CN113610965B - Plant chlorophyll content three-dimensional space stereoscopic distribution visualization method based on point cloud - Google Patents
Plant chlorophyll content three-dimensional space stereoscopic distribution visualization method based on point cloud Download PDFInfo
- Publication number
- CN113610965B CN113610965B CN202110921475.4A CN202110921475A CN113610965B CN 113610965 B CN113610965 B CN 113610965B CN 202110921475 A CN202110921475 A CN 202110921475A CN 113610965 B CN113610965 B CN 113610965B
- Authority
- CN
- China
- Prior art keywords
- color
- chlorophyll content
- plant
- channel
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three-dimensional [3D] modelling for computer graphics
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—Three-dimensional [3D] image rendering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a visualization method for three-dimensional spatial distribution of plant chlorophyll content based on point cloud, which comprises the following steps: collecting color image data of plant leaves; detecting the chlorophyll content of the collected plant leaves by a chlorophyll content measuring instrument; extracting color factors from color image data of plant leaves; performing correlation analysis on the chlorophyll content detected by the chlorophyll content measuring instrument and the extracted color factors, and establishing an optimal regression model of the chlorophyll content; and applying the optimal regression model of the chlorophyll content to the reconstructed plant three-dimensional model to obtain chlorophyll content values corresponding to all points, and realizing three-dimensional spatial distribution visualization of the chlorophyll content of the plant after pseudo-color treatment. The method solves the problem that the chlorophyll content cannot be measured in a large scale, rapidly, accurately and nondestructively in the existing plant phenotype information extraction, and realizes the visualization of the three-dimensional spatial distribution of the plant chlorophyll content so as to visually observe the distribution situation of the plant chlorophyll content.
Description
Technical Field
The invention relates to the field of image analysis, in particular to a method for visualizing three-dimensional spatial distribution of plant chlorophyll content based on point cloud.
Background
When plants are subjected to physiological and biochemical parameter analysis, a mathematical estimation model is established by collecting plant images through a computer vision technology and analyzing color information in image data and parameters detected by a physiological and biochemical content measuring instrument. The method for acquiring the two-dimensional image by using the visible light camera has the advantages of low cost and easy acquisition, and is a more common method in the field of computer vision. The two-dimensional plant image can only carry out single-side imaging analysis of plants, however, the plants have complex spatial morphological structures, obvious morphological structures and physiological and biochemical changes exist in the growth process, and the topological structures are generally complex. Accurate measurement values are difficult to obtain only from two-dimensional image analysis, and complete morphological structure information of plants, such as leaf areas of curved leaves of plants, organ parameters blocked by partial branches and leaves, and the like, cannot be obtained. By establishing a three-dimensional space three-dimensional model of the plant, the color information of each organ of the plant is accurately analyzed, the method can be used for searching the change rule of the physiological and biochemical parameters of each organ of the plant in the whole plant growth cycle process, and has important values for plant fertilization management, phenotype monitoring and pest identification research.
Chlorophyll plays an important role in the absorption and utilization of light energy when plants perform photosynthesis. The distribution of chlorophyll content in plants can be used as the basis of whether the plants lack nutrition or are affected by the environment. The chlorophyll content of the plant has correlation with the nitrogen content, and can be used as an important index for the accurate management of the nitrogen fertilizer of the plant. The chlorophyll content is used for guiding the plant to fertilize, so that not only can the fertilizer waste be effectively reduced, but also excessive fertilization can be avoided. However, the traditional chlorophyll content measurement can only be carried out on plants in a specific time or growth stage, and some plants are separated from the leaves by breaking, picking, cutting and other modes to carry out destructive measurement, so that the workload is large, the efficiency is low, and the measurement can only be carried out on single points on single leaves.
Disclosure of Invention
The invention aims to solve the technical problem of providing a visualization method for three-dimensional spatial distribution of plant chlorophyll content based on point cloud aiming at the defects of the prior art, and the visualization method for three-dimensional spatial distribution of plant chlorophyll content based on point cloud solves the problem that the current plant phenotype information extraction cannot measure chlorophyll content in a large scale, quickly, accurately and nondestructively, and realizes visualization of three-dimensional spatial distribution of plant chlorophyll content so as to observe plant chlorophyll content distribution condition in a visual way.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
a visualization method of three-dimensional spatial distribution of plant chlorophyll content based on point cloud comprises the following steps:
S1, calibrating color information parameters of a visible light camera and collecting color image data of plant leaves;
s2, detecting the chlorophyll content of the collected plant leaves through a chlorophyll content measuring instrument;
s3, processing the collected color image data of the plant leaves, and extracting color factors;
S4, carrying out correlation analysis on the chlorophyll content detected by the chlorophyll content measuring instrument and the color factors extracted after the treatment, and establishing an optimal regression model of the chlorophyll content;
S5, collecting color image data of the plants under multiple visual angles;
s6, extracting characteristic point information in the plant color image acquired under multiple viewing angles by using a scale and rotation invariance algorithm;
S7, carrying out proximity search on the characteristic points in each plant color image in the S6 to carry out characteristic point matching;
s8, obtaining a plant three-dimensional model with color information through a motion restoration structure algorithm;
And S9, applying the optimal regression model of the chlorophyll content established in the step S4 to the plant three-dimensional model reconstructed in the step S8 to obtain chlorophyll content values corresponding to all points, and realizing three-dimensional spatial distribution visualization of the chlorophyll content of the plant after pseudo-color treatment.
