KR20230162210A - Fish volume measurement apparatus and fish volume measurement method using the same - Google Patents

Abstract

The present invention acquires a point cloud based on a measurement unit that measures the object and the measured object, selects a surface area of the object based on the obtained point cloud, and provides first and second restoration information about the object in the selected surface area. It includes a fish volume measuring device including a control unit for obtaining. In addition, a measurement step of measuring the surface of an object and extracting a point cloud for the measured object, a confirmation step of determining a surface area based on the extracted point cloud, and applying a grid to the confirmed surface area and the inside of the applied grid A height line is formed corresponding to the average value of the height information contained in the plurality of point groups located in the first restoration step of forming first restoration information by connecting the plurality of height lines formed, and thickness information corresponding to the formed height line. It provides a fish volume measurement method including a second restoration step of acquiring and forming second restoration information based on the first restoration information and the acquired thickness information.
According to an embodiment of the present invention, the speed and reliability of work on the shape and volume of fish can be significantly increased, and it can be used for individual measurement for research purposes such as fish breed management and classification into products, thereby increasing versatility. You can.

Description

Fish volume measurement apparatus and fish volume measurement method using the same}

The present invention relates to a fish volume measuring device and a method of measuring fish volume using the same. In detail, various embodiments of the present invention relate to technology that can more accurately and easily measure the shape and volume of fish.

Recently, as the importance and interest in ecotourism and ecosystem conservation have increased in various fields of society, interest in the fish themselves living in the sea is also increasing. In addition, as the size of leisure sports and industries such as catching or farming fish increases, the need to measure the specifications of fish for various purposes such as research, ornamentation, and leisure is also increasing.

However, there is a problem that it is generally difficult to measure the volume of fish due to their activity, and it is difficult to obtain accurate specifications using a general camera. In addition, measuring the volume of fish through general photography of fish has very low accuracy because the calculated specifications are calculated differently depending on the camera's irradiation angle and irradiation environment.

As a way to solve this problem, a method is being used to subdivide the taken photo into pixels and convert them into shape dimensions, but this requires measuring equipment such as a conventional scale bar and measuring instrument, and in the case of weight calculation and volume measurement, existing measuring equipment is used. is impossible.

Therefore, there is a need to develop technology to be able to measure the volume of fish more accurately without being limited by the shooting angle of the fish and to calculate this into 3D information.

Various embodiments of the present invention are intended to solve the above problems, and the purpose is to more easily and precisely measure the external specifications of fish, such as shape and volume.

In addition, the problem that the present invention aims to solve is to obtain accurate specifications while freely setting the photography environment for fish.

Additionally, the purpose of the present invention is to obtain restoration information by visualizing fish in three-dimensional form.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

For this purpose, the present invention extracts a point cloud based on a measurement unit that measures the object and the measured object, determines the surface area of the object based on the point cloud, and obtains first restoration information and second information about the object from the surface area. Provided is a fish volume measurement device including a control unit.

In addition, the present invention includes a measurement step of measuring the face half of an object and extracting a point cloud, a confirmation step of determining the face half area based on the extracted point cloud, applying a grid to the determined face half area, and a plurality of point groups located within the applied grid. A first restoration step of forming a height line corresponding to the average value of the height information contained in and connecting the formed plurality of height lines to form first restoration information, and obtaining thickness information corresponding to the formed height line and first restoration information. and a second restoration step of forming second restoration information by interpolating the obtained thickness information.

According to an embodiment of the present invention, the speed and reliability of work on the shape and volume of fish can be significantly improved.

In addition, through the present invention, it can be used for individual measurement for research purposes such as fish breed management and classification into products, thereby increasing versatility.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram illustrating the overall fish volume measuring device according to an embodiment of the present invention.
Figure 2 is a diagram showing the overall fish volume measurement method using a fish volume measurement device according to an embodiment of the present invention.
Figure 3 is a diagram showing measurement steps according to an embodiment of the present invention.
Figure 4 is a diagram showing the confirmation step according to an embodiment of the present invention.
Figure 5 is a diagram showing the point cloud, internal area, and surface area obtained through the measurement step and confirmation step according to an embodiment of the present invention.
Figure 6 is a diagram showing a removal step according to an embodiment of the present invention.
Figure 7 is a diagram showing the axis classification step according to an embodiment of the present invention.
Figure 8 is a diagram showing the first restoration step according to an embodiment of the present invention.
Figure 9 is a diagram showing a grid, height information, and height lines according to the first restoration step according to an embodiment of the present invention.
Figure 10 is a diagram showing first restoration information through connection of height lines and second restoration information through interpolation of the first restoration information and thickness information, respectively, according to an embodiment of the present invention.
Figure 11 is a diagram showing the second restoration step according to an embodiment of the present invention.
Figure 12 is a diagram showing that reference information is provided through an entity recorder according to an embodiment of the present invention.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be a second component within the technical spirit of the present invention.

