KR20210009908A - The method for analyzing crop growth status by using multispectral camera and lidar - Google Patents

Abstract

According to one embodiment of the present invention, a method for analyzing a crop growth status may comprise the steps of: deriving first shape data of target crop through scanning of the target crop; obtaining vegetation data of the target crop based on a spectroscopic image of the target crop; and deriving second shape data of the target crop based on the first shape data and the spectroscopic image. Therefore, the method can accurately determine a growth status of a seedling regardless of the skill level of a worker.

Description

Crop growth status analysis method using multispectral camera and lidar {THE METHOD FOR ANALYZING CROP GROWTH STATUS BY USING MULTISPECTRAL CAMERA AND LIDAR}

The present invention relates to a crop growth state analysis method, and more particularly, to acquire shape data of a target crop based on a point cloud acquired through a lidar sensor for a target crop, and use a spectral image acquired through a multispectral camera. The present invention relates to a method for analyzing the growth state of a crop to analyze the growth state of the target crop by deriving the vegetation index of the target crop.

Analyzing the growth status of seedlings in the process of growing seedlings suitable for planting by cultivating them for a certain period of time by sowing with seeds or nutrients is a very important factor in improving the productivity and quality of seedlings. In the past, the worker looked and checked the appearance of seedlings directly to check the growth status of the seedlings. However, when the worker's empirical judgment as described above determines the growth state of the seedling, there is a problem in that the quality of the seedling may be deteriorated due to the difference in judgment according to the worker's skill level.

Therefore, in order to quantify information related to the growth of crops such as the shape of seedlings and vegetation index, development of a technology for more accurately grasping the growth state of crops is required by acquiring and processing the information.

In particular, using a LiDAR (Light Detection And Ranging) sensor, which is increasing in utility and importance as a core technology of a laser scanner for 3D image restoration and a 3D image sensor for future unmanned vehicles, is used to visualize light. A technology capable of grasping the growth state of crops by acquiring and processing information related to crop growth using a spectroscopic image sensor capable of recording not only the light beam area but also the invisible area such as infrared light has not been developed yet.

Republic of Korea Public Utility Model Publication No. 20-1997-0056381 (Publication date: 1998.10.15)

An object of the present invention is to provide a growth state analysis method capable of accurately determining the growth state of seedlings regardless of the skill level of an operator as a countermeasure to the above-described problem.

As an embodiment of the present invention, a method for analyzing crop growth conditions may be provided.

In the method of analyzing a crop growth state according to an embodiment of the present invention, the first shape data of the target crop is derived through scanning of the target crop, and vegetation data of the target crop is obtained based on a spectral image of the target crop. The step and the step of deriving second shape data of the target crop based on the first shape data and the spectral image may be included.

In the method for analyzing crop growth state according to an embodiment of the present invention, in the step of deriving the first shape data of the target crop through scanning of the target crop, scanning of the target crop is performed using a first sensor module. The step of generating a shape model for the target crop based on the point cloud acquired through scanning, and the step of deriving the first shape data of the target crop using the generated shape model may be further included. have.

In the crop growth state analysis method according to an embodiment of the present invention, a first sensor module includes a LiDAR (Light Detection And Ranging) sensor, and the first shape data includes a length of a target crop, a leaf length, and a leaf width. At least one may be included.

In the method for analyzing the growth state of a crop according to an embodiment of the present invention, in the step of obtaining vegetation data of the target crop based on the spectroscopic image of the target crop, a spectroscopic image of the target crop is performed using a second sensor module. The step of obtaining, the step of extracting the spectral reflectance for each spectral band from the spectral image, and the step of obtaining vegetation data based on the spectral reflectance for each spectral band are included, and the second sensor module includes a multispectral sensor And a hyperspectral sensor, and the vegetation data may be a Normalized Distribution Vegetation Index (NDVI).

In the method for analyzing a crop growth state according to an embodiment of the present invention, in the step of deriving the second shape data of the target crop based on the first shape data and the spectral image, a predetermined threshold value for the spectral image of the target crop The step of generating a binarized image for the target crop as the binarization is performed based on the binarization image, the step of generating a masking image for the target crop according to the masking process for the binarized image, and the masking image and the first shape data Thus, the step of deriving the second shape data may be included, and the second shape data may include the leaf area of the target crop.

