KR102479284B1 - Vegetation index acquisition unit and apparatus for monitoring plant comprising the same - Google Patents

Abstract

One embodiment of the present invention provides a vegetation index obtaining unit capable of easily and accurately obtaining a vegetation index of the entire plant and a plant monitoring device including the same. Here, a vegetation index obtaining unit includes a first photographing unit, a first calculating unit, a second photographing unit, and a second calculating unit. The first photographing unit obtains a first image by photographing a first leaf of a plant. The first calculating unit calculates a first vegetation index for the first leaf. The first photographing unit obtains a second image by photographing a different leaf together with the first leaf. The second calculating unit calculates a second vegetation index of the different leaf by using the first vegetation index for the first leaf.

Description

Vegetation index acquisition unit and plant monitoring device including the same {VEGETATION INDEX ACQUISITION UNIT AND APPARATUS FOR MONITORING PLANT COMPRISING THE SAME}

The present invention relates to a vegetation index acquisition unit and a plant monitoring device including the same, and more particularly, to a vegetation index acquisition unit capable of easily and accurately obtaining a vegetation index of an entire plant and a plant monitoring device including the same.

Vegetation reacts sensitively to climate change and is closely related to the carbon cycle and water cycle. Therefore, continuous observation of vegetation is important for understanding the global environment.

Vegetation data are not only used as basic status observation data for environmental planning, but can also be useful for plant cultivation because they can monitor the state of plants.

One example of vegetation monitoring is field observation. Field observation is the most common method in which an observer directly observes changes in plants with the naked eye. However, although this field observation has high reliability, resource consumption such as time and manpower is high.

Recently, a sensor is installed in the field to observe changes in vegetation, and a vegetation index is used as an example.

Chlorophyll, a pigment in plant leaves, strongly absorbs visible light (400-700 nm) for photosynthesis. On the other hand, the cellular structure of the leaf reflects near-infrared rays (700-1100 nm). The vegetation index is used to quickly check the state of vegetation using these characteristics.

However, in conventional plant monitoring techniques using vegetation indices, vegetation indices are obtained for some leaves of plants, and based on this, the overall state of the plants is predicted. However, since plants may have partially different states, there is a problem in that highly accurate monitoring is difficult in a method of predicting the entire vegetation index of a corresponding plant using the vegetation index obtained from a part of the plant.

Republic of Korea Patent Registration No. 1844678 (2018.04.02. Notice)

In order to solve the above problems, a technical problem to be achieved by the present invention is to provide a vegetation index acquisition unit capable of easily and accurately obtaining a vegetation index of an entire plant and a plant monitoring device including the same.

The technical problem to be achieved by the present invention is not limited to the above-mentioned technical problem, and other technical problems not mentioned can be clearly understood by those skilled in the art from the description below. There will be.

In order to achieve the above technical problem, an embodiment of the present invention is a first photographing unit for obtaining a first image by photographing any first leaf of a plant; a first calculation unit calculating a first vegetation index for the first leaf; a second photographing unit for obtaining a second image by photographing other leaves together with the first leaf; and a second calculator calculating a second vegetation index of the other leaf using the first vegetation index of the first leaf.

In an embodiment of the present invention, the second calculation unit, if the difference between the image information of the other leaf in the second image and the image information of the first leaf in the first image is within a preset reference difference value, The second vegetation index of the other leaf in the second image may be calculated to be the same as the first vegetation index.

On the other hand, in order to achieve the above technical problem, one embodiment of the present invention is a base unit provided to be movable; a vegetation index obtaining unit provided in the base unit; a movement information generation unit provided in the base unit and configured to generate movement information of the base unit; and a matching unit that identifies a plurality of plants based on the movement information and matches the second vegetation index to each plant.

In an embodiment of the present invention, the base unit may further include an autonomous driving control unit provided in the base unit and controlling the base unit to move autonomously.

According to an embodiment of the present invention, since it is possible to generate a three-dimensional second vegetation index by photographing the three-dimensional shape of a plant and easily and accurately calculating the second vegetation index for all parts, Accurate monitoring may be possible.

