KR20220006312A - An apparatus for determination of body weight of korean cattle using ToF camera - Google Patents

Abstract

The present invention relates to an apparatus for measuring the body weight of Korean cattle using a Time of Flight (ToF) camera, comprising: the ToF camera measuring the distance from an upper surface of Korean cattle, and acquiring and providing a point cloud image corresponding to the upper surface of the Korean cattle; a camera holding unit fixing the position of the ToF camera on an upper side of the Korean cattle; a mesh information acquisition unit using a linear interpolation method, and acquiring three-dimensional mesh information corresponding to the point cloud image; a volume calculation unit conducting the three-dimensional modeling based on the three-dimensional mesh information, and generating a Korean cattle torso model, and calculating the volume of the Korean cattle torso based on the Korean cattle torso model; and a body weight calculation unit converting the volume of the Korean cattle torso into a body weight in accordance with a preset linear regression formula and outputting the body weight. The present invention aims to provide an apparatus for measuring the body weight of Korean cattle using a ToF camera, which is capable of simplifying the structure.

Description

ToF camera-based weight measuring device for Korean cattle {An apparatus for determination of body weight of korean cattle using ToF camera}

The present invention relates to a ToF camera-based weighing apparatus for Korean beef that can measure and provide the weight of Korean beef with just one shot using a single ToF camera.

Computer image processing technology has recently been researched and put to practical use, centered on factory automation. Although its practicality has been recognized only in standardized areas, it is expected that practical use will be achieved in many fields that are not standardized in the future.

Although research on weight measurement of Korean cattle using computerized image processing technology has not yet been reported at home and abroad, it is a new technology that is currently being researched. rough

In order to reduce the errors and difficulties in using the multi-lever weight measuring device used in the field, recently, a non-contact weight system applied with image processing technology has been developed and research is being actively conducted to apply it to the livestock field.

In particular, in Korean Patent Registration No. 10-2123761, a 3D scanner unit that obtains a three-dimensional image by 3D scanning Korean beef and a Korean beef weight measurement device that is linked with the 3D scanner unit and calculates the weight of Korean cattle using a three-dimensional image are provided. We are providing a Korean beef tracking system based on 3D model analysis using 3D scanning.

However, in the case of calculating the body weight by 3D scanning Korean beef as in the prior art, a plurality of cameras for 3D scanning must be provided, or images from multiple viewpoints must be repeatedly photographed several times while moving one camera. there was. In other words, there was a problem in that the cost of implementing the system increased or the shooting time was long, so that the movement of Korean cattle occurred, and thus the image accuracy was rapidly deteriorated.

Korean Patent Registration No. 10-1584936 (Registration Date: 2016.01.06)

Accordingly, in order to solve the above problems, the present invention is to provide a ToF camera-based Korean beef weight measurement device that can measure and provide the weight of Korean cattle with just one shot using one ToF camera.

In addition, it is intended to provide a ToF camera-based Korean beef weight measurement device having a new weight measurement method that calculates the volume of Korean cattle from the ToF camera image and converts it into body weight.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned will be clearly understood by those of ordinary skill in the art from the description below.

As a means for solving the above problem, according to an embodiment of the present invention, a time of flight (TOF) for acquiring and providing a point cloud image corresponding to the upper surface of Korean beef by measuring a distance from the upper surface of the Korean beef camera; a camera holder for fixing the TOF camera to the upper side of the Korean beef; a mesh information acquisition unit configured to acquire 3D mesh information corresponding to the point cloud image by using a linear interpolation method; a volume calculator configured to generate a Korean beef torso model by performing three-dimensional modeling based on the three-dimensional mesh information, and then calculating a volume of a Korean beef torso based on the Korean beef torso model; and a weight calculator that converts and outputs the volume of the Korean beef torso into body weight according to a preset linear regression equation.

_{The weight calculator converts the volume (V total} ) of the Korean beef torso into the weight according to the formula of "weight = α + β × V _total ", and the α and β are determined from the regression equation of the measured data. Characterized by constants.

In addition, the apparatus is characterized in that it further comprises a noise canceling unit for removing noise included in the point cloud image using a k-nearest neighbors algorithm.

The camera holder is a folding tripod; a bar-shaped base arm coupled to the upper side of the foldable tripod; a counterweight coupled to one side of the base arm to provide a weight for weight balance; a rod-shaped expansion arm coupled to the other side of the base arm; It characterized in that it comprises a fixing bracket for connecting and fixing the TOF camera on one side of the expansion arm.

According to the present invention, by using a single ToF camera to measure and provide the weight of Korean beef with just one shot, the device configuration can be simplified and the time required to acquire an image can be minimized.

In addition, it is possible to calculate the volume of Korean beef from the ToF camera image and convert it into body weight.

Furthermore, through the camera cradle implemented based on a tripod, the installation and movement of the device can be performed more easily.

