A method for detecting main stem of plants at seedling stage in a phenotypic imaging chamber environment

Abstract

The present invention discloses a method for detecting the main stem of a plant seedling in a phenotypic imaging box environment. The main stem of a plant is detected by utilizing the strong correlation in position and direction of the detection line segment set to which the main stem of the plant belongs in the image. The steps are as follows: (1) detecting the line segment by the LSD method; (2) clustering the line segments according to the position and direction information of the center point of the line segment; (3) calculating the degree of chaos within each line segment class and determining the line segment class to which the main stem of the plant seedling belongs accordingly. The present invention has the advantages of high accuracy, strong robustness, and fewer constraints. In particular, the method has good adaptability to shooting angles, and does not require the main stem of the plant to occupy a prominent position and a large proportion in the image. Therefore, the method is very suitable for use in the main stem detection system of a plant seedling in a phenotypic imaging box environment.

Description

Technical Field

[0001] The invention relates to image processing, computer vision and pattern recognition, and in particular to a method for detecting main stems of plants at the seedling stage in a phenotype imaging box environment. Background Art

[0002] In the plant phenotyping system, the visual perception system can be used to perceive the main stem of the plant seedling stage and collect relevant data. With the development of smart agriculture, more and more image data are collected through various visual sensors. However, with the sharp increase in data and tasks, traditional manual measurement is far from meeting the needs of plant phenotyping tasks. Therefore, realizing intelligent automatic measurement functions that can replace human eyes and applying them to actual plant phenotyping systems has become a common research goal in the fields of computer vision and plant phenotyping.

[0003] As a basic step in visual measurement of the main stem of a plant seedling, obtaining the position information of the main stem pixel plays an important role in determining the measurement accuracy. Automatic detection of the main stem of a plant can be widely used in aspects such as plant height measurement and internode measurement in plant phenotyping. In the application of plant phenotyping, the main stem and the side branches have a certain degree of similarity in appearance, and the occlusion of other plant parts such as leaves also destroys the continuity of the imaging. How to automatically and accurately detect the main stem of a plant seedling in the images captured by the plant phenotyping system has become an urgent problem to be solved in engineering practice.

[0004] After searching the existing technical literature, it is found that almost all the main stem detection methods of plants in the seedling stage are based on Hough transform to realize the straight line detection in the image. At the same time, there are also main stem detection methods of plants in the seedling stage based on deep learning, but the computational overhead is huge. Summary of the invention

[0005] Purpose of the invention: The purpose of the present invention is to provide a method for detecting the main stem of plants in the seedling stage in a phenotypic imaging box environment, so as to detect the main stem of plants in the seedling stage in real time in actual plant phenotyping applications and provide key data information for the phenotyping system.

[0006] Technical solution: The method for detecting the main stem of a plant at the seedling stage in a phenotypic imaging box environment of the present invention comprises the following steps:

[0007] (1) Detect line segments using the LSD method;

[0008] (1.1) Read the surveillance scene images captured by the surveillance camera into the computer and perform some basic image preprocessing on the input source images;

[0009] (1.2) Use the LSD method to detect straight lines in the image and form a set of candidate line segments, represented by L = {l1,…,l m}, m is the total number of detected straight lines, line segment li , the center point of (1≤i≤k) is denoted as C i , whose coordinates are At the same time, the coordinates of the first and last endpoints of this line segment are marked as and The slope is denoted by p i , the calculation formula is:

[0010]

[0011] (2) Cluster the line segments according to the position and direction information of the center points of the line segments;

[0012] (2.1) Among the extracted line segments, K-means method is used for clustering;

[0013] (2.2) Clustering is performed based on the coordinates of the center point of the line segment and the slope of the line segment.

[0014] (3) Calculate the degree of disorder within each line segment class and determine the line segment class to which the main stem of the plant seedling stage belongs based on this.

[0015] (3.1) For the K types of line segments obtained by clustering, their chaos degree is calculated respectively. The chaos degree is calculated as follows: the sum of the mean square error of the XY axis is used to calculate the distribution size of the area where such line segments exist. The chaos degree is the area size divided by the number of such line segments existing in the area.

[0016] (3.2) Determine the line segment category to which the main stem of the plant at the seedling stage belongs.

[0017] A computer storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned method for detecting the main stem of a plant at the seedling stage in a phenotypic imaging box environment.

[0018] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for detecting the main stem of a plant at the seedling stage in a phenotypic imaging box environment is implemented.

[0019] Beneficial effects: Compared with the prior art, the present invention has the following advantages:

[0020] 1. Aiming at the need of collecting line information by video monitoring system in intelligent plant phenotyping system, the invention uses computer vision, image processing, pattern recognition and related technologies to exclude detection line segments generated in the background according to the strong correlation of position and direction of the detection line segment set to which the main stem of the plant seedling in the image belongs. The invention has the advantages of high accuracy, strong robustness and fewer constraints.

[0021] 2. As the inherent arrangement characteristics of the main stem detection line segments of the plant seedling stage are utilized, it has good adaptability to the shooting angle, and it is not necessary to require the main stem road target of the plant seedling stage to occupy a prominent position and a large proportion in the image, so it is very suitable for use in the plant phenotyping system;

[0022] 3. The present invention uses image processing and data analysis technologies such as LSD-based straight line segment detection technology and K-means-based line segment clustering technology to achieve automatic extraction of straight line segments in captured images and selection of main stem line segments in the plant seedling stage, ultimately providing a new data collection and environmental perception method for the intelligent plant phenotyping system. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0024] The technical solution of the present invention is further described below in conjunction with the accompanying drawings.