The effects of the present invention are not limited to the above effects, and should be understood to include all effects that can be inferred from the detailed description of the present invention or the configuration of the invention described in the claims.

1 is a configuration diagram showing a vegetation index acquisition unit according to a first embodiment of the present invention.
2 is an exemplary diagram for explaining a first image acquisition example in a vegetation index acquisition unit according to a first embodiment of the present invention.
3 is an exemplary diagram for explaining an example of obtaining a second image in a vegetation index obtaining unit according to a first embodiment of the present invention.
4 is an image showing a 2-dimensional first vegetation index and a displacement map acquired by the vegetation index acquisition unit according to the first embodiment of the present invention.
5 is an exemplary diagram for explaining image tuning and mapping in a vegetation index acquisition unit according to a first embodiment of the present invention.
6 is a configuration diagram showing a vegetation index acquisition unit according to a second embodiment of the present invention.
7 is an exemplary diagram for explaining an example of obtaining a vegetation index by a vegetation index obtaining unit according to a second embodiment of the present invention.
8 is a configuration diagram showing a plant monitoring device according to an embodiment of the present invention.
9 is an exemplary view showing a use example of a plant monitoring device according to an embodiment of the present invention.

Hereinafter, the present invention will be described with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and, therefore, is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected (connected, contacted, combined)" with another part, this is not only "directly connected", but also "indirectly connected" with another member in between. "Including cases where In addition, when a part "includes" a certain component, it means that it may further include other components without excluding other components unless otherwise stated.

Terms used in this specification are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to indicate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a configuration diagram showing a vegetation index acquisition unit according to a first embodiment of the present invention.

As shown in FIG. 1 , the vegetation index obtaining unit 100 may include a first capturing unit 110, a first calculating unit 120, a second capturing unit 130, and a second calculating unit 140. there is.

2 is an exemplary view for explaining an example of obtaining a first image in a vegetation index acquisition unit according to a first embodiment of the present invention. Referring to FIG. 2 together, the first photographing unit 110 is a A first image 111 may be obtained by photographing the first leaf 11 . Here, the first leaf 11 may be any leaf selected from among several leaves of the plant 10, and is not particularly limited.

The first image 111 may be a two-dimensional image. The first image 111 may include image information of the first leaf 112 generated by photographing the actual first leaf 11 .

The type of the first capturing unit 110 is not particularly limited as long as it can capture the first image 111 . For example, the first photographing unit 110 may include a near-infrared signal analysis camera, a multi-spectral camera, and the like.

The first calculation unit 120 may calculate the first vegetation index 121 based on image information of the first leaf 112 included in the first image 111 . The first vegetation index 121 may be a Normalized Difference Vegetation Index (NDVI).

Since the first image 111 is a two-dimensional image, image information of the first leaf 112 can be accurately processed, and through this, calculation accuracy of the first vegetation index 121 can be increased.

Although the first leaf 11 is shown as one leaf in FIG. 2, this is exemplary, and a plurality of leaves may be selected as the first leaf 11. When the first leaf 11 is a plurality of leaves, the first vegetation index 121 may be calculated for each leaf.

FIG. 3 is an exemplary diagram for explaining an example of obtaining a second image in a vegetation index acquiring unit according to a first embodiment of the present invention, and will be described with further reference to FIG. 3 .

The second photographing unit 130 photographs the first leaf 11 of the plant 10 captured by the first photographing unit 110 and another leaf (hereinafter, referred to as the second leaf 12). 2 images 131 can be obtained.

In FIG. 3 , the second leaf 12 is illustrated as one leaf, but this is exemplary, and the second leaf 12 may collectively refer to all leaves except the first leaf 11 . Accordingly, the second image 131 may be a photograph of all leaves of the plant 10 .

The second image 131 may be a 3D image. That is, the second photographing unit 130 may capture the 3D shape of the plant 10 , and the 3D shape of the plant 10 may be restored from the second image 131 .