As a further improved technical scheme of the invention, the calibration of the color information parameters of the visible light camera in the step S1 specifically comprises the following steps:
s11, firstly, collecting images of red, green and blue three primary color cards through a visible light camera, wherein the RGB color channel values of the red color card are respectively (255, 0), the RGB color channel values of the green color card are respectively (0, 255, 0), and the RGB color channel values of the blue color card are respectively (0, 255);
S12, extracting an R channel from a red color card image, extracting a G channel from a green color card image, extracting a B channel from a blue color card image, calculating the value of an average pixel point under the R channel, marking as Y_r, calculating the value of an average pixel point under the G channel, marking as Y_g, and calculating the value of an average pixel point under the B channel, marking as Y_b, wherein the value calculation formula of the average pixel point is as follows:
Wherein Y_x is the value of the average pixel point under the x channel, and f x (i, j) is the value of the row j column under the x channel;
s13, calculating the value and the theoretical value of the average pixel point under each channel obtained in the step S12 to obtain a color correction proportionality coefficient Z_r under the R channel, a color correction proportionality coefficient Z_g under the G channel and a color correction proportionality coefficient Z_b under the B channel, wherein the calculation function of the color correction proportionality coefficients is as follows:
wherein Z_x is a color correction proportionality coefficient under the x channel, and Y_x is a value of an average pixel point under the x channel;
s14, applying the color correction proportionality coefficients under each channel obtained in the step S13 to all color images acquired by a visible light camera, thereby realizing color correction.
As a further improved technical scheme of the invention, in the step S2, the chlorophyll content of the plant leaf detected and collected by the chlorophyll content measuring apparatus is specifically:
s21, calibrating a chlorophyll content measuring instrument;
S22, measuring the chlorophyll content of three different positions on the collected single plant leaf, and taking the average value of the chlorophyll content of the three different positions as the chlorophyll content of the plant leaf.
As a further improved technical solution of the present invention, the step S3 specifically includes:
S31, firstly, converting the collected plant leaf color image into a gray image;
S32, carrying out binarization processing on the converted gray level image to realize segmentation between the plant leaves and the background;
S33, if a certain noise point exists in the plant leaf image subjected to the binarization treatment, carrying out image noise reduction treatment;
S34, performing mask processing on the image acquired in the step S1 and the binary image subjected to noise reduction in the step S33 through an image mask algorithm, wherein the mask processing refers to: taking a white pixel region in the binary image after the noise reduction treatment in the step S33 as a region of interest (ROI), performing bit operation on the region of interest (ROI) and the image acquired in the step S1, and obtaining an image value of the region still being the own value after the bit operation, wherein the image values of other regions become 0, so that the plant leaf part in the image is completely separated from the background;
S35, converting the plant leaf image processed by the mask in the step S34 into different color spaces, wherein the different color spaces comprise RGB color spaces, la x b color spaces and HSV color spaces, and extracting color factors from the different color spaces, and the color factors comprise R, G, B, H, S, V, L, a, b; calculating the number of pixels occupied by the plant leaves and the sum of color factors under a single channel, and dividing the sum of the color factors under the single channel by the number of pixels occupied by the plant leaves to obtain the numerical value of the color factors of the plant leaves under the channel;
Wherein F x (i, j) is the value of the row i and the column j under the x channel, S is the calculated number of pixels occupied by the plant leaf, and F x is the value of the color factor of the plant leaf under the x channel; the x-channel refers to R, G, B color factors in the RGB color space, H, S, V color factors in the HSV color space, or L, a, b color factors in the La x b color space, respectively;
calculating a color factor combination value comprising G2；
S36, normalizing the values of the color factors and the color factor combination values obtained in the step S35, and converting the values in the original value intervals [0, 255] into the range [0,1] intervals.
As a further improved technical solution of the present invention, the step S4 specifically includes:
And (3) establishing linear and nonlinear polynomial regression models of the color factors extracted by different channels in different color spaces obtained in the step (S3) and the combined values of the color factors and the chlorophyll content values of the plant leaves detected by the chlorophyll content measuring instrument in the step (S2), and selecting a model with the best fitting performance as an optimal regression model of the chlorophyll content by utilizing various model evaluation indexes.
