weight according to the matching livestock standard data may be included as the weight of the 3D livestock data.

The list generator may generate a first candidate list by comparing one or more of the total head direction, floor angle, focal length, length 1, and body half circumference of the three-dimensional livestock data with the livestock standard data.

In addition, the list generator may generate a second candidate list by comparing one or more of the head direction, the total body half circumference, height, length 1, and the median half circumference of the three-dimensional livestock data with the livestock standard data.

In addition, the list generating unit may generate a third candidate list by comparing one or more of the head direction, length 1, chest circumference, middle half circumference, and rear half circumference of the three-dimensional livestock data with the livestock standard data.

Meanwhile, the list generator may also generate the first, second, and third candidate backup lists when the first, second, and third candidate lists are generated, respectively.

The above process will be described in more detail in the following livestock weight estimation method.

The list processing unit may determine the number of cases of condition satisfaction of the generated candidate list (first, second, and third candidate lists), and in some cases may derive a first weight of the three-dimensional livestock data.

The conditional satisfaction is whether or not to have one or more three-dimensional livestock data, and as the first, second and third candidate lists are generated, the number of cases is three satisfied (first to third candidate lists), two satisfied ( 1st and 2nd candidate lists, 2nd and 3rd candidate lists, 1st and 3rd candidate lists), 1 satisfaction (1st, 2nd, 3rd candidate list), 0 satisfactions may occur.

The process of deriving the first weight according to each of these cases will be described in more detail in the following livestock weight estimation method.

The algorithm derivation unit 3321 may derive the second weight by applying a multiple regression formula to the three-dimensional livestock data.

Specifically, the algorithm derivation unit 3321 uses the height, length 2, body half-circumference average, and the number of cloud points of the 3D livestock data among factors of the 3D livestock data to obtain the second value through Equation 1 below. weight can be derived.

[Equation 1]

2nd weight = m ₁ + (h ₁ × height) + (2ㅣ ₁ × length 2) + (g ₁ × body half circumference average) + (p ₁ × number of cloud points in 3D livestock data)

Here, m ₁ is the weight constant, h ₁ is the height constant, 2 ₁ is the length 2 constant, g ₁ is the half-circumference average constant, and p ₁ is the cloud point constant of the 3D livestock data.

In addition, the algorithm derivation unit 3321 may derive the second weight by using Equations 2 to 4, respectively.

More specifically, the algorithm derivation unit 3321 may derive the second weight through Equation 2 by using the height, length 1, the average body half circumference, and the number of cloud points of the three-dimensional livestock data among the factors. there is.

[Equation 2]

2nd weight = m ₂ + (h ₂ × height) + (1ㅣ ₂ × length 1) + (g ₂ × body half circumference average) + (p ₂ × number of cloud points in 3D livestock data)

Here, m ₂ is the weight constant, h ₂ is the height constant, 1ㅣ ₂ is the length 1 constant, g ₂ is the half-circumference average constant, and p ₂ is the cloud point constant of the three-dimensional livestock data.

In addition, the algorithm derivation unit 3321 may derive the second weight through Equation 3 by using the number of cloud points of the height, the body half circumference average, and the three-dimensional livestock data among the factors.

[Equation 3]

Second weight = m ₃ + (h ₃ × height) + (g ₃ × body half circumference average) + (p ₃ × number of cloud points in the three-dimensional livestock data)

Here, m ₃ is the weight constant, h ₃ is the height constant, g ₃ is the half-circumference average constant, and p ₃ is the cloud point constant of the three-dimensional livestock data.

Also, the algorithm derivation unit 3321 may derive the second weight through Equation 4 by using the average body circumference among the factors and the number of cloud points of the 3D livestock data.

[Equation 4]

Second weight = m ₄ + (g ₄ × body half circumference average) + (p ₄ × number of cloud points in the three-dimensional livestock data)

Here, m ₄ is the weight constant, g ₄ is the half-circumference average constant, and p ₄ is the cloud point constant of the three-dimensional livestock data.

The final derivation unit 3322 may derive the estimated weight by using the first weight and the second weight, and may derive the estimated weight according to an absolute value of a value obtained by subtracting the first weight from the second weight. When the absolute value is less than a certain weight value, the second weight is derived as an estimated weight, and when the absolute value is greater than a certain weight value, the estimated weight can be derived as 0 kg.