The second photographing unit 130 may include photographing equipment capable of generating a 3D image, for example, a stereo camera.

The second calculation unit 140 calculates the second vegetation index 141 of the second leaf 12 using the first vegetation index 121 for the first leaf 11 calculated by the first calculation unit 120. can be calculated.

Specifically, the second calculation unit 140 may compare the difference between the image information of the first leaf 132 in the second image 131 and the image information of the first leaf 112 in the first image 111. there is. And, if this difference value is within a preset standard difference value, the second vegetation index 141 of the first leaf 132 in the second image 131 may be calculated to be the same as the first vegetation index 121 .

In addition, the second calculation unit 140 may compare the difference between the image information of the second leaf 133 in the second image 131 and the image information of the first leaf 112 in the first image 111. , If this difference value is within a preset reference difference value, the second vegetation index 141 of the second leaf 133 in the second image 131 can be calculated to be the same as the first vegetation index 121 .

That is, when the second calculation unit 140 synchronizes the vegetation index image and the stereo image, the combination of the vegetation index image and the stereo image among the previously measured data is called A, and the vegetation index is When the signal for each channel of the stereo image of the non-measured part (for example, simple RGB or CMYK without distance information) is very similar, the second calculator 140 may include the vegetation index of A in the non-measured part. can

In addition, the second calculation unit 140 may, for any other second leaf for which the first vegetation index is not calculated, a plurality of second vegetation indices already calculated and obtained, and a second vegetation index of the plurality of second vegetation indices. A second vegetation index may be generated by interpolation based on leaf image information.

4 is an image showing a 2-dimensional first vegetation index and a displacement map acquired by the vegetation index acquisition unit according to the first embodiment of the present invention.

As shown in FIG. 4, a reference that knows the existing accurate location information, reflectivity information, and size information is installed within the shooting angle at the start of measurement to set a benchmark, and at the same time as the measurement starts, trees and vegetation are planted around the benchmark can be filmed. At this time, it is preferable that the first capture unit and the second capture unit are installed on the same axis, through which image synchronization can be performed stably.

Figure 4 (a) is a measurement image showing the measured vegetation index on a two-dimensional plane, Figure 4 (b) shows a displacement map (Disparity Map) obtained from the second capture unit in a two-dimensional plane. The difference in resolution between the measurement image of FIG. 4(a) and the displacement map of FIG. 4(b) can be synchronized by correcting the angle of view with upscale and downscale. Since distance information can be obtained through a displacement map obtained through the second capture unit, it can be converted into a point cloud through an appropriate algorithm.

5 is an exemplary diagram for explaining image tuning and mapping in a vegetation index acquisition unit according to a first embodiment of the present invention.

The 3D vegetation index is obtained by photographing the plant with the first and second photographing units while moving around the plant, synchronizing the position of the leaf where the vegetation index is photographed with a point cloud through 3D imaging, or pixels of a displacement map. It can be constructed by synchronizing the location to obtain a 3-dimensional vegetation index image.

Specifically, as shown in FIG. 5, assuming a spherical virtual plant 10, the right hemisphere 31 of the plant 10 is measured while moving along the right movement path 20 of the plant 10, and then returned When the left hemisphere 32 is measured while moving along the left movement path 21, the converted point cloud is interlocked with the travel distance to complete a 3D model by combining the left and right measurement point clouds at each location where the target plant 10 is measured. can

Synchronizing the left and right images is primarily based on the method of counting the number of plants 10 measured through the average distance measured in the depth image (recognizing the presence or absence of plants when generating a close image) and using GPS coordinates In the case of measuring the same plant 10 from different directions, an algorithm recognizing this may be simultaneously applied. For example, when recording the image of the 2nd plant in gyrus 1, save it as [2, 1], and in the case of the 2nd plant from the end of gyrus 2, set the Lexicon as [2, 2]. can be unified and stored. Through this, 3D shape information for each plant can be configured.