When it is said that a part "includes" a certain element throughout the specification, this means that, unless specifically stated to the contrary, it does not exclude other elements but may further include other elements. In addition, terms such as "... unit" and "module" used in the specification refer to a unit that processes at least one function or operation, which may be implemented as hardware or software, or as a combination of hardware and software. .

Before explaining the present invention in detail, an “object” is an object that is the subject of volume measurement, and in the present invention, the object is described as a fish. Additionally, in the present invention, terms indicating direction will be explained based on the drawings unless otherwise specified. In addition, each component in the fish volume measuring device according to the present invention will be described on the premise that they are connected to each other and transmit and receive various information.

1 is a diagram illustrating the overall fish volume measuring device according to an embodiment of the present invention.

The fish volume measurement device according to the present invention includes a measurement unit 100 that scans an object, an extraction unit 210 that is connected to the measurement unit 100 to extract various information such as a point cloud about the object, and is connected to the extraction unit 210. A calculation unit 220 that calculates various information for calculating first restoration information and second restoration information, a comparison unit 230 that is connected to the calculation unit 220 and compares various information for calculating first restoration information, A grouping unit 240 that is connected to the comparison unit 230 and connects a plurality of point groups arranged on the same plane to form an internal area, and a selection unit that selects one internal area among the plurality of internal areas as the surface area ( 250, a removal unit 260 connected to the selection unit 250 to separate the object from noise in the surface area, and a setting unit 270 connected to the removal unit 260 and applying a grid for calculating the first restoration information. ), and includes a storage unit 280 that visualizes the first restoration information and the second restoration information and outputs them to the outside. Here, the above-described extraction unit 210, calculation unit 220, comparison unit 230, grouping unit 240, selection unit 250, removal unit 260, setting unit 270, and storage unit 280. is a component included in the control unit, and the functions performed by the series of components described above may be performed by one or more instructions based on one or more processors included in the control unit. In addition, in the present invention, each function is explained separately in order to explain each function more clearly, but all functions can be integrated and performed in the control unit.

Figure 2 is a diagram showing the overall fish volume measurement method using a fish volume measurement device according to an embodiment of the present invention.

The fish volume measurement method according to the present invention is implemented through the fish volume measurement device of FIG. 1, and includes a measurement step (s110) of measuring the face face of an object through the measurement unit 100, and a point cloud from the object through the extraction unit 210. A confirmation step (s120) to obtain and determine the surface area based on the corresponding point group through the selection unit 250, a removal step (s130) to extract only objects in the surface area by removing noise, and a long axis targeting the surface area. and an axis classification step (s140) for setting the short axis, a first restoration step (s150) for forming first restoration information by applying a grid to the surface area and connecting height lines corresponding to the average value of the height information included in the point group in the grid. ) and a second restoration step (s160) of extracting thickness information and interpolating it with the first restoration information to form second restoration information. A description of each step will be provided later starting with Figure 3.

Figure 3 is a diagram showing the measurement step (s110) according to an embodiment of the present invention.

The measurement unit 100 is configured to start scanning of an object. In detail, the measurement unit 100 provides material that allows the extraction unit 210, which will be described later, to extract a point cloud based on the result of photographing the shape of the object. For this purpose, the measuring unit 100 may be equipped with an imaging means such as a camera, but is not limited thereto. Here, the shooting angle for the measurement unit 100 to photograph the object is preferably set to a direct upward direction, but is not limited to this, and a predetermined angle between the object and the ground on which the object is placed may be formed, such as by photographing at an angle. When the measurement unit 100 captures an image of an object in a direction directly above the object, it has the effect of minimizing distortion of various data formed by scanning. On the other hand, the result formed by the measurement unit 100 may be in the form of image data containing noise such as a 3D point cloud and foreign matter, and the noise may be generated in a separate fixture provided for positioning the object in the correct position, during the imaging process. It may be provided with detected foreign substances, etc., but is not limited to this. Through the scanning step (s111) in which the measurement unit 100 scans the object, data necessary for extraction of the point cloud can be received.