1 is a diagram illustrating an apparatus for measuring the weight of Korean beef based on a ToF camera according to an embodiment of the present invention.
2 is a view showing a detailed configuration of a camera mounting unit according to an embodiment of the present invention.
3 is a diagram illustrating an example of a point cloud image and a 3D mesh image obtained through a ToF camera-based Korean beef weight measurement apparatus according to an embodiment of the present invention.
4 is a diagram for explaining a volume calculation method of a ToF camera-based Korean beef weight measurement apparatus according to an embodiment of the present invention.

The following is merely illustrative of the principles of the invention. Therefore, those skilled in the art will be able to devise various devices that, although not explicitly described or shown herein, embody the principles of the present invention and are included within the spirit and scope of the present invention. Further, it is to be understood that all conditional terms and examples listed herein are, in principle, expressly intended solely for the purpose of enabling the concept of the present invention to be understood, and not limited to the specifically enumerated embodiments and states as such. should be

Moreover, it is to be understood that all detailed description reciting the principles, aspects, and embodiments of the invention, as well as specific embodiments, are intended to cover structural and functional equivalents of such matters. It should also be understood that such equivalents include not only currently known equivalents, but also equivalents developed in the future, i.e., all devices invented to perform the same function, regardless of structure.

Thus, for example, the block diagrams herein are to be understood as representing conceptual views of illustrative circuitry embodying the principles of the present invention. Similarly, all flowcharts, state transition diagrams, pseudo code, etc. may be tangibly embodied on computer-readable media and be understood to represent various processes performed by a computer or processor, whether or not a computer or processor is explicitly shown. should be

The functions of the various elements shown in the drawings including a processor or functional blocks represented by similar concepts may be provided by the use of dedicated hardware as well as hardware having the ability to execute software in association with appropriate software. When provided by a processor, the functionality may be provided by a single dedicated processor, a single shared processor, or a plurality of separate processors, some of which may be shared.

In addition, the clear use of terms presented as processor, control, or similar concepts should not be construed as exclusively referring to hardware having the ability to execute software, and without limitation, digital signal processor (DSP) hardware, ROM for storing software. It should be understood to implicitly include (ROM), RAM (RAM) and non-volatile memory. Other common hardware may also be included.

In the claims of the present specification, a component expressed as a means for performing the function described in the detailed description includes, for example, a combination of circuit elements that perform the function or software in any form including firmware/microcode, etc. It is intended to include all methods of performing the functions of the device, coupled with suitable circuitry for executing the software to perform the functions. Since the present invention defined by these claims is combined with the functions provided by the various enumerated means and in a manner required by the claims, any means capable of providing the functions are equivalent to those contemplated from the present specification. should be understood as

The above objects, features and advantages will become more apparent through the following detailed description in relation to the accompanying drawings, and accordingly, those of ordinary skill in the art to which the present invention pertains can easily implement the technical idea of the present invention. There will be. In addition, in the description of the present invention, if it is determined that a detailed description of a known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted.

1 is a diagram illustrating an apparatus for measuring the weight of Korean beef based on a ToF camera according to an embodiment of the present invention.

Referring to Figure 1, the apparatus of the present invention is a TOF (Time of Flight) camera 110 that measures the distance to the upper surface of Korean beef and acquires and provides a point cloud image corresponding to the upper surface of the Korean beef, the A camera holding unit 120 for fixing a TOF camera on the upper side of Korean beef, a mesh information obtaining unit 130 for obtaining 3D mesh information corresponding to the point cloud image using a linear interpolation method, 3D mesh information After generating a Korean cattle torso model by performing 3-D modeling based on the Korean cattle torso model, the volume calculator 140 calculates the volume of the Korean cattle torso based on the Korean cattle torso model, and the volume of the Korean cattle torso is converted into body weight according to a preset linear regression equation. and a weight calculation unit 150 for outputting the result.

In particular, in the present invention, only Korean beef has been selected as an example of a large livestock, but if necessary, it goes without saying that the weight measurement operation of the present invention can be equally applied to large cattle, such as cattle and horses.

The TOF camera 110 includes a light source in addition to the camera, performs an image capturing operation in each of the light source turn-on state and the turn-off state, and measures the distance of the subject by using the contrast between the two images. After measuring the distance to the upper surface of Korean beef using

The TOF camera 111 is preferably disposed above the photographing location to photograph the top view of Korean beef, because it can best reflect the top surface of Korean beef and the volume of Korean beef.

The camera holder 120 is for positioning and fixing the TOF camera 110 at a specific point, which is a foldable tripod 121 having three or four legs, a foldable tripod 121 as shown in FIG. 2 . ), a bar-shaped base arm 122 coupled to the upper side, a counterweight 123 coupled to one side of the base arm 122 to provide weight for weight balance, a bar coupled to the other side of the base arm 122 It may be implemented as a fixing bracket 125 for connecting and fixing the TOF camera 110 to one side of the extended arm 124 of the shape and the extended arm 124 .