Meanwhile, FIG. 6 is a configuration diagram showing a vegetation index obtaining unit according to the second embodiment of the present invention, and FIG. 7 is an example for explaining an example of obtaining a vegetation index of the vegetation index obtaining unit according to the second embodiment of the present invention. It is also In the present embodiment, a second vegetation index calculation criterion may be generated and the second vegetation index may be calculated using this criterion, and other basic contents may be the same as those of the first embodiment described above.

As shown in FIGS. 6 and 7 together with FIGS. 2 and 3 , the vegetation index obtaining unit 100 according to the present embodiment may further include a calculation reference generating unit 150 .

The calculation reference generating unit 150 matches the image information of the first leaf 132 included in the second image 131 and the first vegetation index 121 to generate the second vegetation index calculation reference 151. can

The image information of the first leaf 112 in the first image 111 and the image information of the first leaf 132 in the second image 131 may include color information, luminance information, and the like. However, since the second image 131 is a 3D image, the image information of the first leaf 132 in the second image 131 is the image information of the first leaf 112 in the first image 111. may be different from Therefore, when the vegetation index of the actual first leaf 11 is calculated using the image information of the first leaf 132 in the second image 131, the second vegetation index calculated at this time is the first vegetation index calculated above. It may differ from the vegetation index (121).

To solve this problem, in the present invention, the calculation reference generating unit 150 calculates the first vegetation index 121 based on the image information of the first leaf 112 in the first image 111 and the second image ( The second vegetation index calculation criterion 151 may be generated by matching the image information of the first leaf 132 in 131).

When the generated second vegetation index calculation criterion 151 is applied to the second image, a second vegetation index may be calculated in the state of the second image, and the calculated second vegetation index may be the same as the first vegetation index. .

The calculation criterion generation unit 150 generates the second vegetation index calculation criterion 151 and uses the generated second vegetation index calculation criterion 151 as image information of the first leaf 132 in the second image 131. , and check whether the second vegetation index calculated accordingly is the same as the first vegetation index 121, and if the second vegetation index calculated is not equal to the first vegetation index 121, the second vegetation index By repeating the process of correcting the calculation criteria 151, the accuracy of the generated second vegetation index calculation criteria can be further verified.

A method of generating the second vegetation index calculation criterion 151 by the calculation criterion generating unit 150 is not particularly limited.

The second calculation unit 140 applies the second vegetation index calculation criterion 151 to the image information on the second leaf 133 in the second image 131, and through this, the actual second leaf 12 2 Vegetation index (141) can be calculated.

When the actual first leaf 11 is taken as an example, the second vegetation index calculated by the second calculation unit 140 for the first leaf 132 of the second image 131 is the same actual first leaf 11 ) It may be the same value or range value as the first vegetation index 121 calculated for the target.

As described above, since the second leaf 12 may collectively refer to one or more leaves excluding the first leaf 11, the first leaf 11 and the second leaf 12 are the entirety of the plant 10. can mean leaves. Therefore, the calculated second vegetation index 141 may be for almost all leaves of the plant 10, and through this, a three-dimensional, three-dimensional calculation of the second vegetation index for all leaves of the plant 10 may be possible. there is.

In general, it is difficult to calculate the first vegetation index because it is difficult to capture an image or receive a near-infrared ray signal in a part that cannot be photographed by the first photographing unit 110, for example, a part opposite to a plant. However, as in the front of a plant, an image is captured or a near-infrared ray signal is received at a part that can be photographed with the first photographing unit 110, and the first vegetation index is calculated, and the second photographing unit 130 determines the 3D shape of the plant. When the image information is obtained, a second vegetation index calculation criterion 151 is generated, and a second vegetation index of the opposite part of the plant can be generated using the second vegetation index calculation criterion 151 .

Alternatively, a second vegetation index calculation criterion is generated based on the first vegetation index obtained by photographing a part of the leaf (eg, the upper surface) with the first photographing unit 110, and the second vegetation index is photographed and the lower surface of the leaf is photographed. A second vegetation index may be generated by being included in the image.

