KR102663038B1 - Method and device for performing modeling for target plants - Google Patents

Abstract

Obtaining a plurality of images of the target plant in an area adjacent to the target plant; determining an imaging angle corresponding to the plurality of images based on a reference line for the target plant; Obtaining a standard image for a standard angle based on a weighted sum of some images performed based on the imaging angle for some images among the plurality of images; and performing modeling on the target plant using the standard image. A method and device including a method and device are disclosed.

Description

Method and device for performing modeling for target plants {Method and device for performing modeling for target plants}

The technical field of the present disclosure relates to a method and device for performing modeling on a target plant, and more specifically, performing 3D modeling to measure the shape dimensions of the plant by acquiring a plurality of images of the target plant. It relates to methods and devices.

According to the recent global market research company 'Immersion Research', the global market size of artificial intelligence used in agriculture has already exceeded $1.7 billion as of 2021, and is expected to grow at an average annual growth rate of 28% from 2022 to 2030. predicted to be recorded. In addition, it is expected that one of the major fields leading to this rapid growth will be the field of 'generating and analyzing data about crops through sensors.' Amid this global trend, efforts are being made in Korea to collect big data on crops and growing environments, led by the Rural Development Administration. According to the Rural Development Administration's '2022 Revenue and Expenditure Budget Statement', a budget of 3.995 billion won was allocated for 'agricultural big data collection and productivity improvement model development (R&D)', a 27% increase compared to the same item last year. The data obtained from the project with the allocated budget is collected through the 'Smart Farm R&D Big Data Portal', and the refined data can be viewed on the Rural Development Administration website 'Open Public Data'. However, there is a limitation in that the data accumulated through this project cannot be used to develop actual domestic agricultural artificial intelligence programs due to reliability issues. Therefore, there is a need for a system and device that provides a method of performing three-dimensional modeling of plants that can measure the shape dimensions of plants by inferring blind spots in photography.

Korean Patent No. 10-2134396 (2020.07.09) Portable plant image acquisition device

The problem to be solved in the present disclosure is to provide a system and device for performing 3D modeling of plants, obtaining a plurality of images of plants and acquiring images corresponding to preset angles based on the imaging angles for some images. The purpose is to provide a system that allows modeling of plants to be performed accordingly.

As a technical means for achieving the above-described technical problem, a method of performing modeling on a target plant by a device according to the first aspect of the present disclosure includes acquiring a plurality of images of the target plant in an area adjacent to the target plant. ; determining an imaging angle corresponding to the plurality of images based on a reference line for the target plant; Obtaining a standard image for a standard angle based on a weighted sum of some images performed based on the imaging angle for some images among the plurality of images; and performing modeling on the target plant using the standard image.

Additionally, the step of acquiring the standard image may include obtaining a masking image by masking an area corresponding to a preset color range in the partial image; and acquiring the standard image based on a weighted sum of the masking images.

In addition, the step of obtaining internal space information of the target plant using infrared rays irradiated to the target plant; and performing modeling on the target plant using the standard image and the internal space information. Modeling can be performed on the target plant.

In addition, performing modeling on the target plant may include performing shaking correction on the standard image using vibration measurement data obtained from a rail image and a vibration sensor included in the plurality of images; and performing modeling on the target plant based on the results of the shaking correction.

Additionally, the reference line and the imaging angle for the target plant may be determined based on the QR image corresponding to the target plant.

Additionally, acquiring the standard image may include determining the partial image among the plurality of images corresponding to the standard image;

It may include obtaining the standard image based on a weighted sum performed according to the degree to which the imaging angle corresponding to each of the partial images is close to the standard angle.

A device that performs modeling on a target plant according to a second aspect of the present disclosure includes a receiver that acquires a plurality of images of the target plant in an area adjacent to the target plant; and determining an imaging angle corresponding to the plurality of images based on a reference line for the target plant, and based on a weighted sum of the partial images performed based on the imaging angle for some of the plurality of images. It may include a processor that acquires a standard image for a standard angle and performs modeling on the target plant using the standard image.