The extraction unit 210 is connected to the measurement unit 100 and extracts a point cloud related to the object. In detail, the extraction unit 210 extracts a point cloud for extraction of the surface area. To this end, the extraction unit 210 is connected to the measurement unit 100 and obtains a point cloud based on the result of photographing the shape of the object. Here, the point cloud may be comprised of a point provided as a starting point and a collection of height information provided as a normal vector. In the point cloud extraction step (s112), the extraction unit 210 extracts a point cloud from a result related to an object in the form of a point. Accordingly, a point cloud containing height information about an object can be easily obtained.

The measurement step (s110) includes the aforementioned scanning step (s111) and the point cloud extraction step (s112), and each step is performed sequentially. The measurement unit 100 can scan the object through the scanning step (s111) and extract a point cloud about the object through the point cloud extraction step (s112).

Figure 4 is a diagram showing the confirmation step (s120) according to an embodiment of the present invention, and Figure 5 shows the point cloud, internal area, and This is a drawing showing the surface area.

The confirmation step (s120) is provided to confirm the surface area for the point cloud. In detail, in the confirmation step (s120), the internal area and the confirmed area can be sequentially obtained for the point cloud through the calculation unit 220, comparison unit 230, grouping unit 240, and selection unit 250. , for this purpose, information on the critical angle and critical length previously specified in the comparison unit 230 is used. The confirmation step (s120) includes an included angle calculation step (s121), a point-to-point distance calculation step (s122), a critical angle comparison step (s123), a critical length comparison step (s124), a grouping step (s125), and a selection step (s126). And by using the Region Growing technique, it is possible to obtain an easier surface area without being limited to the measurement position and angle of the object.

The calculation unit 220 is configured to calculate the included angle and distance for each point regarding the point cloud in the confirmation step (s120). In detail, the calculation unit 220 calculates the included angle and point-to-point distance between the plurality of point groups, thereby assisting the comparison unit 230, which will be described later, to determine whether the plurality of point groups are arranged on the same plane. To this end, the calculation unit 220 receives information about the point cloud from the extraction unit 210 and derives the included angle and distance for each point.

The included angle is used to determine whether the normal vectors of two or more point clouds are the same, and refers to the angle with a pre-designated reference line. In detail, the included angle is an element used to determine whether the height information provided by the normal vector matches the degree of consistency and confirms whether the corresponding part of the actual object has an inclination compared to a separate reference surface such as the ground for measuring the object. The calculation unit 220 calculates the included angle for a plurality of point clouds through the included angle calculation step (s121).

Point-to-point distance is the distance between two or more point clouds and is a factor used to check whether the point clouds are excessively spaced. If the distance between points is excessively large, the probability that the corresponding point group is placed on the same plane may be determined to be lower than if the distance between points is small. In other words, as the distance between points increases, it can be determined that the corresponding part of the actual object has a relatively large inclination. In the point-by-point distance calculation step (s122), the calculation unit 220 calculates the point-by-point distance for a plurality of point groups, and this may be performed simultaneously with the above-described included angle calculation step (s121) or may be performed afterward.

The calculation unit 220 calculates the included angle and distance for each point for the point group as described above, thereby making it easier to determine whether the comparison unit 230, which will be described later, is arranged on the same plane.

The comparison unit 230 determines whether a plurality of point clouds are arranged on the same plane based on a pre-designated standard rule. In detail, the comparison unit 230 performs a discrimination operation to group point clouds located on the same plane, and performs a critical angle comparison step (s123) in which pre-stored critical angles and critical lengths are used to compare the included angles and distances for each point, respectively. The threshold length comparison step (s124) is performed respectively.

The critical angle is compared with the included angle as a standard for confirming whether the portion where the plurality of point groups are formed is the same plane. In detail, the critical angle is provided to check whether the internal area formed by connecting a plurality of point groups is the same plane.