As a further improved technical solution of the present invention, the step S5 specifically includes:
The visible light camera is fixed, plants are placed on a tray to rotate, or the plants are fixed, the visible light camera is placed on a platform to rotate by taking the plants as the center, image acquisition is carried out on each plant at intervals of 18 degrees as rotation angles, and color image data of 20 plants are acquired on one circumference.
As a further improved technical solution of the present invention, the step S9 specifically includes:
A91, applying the optimal regression model of chlorophyll content in the step S4 to the color information after normalization processing of the plant three-dimensional model reconstructed in the step S8, so that the color information after normalization processing of the three-dimensional model is converted into an estimated value of chlorophyll content;
A92, stretching the distribution range of the chlorophyll content estimated value in the step A91 to be 0, 100, and obtaining the full gray value interval distribution condition of the chlorophyll content of the plant;
and A93, performing pseudo-color treatment on the three-dimensional plant model processed in the step A92, so that the chlorophyll content of the plant shows a visual effect according to spatial distribution.
The beneficial effects of the invention are as follows:
The method for visualizing the three-dimensional distribution of the chlorophyll content of the plant based on the point cloud comprises the steps of establishing a regression model between the chlorophyll content and the plant color factors and reconstructing the three-dimensional model of the plant, applying the regression model to the point cloud and performing pseudo-color treatment, so that the visualization of the three-dimensional distribution of the chlorophyll content of the plant is realized, the problem that the chlorophyll content cannot be measured in a large scale, quickly, accurately and nondestructively in the extraction of the phenotype information of the plant at present is solved, the visualization of the three-dimensional distribution of the chlorophyll content of the plant is realized, and the visual observation of the distribution situation of the chlorophyll content of the plant is facilitated, and the method can be used as a guiding basis for growth monitoring, yield estimation, accurate fertilization management and aging degree judgment of the plant; the chlorophyll content of the plant can be measured at any time, and the chlorophyll content of any point of the plant leaf can be measured and visualized.
Drawings
Fig. 1 is a schematic flow chart of a visualization method of three-dimensional spatial distribution of chlorophyll content in plants based on point clouds.
Fig. 2 is a schematic diagram of a plant leaf image processing flow in the visualization method of three-dimensional spatial distribution of plant chlorophyll content based on point cloud.
Fig. 3 is a schematic diagram of a chlorophyll content space visualization process flow in the point cloud-based plant chlorophyll content three-dimensional spatial distribution visualization method.
Fig. 4 (a) is a schematic diagram of an arabidopsis three-dimensional point cloud model in an application example of the visualization of chlorophyll content space in the visualization method based on three-dimensional spatial distribution of chlorophyll content in a plant.
Fig. 4 (b) is a schematic view of visualization of the spatial distribution of chlorophyll content in arabidopsis in an application example of the spatial visualization of chlorophyll content in the method for visualizing three-dimensional spatial distribution of chlorophyll content in plants based on point clouds.
Fig. 4 (c) is a schematic diagram of a three-dimensional point cloud model of osmanthus tree leaves in an application example of the visualization method for three-dimensional spatial distribution of chlorophyll content in plants based on point clouds.
Fig. 4 (d) is a schematic diagram of the visualization of the spatial distribution of chlorophyll content in osmanthus fragrans leaves in the application example of the spatial visualization of chlorophyll content in the method for visualizing three-dimensional spatial distribution of chlorophyll content in plants based on point clouds.
Fig. 5 (a) is a gray scale view of fig. 4 (a).
Fig. 5 (b) is a gray scale view of fig. 4 (b).
Fig. 5 (c) is a gray scale view of fig. 4 (c).
Fig. 5 (d) is a gray scale image of fig. 4 (d).
Detailed Description
The following is a further description of embodiments of the invention, with reference to the accompanying drawings:
As shown in fig. 1, a flow chart is provided for an embodiment of a method for visualizing three-dimensional spatial distribution of chlorophyll content in a plant based on point cloud, and the image analysis method includes:
S1, calibrating color information parameters of a visible light camera and collecting color image data of plant leaves.
S2, detecting the chlorophyll content of the collected plant leaves through a chlorophyll content measuring instrument.
S3, inputting the collected color image data of the plant leaves into an image processing program, and processing the plant leaf images to extract image color factors, wherein the image color factors comprise R, G, B, G x G,H. s, V, L, a, b, wherein R, G, B, H, S, V, L, a, b is a single channel color factor, G,The color factors after being combined may also be referred to as color factor combination.
S4, establishing a regression model of the chlorophyll content of the plant leaves detected by the chlorophyll content measuring instrument and the color factors extracted after the treatment.