The final derivation unit 3322 may derive the estimated weight through the above-described process, generate the estimated weight data, provide it to the user, and store it in the data storage unit 31 .

When stored in the data storage unit 31, the estimated weight may be matched to the recognized livestock biometric information before measuring the weight of the livestock to store the estimated weight.

At this time, if 0 kg is derived as the estimated weight, it may be considered as 'weighing failure', and accordingly, the final derivation unit 3322 informs the user of 'weighing failure' to re-photograph the livestock to re-estimate or automatically to operate the 3D sensors 2a and 2b to return to the beginning and proceed again.

The shipment determination unit 34 may determine whether shipment is possible by comparing the derived estimated weight with the shipment possible weight. If it is determined that shipment is possible, a signal may be transmitted to the marker unit 5 to operate the marker unit 5 to mark the livestock for shipment.

In addition, when it is determined that the shipment is impossible, the shipment determination unit 34 may transmit a notification signal to notify the user that the measurement of the weight of the livestock has been completed.

The management unit 35 may provide the estimated weight data stored in the data storage unit 31 in an organized form by livestock, by date, by weight, and the like.

The reader 4 is installed in the stationary body part 1 to recognize livestock. Each livestock may have a tag having its own livestock biometric information attached thereto, and the reader 4 may recognize the livestock biometric information by recognizing the tag attached to the livestock. The recognized livestock biometric information may be transmitted to the terminal 3 .

The marker unit 5 is capable of marking livestock for shipment, and by spraying color dye, it is possible to mark the shipment on livestock. The operation may be controlled by the terminal 3 .

A livestock weight estimation method using the livestock weight estimation system as described above will be described in detail below.

8 is a flowchart schematically illustrating a livestock weight estimation method using a stationary type livestock weight estimation system based on a 3D image according to an embodiment of the present invention, and FIG. 9 is a flowchart sequentially illustrating steps S3 of FIG. 10 is a flowchart sequentially illustrating step S32 of FIG. 9 , FIG. 11 is a flowchart sequentially illustrating step S320 of FIG. 10 , and FIG. 12 is a step S3201 when the first, second and third candidate lists satisfy the condition is a flowchart showing a process in which step S32012a of FIG. 12 is performed, FIG. 14 is a flowchart illustrating a process in which step S32016a of FIG. 12 is performed, and FIG. 15 is a first and second candidate list that satisfies the condition It is a flowchart illustrating a process in which step S32010b is performed in step S3201 in the case of , FIG. 16 is a flowchart illustrating step S3201 when the second and third candidate lists satisfy the condition, and FIG. 17 is a process in which step S32013c in FIG. 16 is performed is a flowchart showing a process in which step S32010d is performed in step S3201 when the first and third candidate lists satisfy the condition, and FIG. 19 is a flow chart in step S3201 when only the third candidate list satisfies the condition It is a flowchart illustrating a process in which step S32010e is performed, and FIG. 20 is a flowchart illustrating a process in which step S32010f is performed in step S3201 when there is no condition satisfaction candidate list.

8, the livestock weight estimation method using the stationary type livestock weight estimation system based on a 3D image according to an embodiment of the present invention is a livestock recognition step (S1), a photographing step (S2), a weight estimation step (S3) and a shipment determination step (S$).

First, in the livestock recognition step (S1), the reader 4 may recognize the livestock and transmit livestock biometric information to the terminal 3 .

In the photographing step (S2), when the terminal 3 receives the livestock biometric information from the reader 4, the 3D sensors 2a, 2b are operated to photograph the livestock through the 3D sensors 2a, 2b, and one or more livestock frames can be extracted. Here, the 3D sensors 2a and 2b may be installed indoors by the stationary body 1 .

In step S2, when the terminal 3 receives the livestock biometric information, the livestock weight estimation application 30 is executed, the livestock is photographed through the 3D sensors 2a, 2b, and the screen is captured through the livestock weight estimation application 30 Thus, one or more livestock frames can be extracted. A description thereof will be omitted since it has been described in detail in the above system.

In the weight estimation step (S3), the livestock weight estimation application 30 of the terminal 3 may derive the estimated weight using the extracted livestock frame.

Referring to FIG. 9 , step S3 may include a conversion step ( S30 ), a pre-processing step ( S31 ), and a weight derivation step ( S32 ).

In the transformation step (S30), after arranging one or more livestock frames, it is possible to extract points and convert them into three-dimensional coordinate data.