The comparison unit 230 compares the sizes of the included angle and the critical angle through the critical angle comparison step (s123). Here, when the difference between the plurality of angles corresponding to the plurality of point groups is greater than the critical angle, it is determined that the corresponding point groups are not located on the same plane. On the other hand, when the difference between the respective included angles is smaller than the critical angle, the comparison unit 230 determines that the point groups having the respective included angles exist on the same plane and performs the critical length comparison step (s124).

The critical length is a standard for determining whether the distance between point clouds is excessive, and more specifically, it is provided to check the probability that a plurality of point clouds are not located on the same plane. The comparison unit 230 compares the distance for each point and the size of the predetermined threshold length in the critical length comparison step (s124).

When the critical length is smaller than the point-to-point distance, as the plurality of point groups are relatively large apart, it can be considered that there is a high probability that an unidentified curved surface will be formed within a portion of the object corresponding to the point group. Accordingly, it is determined that the plurality of corresponding point groups are not located on the same plane. On the other hand, if the critical length is greater than or equal to the point-to-point distance, it can be determined that there is a high possibility that a portion of the corresponding object is on the same plane as a plurality of point groups are densely arranged. Accordingly, the comparison unit 230 considers that a plurality of point groups are arranged on the same plane.

The grouping unit 240 is a component that forms an internal area by connecting a plurality of point groups arranged on the same plane. In detail, the grouping unit 240 forms a candidate group for detecting the surface area, and implements this through the grouping step (s125). To this end, the grouping unit 240 receives information about the comparison result formed by the comparing unit 230 and connects a plurality of point groups determined to be arranged on the same plane to form a closed internal area. For easier formation of the internal area, it is preferable that the grouping unit 240 groups three or more point groups so that they are connected. Here, the grouping unit 240 determines whether or not a plurality of point clouds are arranged on the same plane through a pre-designated standard rule.

The internal area is provided to detect the actual surface of the object as 3D data, and more specifically, to detect point groups having the same plane among a plurality of point groups and treat them as one. Through this, the control unit according to the present invention can significantly reduce the number of times it determines all point groups extracted from the measured object to determine the surface area. Therefore, it is possible to more quickly measure the volume of large or large objects by reducing the processing amount of various information.

The standard rule is that, in the above-mentioned critical angle comparison step (s123) and critical distance comparison step, if the difference between angles and the distance between points is less than or equal to the critical angle and critical length, the corresponding point groups are grouped and connected to each other. Referring to FIG. 6, it can be seen that when a plurality of point clouds are provided, the height information provided as normal vectors is similar, so there is a slight difference in the included angle, and the point clouds with small distances between points are grouped and connected to each other. In other words, the reference rule is a rule that considers point clouds with similar sizes of included angle and height information as being on the same plane. This has the effect of significantly increasing the computation processing speed compared to calculating conditions for each point for all point clouds without reference rules.

The selection unit 250 is a component that determines the surface area. In detail, the selection unit 250 performs a selection step (s126) of determining the surface area of the object based on a plurality of point clouds, thereby performing a removal step (s130), an axis classification step (s140), and a first restoration step, which will be described later. (s150) and the second restoration step (s160) are induced to proceed sequentially. To this end, the selection unit 250 is connected to the grouping unit 240 to receive information about the clustered point cloud, and correspondingly selects one of the plurality of internal areas as the surface area. Specifically, the selection unit 250 designates one internal area with the largest internal area among the plurality of internal areas as the surface area. Accordingly, a surface area is formed, the central part becomes the center, and the coordinates of the point cloud can be converted using the height information as the Z axis. The user using the fish volume measurement device according to the present invention may designate an internal area through a separately connected input means, and the designation method is not limited to this.

Through the above-described confirmation step (s120), the specific area can be easily obtained using the Region Growing technique without having to measure the fish in the correct position. This has the effect of reducing the inconvenience in the process of photographing an object by lowering the difficulty of photographing. In addition, by determining one of the plurality of internal areas with the largest size as the surface area, the data processing speed can be increased and the reliability of the process of acquiring the first and second restored information can be increased.