S5, rotary shooting (a visible light camera is fixed, plants are placed on a tray to rotate or the plants are fixed, the visible light camera is placed on a platform to rotate by taking the plants as the center), color image data of the plants under multiple visual angles are collected, image collection is carried out at intervals of 18 degrees by taking the rotation angles as rotation angles, and color image data of 20 plants are collected on one circumference.
And S6, extracting characteristic point information in the plant color image acquired under multiple viewing angles by using a Scale-INVARIANT FEATURE TRANSFORM (SIFT) algorithm.
And S7, carrying out adjacent search on the characteristic points in each plant color image in the step S6 to carry out characteristic point matching.
And S8, obtaining a plant three-dimensional model with color information through a motion restoration structure algorithm (Structure from motion, SFM).
And S9, applying the regression model established in the step S4 to the plant three-dimensional model reconstructed in the step S8, obtaining chlorophyll content values corresponding to all points, stretching the chlorophyll content values to the interval range of [0, 255], and realizing three-dimensional spatial distribution visualization of the chlorophyll content of the plant after pseudo-color treatment.
The color image data of the plant leaves in the step S1 are collected through a visible light camera, the conditions such as light environment, visible light camera position and the like are consistent, the color parameters of the visible light camera are calibrated before collection, and the color parameters of the visible light camera are calibrated, and the method comprises the following steps:
S11, firstly, images of three primary colors of red, green and blue are collected through a visible light camera, wherein RGB color channel values of the three color cards of red, green and blue are respectively (255, 0), (0, 255, 0) and (0, 255).
S12, extracting an R channel from the acquired red color card image, extracting a G channel from the acquired green color card image, extracting a B channel from the acquired blue color card image, calculating the value Y_r of an average pixel point under the R channel, calculating the value Y_g of the average pixel point under the G channel, and calculating the value Y_b of the average pixel point under the B channel, wherein the calculation formula of the average pixel point is as follows:
wherein y_x is the value of the average pixel point under the x channel, and f x (i, j) is the value of the row j column under the x channel.
S13, calculating the value and the theoretical value of the average pixel point under each channel obtained in the S12 to obtain a color correction proportionality coefficient Z_r under the R channel, a color correction proportionality coefficient Z_g under the G channel and a color correction proportionality coefficient Z_b under the B channel, wherein the calculation function of the color correction proportionality coefficients is as follows:
wherein Z_x is the color correction scaling factor under the x channel, and Y_x is the value of the average pixel under the x channel.
S14 applies the respective channel color correction scaling coefficients obtained in S13 described above to all color images after that for color correction.
When the chlorophyll content measuring apparatus in step S2 is used for collecting, firstly, the measuring apparatus is calibrated, after the calibration is completed, the plant leaf (avoiding the veins) is inserted and the measuring probe is closed, three different positions are found on the plant leaf, the operation is repeated, and the average value of the three measured values is taken as the chlorophyll content of the leaf collected in step S1.
As shown in fig. 2, the image processing algorithm for processing the plant leaf image in step S3 to extract the image color factor includes the steps of:
s31 first converts the plant leaf color image into a gray image, the conversion function is as follows:
Wherein I is a gray value, and f x (I, j) is a value of I rows and j columns under the x channel.
S32, carrying out binarization processing on the gray level image converted in the step S31, and realizing segmentation between the plant leaves and the background.
If the plant leaf image after the thresholding in S32 has a certain noise, the image noise reduction processing is performed by setting an open operation algorithm in the image morphology and setting a proper convolution kernel, and the open operation function is as follows:
Wherein A is an image set, B is a convolution kernel, D is expansion operation, and E is corrosion operation.
S34, performing mask processing on the image in S1 and the binary image after the S33 noise reduction processing through an image mask algorithm, wherein the mask processing refers to performing bit operation on a white pixel area in the binary image after the S33 processing as an interested area ROI (Re gion of Interest) and the image in S1, and when the numerical value in the image of S1 and the interested area are subjected to bit operation, the obtained numerical value still is the numerical value of the other part, and the numerical value of the other part becomes 0, so that the plant leaf part in the image is completely separated from the background.
S35 converts the plant leaf image after the mask processing in S34 to a different color space including RGB (Red, green, blue) color space, la (Lab color space) color space, HSV (Hue, satura tion, value) color space, and combinations thereof, as shown in table 1. And calculating the sum of the number of pixels occupied by the plant leaf and the color factors under a single channel, wherein the sum of the color factors under the single channel is divided by the number of pixels occupied by the plant leaf to be used as the numerical value of the color factors of the plant leaf under the channel.
Wherein F x (i, j) is the value of the row j column under the x channel, S is the calculated number of pixels occupied by the plant leaf, F x is the value of the color factor under the x channel, and the x channel refers to the R, G, B color factor in the RGB color space, the H, S, V color factor in the HSV color space and the L, a and b in the La x b x color space respectively.
The R, G, B three color factors are combined and calculated, and the color components which can reflect the green degree are considered to be converted into another 4 common color factors (namelyG2，G 2 is a combined color factor, which may also be referred to as a color factor combination).