[0025] In order to better understand the method proposed in the present invention, a picture of a plant seedling taken by a monitoring camera in a phenotypic imaging box is selected as a test picture. The resolution of the picture is 4288*2848, and the main stem of the plant is visible in the picture.

[0026] like Figure 1 As shown, the plant main stem detection method based on line segment clustering specifically includes the following steps:

[0027] S1. Detect line segments using the LSD method.

[0028] S1.1. Read the surveillance scene images captured by the surveillance camera into the computer and perform some basic image preprocessing on the input source images.

[0029] In this embodiment, initially, it is necessary to use the function in OpenCV (Intel open source computer vision library) to read the image, and read the monitoring scene image captured by the monitoring camera into the computer.

[0030] The preprocessing includes converting a color image into a grayscale image, removing image noise (for example, using a Gaussian filter to remove noise from the image), and the like.

[0031] S1.2. For the preprocessed image, detect the plant main stem line segments and record the line segment information.

[0032] In this embodiment, the LSD (Line Segment Detection) method published in PAMI 2010 is used to ensure that the line segment detection with sub-pixel accuracy is obtained in linear time. Due to the interference of side branches, the number of detected line segments is relatively large.

[0033] In this embodiment, the length of each line segment is calculated, and the first 50% of the line segments are selected to form a set of candidate plant main stem line segments, which is represented by L = {l1, ..., l m}, m is the total number of detected straight lines. Line segment l i , the center point of (1≤i≤k) is denoted as C i , whose coordinates are At the same time, the coordinates of the first and last endpoints of this line segment are marked as and The slope is denoted by p i , the calculation formula is:

[0034]

[0035] S2. Cluster the line segments according to the position and direction information of the center points of the line segments.

[0036] S2.1. Among the extracted line segments, K-means method is used for clustering.

[0037] S2.2. Clustering is performed based on the center point coordinates and line segment slopes of the line segments.

[0038] The two types of information need to be weighted during use. In this embodiment, the weight of the center point coordinates is set to 0.005, and the weight of the line segment slope is set to 200.

[0039] S3. Evaluate the chaos of each line segment class, and the class with small chaos is marked as the plant main stem line segment class.

[0040] S3.1. Calculate the chaos degree of each line segment class. The formula is as follows:

[0041] Clutter i =std x +std y / n i

[0042] Clutter i is the chaos degree of the i-th line segment class. std x and std y is the mean square error of the coordinates of the center points of each line segment in the i-th line segment class in the X and Y axis directions, n i is the number of line segments in the line segment class. When the mean square error is larger and the number of line segments is smaller, it means that the line segments in the line segment class are more dispersed, and the value of the chaos degree is larger, which is also called more chaotic.

[0043] S3.2, setting a threshold, and selecting a line segment class smaller than the threshold as a plant main stem line segment class according to the disorder degree of each line segment class. In the embodiment of the present invention, the threshold is set to 0.06.

[0044] S3.3. In the K-means algorithm, count the distances between each line segment in each plant main stem line segment class and the class center point. Take the first 50% as the plant main stem detection line segments and present them on the image.

Claims

1. A method for detecting the main stem of a plant at the seedling stage in a phenotypic imaging chamber environment, characterized in that: The following steps are involved: (1) Detect line segments using the LSD method; (2) Cluster the line segments according to the position and direction information of the center points of the line segments; (3) Calculate the degree of chaos within each line segment class and determine the line segment class to which the main stem of the plant seedling stage belongs based on this. The method for calculating the degree of chaos is: the sum of the mean square deviations of the coordinates of the center points of each line segment in the line segment class in the X and Y axis directions divided by the number of line segments in the line segment class; determine the line segment class of the main stem of the plant based on the degree of chaos of each line segment class.

2. The method for detecting the main stem of a plant at the seedling stage in a phenotypic imaging box environment according to claim 1, characterized in that: The step (1) is specifically: (1.1) Read the surveillance scene images captured by the surveillance camera into the computer and perform some basic image preprocessing on the input source images; (1.2) Use the LSD method to detect straight lines in the image and form a set of candidate line segments, represented by L = {l1,…,l m }, m is the total number of detected straight lines, line segment l i , the center point of (1≤i≤k) is denoted as C i , whose coordinates are At the same time, the coordinates of the first and last endpoints of this line segment are marked as and The slope is denoted by p i , the calculation formula is:

3. The method for detecting the main stem of a plant at the seedling stage in a phenotypic imaging box environment according to claim 1, characterized in that: The step (2) is specifically: (2.1) Among the extracted line segments, K-means method is used for clustering; (2.2) Clustering is performed based on the coordinates of the center point of the line segment and the slope of the line segment.

4. A computer memory having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a main stem detection method for plants at the seedling stage in a phenotypic imaging chamber environment as described in any one of claims 1 to 3 is implemented.

5. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, a method for detecting the main stem of a plant at the seedling stage in a phenotypic imaging box environment is implemented as described in any one of claims 1-3.

Images