Figure 6 is a diagram showing the removal step (s130) and the surface area formed through the removal step (s130) according to an embodiment of the present invention. Figure 6a is a flowchart for the removal step (s130) and Figure 6b is a removal step (s130). ) indicates an object that has been separated from noise.

The removal unit 260 removes noise and extracts only the object by performing the removal step (s130). To this end, the removal unit 260 is connected to the extraction unit 210 and the selection unit 250, receives information about the surface area from the selection unit 250, and removes noise. In detail, the removal unit 260 removes the remaining internal area excluding the internal area that can be integrated into a fish shape based on the surface area. Accordingly, the surface area and internal area regarding the object remain. Information about the surface plate area processed as described above is moved from the removal unit 260 to the extraction unit 210.

Figure 7 is a diagram showing the axis classification step (s140) according to an embodiment of the present invention.

The axis classification step (s140) is to set the major and minor axes and set the restoration range for easy performance of the first restoration step (s150) and the second restoration step (s160), which will be described later, and is performed in the extraction unit 210. carried out by To this end, the extraction unit 210 includes information on the long axis and short axis in advance, receives information on the processed surface area from the removal unit 260, and sets the long axis and short axis. As the long and short axes are provided as x-axis and y-axis, respectively, information about the surface area is arranged in two-dimensional coordinates.

The long axis is an axis provided as a long line segment based on the shape of the object, and in the case of fish, it refers to the axis pointing toward the head and tail. The minor axis is provided in a direction perpendicular to the long axis described above, and in the case of fish, it is set as the axis facing the back and belly parts corresponding to the head and tail.

The surface area having the shape of the object is aligned to the x-axis and y-axis through the axis classification step (s140) performed in the extraction unit 210. Accordingly, the extraction unit 210 can set the area where the surface area is formed as the application range of the first restoration step (s150) and the second restoration step (s160). Setting of the application range can also be performed in the setting unit 270, which will be described later. Through the axis classification step (s140), the cross-sectional area in the y-axis direction of the object provided as a fish is aligned based on the widest surface area, so the curved shape and shape can be easily restored and more accurate volume measurement is possible. possible.

In addition, by selecting and removing the internal area formed by a plurality of point groups that were not selected as the surface area as noise, inaccurate height line and volume calculations due to noise in the first and second restoration stages, which will be described later, can be prevented in advance. You can block it.

Figure 8 is a diagram showing the first restoration step (s150) according to an embodiment of the present invention, and Figure 9 is a diagram showing a grid, height information, and height line according to the first restoration step (s150) according to an embodiment of the present invention. It is a drawing.

Figure 9a shows that a plurality of preset grids are applied to the surface area by the setting unit 270, and Figures 9b and 9c show that the extraction unit 210 performs the height information extraction step (s152) for a plurality of point groups in the grid. This is a diagram showing height information and average values calculated through .

The first restoration step (s150) is provided to form first restoration information, and more specifically, to restore the cross-sectional shape by forming a height line. To this end, the first restoration step (s150) is performed through the extraction unit 210, removal unit 260, setting unit 270, calculation unit 220, and storage unit 280, and the grid application step (s151) , includes a height information extraction step (s152), an average value calculation step (s153), and a height line connection step (s154).

The setting unit 270 applies a grid to the surface area, leading to easier formation of height lines and thickness information. To this end, the setting unit 270 is connected to the removal unit 260 and the calculation unit 220, and includes information about a pre-designated grid. Additionally, the setting unit 270 receives information about the surface area from the removal unit 260 and performs a grid application step (s151) of setting a grid.

The grid is provided as a partition having a square shape, and a plurality of grids are arranged to have a grid arrangement. Additionally, the interior of the grid has an opening so that the point group within the surface area is aligned. A plurality of grids as described above are applied to the surface area by the setting unit 270. Accordingly, as shown in Figure 9a, the border portion of the surface area is made up of a set of square grids and has the overall shape of an object. The point group arranged in the grid is arranged with coordinates in the major axis direction (x-axis direction in FIG. 9) and minor axis direction (y-axis direction in FIG. 9).

The extraction unit 210 performs a height information extraction step (s152) of extracting height information. In detail, the extraction unit 210 extracts height information targeting the surface area to which the grid is applied. Here, the object of height information extraction is a point group provided in the open space of one grid, and height information corresponding one-to-one to the point group is extracted.