Table 1:
S36, normalizing the values of the color factors and the color factor combination values obtained in the S35, and converting the values in the original value interval [0, 255] into the range [0,1] interval.
In the step S4, the color factors and the color factor combinations extracted by different channels in different color spaces obtained in the step S3 are subjected to linear and nonlinear polynomial regression model establishment with the chlorophyll content values of the plant leaves detected by the chlorophyll content measuring instrument in the step S2; specifically, a single or a plurality of color factors are randomly selected from all the color factors in table 1, and correlation analysis is carried out on the color factors and chlorophyll content values of plant leaves detected by a chlorophyll content measuring instrument, so that a linear and nonlinear polynomial regression model is established. And selecting a model with the best fitting performance as an optimal regression model by utilizing various model evaluation indexes. The multiple model evaluation indexes comprise Root Mean Square Error (RMSE) and a decision coefficient R 2.
The above formula is a unified expression of the regression model, wherein Y is chlorophyll content obtained by the regression model, X 1、X2…Xn is color factors and color factor combinations of each channel in n different color spaces, namely n color factors in table 1, n is greater than or equal to 1 and less than or equal to 13, w 1、w2…wn is a weight coefficient, A 1、A2…An is a logarithmic base number, B is a bias coefficient, a, B and c … n are frequency terms, and the table 2 is a color factor regression model under different color spaces. The RMSE described in table 2 represents the average prediction error compared to the measured value, with lower values indicating higher accuracy. R 2 represents the model fitting effect, the percentage of the measurement variance explained by the algorithm model is the value range of [0,1], and the larger R 2 is, the better the model fitting effect is.
Wherein y real is a true value clamped by the handheld chlorophyll measuring instrument, and is a dimensionless unit; y pred is a value predicted by the multi-color factor correlation model, and is a dimensionless unit; m is data, and the unit is a group; y mean is the average value of all the multi-color factor correlation model predicted values, and is a dimensionless unit.
Table 2:
numbers 1-5 in table 2 are established linear regression models, 6-15 are established nonlinear regression models, from which it can be seen that the regression model 14 constructed with color factors lg (G), R, G, B, G/R, G/B and the regression model 15 constructed with color factors lg (G), R, G, B, G/(r+b) all have a determination coefficient R 2 as high as 0.73, but the model 14 incorporating G/R and G/B color factors has a smaller error (rmse=2.16 < 2.21), so that the regression model 14: y= -8.51 x lg (G) +11.68 x R-26.48 x g+18.30 x b+2.81 x G/r+3.85 x G/b+40 and SPAD values fit best, show the most significant regression, and are the best chlorophyll content fitting models. The G/R and G/B in the linear regression model prove that the ratio G/(R+B) color factor can better reflect the green degree of the plant leaves, and the effects of the quadratic regression model with the number of 7-10 and the logarithmic regression model with the number of 11-15 also prove that the G/R and the G/B can be separately adjusted as two parameters, so that the relative green degree of the plant leaves can be better fitted.
In step S5, the specific implementation of collecting the color image data of the plant under multiple viewing angles is that the visible light camera is fixed, the plant is placed on the tray to rotate or the plant is fixed, and the visible light camera is placed on the platform to rotate with the plant as the center. The precise control device circumferentially rotates, image acquisition is carried out on each plant at intervals of 18 degrees serving as a rotation angle, and color image data of 20 plants are acquired on one circumference.
In the step S6, the plant image feature detection uses a SIFT algorithm, the SIFT algorithm calculates the position information (x, y) of the feature points through Gaussian filters with different sizes, and meanwhile, descriptor information is provided, and in a grid histogram around the feature points, each histogram contains gradient directions, so that multidimensional feature vectors are obtained, and feature detection of the plant image is realized.
In step S7, the feature matching is performed, the nearest neighbor distance is set to d1 by the proximity search algorithm, the distance between the second nearest matching points is found to be d2, if the ratio of the two distances d1 and d2 is smaller than a threshold value, an acceptable matching pair can be determined, a sampling consistency algorithm (Random sample consensus, RANSC) is adopted to calculate a base matrix for the matching points, and the matching pair which does not meet the base matrix is removed. The principle function of feature point matching is as follows:
Where F d1 is a feature point, F d2 is another feature point on the image, F nn is a nearest neighbor feature vector, and F (J) is image J.
As shown in fig. 3, the three-dimensional spatial distribution visualization of chlorophyll content in S9 includes the steps of:
S91, applying the chlorophyll content regression model in the S4 to the normalized color information of the plant three-dimensional model reconstructed in the S8, so that the normalized color information of the three-dimensional model is converted into an estimated value of chlorophyll content.