The pre-processing step (S31) may pre-process the converted three-dimensional coordinate data to generate three-dimensional livestock data, respectively.

To this end, step S32 may include a validation step, a noise removal step, and a factor extraction step.

The validation step may determine the validity of each three-dimensional coordinate data, and may drop out the invalid three-dimensional coordinate data. A detailed description has been made in the above system, so it will be omitted.

The noise removing step may remove noise from the 3D coordinate data. A detailed description has been made in the above system, so it will be omitted.

In the factor extraction step, a factor may be extracted from the 3D coordinate data and generated as 3D livestock data. A detailed description has been made in the above system, so it will be omitted.

The weight derivation step (S32) can derive the estimated weight from the three-dimensional livestock data, and this step S32 is repeated according to the number of the three-dimensional livestock data to derive the estimated weight according to each three-dimensional livestock data one by one. . However, the present invention is not limited thereto and may be performed at once.

Referring to FIG. 10 , step S32 may include a first weight deriving step (S320), a second weight deriving step (S321) and an estimated weight deriving step (S322).

In the first weight derivation step (S320), one or more of the three-dimensional livestock data is selected according to a factor to generate a candidate list, and the number of cases of condition satisfaction of the generated candidate list is determined to determine the first of the three-dimensional livestock data. weight can be derived.

Referring to FIG. 11 , step S320 may include a list generation step ( S3200 ) and a list processing step ( S3201 ).

The list creation step ( S3200 ) may generate a candidate list by selecting one or more of the three-dimensional livestock data as candidates according to a factor.

That is, in step S3200, one or more three-dimensional livestock data is compared through a factor based on the livestock standard data, respectively, and if it belongs to the livestock standard data, candidate 1, candidate 2, and candidate 3 are selected as the first, second and third By adding to the candidate list, the final first, second, and third candidate lists may be generated.

To this end, step S3200 may include a first candidate step, a second candidate step, and a third candidate step.

The first candidate step may generate a first candidate list by comparing one or more of the total of head direction, floor angle, focal length, length 1, and body half circumference of each three-dimensional livestock data with the livestock standard data. Compared with the livestock standard data, if the 3D livestock data falls within it, the 3D livestock data may be selected as candidate 1 and added to the first candidate list. Through this process, the first candidate list may be generated.

More specifically, the first candidate step is whether the three-dimensional livestock data is the same as the head direction of the livestock standard data, 'is within the floor angle range', 'within the focal length range', 'within the length 1 range', ' It is possible to add only 3D livestock data that is YES in all cases to the first candidate list by performing the comparison in the order of 'whether it is within the total range of the body half circumference', and only in the case of YES (true), to proceed to the following order.

It is not limited to the above order, and may be easily changed and applied.

In addition, the first candidate step can also generate a first candidate backup list, by adding 3D livestock data that is NO (no) to the first candidate backup list only in the last order, 'whether it is within the total body half circumference', to the first candidate backup list. 1 Can create a candidate backup list.

When added to the list, the 3D livestock data may include a weight according to the corresponding livestock standard data as the weight of the 3D livestock data.

The second candidate step compares one or more of the head direction, total body half circumference, height, length 1, and median half circumference of each 3D livestock data with the livestock standard data, and if the 3D livestock data falls within it, the 3D A second candidate list may be generated by selecting livestock data as candidate 2 and adding it to the second candidate list.

More specifically, the second candidate step is whether the three-dimensional livestock data is the same as the head direction of the livestock standard data, 'is within the total body half circumference', 'within the height range', 'within the length 1 range', Comparison is performed in the order of 'whether it is within the median half circumference range', and only the 3D livestock data that is YES in all cases can be added to the second candidate list by proceeding to the following order only in the case of YES. It is not limited to the above order, and may be easily changed and applied.

In addition, the second candidate step can also generate a second candidate backup list, by adding the 3D livestock data that is NO (no) only to the last order, 'whether it is within the median half circumference range', to the second candidate backup list. You can create a candidate backup list.

The third candidate step compares one or more of the head direction, length 1, chest circumference, middle half circumference, and rear half circumference of each of the three-dimensional livestock data with the livestock standard data, and if the three-dimensional livestock data belongs therein, the corresponding A third candidate list may be generated by selecting 3D livestock data as candidate 3 and adding it to the third candidate list.