According to an embodiment of the present disclosure, there is an effect that image accuracy can be improved because a plurality of standard images are acquired according to a weighted sum of some images based on the imaging angle of some images.

In addition, when performing modeling for plants, efficiency can be improved in that costs can be reduced by using camera sensors in the visible and infrared regions.

In addition, since more information on the interior space of the plant is obtained using infrared rays, efficiency can be improved in that it is possible to confirm the shape of the plant.

In addition, since shake correction is possible using rail images included in a plurality of images, there is an effect of obtaining and providing images with high accuracy.

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

Figure 1 is a block diagram schematically showing the configuration of a device according to an embodiment.
Figure 2 is a flowchart illustrating each step of a device that performs modeling on a target plant according to an embodiment.
FIG. 3 is a diagram illustrating an example in which scanning of a plant is performed as a device rotates around the plant, according to an embodiment.
FIG. 4 is a diagram illustrating an example in which a standard image for a standard angle is acquired according to an embodiment.
FIG. 5 is a diagram illustrating an example in which a device acquires a masking image according to an embodiment.
FIG. 6 is a diagram illustrating an example in which a device performs shake correction using a rail image according to an embodiment.
FIG. 7 is a diagram illustrating an example in which a device according to an embodiment acquires information on the internal space of a target plant using infrared rays.
FIG. 8 is a diagram illustrating an example in which a device sequentially scans a plurality of plants according to another embodiment.
FIG. 9 is a diagram illustrating a method in which a device sequentially scans a plurality of plants according to another embodiment.
FIG. 10 is a diagram illustrating an example in which a device according to an embodiment provides 3D modeling information based on a QR code corresponding to a plant.

Advantages and features in the present disclosure, and methods for achieving them, will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure is complete and to those skilled in the art. It is provided to provide complete information.

The terms used herein are for describing embodiments and are not intended to limit the disclosure. 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 the second component within the technical spirit of the present disclosure.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless clearly specifically defined.

Spatially relative terms such as “below”, “beneath”, “lower”, “above”, “upper”, etc. are used as a single term as shown in the drawing. It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms that include different directions of components during use or operation in addition to the directions shown in the drawings. For example, if a component shown in a drawing is flipped over, a component described as "below" or "beneath" another component will be placed "above" the other component. You can. Accordingly, the illustrative term “down” may include both downward and upward directions. Components can also be oriented in other directions, so spatially relative terms can be interpreted according to orientation.

Hereinafter, various embodiments will be described in detail with reference to the drawings.

FIG. 1 is a block diagram schematically showing the configuration of a device 100 according to an embodiment.

Referring to FIG. 1, device 100 may include a receiver 110 and a processor 120.

The receiver 110 according to one embodiment may acquire a plurality of images of the target plant in an area adjacent to the target plant.

The processor 120 according to an embodiment may determine an imaging angle corresponding to a plurality of images based on a reference line for the target plant. Additionally, the processor 120 may obtain a standard image for a standard angle based on a weighted sum of some images performed based on the imaging angles of some of the plurality of images. Additionally, the processor 100 may perform modeling on the target plant using a standard image.

In addition, the device 100 that performs modeling on the target plant acquires a plurality of images of the target plant from the receiver 110, acquires the imaging angle and standard image from the processor 120, and performs modeling on the plant. It should be noted that in the process of providing modeling information, various existing networks such as Internet networks or mobile communication networks can be combined, and there are no special restrictions on this.

In addition, those skilled in the art can understand that other general-purpose components in addition to the components shown in FIG. 1 may be further included in the device 100 that performs modeling on a target plant. For example, the device 100 that performs modeling on a target plant includes a display (not shown) that provides modeling information about the plant, an imaging angle determined by the processor 120, information about a standard image for a standard angle, etc. It may further include a memory (not shown) to store. Alternatively, according to another embodiment, those skilled in the art may understand that some of the components shown in FIG. 1 may be omitted.