S92, the estimated value range of chlorophyll content in the S91 is [0, 100], and the estimated value distribution range of chlorophyll content is stretched to [0, 255], so as to obtain the full gray value interval distribution condition of chlorophyll content of the plant.
S93, performing pseudo-color treatment on the three-dimensional plant model processed in the step S92, so that the chlorophyll content of the plant shows a visual effect according to spatial distribution.
r(i，j＝TR[f(i，j)]
g(i，j＝TG[f(i，j)]
b(i,j＝TB[f(i,j)]
Where r (i, j, g (i, j are the values of the three components red, green, and blue of the pseudo-color image, respectively), f (i, j are the gray levels of the original image, T R、TB、TG is the linear mapping relationship representing the gray levels and R, G, B three primary colors, respectively, where T R is the red that has a gray level lower than H max/2 and is mapped to the darkest, the gray level is between H max/2～3Hmax/4, the brightness of the red increases linearly with the gray level, the gray level is between 3H max/4～Hmax, the red remains unchanged at the brightest level, and T B、TC is the same as the above-described T R mapping relationship, where H max is the maximum gray value 255.
Fig. 4 is a schematic diagram of an application example (arabidopsis, osmanthus tree leaves) of the visualization of chlorophyll content space in the visualization method based on three-dimensional spatial distribution of chlorophyll content in plants. In fig. 4, (a) is a schematic diagram of an arabidopsis three-dimensional point cloud model constructed according to steps S5-S8. Fig. 4 (b) is a schematic view showing the spatial distribution of chlorophyll content in arabidopsis thaliana established in accordance with step S9. Fig. 4 (c) is a schematic diagram of a three-dimensional point cloud model of osmanthus tree leaves constructed according to steps S5-S8.
Fig. 4 (d) is a schematic view of the spatial distribution of chlorophyll content in leaves of osmanthus tree according to the step S9. Fig. 5 is a gray scale of fig. 4.
According to the invention, the plant leaf image is processed, the color factors and the combinations thereof of the plant leaf are extracted, a regression model between the color factors and the combinations thereof of the plant leaf and the chlorophyll content obtained by the chlorophyll content measuring instrument is established, the regression model is applied to a plant three-dimensional model, the chlorophyll content of all point clouds is obtained, and after normalization and pseudo-color treatment are carried out, the spatial vivid distribution of the chlorophyll content of the plant is obtained. The chlorophyll content of the whole plant is displayed on the three-dimensional structure of the plant in different colors, and the change can be seen before the change is seen by naked eyes, and quantitative analysis is performed.
The visualization method of the three-dimensional spatial distribution of the chlorophyll content of the plant based on the point cloud provides guiding basis for growth monitoring, yield estimation, accurate fertilization management and aging degree judgment of the plant, and has very important significance.
The scope of the present invention includes, but is not limited to, the above embodiments, and any alterations, modifications, and improvements made by those skilled in the art are intended to fall within the scope of the invention.
Claims (4)
1. The visualization method for three-dimensional spatial distribution of plant chlorophyll content based on point cloud is characterized by comprising the following steps of: the method comprises the following steps:
S1, calibrating color information parameters of a visible light camera and collecting color image data of plant leaves;
s2, detecting the chlorophyll content of the collected plant leaves through a chlorophyll content measuring instrument;
s3, processing the collected color image data of the plant leaves, and extracting color factors;
S4, carrying out correlation analysis on the chlorophyll content detected by the chlorophyll content measuring instrument and the color factors extracted after the treatment, and establishing an optimal regression model of the chlorophyll content;
S5, collecting color image data of the plants under multiple visual angles;
s6, extracting characteristic point information in the plant color image acquired under multiple viewing angles by using a scale and rotation invariance algorithm;
S7, carrying out proximity search on the characteristic points in each plant color image in the S6 to carry out characteristic point matching;
s8, obtaining a plant three-dimensional model with color information through a motion restoration structure algorithm;
s9, applying the optimal regression model of the chlorophyll content established in the S4 to the plant three-dimensional model reconstructed in the S8 to obtain corresponding chlorophyll content values of all points, and realizing three-dimensional spatial distribution visualization of the chlorophyll content of the plant after pseudo-color treatment;
the step S1 of calibrating the color information parameters of the visible light camera specifically comprises the following steps:
s11, firstly, collecting images of red, green and blue three primary color cards through a visible light camera, wherein the RGB color channel values of the red color card are respectively (255, 0), the RGB color channel values of the green color card are respectively (0, 255, 0), and the RGB color channel values of the blue color card are respectively (0, 255);