More specifically, the third candidate step is whether the 3D livestock data is 'same as the head direction', 'within the length 1 range', 'within the chest circumference range', 'within the median half circumference range' of the livestock standard data. , 'Whether it is within the perimeter of the second half', the comparison proceeds in the order, and only in the case of YES (true), only the 3D livestock data that is YES can be added to the third candidate list by proceeding to the following order. It is not limited to the above order, and may be easily changed and applied.

In addition, the third candidate step can also generate a third candidate backup list, by adding the 3D livestock data that is NO (no) only to the last order, 'whether it is within the posterior half circumference', to the third candidate backup list. You can create a candidate backup list.

The list processing step (S3201) may determine the number of cases of condition satisfaction of the generated candidate list (the first, second and third candidate lists), and in some cases derive the first weight of the three-dimensional livestock data. .

The condition satisfaction is whether or not it has one or more three-dimensional livestock data, and as the first, second and third candidate lists are generated, the number of cases is three satisfactions (first to third candidate lists), two satisfactions ( 1st and 2nd candidate lists, 2nd and 3rd candidate lists, 1st and 3rd candidate list), 1 satisfaction (1st, 2nd, 3rd candidate list), 0 satisfactions may occur.

Each of the processes in which step S3201 proceeds according to the number of cases of condition satisfaction will be described in detail.

Referring to FIG. 12 , step S3201 includes a first number determination step (S22010a) when the first, second and third candidate lists all have one or more three-dimensional livestock data (in the case of three satisfactions). can

In the first number determination step S32010a, it may be determined whether there is one 3D livestock data of the first candidate list. Here, depending on whether there is one or not, step S3201 includes the first detection step (S32011a) and the first derivation step (S32012a) or the length determination step (S32013a), the second detection step (S32014a), the temporary list generation step (S32015a) and the second step 2 may include a derivation step (S32016a).

First, a case in which there is one 3D livestock data of the first candidate list in step S32010a will be described.

In the first detection step (S32011a), if the 3D livestock data of the first candidate list is one in the step S32010a, the weight of the 3D livestock data of the 1st candidate list is selected as the predicted weight, and then the second and third candidate lists are It can be found whether there is 3D livestock data having the same weight as the predicted weight among the 3D livestock data.

The first derivation step (S32012a) may derive the first weight according to the result of the step S32011a, that is, the first weight according to whether there is 3D livestock data having the same weight as the predicted weight in both the second and third candidate lists. can be derived.

In step S32012a, as shown in FIG. 13 , when there is 3D livestock data having the same weight as the predicted weight in both the second and third candidate lists, the first weight may be derived from Equations 5 and 6 below.

[Equation 5]

Average range = Body half circumference average - Body half circumference average of 3D livestock data of the first candidate list

Here, the body half-circumference average is the body half-circumference average of the three-dimensional livestock data for which the estimated weight is to be derived.

[Equation 6]

1st weight = predicted weight + (average range Х 1.5)

In addition, in step S32012a, when there is no three-dimensional livestock data having the same weight as the predicted weight at least one of the second and third candidate lists, the predicted weight may be derived as the first weight.

Next, a case in which there is not one 3D livestock data of the first candidate list in step S32010a will be described.

In the length determination step (S32013a), if the 3D livestock data of the first candidate list is not one in the step S32010a, the length 2 of the 3D livestock data from which the estimated weight is to be derived is the nth 3D livestock data of the first candidate list. It can be determined whether it is within the range of length 2.

Here, n is 2 or more, and is the number of three-dimensional livestock data in the first candidate list, and the length determination step (S32013a), the second detection step (S32014a), and the temporary list generation step (S32015a) are repeated n times.

If the length 2 of the 3D livestock data in the step S32013a is within the range of the length 2 of the nth 3D livestock data of the first candidate list, it proceeds to the second detection step (S32014a), and the length 2 of the 3D livestock data is the second 1 If it is not within the range of length 2 of the nth three-dimensional livestock data of the candidate list, the step S32013a may be performed again or the second derivation step (S320216a) may be performed by checking the number of repetitions.

In the second detection step (S32014a), when the length of the nth 3D livestock data of the first candidate list is within the range of 2, after selecting the weight of the nth 3D livestock data of the first candidate list as the predicted weight, the second and whether there is data having the same weight as the predicted weight among the three-dimensional livestock data of the third candidate list.

Temporary list generation step (S32015a) is based on whether both the second and third candidate lists have 3D livestock data having the same weight as the predicted weight through the result of step S32014a, n of the first candidate list in the first temporary list A second 3D livestock data can be added.