The height information is included in the point group and provided in the form of a normal vector, is provided in the z-axis direction (positive or negative projection direction from FIG. 9), and has a length corresponding to each point group. In other words, the height information means the height from the base area in the z-axis direction of the point cloud, and it can be determined that the larger the height information is, the farther away it is from the base area. Using FIG. 9B as an example, it can be seen that the height information of point cloud 2 is provided so that it is smaller than the height information of point cloud 3, so that point cloud 2 is placed closer to the surface area than point cloud 3.

The average value calculation step (s153) is to select a standard for forming a height line, and a predetermined number of height lines (e.g., 1) are formed for each grid. To this end, the calculation unit 220 calculates an average value provided as a representative height when the height information extraction step (s152) described above is completed.

The average value is the average value of the height information within the grid, and is calculated as the average of the plurality of height information when a plurality of point groups are arranged within the grid. Here, in the case of a single point group within the grid, the height information of the point group is determined as the average value.

Afterwards, the calculation unit 220 forms first restoration information through the height line connection step (s154). In detail, in the height line connecting step s154, the calculation unit 220 restores the cross-sectional shape of a straight line or curve by connecting a predetermined number of height lines formed for each grid. More specifically, when connecting height lines by the calculation unit 220, height lines located on the same plane based on the long axis or short axis may be connected.

For example, the calculation unit 220 may connect height lines to multiple grids located at the same x-axis coordinate. In this case, the plurality of height lines are arranged along the y-axis and their end points are connected to each other to form a cross-section based on the ).

As another example, the calculation unit 220 may connect each height line corresponding to a plurality of grids arranged on the same y-axis coordinate. In this case, a plurality of height lines are arranged along the x-axis and the end points are connected to form a cross-section based on the y-axis. The cross section is provided in the form of a cross section cut from the head to the tail fin based on the fish.

Through the series of configurations and first restoration step (s150) as described above, a plurality of circles as shown in Figure 10a are formed around the long axis (x-axis), or a plurality of concentric circles are formed around the short axis (y-axis). The first restoration information can be obtained. Meanwhile, the first restoration information as described above can be moved from the calculation unit 220 to the storage unit 280 and visually viewed by the user.

Figure 10 is a diagram showing first restoration information through connection of height lines and second restoration information through interpolation of the first restoration information and thickness information according to an embodiment of the present invention, and Figure 11 is an embodiment of the present invention. This is a drawing showing the second restoration stage according to .

The second restored information is formed through the extraction unit 210 and the calculation unit 220, and is achieved through processing of the first restored information. To this end, the second restoration step (s160) for forming the second restoration information includes a thickness information extraction step (s161) of extracting thickness information and a volume calculation step (s162) of calculating the volume.

The thickness information extraction step (s161) is performed through the extraction unit 210. In detail, the extraction unit 210 receives first restoration information from the calculation unit 220 or the storage unit 280 and calculates thickness information from the received first restoration information.

Thickness information is information about the distance between a plurality of concentric circles formed by connecting a plurality of height lines, and is the distance between the centers of the plurality of concentric circles. Using Figure 10A as an example, thickness information is calculated as the distance between the centers of a plurality of concentric circles that share the same y-axis coordinate but are formed along the x-axis.

The volume calculation step (s162) is performed after the thickness information extraction step (s161) and is performed by the calculation unit 220. The calculation unit 220 calculates the volume by interpolating the thickness information and first restoration information obtained by the extraction unit 210.

For example, in the case of the first restored information as shown in FIG. 10A, the volume is calculated through interpolation by multiplying the size of the thickness information formed along the x-axis and the area of the corresponding concentric circle. This process is performed for each of the plurality of concentric circles, and the sum of the obtained volumes is calculated as the volume of the entire object and formed as second restoration information.

As described above, through calculation of the second restoration information through interpolation of the first restoration information and thickness information, more accurate measurement of the volume of the object and scanning of the object in 3D form are completed.

As another embodiment of the present invention, an entity recorder may be further included. The object recorder is included in the control unit and is provided for faster and easier recognition and classification of objects. In detail, the object recorder stores information about the recognized object and assists in enabling easier and faster recognition when recognizing other objects in the future. For this purpose, the entity recorder is connected to the calculation unit and the storage unit, and receives and stores the first restoration information and the second restoration information.