As an embodiment of the present invention, a computer-readable recording medium in which a program for implementing the above-described method is recorded may be provided.

According to an embodiment of the present invention, there is an effect of accurately determining the growth state of seedlings regardless of the skill level of the worker.

1 is a flow chart showing a method for analyzing a crop growth state according to an embodiment of the present invention.
2 is a flowchart illustrating a process of deriving first shape data in a method for analyzing a crop growth state according to an embodiment of the present invention.
3 is a flow chart illustrating a process of obtaining vegetation data in a method for analyzing a crop growth state according to an embodiment of the present invention.
4 is a flowchart illustrating a process of deriving second shape data in a method for analyzing a crop growth state according to an embodiment of the present invention.
5 is an exemplary view showing a process in which a method for analyzing a crop growth state according to an embodiment of the present invention is performed.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are assigned to similar parts throughout the specification.

The terms used in the present specification will be briefly described, and the present invention will be described in detail.

The terms used in the present invention have been selected from general terms that are currently widely used while considering functions in the present invention, but this may vary depending on the intention or precedent of a technician working in the field, the emergence of new technologies, and the like. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning of the terms will be described in detail in the description of the corresponding invention. Therefore, the terms used in the present invention should be defined based on the meaning of the term and the overall contents of the present invention, not a simple name of the term.

When a part of the specification is said to "include" a certain component, it means that other components may be further included rather than excluding other components unless otherwise stated. In addition, terms such as "... unit" and "module" described in the specification mean units that process at least one function or operation, which may be implemented as hardware or software, or as a combination of hardware and software. . In addition, when a part is "connected" to another part throughout the specification, this includes not only a case in which it is "directly connected", but also a case in which it is connected "with another element in the middle."

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

As an embodiment of the present invention, a method for analyzing crop growth conditions may be provided.

1 is a flowchart showing a method of analyzing a crop growth state according to an embodiment of the present invention, and FIG. 5 is an exemplary view showing a process in which the method of analyzing a crop growth state according to an embodiment of the present invention is performed.

Referring to FIGS. 1 and 5, the method of analyzing a crop growth state according to an embodiment of the present invention is a step of deriving first shape data of the target crop 20 through scanning of the target crop 20 (S100). , A target crop based on the step (S200) of obtaining the vegetation data 400 of the target crop 20 based on the spectral image 100 for the target crop 20 and the first shape data and the spectral image 100 The step (S300) of deriving the second shape data 300 of (20) may be included.

According to an embodiment of the present invention, a method for analyzing crop growth conditions includes first shape data, second shape data 300, and vegetation data for the target crop 20 obtained through the above process (S100-S300). 400), it is possible to grasp the growing state of the target crop 20. For example, by quantifying the first shape data, the second shape data 300, and the vegetation data 400 for the target crop 20, the user can intuitively recognize it. In addition, by assigning different weights to each of the first shape data, the second shape data 300, and the vegetation data 400 for the quantified target crop 20, an index for determining the growing state may be generated. The user can check the growing state of the target crop 20 by using the index generated as described above. However, the above-described contents are only illustrative and are not limited thereto, and the target crop 20 using the first shape data, the second shape data 300 and the vegetation data 400 for the target crop 20 The method for determining and analyzing the growth state of the present invention is included in the scope of protection.

In the present specification, the target crop 20 to be analyzed by the method for analyzing the crop growth state may be included if it is a plant and a tree for cultivation, and may correspond to the'crop' of the present invention even if it is not for cultivation. In particular, the target crop 20 may include seedlings for selecting seedlings suitable for transplanting and growing for a predetermined period by a method such as sowing.

In the following, the step of deriving the first shape data (S100), the step of obtaining the vegetation data 400 of the target crop 20 based on the spectroscopic image 100 of the target crop 20 (S200) and the first 1 A step (S300) of deriving the second shape data 300 of the target crop 20 based on the shape data 200 and the spectral image 100 will be sequentially described.

First, FIG. 2 is a flow chart illustrating a process of deriving the first shape data 200 in the method for analyzing the growth state of a crop according to an embodiment of the present invention.

Referring to FIG. 2, in the method for analyzing a crop growth state according to an embodiment of the present invention, the step of deriving the first shape data 200 of the target crop 20 through scanning of the target crop 20 ( In S100, a step in which the target crop 20 is scanned using a first sensor module (S110), and a shape model for the target crop 20 based on a point cloud acquired through scanning The generated step S120 and the step S130 of deriving the first shape data 200 of the target crop 20 using the generated shape model may be further included.