In step S32015a, when there is 3D livestock data having the same weight as the predicted weight in both the second and third candidate lists, the nth 3D livestock data of the first candidate list may be added to the first temporary list.

On the other hand, when there is no 3D livestock data having the same weight as the predicted weight at least one of the second and third candidate lists, the nth 3D livestock data of the first candidate list is not added to the first temporary list.

When the above step is repeated and the number of repetitions becomes equal to n, the second derivation step (S32016a) may be performed.

In the second derivation step (S32016a), the first weight may be derived according to the number of 3D livestock data in the generated first temporary list.

In step S32016a, as shown in FIG. 12 , it is determined whether the number of 3D livestock data in the generated first temporary list is one, and when not more than one, the first weight can be derived as 0 kg.

Also, in step S32016a, when the number of 3D livestock data in the first temporary list is one or more, it may be determined whether the number of 3D livestock data in the generated first temporary list is one.

Accordingly, in step S32016a, when the number of three-dimensional livestock data in the first temporary list is one, the weight of the three-dimensional livestock data in the first temporary list can be derived as the first weight, and when not one (meaning two or more) ) The average weight of the three-dimensional livestock data of the first temporary list may be derived as the first weight.

15 , in step S3201, when both the first and second candidate lists have one or more three-dimensional livestock data (in the case of the first and second candidate lists of two satisfactions), the third derivation step (S32010b) may include

The third derivation step (S32010b) may derive the first weight according to whether the height of the 3D livestock data from which the estimated weight is to be derived is greater than the height of the first 3D livestock data of the first candidate list.

In detail, step S32010b determines whether the height of the three-dimensional livestock data is greater than the height of the first three-dimensional livestock data of the first candidate list, and when it is greater than the height of the first three-dimensional livestock data of the first candidate list, the following mathematics The first weight can be derived from Equation 7.

[Equation 7]

1st weight = list01.data(0).weight + (list01.data(0).weight × 0.03)

Here, list01.data(0).weight is the weight of the first three-dimensional livestock data of the first candidate list.

In addition, in step S32010b, if the height of the three-dimensional livestock data is less than or equal to the height of the first three-dimensional livestock data of the first candidate list, whether the height of the three-dimensional livestock data is less than or equal to the height of the last three-dimensional livestock data of the first candidate list can judge

Accordingly, in step S32010b, when the height of the last three-dimensional livestock data of the first candidate list is less than or equal to the height, the first weight may be derived from the following Equation (8).

[Equation 8]

1st weight = list01.data(last).weight + (list01.data(last).weight × 0.03)

Here, list01.data(last).weight is the weight of the last 3D livestock data in the first candidate list.

In addition, in step S32010b, when the height of the last 3D livestock data of the first candidate list is not lower than the height, the average weight of the 3D livestock data of the first candidate list may be derived as the first weight.

Referring to FIG. 16 , in step S3201, when both the second and third candidate lists have one or more three-dimensional livestock data (in the case of the second and third candidate lists with two satisfactions), the second number determination step (S32010c) ) may be included.

In the second number determination step S32010c, it may be determined whether there is more than one 3D livestock data of the third candidate list. Here, step S3201 may include a 4-1 derivation step (S32011c) or a calculation step (S32012c) and a 4-2 derivation step (S32013c) depending on whether one is exceeded or not.

First, a case in which the 3D livestock data of the third candidate list exceeds one in step S32010c will be described.

In the 4-1 derivation step (S32011c), if the 3D livestock data of the third candidate list is more than one in the step S32010c, the average weight of the 3D livestock data of the second candidate list may be derived as the first weight.

Next, a case in which the 3D livestock data of the third candidate list does not exceed one (meaning one) in step S32010c will be described.

The calculation step (S32012c) can be calculated by classifying the 3D livestock data of the second candidate list according to whether the weight of the k-th 3D livestock data of the second candidate list is equal to or greater than the weight of the 3D livestock data of the third candidate list. .

Here, k is 1 or more, and is the number of 3D livestock data in the second candidate list, and the calculation step (S32012c) may be repeated k times.