The device 100 that performs modeling on a target plant according to an embodiment may be used by a user and may be touch-sensitive such as a mobile phone, smartphone, PDA (Personal Digital Assistant), PMP (Portable Multimedia Player), tablet PC, etc. It can be linked with all types of handheld wireless communication devices equipped with a screen panel, and can also install and run applications such as desktop PCs, tablet PCs, laptop PCs, and IPTVs including set-top boxes. It can be included in or linked to an existing device.

The device 100 that performs modeling on a target plant may be implemented as a terminal such as a computer that operates through a computer program to realize the functions described in this specification.

The device 100 that performs modeling of a target plant according to an embodiment may include, but is not limited to, a system (not shown) that performs 3D modeling of a plant and a related server (not shown). The server according to one embodiment may support an application that provides information about 3D modeling of plants.

Hereinafter, the description will focus on an embodiment in which the device 100, which performs modeling on a target plant according to an embodiment, independently performs modeling on a plant. However, as described above, the device 100 performs modeling on a target plant independently. It may be possible. That is, the device 100 and the server that perform modeling for the target plant according to one embodiment may be integrated in terms of their functions, and the server may be omitted, and is not limited to any one embodiment. Able to know.

In one embodiment, the device 100 and the server may be linked, and the configuration of providing a service that performs modeling for plants or provides modeling information to a user account may be performed by the server and is performed by the device 100. It could be. For example, the device 100 can operate as a server, and hereinafter it will be collectively referred to as the device 100 and described later.

FIG. 2 is a flowchart illustrating each step of operation of the device 100 that performs modeling on a target plant according to an embodiment.

Referring to step S210, the device 100 according to an embodiment may acquire a plurality of images of the target plant in an area adjacent to the target plant. In one embodiment, the device 100 may acquire a plurality of images of the target plant using a camera sensor in the visible light and infrared regions as it moves in an area within a preset distance from the target plant.

Referring to step S220, the device 100 according to an embodiment may determine an imaging angle corresponding to a plurality of images based on a reference line for the target plant. In one embodiment, the reference line may refer to a line that serves as a reference for determining the imaging angle. For example, the reference line may correspond to a line passing through the center of a point corresponding to the location of the plant. Accordingly, the angle from the reference line for the plant to the position where the plurality of images are captured may be determined as the imaging angle corresponding to each image.

Referring to step S230, the device 100 according to an embodiment may acquire a standard image for a standard angle based on a weighted sum of some images performed based on the imaging angle for some of the plurality of images. . In one embodiment, the standard image may correspond to a frame at an angle that the user wishes to obtain, and the standard angle may be preset by the user (administrator) to mean an angle corresponding to the standard image. Additionally, in one embodiment, the device 100 may extract a plurality of images for each angle. In order to acquire a standard image at a preset standard angle, some images at an imaging angle corresponding to an angle within the standard angle and a preset range may be determined among a plurality of images acquired for each angle. The device 100 according to an embodiment may obtain a masking image by performing masking on an area corresponding to a preset color range in some images and may obtain a standard image based on a weighted sum of the masking images. The device 100 can distinguish between a part to which the effect is not applied and a part to which the effect is applied so that the effect is applied only to a specific area of the image, and at this time, a preset color range can be used. For example, the device 100 may acquire a green area corresponding to a range of preset R, G, and B values corresponding to a plant as a masking image. The device 100 can extract the green area based on the HSV color, extract the largest object from the extraction result, and obtain a masking image based on the GRABCUT algorithm. The device 100 can calculate a weighted sum for pixel values existing at the same location in a masking image obtained from a plurality of partial images and obtain a standard image by overlapping the images by multiplying each image by the weight.

Referring to step S240, the device 100 according to one embodiment may perform 3D modeling on a target plant using a standard image. For example, output spaces (x,y,z) that have matrix values for specific points of an image at a certain angle, and among the points on the output space, the output value (px_1, py_1) is above the preset level at a certain angle. By outputting points on the space in the angular image, modeling of plants can be performed using one point of the 3D shape detected by the two images. Additionally, the device 100 may obtain information on the internal space of the target plant using infrared rays irradiated to the target plant. In one embodiment, the device 100 may obtain color and internal space information of a target plant from a camera sensor in the visible and infrared regions. In one embodiment, the internal space information may include information about the thickness of the plant's leaves, stems, etc., and the device 100 may obtain shape information of the tree crown by acquiring the internal space information. Accordingly, the device 100 may perform modeling on the target plant using the standard image and internal spatial information. Therefore, the plant's leaf shape (leaf color distribution, leaf area, leaf length, leaf width, distribution of leaf veins, etc.), stem and branch shape (stem length, stem thickness, stem color, number of side branches, etc.) , distribution of side branches, length of side branches, color of side branches), information on harvest shape (volume of flesh, circumference of flesh, length of flesh, color of flesh, color of flower, shape of flower, length of flower, etc.) It has the effect of being able to be checked and recorded. Additionally, the device 100 according to an embodiment may perform vibration correction on a plurality of images using rail images included in the plurality of images and vibration measurement data obtained from a vibration sensor. For example, a rail image may be included in a plurality of images obtained by rotating a rail (circular rail) corresponding to the boundary of an area within a preset distance based on the target plant. The device 100 according to one embodiment may perform tremor correction by applying a preset algorithm (Bgsegm) to a certain area within a plurality of acquired images. Additionally, the device 100 may perform vibration correction by performing vibration correction. In one embodiment, the vibration sensor may include a gyro sensor or a piezo vibration sensor. For example, the device 100 may perform tremor correction by measuring vibration using a gyro sensor or piezoelectric vibration sensor close to the image sensor and correcting tremor in image software. Accordingly, the device 100 may perform modeling on the target plant based on the results of shaking correction.

The device 100 according to one embodiment may determine some images that correspond to standard images among a plurality of images. Additionally, the device 100 may acquire standard images based on a weighted sum performed according to the degree to which the shooting angle corresponding to each of some images is close to the standard angle. For example, as described above, in order to acquire a standard image at a preset standard angle, the device 100 selects an image at an imaging angle corresponding to an angle within the standard angle and a preset range among a plurality of images acquired for each angle. Some images may be determined, and some images determined at this time may be images that correspond to standard images. Additionally, some images may correspond to images within an angle corresponding to an imaging angle within a preset standard angle range from a standard angle. In one embodiment, the preset standard angle range may be preset by a user (administrator) and may mean a degree range of an angle away from the angle corresponding to the standard image to determine the standard image. For example, among the imaging angles of some images within the standard angle range, the imaging angle closest to the standard angle and the difference from the standard angle; the imaging angle furthest from the standard angle among the imaging angles of some images within the standard angle range; and the difference between the standard angle and the Considering the difference, the number of some images and the size of the weight given to some images can be determined depending on the degree of proximity to the standard angle. If the number of some images included within the preset standard angle range is two, the device 100 may acquire a standard image using two images. In addition, if the number of partial images included within the preset standard angle range exceeds two, the number of partial images and partial images corresponding to two or more are based on the difference between the imaging angle and standard angle corresponding to each image. The size of the weight given to can be determined. For example, if the standard angle is 45 degrees and the standard angle range is a range corresponding to -15 degrees and +15 degrees from the standard angle, the standard angle range may correspond to a range of 30 degrees to 60 degrees. At this time, if the imaging angles corresponding to some images included in the standard angle range are 40 degrees and 60 degrees, the two images may be determined as partial images. The device 100 can acquire a standard image based on a weighted sum by assigning a higher weight to the image corresponding to 40 degrees, which has a small difference between the imaging angle corresponding to some images and the standard angle, than to the image corresponding to 60 degrees. there is. Additionally, if the imaging angles corresponding to some images included within the standard angle range are 35 degrees, 41 degrees, and 50 degrees, the three images may be determined as partial images. The device 100 may assign the highest weight to the image corresponding to 41 degrees, which has the smallest difference between the imaging angle corresponding to some images and the standard angle, and assign the second highest weight to the image corresponding to 50 degrees. A standard image can be obtained based on the weighted sum of assigning the third highest weight to the image corresponding to 35 degrees. Accordingly, the device 100 obtains a standard image by assigning a higher weight as the imaging angle corresponding to a plurality of partial images approaches the standard angle, which has the effect of obtaining a more accurate image. Additionally, the device 100 according to one embodiment may update the preset standard angle range depending on the situation. For example, some images may exist only in a range corresponding to the negative angle based on the standard angle. In one embodiment, when the standard angle is 45 degrees and the preset standard angle range corresponds to 30 degrees to 60 degrees, if the imaging angles corresponding to some images are 30 degrees and 40 degrees, both images are based on the standard angle. Therefore, since the image is included only in the range corresponding to the minus, the accuracy of the standard image may be reduced, so the device 100 may update the preset standard angle range. For example, the device 100 may determine the imaging angle closest to the standard angle as the starting angle of the standard angle range. As described above, when the imaging angles corresponding to some images are 30 degrees and 40 degrees, the standard angle range can be updated to 40 degrees to 70 degrees because the imaging angle closest to the standard angle of 45 degrees is 40 degrees. In addition, if some images do not exist between 45 degrees and 70 degrees, the device 100 may allow the standard angle range to be extended back and forth by the difference between the second closest imaging angle and the closest imaging angle based on the standard angle. . For example, if some images do not exist in the range corresponding to the plus based on the standard angle even though the standard angle range has been primarily updated, the standard angle range is extended back and forth by 10 degrees, which is the difference between 30 degrees and 40 degrees, and the standard angle The range can be updated from 30 to 80 degrees. In addition, if some images do not exist in the primarily updated range (if they do not exist in the plus area based on the standard angle), the device 100 responds to the plus based on the standard angle to further increase accuracy. Images corresponding to the closest imaging angle in the range (images corresponding to angles exceeding the standard angle range) and images corresponding to the closest imaging angle in the minus corresponding range based on the standard angle (for example, 40 degrees) By overlapping the images, an image corresponding to the intermediate angle can be obtained, and the image at that position (angle) can be determined as a partial image. Accordingly, the device 100 can use some newly acquired images together to obtain a standard image based on a weight given according to the degree of proximity. Accordingly, the device 100 has the effect of being able to obtain a standard image with higher accuracy by updating the standard angle range even when some images are biased to only one side.

In another embodiment, the device 100 generally assigns a higher weight as the imaging angle corresponding to some images approaches the standard angle and determines the size of the weight to be inversely proportional to the difference angle from the standard angle. However, in some images If there are three or more, the size of the weight given to each image may be determined by further considering a plurality of other factors rather than being linearly inversely proportional. For example, when the distance between the target plant and the imaging location, the distance between the outermost point of the target plant and the center of the target plant, and the number of images corresponding to the standard angle and the imaging angle closer than the preset level are greater than a certain level. can be further considered. In one embodiment, the distance between the target plant and the imaging location may be different for each partial image because the rail may not be exactly circular and the plant may not be exactly centered. Therefore, 1.5 times more weight can be given to the image with the shortest distance between some image target plants and the imaging location, and the distance between the outermost point and the midpoint of the plant can correspond to the radius of the plant, but plants are not perfectly symmetrical. Because each radius may be different. When acquiring multiple images using a camera sensor in the infrared range, 1.5 times more weight is given to the image at the location with the shortest plant radius, given that the shorter the plant's radius, the more accurate internal space information can be. can do. In addition, if the number of images corresponding to an imaging angle that is closer to the standard angle and the preset level (e.g. 10 degrees) is greater than a certain level (e.g. 4), it is included within the standard angle range and is at the preset level. The weight given to some images that are not included in the range corresponding to the imaging angle closer than above is determined to be 0, or the size of the given weight is reduced to more than 1/2 (half), and the weight given is set to a certain level closer than the preset level. The size of the weight given to some images can be increased by more than 1/2. In this way, the device 100 can obtain a standard image with higher accuracy by varying the weight assigned to each of some images depending on the situation.

FIG. 3 is a diagram illustrating an example in which scanning of a plant is performed as the device 100 rotates around the plant, according to an embodiment. Referring to FIG. 3, the device 100 according to one embodiment may acquire a plurality of images of the target plant by scanning the target plant through a camera sensor that moves along a circular rail.

FIG. 4 is a diagram illustrating an example in which a standard image for a standard angle is acquired according to an embodiment. Referring to FIG. 4, the device 100 according to an embodiment can acquire a plurality of images of the target plant in an area adjacent to the target plant, and the imaging angle 410 corresponding to the acquired images is 0 degrees and 30 degrees, respectively. It can be 60 degrees or 90 degrees. Additionally, although not shown in the drawing, a plurality of imaging angles 410 may be further included after 90 degrees. Additionally, the device 100 may acquire a standard image corresponding to a preset standard angle in the standard angle area 420 using a plurality of images from a plurality of imaging angles 410. For example, if the preset standard angle in the standard angle area 420 corresponds to 15 degrees, the device 100 creates a standard image using some images corresponding to the imaging angle 410 of 0 degrees and 30 degrees. It can be obtained. In one embodiment, the imaging angle 410 is indicated as 0 degrees, 30 degrees, 60 degrees, 90 degrees, etc., but it is not limited thereto and it will be understood by those skilled in the art that it may be applied differently depending on the situation.

FIG. 5 is a diagram illustrating an example in which the device 100 acquires a masking image according to an embodiment. Referring to FIG. 5, as described in step S230, the device 100 may obtain a masking image by performing masking on an area corresponding to a preset color range in some images and obtain a standard image based on the weighted sum of the masking images. Images can be obtained. The device 100 may distinguish between a part to which the effect is not applied and a part to which the effect is applied in order to apply the effect only to a specific area of the image. Therefore, a masking image of the plant can be obtained.

FIG. 6 is a diagram illustrating an example in which the device 100 performs shake correction using a rail image according to an embodiment. Referring to FIG. 6, as described in step S240, a plurality of images obtained by rotating a rail (circular rail) corresponding to the boundary of an area within a preset distance based on the target plant may include rail images, The device 100 according to an embodiment may perform shaking correction by applying a correction algorithm using a preset algorithm (Bgsegm) and output data of a vibration sensor adjacent to the image sensor to a certain area in the acquired standard image.

FIG. 7 is a diagram illustrating an example in which the device 100 according to an embodiment acquires information on the internal space of a target plant using infrared rays. Referring to FIG. 7, the device 100 can obtain information on the internal space of a plant using a camera sensor in the infrared region. Additionally, the internal space information may include shape information of the plant's crown. Accordingly, the device 100 can obtain thickness and crown information about the target plant.

FIG. 8 is a diagram illustrating an example in which the device 100 sequentially scans a plurality of plants according to another embodiment. Referring to FIG. 8 , the device 100 may acquire a plurality of images by moving a straight rail rather than acquiring a plurality of images by rotating the circular rail.

FIG. 9 is a diagram illustrating a method in which the device 100 sequentially scans a plurality of plants according to another embodiment. Referring to FIG. 9, when the device 100 according to one embodiment acquires a plurality of images by moving a straight rail, the two axes connected with the cylinder as an axis move left and right, respectively, so that a camera is placed around the target plant. Multiple images can be acquired by allowing the to be positioned. Accordingly, the device 100 can acquire a plurality of images by allowing the camera to position and move along the camera path 910 as the two axes move left and right on both sides based on the target plant.

FIG. 10 is a diagram illustrating an example in which the device 100 provides 3D modeling information based on a QR code corresponding to a plant, according to an embodiment. In one embodiment, the reference line and imaging angle for the target plant may be determined based on the QR image corresponding to the target plant. Referring to FIG. 10, the target plant may include a plurality of QR images, and the device 100 determines the imaging angle according to the QR image acquired from the user terminal in conjunction with the application, or 3D modeling information about images can be displayed. For example, the device 100 may retrieve information about a target plant through a QR image obtained from a user account. In addition, the location where the plant image obtained from the user account was taken can be confirmed based on the angle and distance in the coordinates (r, θ, ψ) in 3D space away from the reference line for the plant, and the plant image was acquired accordingly. The location can be determined.

According to one embodiment, since a plurality of standard images are acquired according to a weighted sum of some images based on the imaging angle of some images, the accuracy of the images can be improved, and modeling for plants is performed. Efficiency can be improved in that costs can be reduced by using camera sensors in the visible and infrared regions. In addition, by using infrared rays to obtain more information on the internal space of the plant, efficiency can be improved in that it is possible to confirm the shape of the plant, and by using rail images included in multiple images, Because correction is possible, it is effective in obtaining and providing high-accuracy images.

Various embodiments of the present disclosure are implemented as software including one or more instructions stored in a storage medium (e.g., memory) that can be read by a machine (e.g., a display device or computer). It can be. For example, the processor 120 of the device (eg, processor 120) may call at least one instruction among one or more instructions stored from a storage medium and execute it. This allows the device to be operated to perform at least one function according to the at least one instruction called. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. A storage medium that can be read by a device may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain signals (e.g. electromagnetic waves). This term refers to cases where data is stored semi-permanently in the storage medium. There is no distinction between temporary storage cases.

According to one embodiment, methods according to various embodiments disclosed in the present disclosure may be included and provided in a computer program product. Computer program products are commodities and can be traded between sellers and buyers. The computer program product may be distributed in the form of a machine-readable storage medium (e.g. compact disc read only memory (CD-ROM)) or via an application store (e.g. Play StoreTM) or on two user devices (e.g. It can be distributed (e.g. downloaded or uploaded) directly between smartphones) or online. In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

Although the present invention has been described with reference to the illustrative drawings, it is not limited to the disclosed embodiments and drawings, and those skilled in the art in the technical field related to the present embodiments may make modifications without departing from the essential characteristics of the above-mentioned description. You will be able to understand that it can be implemented in a certain form. Therefore, the disclosed methods should be considered from an explanatory rather than a restrictive perspective. Even if the operational effects according to the configuration of the present invention are not explicitly described and explained in the description of the embodiment, the effects that can be predicted by the configuration may also be recognized. The scope of the present invention is indicated in the claims rather than the foregoing description, and all differences within the equivalent scope should be construed as being included in the present invention.

100: device
110: receiving unit 120: processor
410: Imaging angle 420: Standard angle area
910: Camera path

Claims (7)

In a method of performing modeling on a target plant,
Obtaining a plurality of images of the target plant in an area adjacent to the target plant;
determining an imaging angle corresponding to the plurality of images based on a reference line for the target plant;
Obtaining a standard image for a standard angle based on a weighted sum of some images performed based on the imaging angle for some images among the plurality of images; and
Comprising: performing modeling on the target plant using the standard image,
The step of acquiring the standard image is
determining the partial image among the plurality of images corresponding to the standard image;
Obtaining the standard image based on a weighted sum performed according to the degree to which the imaging angle corresponding to each of the partial images is close to the standard angle.
According to claim 1,
The step of acquiring the standard image is
Obtaining a masking image by masking an area corresponding to a preset color range in the partial image; and
Obtaining the standard image based on a weighted sum of the masking images.
According to claim 1,
Comprising: acquiring internal space information of the target plant using infrared rays irradiated to the target plant,
The step of performing modeling on the target plant is
Method for performing modeling on the target plant using the standard image and the internal space information.
According to claim 1,
The step of performing modeling on the target plant is
performing vibration correction on the standard image using rail images included in the plurality of images and vibration measurement data obtained from a vibration sensor; and
A method comprising: performing modeling on the target plant based on a result of performing the shaking correction.
According to claim 1,
The reference line and the imaging angle for the target plant are determined based on the QR image corresponding to the target plant.
delete In a device that performs modeling on a target plant,
a receiving unit that acquires a plurality of images of the target plant in an area adjacent to the target plant; and
Determine an imaging angle corresponding to the plurality of images based on a reference line for the target plant,
Obtaining a standard image for a standard angle based on a weighted sum of some images performed based on the imaging angle for some images of the plurality of images,
Perform modeling on the target plant using the standard image,
Determining the partial images among the plurality of images that correspond to the standard images,
A device comprising: a processor for obtaining the standard image based on a weighted sum performed according to the degree to which the imaging angle corresponding to each of the partial images is close to the standard angle.