In addition, in the method for analyzing crop growth status according to an embodiment of the present invention, a first sensor module includes a LiDAR (Light Detection And Ranging) sensor, and the first shape data 200 includes a target crop 20 ) May include at least one of the plant length, leaf length, and leaf width.

The lidar sensor may refer to a sensor capable of detecting distance, direction, speed, temperature, material distribution, and concentration characteristics to the object by shining light onto the object. The lidar sensor may include a two-dimensional lidar sensor, a three-dimensional lidar sensor, and the like, but a three-dimensional lidar sensor is preferred in application to the present invention. That is, a series of 3D data acquired through 3D scanning through the lidar sensor may correspond to a point cloud. In addition, it is natural that the point cloud can be obtained through scanning through at least one lidar sensor.

After the 3D scanning (S110), a shape model for the target crop 20 may be generated (S120) according to the point cloud. The shape model may correspond to a point cloud model for representing the target crop 20 by forming a group of points corresponding to the target crop 20.

The first shape data 200 of the target crop 20 may be derived (S130) using the shape model generated as described above. As described above, the first shape data 200 may include at least one of the height, leaf length, and leaf width of the target crop 20. The user can grasp the growth state of the target crop 20 by using the first shape data 200 such as the length, leaf length, and leaf width of the target crop 20 derived according to the above process.

Next, in the crop growth state analysis method according to an embodiment of the present invention, the step of obtaining the vegetation data 400 of the target crop 20 based on the spectroscopic image 100 of the target crop 20 ( In S200), a step of obtaining a spectral image 100 for the target crop 20 using a second sensor module (S210), and a step of extracting spectral reflectance for each of a plurality of spectral bands from the spectral image 100 (S220). ) And the step of obtaining the vegetation data 400 based on the spectral reflectance for each spectral band (S230), and the second sensor module includes any of a multispectral sensor and a hyperspectral sensor. One is included, and the vegetation data 400 may be a Normalized Distribution Vegetation Index (NDVI).

That is, in S210, the spectroscopic image 100 refers to an image acquired using a spectroscopic image sensor such as a multispectral sensor and a hyperspectral sensor. In other words, the spectral image 100 for the target crop 20 may be obtained using the second sensor module, and the spectral image 100 is a spectral reflectance diagram for each of a plurality of spectral bands for the target crop 20 It may correspond to an image generated based on. The spectral band may include a red wavelength band (600nm ~ 700nm), a blue wavelength band (400nm ~ 500nm), a green wavelength band (500nm ~ 600nm), a near infrared (NIR) wavelength range (750nm ~ 900nm), etc. have. However, since the above-described spectral band is only exemplary, it is not limited thereto, and the spectral image 100 may be generated based on various spectral bands according to a user's purpose and use.

A normalized vegetation index (NDVI) may be derived based on the obtained spectral reflectance for each spectral band. The normalized vegetation index corresponds to an index for grasping vegetation characteristics of the target crop 20 based on the spectral difference generated between the near-infrared (NIR) region and the visible ray region. The normalized vegetation index may be used as an index for indicating vegetation vitality for the target crop 20. That is, the user may obtain information related to the level of vitality of the target crop 20 by using the normalized vegetation index obtained in the above process (S200).

Next, in the crop growth state analysis method according to an embodiment of the present invention, based on the first shape data 200 and the spectral image 100, the second shape data 300 of the target crop 20 is derived. In the step (S300), the binarization image for the target crop 20 is generated as the binarization is performed based on a predetermined threshold for the spectral image 100 of the target crop 20 (S310), binarization The step of generating a masking image for the target crop 20 according to a masking process for the image (S320), and the second shape data 300 is derived based on the masking image and the first shape data 200 Step S330 is included, and the leaf area of the target crop 20 may be included in the second shape data 300.

As shown in FIG. 5, before binarization is performed on the spectral image 100 obtained in the above-described S200 process, a color space conversion process (S305) may be performed on the spectral image 100. Information related to an RGB color space representing colors using light characteristics may be obtained from the spectral image 100 obtained in step S200, and the RGB data to be converted into an HSL color space primarily for image processing. I can. That is, information on hue, saturation, and lightness may be obtained from RGB pixel data through the color space conversion process S305.