In step S32012c, the three-dimensional livestock data of the second candidate list has a weight greater than or equal to the weight of the three-dimensional livestock data of the third candidate list (three-dimensional livestock data greater than or equal to the weight) and having a weight less than the weight (three-dimensional livestock that is less than the weight) data), and the total weight (sum01,sum02), number (cnt01, cnt02), and weight average (avr01, avr02) of 3D livestock data above weight and 3D livestock data below weight can be obtained. .

When the above step is repeated and the number of repetitions becomes equal to k, the 4-2 derivation step (S32013c) may proceed.

In the 4-2 derivation step ( S32013c ), the first weight may be derived according to whether the height of the 3D livestock data from which the estimated weight is to be derived is equal to or greater than the height of the 3D livestock data of the third candidate list.

Specifically, as shown in FIG. 17 , in step S32013c, when the height of the 3D livestock data is greater than or equal to the height of the 3D livestock data of the third candidate list, it may be determined whether sum01 is greater than 0.

This is to prevent a case in which the first weight cannot be obtained by checking an error before deriving the first weight because there may be a case where sum01 is 0 because there is no three-dimensional livestock data that is more than the weight.

Accordingly, in step S32013c, when sum01 is greater than 0, the first weight may be derived through Equation 9 below.

[Equation 9]

1st weight = sum01/cnt01

Here, sum01 is the total weight of three-dimensional livestock data over weight, and cnt01 is the number of three-dimensional livestock data over weight.

Also, when sum01 is not greater than 0, the first weight may be derived through Equation 10 below.

[Equation 10]

1st weight = sum02/cnt02

Here, sum02 is the total weight of the three-dimensional livestock data that is less than the weight, and cnt02 is the number of three-dimensional livestock data that is less than the weight.

On the other hand, in step S32013c, when the height of the 3D livestock data is less than the height of the 3D livestock data of the third candidate list, it may be determined whether sum02 is greater than 0.

As above, since there may be a case where sum02 is 0 because there is no three-dimensional livestock data that is less than the weight, an error is checked before deriving the first weight.

Accordingly, in step S32013c, when sum02 is greater than 0, the first weight can be derived through Equation 10, and when sum02 is not greater than 0, the first weight can be derived through Equation 8.

Through this, it is possible to improve the estimation efficiency by preventing 0 as the value of the first weight.

Referring to FIG. 18 , in step S3201, when both the first and third candidate lists have one or more three-dimensional livestock data (in the case of the first and third candidate lists of two satisfactions), the fifth derivation step (S32010d) may include

In the fifth derivation step (S32010d), the first weight may be derived according to whether the height of the 3D livestock data from which the estimated weight is to be derived is greater than or equal to the height of the first 3D livestock data of the third candidate list.

In detail, step S32010d determines whether the height of the three-dimensional livestock data is greater than or equal to the height of the first three-dimensional livestock data of the third candidate list, and when it is greater than or equal to the height of the first three-dimensional livestock data of the third candidate list, the following equation The first weight can be derived from 11 .

[Equation 11]

1st weight = list03.data(0).weight + (list03.data(0).weight × 0.03)

Here, list03.data(0).weight is the weight of the first three-dimensional livestock data of the third candidate list.

In addition, in step S32010d, if the height of the 3D livestock data is less than the height of the first 3D livestock data of the third candidate list, the height of the 3D livestock data is less than or equal to the height of the last 3D livestock data of the third candidate list can judge

Accordingly, in step S32010d, when the height of the last 3D livestock data of the third candidate list is less than or equal to the height, the first weight may be derived from Equation 12 below.

[Equation 12]

1st weight = list03.data(last).weight + (list03.data(last).weight × 0.03)

Here, list03.data(last).weight is the weight of the last 3D livestock data in the third candidate list.

In addition, in step S32010d, when the height of the last 3D livestock data of the third candidate list is not lower than the height, the average weight of the 3D livestock data of the third candidate list may be derived as the first weight.

Step S3201 may include a sixth derivation step when only the first candidate list has one or more three-dimensional livestock data (in the case of the first candidate list of one satisfaction).

In the sixth derivation step, the weight of the first three-dimensional livestock data of the first candidate list may be derived as the first weight.

Step S3201 may include a seventh derivation step when only the second candidate list has one or more three-dimensional livestock data (in the case of the second candidate list of one satisfaction).

In the seventh derivation step, the average weight of the three-dimensional livestock data of the second candidate list may be derived as the first weight.

Referring to FIG. 19 , step S3201 may include an eighth derivation step ( S32010e ) when only the third candidate list has one or more three-dimensional livestock data (the third candidate list of one satisfaction).