Alternatively, the second vegetation index may be generated by interpolating overall measured values for objects that are difficult to pixelate, such as needles.

In the case where the plant 10 is a leafy vegetable including gondola, crown daisy, sesame, amaranth, butterbur, etc. whose leaves are used for food, the vegetation state of the other leaves is also based on the vegetation state of any one leaf. If it is simply predicted that it will be the same, it can be difficult to manage the quality of harvested leafy vegetables.

That is, when the vegetation indices of the remaining leaves are predicted based on the vegetation indices of some leaves, the vegetation indices of the remaining leaves may be affected by the vegetation indices that are the basis. For example, if the vegetation index of some leaves is good, the vegetation index of the remaining leaves may also be predicted to be good. However, since the growth state of each part of a plant may be different, this vegetation index prediction method may have low accuracy. However, if each leaf is photographed one by one and the vegetation index is calculated, it may take considerable time.

However, according to the present invention, since the 3D shape of a plant can be photographed and the second vegetation index can be easily and accurately calculated for all leaves, it is possible to accurately and quickly monitor the plant.

Meanwhile, although it has been described above that the second vegetation index is calculated for the leaves of plants, the calculation target for the second vegetation index is not necessarily limited to leaves. That is, vegetables such as paprika and red pepper, fruit vegetables such as strawberries, or fruit crops may also be included in the calculation of the second vegetation index.

In addition, when the first vegetation index 121 is obtained for each of a plurality of leaves and the number is large, the number of second vegetation index calculation criteria generated by the calculation criteria generation unit 150 may increase. Then, since the second vegetation index calculation criterion 151 may be finally generated using the average value of the plurality of second vegetation index calculation criteria, the accuracy of the second vegetation index calculation criterion 151 may be increased.

8 is a configuration diagram showing a plant monitoring device according to an embodiment of the present invention.

As shown in FIG. 8 , the plant monitoring device may include a base unit 200 , a vegetation index acquisition unit 100 , a movement information generation unit 300 and a matching unit 400 .

The base unit 200 may be provided to be movable. For example, the base unit 200 may have wheels (not shown) and may have a driving system (not shown) capable of rotating the wheels. The wheels may be implemented in various forms, such as rolling directly on a road surface with rubber tires or rolling along rails installed on the ground.

Through this, the plant monitoring device may be movable in outdoor terrains such as mountains, parks, orchards, or facilities such as houses, greenhouses, and smart farms.

Since the vegetation index obtaining unit 100 has been described above, descriptions of repetitive contents will be omitted as much as possible.

The vegetation index acquisition unit 100 may be provided in the base unit 200, and captures a plant while moving with the base unit 200 to generate a 3D image, and obtains a second vegetation index for leaves of the entire plant. It is possible to generate a three-dimensional second vegetation index by calculation.

The movement information generation unit 300 may be included in the base unit 200 and may generate movement information of the base unit 200 . The movement information may include location information and movement speed information of the base unit 200 . The movement information generation unit 300 may include an inertial measurement unit (IMU) or the like.

The matching unit 400 may classify a plurality of plants based on the movement information generated by the movement information generating unit 300, and match the calculated second vegetation index to each of the classified plants.

The matching unit 400 may be provided on the base unit 200 or may be provided in another location apart from the base unit 200 . The matching unit 400 may perform wired or wireless communication with the vegetation index acquisition unit 100 and the movement information generation unit 300 .

The plant monitoring device may further include an autonomous driving control unit 500 . The autonomous driving control unit 500 is provided in the base unit 200 and can control the base unit 200 to move autonomously. The autonomous driving control unit 500 may include a processor having software for autonomous driving control and a sensor including lidar for detecting obstacles, objects, and the like.

In addition, the plant monitoring device may further include a selection unit 600 and a display unit 700 .

The selection unit 600 may select leaves of a second vegetation index less than a predetermined reference second vegetation index from among the second vegetation indexes calculated by the vegetation index obtaining unit 100 .