The binarization of the spectral image 100 may be performed (S310) based on the information obtained according to the color space conversion. Various known methods may be applied in relation to image binarization, and the spectral image 100 may be binarized based on a threshold value obtained according to the Otsu method in the crop growth state analysis method of the present invention. The Otsu method refers to a method for finding a threshold value for optimally dividing an image into two classes for an image histogram. That is, when the image information data (ex. pixel value, brightness, etc.) is classified into two classes based on the threshold value T, the threshold value T that maximizes the value of the between-class variance. Refers to how to find. As the spectral image 100 is binarized based on the threshold value for classification using the aforementioned Otsu method, a binarized image may be generated.

Thereafter, as image masking is performed on the binarized image generated in the step S310, a masking image may be generated. A known method may be applied in relation to image masking, and a masked image may be obtained as masking is performed so that only the target crop 20 is represented in the binarized image.

Next, the second shape data 300 may be obtained by fusing the masking image with the first shape data 200 obtained in the process S100. As described above, the second shape data 300 may include the leaf area of the target crop 20. That is, since the leaf area may be determined according to the leaf length and the leaf width, the leaf area may be calculated based on data related to the leaf length, leaf width, and plant height corresponding to the first shape data 200 and the masking image generated in S320.

That is, the user uses the method for analyzing the growth state of the crop according to an embodiment of the present invention, using the first shape data (Ex. plant height, leaf width, leaf length, etc.) of the target crop 20, and the second shape data (Ex. leaf area, etc.) ) And vegetation data (Ex. normalized vegetation index) can be obtained, and the growth state of the target crop 20 can be grasped using the obtained data.

Meanwhile, as an embodiment of the present invention, a computer-readable recording medium in which a program for implementing the above-described method is recorded may be provided.

In addition, the above-described method can be written as a program that can be executed on a computer, and can be implemented in a general-purpose digital computer that operates the program using a computer-readable medium. Further, the structure of the data used in the above-described method may be recorded on a computer-readable medium through various means. A recording medium for recording executable computer programs or codes for performing various methods of the present invention should not be understood as including temporary objects such as carrier waves or signals. The computer-readable medium may include a storage medium such as a magnetic storage medium (eg, ROM, floppy disk, hard disk, etc.), and an optical reading medium (eg, CD-ROM, DVD, etc.).

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to 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, it should be understood that the embodiments described above are 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 being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention do.

20: target crop
100: spectral image
200: first shape data
300: second shape data
400: vegetation data

Claims (6)

In the method for analyzing crop growth conditions,
Deriving first shape data of the target crop through scanning of the target crop;
Obtaining vegetation data of the target crop based on the spectral image of the target crop; And
And deriving second shape data of the target crop based on the first shape data and the spectral image.
The method of claim 1,
The step of deriving the first shape data of the target crop through scanning of the target crop includes: performing scanning of the target crop using a first sensor module;
Generating a shape model for the target crop based on a point cloud acquired through the scanning; And
A method for analyzing a crop growth state further comprising the step of deriving first shape data of the target crop by using the generated shape model.
The method of claim 2,
The first sensor module includes a LiDAR (Light Detection And Ranging) sensor, and the first shape data includes at least one of a plant height, a leaf length, and a leaf width of the target crop.
The method of claim 3,
Acquiring the vegetation data of the target crop based on the spectroscopic image of the target crop includes: obtaining a spectroscopic image of the target crop using a second sensor module;
Extracting spectral reflectance for each spectral band from the spectral image; And
It includes the step of obtaining the vegetation data based on the spectral reflectance for each spectral band,
The second sensor module includes any one of a multispectral sensor and a hyperspectral sensor, and the vegetation data is a crop growth state analysis, which is a Normalized Distribution Vegetation Index (NDVI). Way.
The method of claim 3,
In the step of deriving the second shape data of the target crop based on the first shape data and the spectral image, as binarization is performed based on a predetermined threshold for the spectral image of the target crop, Generating a binarized image;
Generating a masked image for the target crop according to a masking process for the binarized image; And
And deriving the second shape data based on the masking image and the first shape data,
The second shape data includes a crop growth state analysis method including the leaf area of the target crop.
A computer-readable recording medium in which a program for implementing the method of any one of claims 1 to 5 is recorded.

Images