In the eighth derivation step ( S32010e ), a first weight for deriving a first weight may be derived according to whether there is one 3D livestock data in the third candidate list.

First, in step S32010e, it is determined whether there is one 3D livestock data of the third candidate list, and when the 3D livestock data of the third candidate list is one, the 3D livestock data of the third candidate list is derived as the first weight. can

On the other hand, in step S32010e, when the 3D livestock data of the third candidate list is not one, the first weight can be derived by determining whether the height of the 3D livestock data is greater than or equal to the height of the first 3D livestock data of the third candidate list. .

In addition, in step S32010e, when the height of the 3D livestock data is greater than or equal to the height of the first 3D livestock data of the third candidate list, the first weight may be derived from Equation (11).

In step S32010e, if the height of the first three-dimensional livestock data of the third candidate list is less than the height, the first weight is derived by determining whether the height of the next three-dimensional livestock data is less than or equal to the height of the last three-dimensional livestock data of the third candidate list can do.

In step S32010e, when the height of the 3D livestock data is less than or equal to the height of the last 3D livestock data of the third candidate list, the first weight may be derived from Equation 12, and the height of the last 3D livestock data of the third candidate list If it exceeds, the average weight of the three-dimensional livestock data of the third candidate list may be derived as the first weight.

Referring to FIG. 20 , step S3201 may include a ninth derivation step ( S32010f ) when none of the first to third candidate lists have 3D livestock data (0 is satisfied).

In the ninth derivation step (S32010f), it may be determined whether the number of 3D livestock data in the second candidate backup list is greater than zero.

S32010f determines that if the number of three-dimensional livestock data in the second candidate backup list is greater than 0, the average of the three-dimensional livestock data is within the average range of the waist circumference of the j-th three-dimensional livestock data of the second candidate backup list. It can be calculated by classifying the 3D livestock data of the second candidate backup list.

Here, j is 1 or more, and is the number of three-dimensional livestock data in the second candidate backup list.

In the above process, S32010f determines that the 3D livestock data of the second candidate backup list falls within the range (three-dimensional livestock data within the range) and that the average waist circumference of the 3D livestock data does not fall within the range (out of the range) 3D livestock data), and the total weight (sum03, sum04), number (cnt03, cnt04), etc. of each can be calculated.

Next, S32010f may determine whether sum03 is greater than 0, and when sum03 is greater than 0, the first weight is derived by Equation 13 below, and when sum03 is 0 or less, the first weight can be derived by Equation 14 below. there is.

[Equation 13]

1st weight = sum03/cnt03

Here, sum03 is the total weight of 3D livestock data within the range, and cnt03 is the number of 3D livestock data within the range.

[Equation 14]

1st weight = sum04/cnt04

Here, sum04 is the total weight of out-of-range 3D livestock data, and cnt04 is the number of out-of-range 3D livestock data.

On the other hand, in S32010f, when the number of 3D livestock data in the second candidate backup list is less than 0, the first weight may be derived as 100 kg. This may mean 'weighing failure'.

In the second weight derivation step (S321), the second weight can be derived by applying one of Equations 1 to 4, which is a multiple regression formula, to the dimensional livestock data, and it is preferable to apply Equation 1, but is not limited thereto does not Since detailed descriptions have been made in the description of the system, they will be omitted.

In the estimated weight deriving step (S322), the estimated weight may be derived using the derived first weight and the second weight, and estimated weight data may be generated and stored. Since detailed descriptions have been made in the description of the system, they will be omitted.

The shipment determination step (S4) may determine whether shipment is possible by comparing the estimated weight derived by the livestock weight estimation application 30 and the available weight for shipment. When it is determined that shipment is possible, a shipment indication step (not shown) may be further included, and when it is determined that shipment is not possible, a notification signal may be transmitted to notify the manager that the weight measurement of the livestock is complete.

In the shipment display step, when it is determined that shipment is possible in step S4 , the livestock weight estimation application 30 may transmit a signal to the marker unit 5 so that the marker unit 5 may mark the shipment on the livestock.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present invention as defined in the following claims are also provided. is within the scope of the right.