Information about the object stored in the object record includes items that can recognize the recognized object among various fish, such as fish name, discovery location, age, and unique features. Through a separate input means connected to the object recorder, the user inputs information about the object, and in response to the input, the first restoration information, the second restoration information, and the information about the object are added and stored. The method of storing the object record is not limited to transferring the information to a separate storage medium or cloud server, or storing it locally.

After storing information about the recognized object, the object record provides reference information during the first and second restoration steps for other objects. In detail, when the shape and volume of another object are calculated, the object recording unit provides the stored first restoration information, second restoration information, and information about the object of the stored recognition object to the calculation unit as reference information. As the number and type of recognized objects increase, the recognition efficiency for other objects can be maximized.

In the present invention, after capturing an object, it is transformed into a level map using the Region Growing technique, and the shape and volume can be easily calculated using height information and thickness information. Therefore, there is no need to separately process the RGB video image after forming it to identify existing fish, thereby reducing the processing amount of related information.

In addition, because the present invention uses a method of calculating the average of data related to the coordinates of a point cloud, it has a different configuration and effect compared to the existing fish measurement method that extracts the characteristic parts of the fish and compares them with the illustrated book. In addition, compared to existing methods, the process of comparing with the atlas can be omitted, thereby solving problems such as non-recognition due to the appearance of new fish during the fish scanning process for research purposes.

In addition, because the present invention is not limited to the shooting angle of fish, work convenience can be greatly improved.

The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. The software module may be RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which the present invention pertains.

Above, embodiments of the present invention have been described with reference to the attached drawings, but those skilled in the art will understand that the present invention can be implemented in other specific forms without changing its technical idea or essential features. You will be able to understand it. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

100: measurement unit 210: extraction unit
220: calculation unit 230: comparison unit
240: grouping section 250: selection section
260: Removal part 270: Setting part
s110: measurement stage s120: confirmation stage
s130: Removal step s140: Axis classification step
s150: 1st restoration stage s160: 2nd restoration stage

Claims (10)

A measurement unit that measures an object; and
A control unit that acquires a point cloud based on the measured object, selects a surface area of the object based on the acquired point cloud, and acquires first restoration information and second restoration information about the object in the selected surface area. Fish volume measurement device including ; According to claim 1,
The control unit,
A fish volume measurement device that determines whether or not a plurality of point groups are arranged on the same plane based on preset reference rules. According to claim 1,
The control unit,
Obtaining information about the included angle and distance for each point from the plurality of point clouds,
A fish volume measurement device that compares a predetermined critical angle and critical length with the obtained included angle and point-to-point distance. According to claim 2,
The control unit,
A fish volume measuring device that forms an internal area by connecting the plurality of point groups arranged on the same plane. According to claim 4,
The control unit,
A fish volume measuring device that determines an inner region with the maximum area among a plurality of formed inner regions as a surface region. According to claim 1,
The control unit,
A fish volume measurement device that selects and removes an internal area formed by a plurality of point groups that are not selected as the surface area as noise. According to claim 1,
The control unit,
A fish volume measurement device that aligns a plurality of point groups included in the surface area by applying a plurality of preset grids to the surface area. According to claim 7,
The control unit,
Extracting height information from a plurality of point groups arranged inside the plurality of grids,
Calculating an average value for the extracted height information, and forming a height line in the vertical direction from the surface area based on the calculated average value,
A fish volume measuring device that connects the plurality of height lines formed to form first reconstruction information. According to claim 8,
The control unit,
Extracting thickness information in the major or minor axis direction based on the plurality of height lines formed,
A fish volume measuring device that calculates second restoration information by interpolating the first restoration information and the thickness information. A measurement step of measuring an object in face 2 and extracting a point cloud from the measured object;
A confirmation step of determining the surface area based on the extracted point cloud;
A grid is applied to the determined surface area, a height line is formed corresponding to the average value of the height information contained in a plurality of point groups located inside the applied grid, and the plurality of height lines formed are connected to perform a first restoration. A first restoration step of forming information; and
A fish volume measurement method comprising a second restoration step of acquiring thickness information corresponding to the formed height line and forming second restoration information based on the first restoration information and the obtained thickness information.