However, it goes without saying that the detailed implementation method may be variously changed according to the device application environment.

The noise removing unit 130 removes all noises included in the point cloud image, ie, outliers due to noise, using a k-nearest neighbors algorithm.

In the present invention, by using the moving average method, by comparing the average height value of the surrounding 10 points with the height value of the corresponding point, if the difference is 5 to 10 mm or more, it can be determined as noise, and the height difference of 5 to 10 mm or more based on the corresponding point However, if there is a difference within 5 to 10 mm from the points immediately adjacent to the left and right or up and down, noise removal and boundary line search methods may be used to set the boundary as the boundary.

The mesh information obtaining unit 140 converts the point cloud image into a three-dimensional mesh image having depth information of each point as shown in FIG. 3 by using a linear interpolation method in order to convert the point cloud image into a form capable of calculating a volume.

In addition, when an empty space is generated in the 3D mesh image, all points corresponding to the Korean beef body can be generated by using the hole filling method for generating new points by referring to information of neighboring points.

In this case, the hole filling technique may be performed by a local optimization method or a global optimization method, and the local optimization method is to generate a new three-dimensional point based on the positional continuity of neighboring points, and global optimization The method is a volume prediction method that generates a new 3D point by predicting an invisible surface based on a currently generated volume.

The volume calculation unit 150 generates a Korean cattle body model by performing 3D modeling based on the 3D mesh information, and then acquires and outputs the volume of Korean cattle based on the Korean cattle body model.

For example, by applying 3D mesh triangulation to 3D mesh information, it is possible to generate a mesh model composed of triangles by edge-connecting points in 3D mesh information. Then, the mesh model is first divided into a first distance interval D1 along the X-axis direction (Y-axis direction), and then secondarily divided into a second distance interval D2 along the Y-axis direction (X-axis direction). By doing so, a plurality of unit grids are generated. Then, by collecting and averaging the height values of points belonging to the unit grid, the height value H of the unit grid is determined, and then the volume V _{i of} each unit grid is obtained according to Equation 1 below. Then, the mesh model, that is, the final volume (V _total ) of Korean beef is obtained by summing all the volumes of all the unit cells.

[Equation 1]

V _i = D1 × D2 × H

In this case, i means the unit lattice order.

[Equation 2]

V _{total =}

In this case, N is the total number of unit cells.

_{Then, the weight calculator 160 converts the volume (V total} ) of the Korean beef torso into a weight according to a linear regression equation as in Equation 3 below and outputs the converted weight.

[Equation 3]

weight = α + β × V _total

In this case, α and β are constants determined in the regression analysis step using the measured image data. For example, α may be 50.7148 and β may be 0.20038, but these are values that can be changed later.

The method according to the present invention described above may be produced as a program to be executed by a computer and stored in a computer-readable recording medium. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape. , a floppy disk, an optical data storage device, and the like, and also includes those implemented in the form of a carrier wave (eg, transmission through the Internet).

The computer-readable recording medium is distributed in a network-connected computer system, so that the computer-readable code can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the method can be easily inferred by programmers in the art to which the present invention pertains.

In the above, preferred embodiments of the present invention have been illustrated and described, but the present invention is not limited to the specific embodiments described above, and it is common in the technical field to which the present invention pertains without departing from the gist of the present invention as claimed in the claims. Various modifications may be made by those having the knowledge of, of course, and these modifications should not be individually understood from the technical spirit or perspective of the present invention.

Claims (4)

A TOF (Time of Flight) camera that measures a distance from the upper surface of Korean beef to obtain and provides a point cloud image corresponding to the upper surface of the Korean beef;
a camera holder for fixing the TOF camera to the upper side of the Korean beef;
a mesh information acquisition unit configured to acquire 3D mesh information corresponding to the point cloud image by using a linear interpolation method;
a volume calculator configured to generate a Korean beef torso model by performing three-dimensional modeling based on the three-dimensional mesh information, and then calculating a volume of a Korean beef torso based on the Korean beef torso model; and
and a weight calculator that converts and outputs the volume of the Korean beef torso into body weight according to a preset linear regression equation. The method of claim 1, wherein the weight calculator
According to the formula of "weight = α + β × V _total ", the volume (V _total ) of the Korean beef torso is converted into the weight, wherein α and β are constants determined from the regression equation of the measured data. A ToF camera-based weighing device for Korean beef. According to claim 1,
ToF camera-based Korean beef weight measurement device, characterized in that it further comprises a noise removing unit for removing noise included in the point cloud image using the k-nearest neighbors algorithm. The method of claim 1, wherein the camera holder
folding tripod;
a bar-shaped base arm coupled to the upper side of the foldable tripod;
a counterweight coupled to one side of the base arm to provide a weight for weight balance;
a rod-shaped expansion arm coupled to the other side of the base arm;
ToF camera-based Korean beef weight measurement device, characterized in that it comprises a fixing bracket for connecting and fixing the TOF camera on one side of the extension arm.

Images