S12, extracting an R channel from a red color card image, extracting a G channel from a green color card image, extracting a B channel from a blue color card image, calculating the value of an average pixel point under the R channel, marking as Y_r, calculating the value of an average pixel point under the G channel, marking as Y_g, and calculating the value of an average pixel point under the B channel, marking as Y_b, wherein the value calculation formula of the average pixel point is as follows:
Wherein Y_x is the value of the average pixel point under the x channel, and f x (i, j) is the value of the row j column under the x channel;
s13, calculating the value and the theoretical value of the average pixel point under each channel obtained in the step S12 to obtain a color correction proportionality coefficient Z_r under the R channel, a color correction proportionality coefficient Z_g under the G channel and a color correction proportionality coefficient Z_b under the B channel, wherein the calculation function of the color correction proportionality coefficients is as follows:
wherein Z_x is a color correction proportionality coefficient under the x channel, and Y_x is a value of an average pixel point under the x channel;
s14, applying the color correction proportionality coefficients under each channel obtained in the step S13 to all color images acquired by a visible light camera so as to realize color correction;
In the step S2, the chlorophyll content of the plant leaf detected and collected by a chlorophyll content measuring instrument is specifically as follows:
s21, calibrating a chlorophyll content measuring instrument;
S22, measuring the chlorophyll content of three different positions on the collected single plant leaf, and taking the average value of the chlorophyll content of the three different positions as the chlorophyll content of the plant leaf;
The step S3 specifically includes:
S31, firstly, converting the collected plant leaf color image into a gray image;
S32, carrying out binarization processing on the converted gray level image to realize segmentation between the plant leaves and the background;
S33, if a certain noise point exists in the plant leaf image subjected to the binarization treatment, carrying out image noise reduction treatment;
S34, performing mask processing on the image acquired in the step S1 and the binary image subjected to noise reduction in the step S33 through an image mask algorithm, wherein the mask processing refers to: taking a white pixel region in the binary image after the noise reduction treatment in the step S33 as a region of interest (ROI), performing bit operation on the region of interest (ROI) and the image acquired in the step S1, and obtaining an image value of the region still being the own value after the bit operation, wherein the image values of other regions become 0, so that the plant leaf part in the image is completely separated from the background;
S35, converting the plant leaf image processed by the mask in the step S34 into different color spaces, wherein the different color spaces comprise RGB color spaces, la x b color spaces and HSV color spaces, and extracting color factors from the different color spaces, and the color factors comprise R, G, B, H, S, V, L, a, b; calculating the number of pixels occupied by the plant leaves and the sum of color factors under a single channel, and dividing the sum of the color factors under the single channel by the number of pixels occupied by the plant leaves to obtain the numerical value of the color factors of the plant leaves under the channel;
Wherein F x (i, j) is the value of the row i and the column j under the x channel, S is the calculated number of pixels occupied by the plant leaf, and F x is the value of the color factor of the plant leaf under the x channel; the x-channel refers to R, G, B color factors in the RGB color space, H, S, V color factors in the HSV color space, or L, a, b color factors in the La x b color space, respectively;
calculating a color factor combination value comprising G2；
S36, normalizing the values of the color factors and the color factor combination values obtained in the step S35, and converting the values in the original value intervals [0, 255] into the range [0,1] intervals.
2. The method for visualizing the three-dimensional spatial distribution of chlorophyll content in a plant based on point clouds as set forth in claim 1, wherein: the step S4 specifically includes:
And (3) establishing linear and nonlinear polynomial regression models of the color factors extracted by different channels in different color spaces obtained in the step (S3) and the combined values of the color factors and the chlorophyll content values of the plant leaves detected by the chlorophyll content measuring instrument in the step (S2), and selecting a model with the best fitting performance as an optimal regression model of the chlorophyll content by utilizing various model evaluation indexes.
3. The method for visualizing the three-dimensional spatial distribution of chlorophyll content in a plant based on point clouds as set forth in claim 1, wherein: the step S5 specifically includes:
The visible light camera is fixed, plants are placed on a tray to rotate, or the plants are fixed, the visible light camera is placed on a platform to rotate by taking the plants as the center, image acquisition is carried out on each plant at intervals of 18 degrees as rotation angles, and color image data of 20 plants are acquired on one circumference.