1: Stationary body part
2a,b: 3D sensor
3: terminal
30: Livestock Weight Estimation Application
31: data storage unit
32: sensor photographing unit
33: weight estimator
330: conversion unit
331: preprocessor
332: weight derivation unit
3320: Candidate list unit
3321: algorithm derivation unit
3322: final derivation
34: shipment decision unit
35: management
4: Reader
5: Marker part

Claims (11)

In the system for estimating the weight of livestock formed in a stationary type that can be installed indoors, and using a livestock weight estimation application based on a 3D image,
a stationary body that can be installed indoors;
One or more 3D sensors installed in the stationary body to photograph livestock; and
A stationary livestock weight estimation system based on a 3D image including a terminal including a livestock weight estimation application for estimating the weight of livestock using the livestock frame extracted through the 3D sensor.
According to claim 1,
The livestock weight estimation application is,
A sensor photographing unit that operates the 3D sensor to photograph livestock and extracts one or more livestock frames; and
A stationary livestock weight estimation system based on a 3D image including a weight estimator that derives an estimated weight using the extracted livestock frame.
3. The method of claim 2,
Further comprising a reader installed in the stationary body portion for recognizing livestock,
The sensor photographing unit,
When livestock biometric information is received from the reader, the 3D sensor is operated to photograph the livestock and extract the livestock frame.
3. The method of claim 2,
The weight estimation unit,
a conversion unit that converts the extracted livestock frame into 3D coordinate data;
A pre-processing unit for pre-processing the converted three-dimensional coordinate data to generate three-dimensional livestock data; and
A stationary livestock weight estimation system based on a 3D image including a weight derivation unit for deriving an estimated weight from the three-dimensional livestock data.
5. The method of claim 4,
The preprocessor is
A factor extracting unit for extracting a factor from the three-dimensional coordinate data,
The factor is
3D including at least one of head direction, floor angle, focal length, height, length 1, chest circumference, mid-fold circumference, posterior half circumference, average body half circumference, total body half circumference, and number of cloud points An image-based stationary livestock weight estimation system.
(Here, length 1 is the distance from the front leg with the head removed to the tip of the buttocks, and length 2 is the distance between the front and hind legs.)
6. The method of claim 5,
The weight deriver,
a candidate list unit for generating a candidate list by selecting one or more of the three-dimensional livestock data according to a factor, and deriving a first weight of the three-dimensional livestock data by determining the number of cases of condition satisfaction of the generated candidate list;
An algorithm derivation unit for deriving a second weight by applying a multiple regression formula to the three-dimensional livestock data; and
A stationary livestock weight estimation system based on a 3D image including a final derivation unit for deriving an estimated weight using the first weight and the second weight.
7. The method of claim 6,
The candidate list unit,
a list generator for generating a candidate list by selecting one or more of the three-dimensional livestock data as candidates according to a factor; and
A stationary livestock weight estimation system based on a 3D image, comprising a list processing unit that determines the number of cases of condition satisfaction of the generated candidate list and, in some cases, derives a first weight of the three-dimensional livestock data.
7. The method of claim 6,
The algorithm derivation unit,
Based on a 3D image, characterized in that the second weight is derived through Equation 1 below using the height, length 2, the average body half circumference, and the number of cloud points among the factors of the three-dimensional livestock data. Stationary livestock weight estimation system.
[Equation 1]
2nd weight = m ₁ + (h ₁ × height) + (2ㅣ ₁ × length 2) + (g ₁ × body half circumference average) + (p ₁ × number of cloud points in 3D livestock data)
(Where m ₁ is the weight constant, h ₁ is the height constant, 2ㅣ ₁ is the length 2 constant, g ₁ is the half-circumference average constant, and p ₁ is the cloud point constant of the 3D livestock data)
3. The method of claim 2,
The livestock weight estimation application is,
Further comprising a shipment determination unit to determine whether shipment is possible by comparing the derived estimated weight with the shipment possible weight,
When it is determined that the shipment is possible by the shipment determination unit, the stationary livestock weight estimation system based on a 3D image further comprising a marker unit for marking the shipment on the livestock.
In a livestock weight estimation method using a stationary livestock weight estimation system based on a 3D image,
(a) a photographing step of extracting one or more livestock frames by photographing livestock through a 3D sensor installed indoors by a stationary body part; and
(b) a method for estimating the weight of livestock including a weight estimation step in which the terminal derives an estimated weight using the extracted livestock frame.
11. The method of claim 10,
After the weight estimation step,
The method of estimating the weight of livestock further comprising a shipment judgment step of determining whether shipment is possible by comparing the derived estimated weight with the available shipment weight.

Images