In plants, the part calculated by the second vegetation index higher than the standard second vegetation index can be judged to have good growth, and the part calculated by the second vegetation index lower than the standard second vegetation index can be judged to have poor growth. The second vegetation index may be set in advance based on the type of plant, season, and the like.

In addition, the display unit 700 provides information on the leaves selected by the sorting unit 600, that is, plants having parts (for example, leaves, vegetables, etc.) that are calculated as the second vegetation index less than the reference second vegetation index. can be displayed.

The display unit 700 displays only the location information of plants having parts (eg, leaves, vegetables, etc.) selected by the sorting unit 600 or the parts selected by the sorting unit 600 (eg, leaves, vegetables, etc.) For example, the location information of leaves, vegetables, etc.) can be displayed.

Through this, the user can accurately identify the poor growth state of the plant, accurately analyze the growth of the plant based on this information, and further predict the growth.

Hereinafter, an operation example of the plant monitoring device will be described as an example of a case in which the plant monitoring device is used in a smart farm where plants are grown.

9 is an exemplary view showing a use example of a plant monitoring device according to an embodiment of the present invention. Referring further to FIG. 9, a base unit 200 is installed between plants 10 planted in an orchard or greenhouse. ) travels, the movement information generating unit 300 may generate movement information of the base unit 200 . At the same time, the vegetation index acquisition unit 100 may acquire second vegetation indexes of plants 10 on the driving route 22 of the base unit 200 . Then, the matching unit 400 may match the second vegetation index for each plant 10 .

If the plant monitoring device 1000 does not have an autonomous driving function, the plant monitoring device 1000 may be moved by a worker. However, when the plant monitoring device 1000 includes the autonomous driving control unit 500 , the base unit 200 may be autonomously moved by the autonomous driving control unit 500 .

The sorting unit 600 may select leaves of a second vegetation index less than the reference second vegetation index among the calculated second vegetation indexes, and the display unit 700 may display information on plants having leaves selected in this way. can Through this, it is possible to help a worker easily identify and check not only the position of a plant in a poor growth state, but also a part of the plant with a leaf in a poor growth state.

In order to increase the plant growth monitoring effect, plant monitoring using the plant monitoring device 1000 may be performed regularly.

The above description of the present invention is for illustrative purposes, and those skilled in the art can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts should be interpreted as being included in the scope of the present invention.

100: vegetation index acquisition unit
110: first shooting unit
111: first image
120: first calculation unit
121: first vegetation index
130: second shooting unit
131: second image
140: second calculation unit
141: second vegetation index
150: calculation reference generating unit
151: second vegetation index calculation criteria
200: base unit
300: movement information generating unit
400: matching unit
500: autonomous driving control unit
600: sorting unit
700: display unit

Claims (4)

a first photographing unit for obtaining a first image by photographing a first leaf of a plant;
a first calculation unit calculating a first vegetation index for the first leaf from the first image;
a second photographing unit for obtaining a second image by photographing other leaves together with the first leaf;
a second calculation unit calculating a second vegetation index of the other leaf of the second image by using the first vegetation index of the first leaf; and
A calculation criterion generation unit configured to generate a second vegetation index calculation criterion by matching image information about the first leaf in the second image with the first vegetation index,
The first image is a two-dimensional image,
The second image is a three-dimensional image in which the three-dimensional shape of the plant is restored,
The second calculator,
Calculating the second vegetation index of the other leaf by applying the second vegetation index calculation criterion to the image information on the other leaf in the second image to calculate the three-dimensional 3-dimensional second vegetation index of the plant Characteristic vegetation index acquisition unit. delete a base unit provided to be movable;
a vegetation index acquisition unit provided in the base unit and described in claim 1;
a movement information generation unit provided in the base unit and configured to generate movement information of the base unit; and
and a matching unit that identifies a plurality of plants based on the movement information and matches the second vegetation index to each plant. According to claim 3,
The plant monitoring device further comprises an autonomous driving control unit provided in the base unit and controlling the base unit to autonomously move.

Images