4. The method for visualizing the three-dimensional spatial distribution of chlorophyll content in a plant based on point clouds as set forth in claim 1, wherein: the step S9 specifically includes:
A91, applying the optimal regression model of chlorophyll content in the step S4 to the color information after normalization processing of the plant three-dimensional model reconstructed in the step S8, so that the color information after normalization processing of the three-dimensional model is converted into an estimated value of chlorophyll content;
A92, stretching the distribution range of the chlorophyll content estimated value in the step A91 to be 0, 100, and obtaining the full gray value interval distribution condition of the chlorophyll content of the plant;
and A93, performing pseudo-color treatment on the three-dimensional plant model processed in the step A92, so that the chlorophyll content of the plant shows a visual effect according to spatial distribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110921475.4A CN113610965B (en) | 2021-08-11 | 2021-08-11 | Plant chlorophyll content three-dimensional space stereoscopic distribution visualization method based on point cloud |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110921475.4A CN113610965B (en) | 2021-08-11 | 2021-08-11 | Plant chlorophyll content three-dimensional space stereoscopic distribution visualization method based on point cloud |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113610965A CN113610965A (en) | 2021-11-05 |
| CN113610965B true CN113610965B (en) | 2024-09-24 |
Family
ID=78308282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110921475.4A Active CN113610965B (en) | 2021-08-11 | 2021-08-11 | Plant chlorophyll content three-dimensional space stereoscopic distribution visualization method based on point cloud |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610965B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114544576A (en) * | 2022-02-28 | 2022-05-27 | 广东弘科农业机械研究开发有限公司 | Device and method for monitoring plant photosynthetic physiological information in real time based on fluorescence spectrum |
| CN115914311A (en) * | 2022-12-14 | 2023-04-04 | 宁夏农林科学院农作物研究所（宁夏回族自治区农作物育种中心） | A crop growth information detection system |
| CN116183519A (en) * | 2022-12-29 | 2023-05-30 | 华南师大(清远)科技创新研究院有限公司 | Test method, device and medium for plant stress resistance physiological parameters |
| CN116429703A (en) * | 2023-02-23 | 2023-07-14 | 陕西理工大学 | A kind of tea pigment type and content detection method of tea and tea products |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108680513A (en) * | 2018-06-12 | 2018-10-19 | 山东省林业科学研究院 | Plant chlorophyll assay method and extraction element |
| CN111551530A (en) * | 2020-04-23 | 2020-08-18 | 江苏大学 | Method and device for acquiring three-dimensional distribution information of chlorophyll fluorescence of canopy of crop group |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10520482B2 (en) * | 2012-06-01 | 2019-12-31 | Agerpoint, Inc. | Systems and methods for monitoring agricultural products |
-
2021
- 2021-08-11 CN CN202110921475.4A patent/CN113610965B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108680513A (en) * | 2018-06-12 | 2018-10-19 | 山东省林业科学研究院 | Plant chlorophyll assay method and extraction element |
| CN111551530A (en) * | 2020-04-23 | 2020-08-18 | 江苏大学 | Method and device for acquiring three-dimensional distribution information of chlorophyll fluorescence of canopy of crop group |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113610965A (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113610965B (en) | Plant chlorophyll content three-dimensional space stereoscopic distribution visualization method based on point cloud | |
| Shu et al. | Improving the estimation accuracy of SPAD values for maize leaves by removing UAV hyperspectral image backgrounds | |
| CN105021529B (en) | Fusion spectrum and the crop disease and insect of image information identify and distinguish between method | |
| CN109522929A (en) | It is a kind of based on multi-source image fusion natural environment under wheat weeds recognition methods | |
| CN108520127A (en) | A Hyperspectral Inversion Method for Tree Species Leaf Area Index | |
| CN113421301B (en) | Method and system for positioning central area of field crop | |
| CN112949607A (en) | Wetland vegetation feature optimization and fusion method based on JM Relief F | |
| CN113570538B (en) | Blade RGB image bias distribution parameter information acquisition and analysis method | |
| CN109827957A (en) | A kind of rice leaf SPAD value estimating and measuring method based on computer vision and system | |
| He et al. | A calculation method of phenotypic traits of soybean pods based on image processing technology | |
| CN113607734B (en) | Visualization method for nondestructively estimating chlorophyll content and chlorophyll distribution of plant | |
| Sun et al. | Monitoring drought induced photosynthetic and fluorescent variations of potatoes by visible and thermal imaging analysis | |
| Huang et al. | Rapid mapping of soybean planting areas under complex crop structures: A modified GWCCI approach | |
| Akila et al. | Automation in plant growth monitoring using high-precision image classification and virtual height measurement techniques | |
| Ibaraki et al. | Image analysis for plants: basic procedures and techniques | |
| Cai et al. | Rapid measurement of potato canopy coverage and leaf area index inversion | |
| Wang et al. | Study on estimation method of plant leaf area based on image processing technology | |
| Pane et al. | Assessing Palm Plant Health through Color Analysis of Leaves Using MATLAB-Based Digital Image Processing | |
| Wang et al. | Maize plant drought stress phenotype testing method based on time-series images | |
| Yao et al. | Image-based plant nutrient status analysis: An overview | |
| JP2009014354A (en) | Image processor and image processing program | |
| Li et al. | Three-dimensional reconstruction and phenotypic identification of the wheat plant using RealSense D455 sensor | |
| Riheb et al. | Unveiling the potential of artificial intelligence in plant phenotyping and disease detection: A survey | |
| CN120388285B (en) | Traditional Chinese medicine sample acquisition and informatization processing method based on image machine learning | |
| Putra et al. | A Modified Watershed Algorithm for Rice Plant Growth Stage Analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |