CN112001910A - Method and device for automatically identifying number of plant ears, electronic equipment and storage medium - Google Patents
Method and device for automatically identifying number of plant ears, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112001910A CN112001910A CN202010870458.8A CN202010870458A CN112001910A CN 112001910 A CN112001910 A CN 112001910A CN 202010870458 A CN202010870458 A CN 202010870458A CN 112001910 A CN112001910 A CN 112001910A
- Authority
- CN
- China
- Prior art keywords
- view
- plant
- ear
- infrared imaging
- imaging side
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 210000005069 ears Anatomy 0.000 title claims abstract description 52
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 241000196324 Embryophyta Species 0.000 claims abstract description 142
- 238000003331 infrared imaging Methods 0.000 claims abstract description 107
- 238000012545 processing Methods 0.000 claims abstract description 51
- 241001024327 Oenanthe <Aves> Species 0.000 claims abstract description 16
- 230000009467 reduction Effects 0.000 claims abstract description 16
- 238000003384 imaging method Methods 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 17
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 241000209140 Triticum Species 0.000 abstract description 61
- 238000001931 thermography Methods 0.000 abstract description 35
- 235000021307 Triticum Nutrition 0.000 abstract description 24
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 13
- 241000495841 Oenanthe oenanthe Species 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000005259 measurement Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000209499 Lemna Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 230000009418 agronomic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of plant spike number detection, and particularly relates to a method and a device for automatically identifying the number of plant spikes, electronic equipment and a storage medium. The method comprises the following steps: extracting a contour map of the plant with the ear by utilizing the visible light side view of the plant with the ear; carrying out noise reduction pretreatment on the infrared imaging side view of the plant with the ear to generate a first-level infrared imaging side view; matching and fusing the contour map of the plant with the ear to a primary infrared imaging side view to generate a secondary infrared imaging side view; ear information is extracted through a deep processing secondary infrared imaging side view so as to identify the number of ears of plants. The method can automatically identify the number of the wheatears through the wheat thermal imaging graph, and improve the statistical efficiency, accuracy and reliability of the number of the wheatears.
Description
Technical Field
The invention relates to the technical field of detection of plant spike number, in particular to a method and a device for automatically identifying the plant spike number, electronic equipment and a storage medium.
Background
The ear density is one of the most important agronomic yield components of wheat, the quantity of the ear density directly reflects the growth condition and yield information of the wheat, and the ear density is also an important index for breeding and new variety identification. At present, the ear counting mainly adopts a manual counting method and a visible light imaging identification method, the manual counting method mainly depends on human eyes to observe and count, time and labor are wasted, the influence of the subjectivity of a statistic staff is large, a unified counting standard is lacked, and the overall objectivity and the accuracy are poor; the visible light imaging identification method is mainly based on RGB side view images of plants with ears, processing and analyzing are carried out by using an image processing algorithm, the number of the ears of the plants is identified, however, the ears of the wheat are inevitably shielded by leaves, errors of an analysis result often occur, and the reliability of experimental data is reduced.
Infrared thermal imaging is one of the commonly used imaging techniques, and can detect infrared power signals radiated by an object and convert the infrared power signals into electric signals, so as to obtain a thermal imaging image in an instrument. At present, the infrared thermal imaging technology is widely applied to a plurality of fields of agricultural production due to the high sensitivity of the infrared thermal imaging technology to temperature and the feasibility of on-line detection. However, due to the low resolution of infrared thermal imaging, the edge detection processing algorithm is not mature, which often results in inaccurate extraction of the target object and causes misjudgment of the wheatear.
Disclosure of Invention
Aiming at the problems encountered in the wheat ear counting process, the invention provides a method, a device, electronic equipment and a storage medium for automatically identifying the number of plant ears, which can automatically identify the number of wheat ears through a wheat thermal imaging graph and improve the statistical efficiency, accuracy and reliability of the number of the wheat ears.
In one aspect, the invention provides a method for automatically identifying the number of plant ears, which comprises the following steps:
extracting a contour map of the plant with the ear by utilizing a visible light side view of the plant with the ear;
carrying out noise reduction pretreatment on the infrared imaging side view of the plant with the ear to generate a primary infrared imaging side view;
matching and fusing the contour map of the plant with the ear to the primary infrared imaging side view to generate a secondary infrared imaging side view;
and extracting ear information through deep processing of the secondary infrared imaging side view so as to identify the number of ears of the plant.
Further preferably, the extracting the contour map of the plant with the ear by using the visible light side view of the plant with the ear comprises the following steps:
demosaicing the visible light side view, interpolating the numerical values of image pixels and color channels of the visible light side view, and reconstructing a full-color visible light side view;
converting the full-color visible light side view into a gray-scale visible light side view, performing binarization processing on the gray-scale visible light side view, and adjusting a threshold value to obtain a black-and-white image of the plant with the spike;
filtering interference noise in the black-and-white image of the plant with the ear by using median filtering, extracting information of the plant with the ear, and extracting contour information of the plant with the ear from the information of the plant with the ear through foreground integration to generate a contour map of the plant with the ear.
Further preferably, the noise reduction preprocessing is performed on the infrared imaging side view of the plant with the ear to generate a primary infrared imaging side view, and the method comprises the following steps:
performing wavelet transformation on the infrared imaging side view of the plant with the ear;
separating signals and noise in the infrared imaging side view of the plant with the ear to finish the noise reduction pretreatment and obtain the primary infrared imaging side view;
wherein the primary infrared imaging side view comprises a grayscale infrared imaging side view.
Further preferably, the matching and fusing the contour map of the plant with the ear to the primary infrared imaging side view to generate a secondary infrared imaging side view includes the steps of:
copying the contour map of the plant with the ear into the side view of the primary infrared imaging;
adjusting the contour map of the plant with the ear to fuse the contour map to the primary infrared imaging side view;
wherein, the adjusting mode comprises shifting and zooming.
Further preferably, the extracting ear information by depth processing the secondary infrared imaging side view to identify the number of ears of plant comprises the steps of:
converting the secondary processed imaging side view into a secondary processed imaging side view in the form of a pseudo-color image;
and mapping the color information of the wheat ears by utilizing the temperature difference information of all parts of the plants with the wheat ears in the secondary infrared imaging side view in the form of pseudo-color images so as to identify the number of the wheat ears.
Further preferably, the converting the secondary processing imaging side view into a secondary processing imaging side view in the form of a pseudo-color image specifically includes the steps of:
performing histogram equalization processing on the secondary infrared imaging side view to enhance the gray scale contrast of the secondary infrared imaging side view;
adjusting a gray threshold of the secondary infrared imaging side view, and separating a light part and a dark part of the secondary infrared imaging side view;
carrying out gray scale grading processing on the secondary infrared imaging side view;
and converting the secondary infrared imaging side view after the gray scale processing into the secondary infrared imaging side view in a pseudo-color image form.
Further preferably, before the extracting the contour map of the ear-bearing plant by using the visible light side view of the ear-bearing plant, the method further comprises the following steps:
and collecting a visible light side view of the plant with the ear and an infrared imaging side view of the plant with the ear from a preset angle.
On the other hand, the invention also provides a device for automatically identifying the number of the plant ears, which is applied to the method for automatically identifying the number of the plant ears, and comprises the following steps:
the outline extraction module is used for extracting an outline drawing of the plant with the ear by utilizing the visible light side view of the plant with the ear;
the preprocessing module is used for carrying out noise reduction preprocessing on the infrared imaging side view of the plant with the ear to generate a primary infrared imaging side view;
the matching module is used for matching and fusing the contour map of the plant with the ear to the primary infrared imaging side view to generate a secondary infrared imaging side view;
and the identification module is used for extracting the ear information through the deep processing of the secondary infrared imaging side view so as to identify the number of ears of the plant.
In yet another aspect, the present invention also provides an electronic device, including:
a processor; and a memory storing computer executable instructions that, when executed, cause the processor to perform a method of automatically identifying ears of plants from the plant.
In still another aspect, the present invention further provides a storage medium, where at least one instruction is stored, and the instruction is loaded and executed by a processor to implement the operations performed by the method for automatically identifying the number of ears of plant.
The method, the device, the electronic equipment and the storage medium for automatically identifying the number of the plant spikes provided by the invention at least have the following beneficial effects:
1) the invention provides a method capable of automatically identifying the number of wheat ears through a wheat thermal imaging graph aiming at the problems encountered in the wheat ear counting process, and improves the statistical efficiency, accuracy and reliability of the number of wheat ears.
2) In the invention, when the visible light and the infrared thermal imaging side view of the wheat plant are collected, the visible light and the infrared thermal imaging side view are collected by high-flux automatic surface type equipment, the image collection is carried out in a dark room with uniform and stable environment, the interference of an external light source is avoided, and the quality of the image is improved.
3) The method combines the visible light imaging and the infrared thermal imaging, not only avoids the interference of the shielding of the blades under the visible light, but also eliminates the defect that the resolution of the infrared thermal imaging is lower to cause inaccurate extraction of the target object, and the measurement of the spike number is carried out by utilizing the gray level difference, so that the measurement precision is higher; and because wheat ear is extracted based on the image, compared with the traditional manual measurement, the efficiency and accuracy are greatly improved.
Drawings
The invention is described in further detail below with reference to the following figures and detailed description:
FIG. 1 is a schematic flow chart diagram illustrating an embodiment of a method for automatically identifying the number of ears of a plant according to the present invention;
FIG. 2 is a schematic flow chart of the present invention for extracting the outline of the plant with ears from the visible side view of the plant with ears in step S100;
FIG. 3 is a schematic flow chart illustrating the process of extracting ear information by deep processing the secondary infrared imaging side view to identify the number of ears of plant in step S400 according to the present invention;
FIG. 4 is a schematic diagram of the process of extracting the contour map of the plants with ears according to the present invention;
FIG. 5 is a schematic flow chart illustrating another embodiment of the method for automatically identifying the number of ears of a plant according to the present invention;
FIG. 6 is a side view of a two-level infrared imaging system according to the present invention;
FIG. 7 is a two-stage processing imaging side view in the form of a pseudo-color image of the present invention
FIG. 8 is a schematic representation of the number of ears extracted according to the present invention;
FIG. 9 is a visible side view of the present invention;
FIG. 10 is a side view of infrared imaging of the present invention;
FIG. 11 is a side view of a primary infrared imaging of the present invention;
FIG. 12 is a schematic flow chart illustrating another embodiment of a method for automatically identifying the number of ears of a plant according to the present invention;
FIG. 13 is a schematic structural diagram of an apparatus for automatically identifying the number of ears of a plant according to the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
For the sake of simplicity, the drawings only schematically show the parts relevant to the present invention, and they do not represent the actual structure as a product. In addition, in order to make the drawings concise and understandable, components having the same structure or function in some of the drawings are only schematically illustrated or only labeled. In this document, "one" means not only "only one" but also a case of "more than one".
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
In this context, it is to be understood that, unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not intended to indicate or imply relative importance.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.
Example one
In one aspect, as shown in fig. 1, the present invention provides an embodiment of a method for automatically identifying the number of ears of a plant, comprising the following steps:
s100, extracting a contour map of the plant with the ear by utilizing a visible light side view of the plant with the ear.
Specifically, the plants with ears may include wheat plants, rice plants, and the like.
Illustratively, when the plant with the ear is a wheat plant, the visible light side view of the wheat plant is subjected to series of image processing to extract the contour information of the wheat plant, and the method specifically comprises the following steps:
1) demosaicing, filtering noise and reconstructing full-color image; 2) converting the full-color image into a gray-scale image, namely obtaining one of RGB, HSI, LAB and LUV information of the image by dimensionality reduction, and aiming at obtaining a gray-scale image with the maximum contrast between the wheat plant and the background; 3) carrying out binarization processing on the gray level image to obtain a black-white image so as to extract a wheat plant conveniently, and adjusting a threshold value to ensure that the foreground (the wheat plant) is white and the background is black; 4) filtering noise, namely filtering background interference information which influences foreground extraction as much as possible; 5) and integrating the foreground and extracting outline information, namely integrating all dispersed white information on the black and white image into a whole to be output, namely a wheat plant, and then extracting the outline of the whole wheat plant on the basis.
S200, noise reduction pretreatment is carried out on the infrared imaging side view of the plant with the ear to generate a primary infrared imaging side view.
Specifically, regarding step S200, performing noise reduction preprocessing on the infrared imaging side view of the plant with the ear, and generating a primary infrared imaging side view may include:
illustratively, the infrared imaging side view of the wheat plant is subjected to denoising preprocessing, that is, wavelet transformation is performed on the acquired infrared thermal imaging original image of the wheat plant, and signals and noise are separated, so as to implement image denoising, and obtain a primary infrared imaging side view as shown in the figure.
S300, matching and fusing the contour map of the plant with the ear to the primary infrared imaging side view to generate a secondary infrared imaging side view.
Matching and fusing the contour map of the plant with the ear to the primary infrared imaging side view to generate a secondary infrared imaging side view in relation to the step S300, comprising the steps of:
specifically, copying the contour map of the plant with the ear into the side view of the primary infrared imaging; and adjusting the contour map of the plant with the ear to fuse the contour map to the primary infrared imaging side view. Wherein, the adjusting mode comprises shifting and zooming.
Exemplary matching visible light profile information in a profile map of a wheat plant to an infrared thermography map may include:
1) copying the outline information of the visible light wheat plant to an infrared thermal imaging gray scale map; 2) the visible light profile is perfectly fitted to the wheat plant in the infrared thermal imaging by means of shifting, zooming and the like, as shown in fig. 6.
S400, ear information is extracted through deep processing of the secondary infrared imaging side view so as to identify the number of ears of the plant.
Specifically, the secondary infrared imaging side view is a primary infrared imaging side view fused with the contour information, and illustratively, the depth processing of the secondary infrared imaging side view extracts ear information to identify the number of ears of a plant, which may include:
1) histogram equalization processing; 2) adjusting a gray threshold; 3) grading the gray scale; 4) conversion to a pseudo-color image, 5) ear identification.
Through the steps 1) to 3), detailed and accurate gray intensity distribution conditions of infrared thermal imaging can be obtained, the gray intensity difference corresponds to the difference of temperatures of different parts of the wheat plant, namely the higher the temperature is, the higher the gray value is, the lower the temperature is, the lower the gray value is, the gray value is changed from low to high to correspond to the graded color in the pseudo-color image from blue → green → yellow → red, and the pseudo-color image for highlighting the ear information can be obtained according to the gray difference of the ear and the leaf of the wheat.
Example two
As shown in fig. 2, based on the above embodiment, the same parts as those in the above embodiment are not repeated, and in this embodiment, the extracting the contour map of the plant with ears by using the visible light side view of the plant with ears in step S100 includes steps of:
s101, demosaicing processing is carried out on the visible light side view, interpolation processing is carried out on numerical values of image pixels and color channels of the visible light side view, and a full-color visible light side view is reconstructed.
Specifically, in the process of performing a series of image processing on the visible light side view of the wheat plant to extract the profile containing the profile information of the wheat plant, firstly, demosaicing is performed on the collected 0 ° visible light original image of the wheat plant, so as to filter noise, perform interpolation processing on the numerical values of image pixels and color channels, and reconstruct a full-color image with complete pixels and accurate colors, as shown in the schematic diagram labeled (a) in fig. 4.
S102, converting the full-color visible light side view into a gray-scale visible light side view, and obtaining a black-and-white image of the plant with the ear by carrying out binarization processing on the gray-scale visible light side view and adjusting a threshold value.
For example, after the mosaic processing is performed on the visible light side view, to convert the full-color image into a gray-scale image, in this embodiment, the gray-scale image obtained by reducing the dimension of the RGB, HSI, LAB, and LUV information of the picture is compared, and the hue gray-scale image obtained by reducing the dimension of HIS (hue, saturation, and intensity) is selected, as shown in the schematic diagram labeled as (B) in fig. 4.
In addition, the gray level image is binarized, and a black and white image of the wheat plant is obtained by adjusting the threshold value, that is, the potted wheat plant is white, and the background is black, as shown in the schematic diagram of reference number (C) in fig. 4.
S103, filtering interference noise in the black-and-white image of the plant with the ear by using median filtering, extracting information of the plant with the ear, and extracting contour information of the plant with the ear from the information of the plant with the ear through foreground integration to generate a contour map of the plant with the ear.
Specifically, the picture processed in step S102, that is, the black-and-white image of the wheat plant, is cut, and the median filter is used to filter the interference noise in the picture, so as to finally extract complete wheat plant information.
The median filtering method is a non-linear smoothing technique, and it sets the gray value of each pixel point as the median of the gray values of all pixel points in a certain neighborhood window of the point, and is the optimal filtering under the criterion of "minimum absolute error", and the image after median filtering is shown as the schematic diagram labeled (D) in fig. 4.
In addition, foreground integration is performed and profile information is extracted, that is, all dispersed white information on the black-and-white image is integrated into a whole to be output, that is, a wheat plant, and then the profile of the whole wheat plant is extracted on the basis, as shown in a schematic diagram labeled as (E) in fig. 4.
EXAMPLE III
As shown in fig. 3, based on the above embodiment, the same parts as those in the above embodiment are not repeated one by one, and in this embodiment, the step S400 of extracting ear information by depth processing of the secondary infrared imaging side view to identify the number of ears of a plant includes the steps of:
s401 converts the two-stage-processed imaging side view into a two-stage-processed imaging side view in the form of a pseudo-color image.
S402, mapping the color information of the wheat ears by utilizing the temperature difference information of all parts of the plants with the wheat ears in the secondary infrared imaging side view in the form of pseudo-color images so as to identify the number of the wheat ears.
In this embodiment, regarding the step S401 of converting the secondary processing imaging side view into a secondary processing imaging side view in the form of a pseudo color image, the method specifically includes the steps of:
and performing histogram equalization processing on the secondary infrared imaging side view to enhance the gray scale contrast of the secondary infrared imaging side view.
And adjusting the gray threshold value of the secondary infrared imaging side view, and separating the bright part and the dark part of the secondary infrared imaging side view.
And carrying out gray scale grading processing on the secondary infrared imaging side view.
And converting the secondary infrared imaging side view after the gray scale processing into the secondary infrared imaging side view in a pseudo-color image form.
1) Histogram equalization processing is carried out on the infrared thermal imaging picture, namely, the histogram of the original picture is converted into a uniformly distributed form so as to increase the dynamic range of the pixel gray value and achieve the effect of enhancing the integral gray contrast of the image.
2) And adjusting a gray threshold value, and separating bright and dark parts in the image by setting the threshold value.
3) And gray scale grading, namely, the gray intensity is higher, the temperature is higher, the gray intensity is lower, and the temperature is lower.
4) The conversion to a pseudo-color image is that each gray in the gray map is mapped to one color, and the gradation colors mapped in the pseudo-color image in the present embodiment from low to high in gray intensity vary from blue → green → yellow → red.
5) The ear recognition is to reflect the temperature difference between the ear and other parts of the wheat to the pseudo-color image of the gray scale intensity mapping, so that the ear and other parts of the wheat form obvious color difference, as shown in fig. 7.
Example four
As shown in fig. 5, the present invention provides an embodiment of a method for automatically identifying the number of ears of a plant, comprising the following steps:
s000, collecting a visible light side view of the plant with the ear and an infrared imaging side view of the plant with the ear from a preset angle.
In an embodiment, a visual light and infrared thermal imaging side view of a wheat plant is acquired by utilizing a German LemnaTec high-throughput plant phenotype automatic acquisition platform, and the system can be completely controlled by software, fully automatically performs 3D imaging on the plant and records data. The potted wheat to be detected is placed on the conveying vehicle, the automatic conveying system can convey the potted wheat to the infrared thermal imaging darkroom and the visible light imaging darkroom one by one according to a preset program of an instrument, the two imaging darkrooms are uniform and stable in environment and are not interfered by an external light source, the rotary imaging platform is arranged in the center of the darkroom, the wheat images can be collected from different angles, and in the embodiment, the 0-degree visible light image and the 0-degree infrared thermal imaging of the wheat plant are collected uniformly, as shown in fig. 9 and 10.
In this embodiment, the processing and analysis of the visible light and infrared thermography images are preferably based on lemna grid analysis software, which includes algorithm modules capable of analyzing various types of images, and these modules are connected and combined to analyze the images to obtain parameters required by us.
S100, extracting a contour map of the plant with the ear by utilizing a visible light side view of the plant with the ear.
Specifically, 1) the collected 0 ° visible light original image of the wheat plant is demosaiced as shown in fig. 9, so as to filter noise, interpolate the values of the image pixels and color channels, and reconstruct a full-color image with complete pixels and accurate color, as shown in the schematic diagram labeled (a) in fig. 4.
2) In this embodiment, the gray-scale image obtained by comparing the RGB, HSI, LAB, and LUV information of the picture and reducing the dimension is selected as the hue gray-scale image after HIS (hue, saturation, and intensity) dimension reduction, as shown in the schematic diagram labeled as (B) in fig. 4.
3) And (3) carrying out binarization processing on the gray level image, and obtaining a black and white image of the wheat plant by adjusting a threshold value, namely the potted wheat plant is white, and the background is black, as shown in a schematic diagram with the reference number (C) in fig. 4.
4) The picture is cut, interference noise is filtered by using median filtering, and complete wheat plant information is finally extracted, wherein the median filtering method is a nonlinear smoothing technology, the gray value of each pixel point is set as the median of the gray values of all the pixel points in a certain neighborhood window of the point, the median filtering is the optimal filtering under the criterion of the minimum absolute error, and the image after median filtering processing is shown as a schematic diagram marked with a reference number (D) in fig. 4.
5) The foreground is integrated and extracted with outline information, i.e. all the dispersed white information on the black and white image is integrated into a whole output, i.e. the wheat plant, and then the outline of the whole wheat plant is extracted on the basis, as shown in the schematic diagram labeled (E) in fig. 4.
S200, noise reduction pretreatment is carried out on the infrared imaging side view of the plant with the ear to generate a primary infrared imaging side view.
Wavelet transformation is carried out on the acquired 0-degree infrared thermal imaging original image of the wheat plant as shown in fig. 10, and signals and noise are separated to realize image noise reduction as shown in fig. 11.
S300, matching and fusing the contour map of the plant with the ear to the primary infrared imaging side view to generate a secondary infrared imaging side view.
Specifically, the method comprises the following steps: 1) copying visible light wheat contour information to an infrared thermal imaging gray scale image; 2) the visible light profile is perfectly fitted to the wheat plant in the infrared thermal imaging by means of shifting, zooming and the like, as shown in fig. 6.
S400, ear information is extracted through deep processing of the secondary infrared imaging side view so as to identify the number of ears of the plant.
Exemplary, the method may specifically include:
1) histogram equalization processing is carried out on the infrared thermal imaging picture, namely, the histogram of the original picture is converted into a uniformly distributed form so as to increase the dynamic range of the pixel gray value and achieve the effect of enhancing the integral gray contrast of the image.
2) And adjusting a gray threshold value, and separating bright and dark parts in the image by setting the threshold value.
3) And gray scale grading, namely, the gray intensity is higher, the temperature is higher, the gray intensity is lower, and the temperature is lower.
4) The conversion to a pseudo-color image is that each gray in the gray map is mapped to one color, and the gradation colors mapped in the pseudo-color image in the present embodiment from low to high in gray intensity vary from blue → green → yellow → red.
5) The ear recognition is to reflect the temperature difference between the ear and other parts of the wheat to the pseudo-color image of the gray scale intensity mapping, so that the ear and other parts of the wheat form obvious color difference, as shown in fig. 7.
In the above embodiment, the ear number is extracted and counted, that is, ear information is extracted by the color difference and the ear number is counted, as shown in fig. 8.
Illustratively, as shown in fig. 12, S1 collects visible light and infrared thermal imaging side views of wheat plants; s2, performing series of image processing on the visible light side view of the wheat to extract the outline information of the wheat; s3, preprocessing the infrared thermal imaging side view of the wheat; s4, matching the visible light outline information of the wheat to an infrared thermal imaging graph; s5, performing wheat infrared thermal imaging image deep processing to identify ear information; s6, extracting and counting the number of wheat ears.
The method in the embodiment is used for identifying and verifying the ear number of 100 wheat sample images of 3 varieties, the ear number is compared with the actual ear number obtained by manual counting, the comparison result is shown in table 1, and the table shows that the average accuracy of the identification method for automatically identifying the ear number of wheat reaches 81.55%, which is higher than the accuracy of the visible light image identification method reported in the prior literature.
Table 1: ear number of wheat identification
EXAMPLE seven
On the other hand, as shown in fig. 13, the present invention further provides an apparatus for automatically identifying the number of ears of a plant, which is applied to the method for automatically identifying the number of ears of a plant, and the method includes:
and the contour extraction module 10 is used for extracting a contour map of the plant with the ear by utilizing the visible light side view of the plant with the ear.
And the preprocessing module 20 is used for performing noise reduction preprocessing on the infrared imaging side view of the plant with the ear to generate a primary infrared imaging side view.
And the matching module 30 is used for matching and fusing the contour map of the plant with the ear to the primary infrared imaging side view to generate a secondary infrared imaging side view.
And the identification module 40 is used for extracting the ear information by deeply processing the secondary infrared imaging side view so as to identify the number of ears of the plant.
In this embodiment, the demosaicing mode related to the preprocessing module 20 is only applicable to Lemnatec corollary software. All modules in the embodiment are preferably suitable for Lemnatec supporting software LemnaGrid, but the functional implementation of the modules includes but is not limited to the functional implementation by other software such as MATLAB, python and the like.
Can provide a device that can be through wheat thermal imaging picture automatic identification wheatear number to the problem that meets in the wheatear counting process through this embodiment, improve the statistical efficiency, accuracy and the reliability of wheatear number.
Meanwhile, when the visible light and infrared thermal imaging side views of the wheat plants are collected in the embodiment, the visible light and infrared thermal imaging side views are collected through high-throughput automatic surface equipment, the image collection is carried out in a dark room with uniform and stable environment, the interference of an external light source is avoided, and the quality of the image is improved.
By the method, visible light imaging and infrared thermal imaging methods can be combined, interference caused by shielding of the blades under visible light is avoided, the defect that target extraction is not accurate due to low resolution of infrared thermal imaging is overcome, spike number is measured by utilizing gray level difference, and measurement accuracy is high; and because wheat ear is extracted based on the image, compared with the traditional manual measurement, the efficiency and accuracy are greatly improved.
In yet another aspect, the present invention also provides an electronic device, including:
a processor; and a memory storing computer executable instructions that, when executed, cause the processor to perform a method of automatically identifying ears of plants from the plant.
In still another aspect, the present invention further provides a storage medium, where at least one instruction is stored, and the instruction is loaded and executed by a processor to implement the operations performed by the method for automatically identifying the number of ears of plant.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described system embodiments are merely exemplary, and it is exemplary that the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, and it is exemplary that a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
It should be noted that the above embodiments can be freely combined as necessary. The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for automatically identifying the number of ears of a plant is characterized by comprising the following steps:
extracting a contour map of the plant with the ear by utilizing a visible light side view of the plant with the ear;
carrying out noise reduction pretreatment on the infrared imaging side view of the plant with the ear to generate a primary infrared imaging side view;
matching and fusing the contour map of the plant with the ear to the primary infrared imaging side view to generate a secondary infrared imaging side view;
and extracting ear information through deep processing of the secondary infrared imaging side view so as to identify the number of ears of the plant.
2. The method for automatically identifying the number of ears of plant as claimed in claim 1, wherein said extracting the contour map of said ear-bearing plant by using the visible side view of said ear-bearing plant comprises the steps of:
demosaicing the visible light side view, interpolating the numerical values of image pixels and color channels of the visible light side view, and reconstructing a full-color visible light side view;
converting the full-color visible light side view into a gray-scale visible light side view, performing binarization processing on the gray-scale visible light side view, and adjusting a threshold value to obtain a black-and-white image of the plant with the spike;
filtering interference noise in the black-and-white image of the plant with the ear by using median filtering, extracting information of the plant with the ear, and extracting contour information of the plant with the ear from the information of the plant with the ear through foreground integration to generate a contour map of the plant with the ear.
3. The method for automatically identifying the number of ears of a plant as claimed in claim 1, wherein the step of performing noise reduction preprocessing on the infrared imaging side view of the ear-bearing plant to generate a primary infrared imaging side view comprises the steps of:
performing wavelet transformation on the infrared imaging side view of the plant with the ear;
separating signals and noise in the infrared imaging side view of the plant with the ear to finish the noise reduction pretreatment and obtain the primary infrared imaging side view;
wherein the primary infrared imaging side view comprises a grayscale infrared imaging side view.
4. The method for automatically identifying the number of ears of plant as claimed in claim 1, wherein the matching and fusing the contour map of the ear-bearing plant to the primary infrared imaging side view to generate a secondary infrared imaging side view comprises the steps of:
copying the contour map of the plant with the ear into the side view of the primary infrared imaging;
adjusting the contour map of the plant with the ear to fuse the contour map to the primary infrared imaging side view;
wherein, the adjusting mode comprises shifting and zooming.
5. The method for automatically identifying the number of ears of plant as claimed in claim 1, wherein the step of extracting ear information by deep processing the secondary infrared imaging side view to identify the number of ears of plant comprises the steps of:
converting the secondary processed imaging side view into a secondary processed imaging side view in the form of a pseudo-color image;
and mapping the color information of the wheat ears by utilizing the temperature difference information of all parts of the plants with the wheat ears in the secondary infrared imaging side view in the form of pseudo-color images so as to identify the number of the wheat ears.
6. The method for automatically identifying the number of ears of plant as claimed in claim 1, wherein the step of converting the secondary processing imaging side view into a secondary processing imaging side view in the form of a pseudo-color image comprises the following steps:
performing histogram equalization processing on the secondary infrared imaging side view to enhance the gray scale contrast of the secondary infrared imaging side view;
adjusting a gray threshold of the secondary infrared imaging side view, and separating a light part and a dark part of the secondary infrared imaging side view;
carrying out gray scale grading processing on the secondary infrared imaging side view;
and converting the secondary infrared imaging side view after the gray scale processing into the secondary infrared imaging side view in a pseudo-color image form.
7. The method for automatically identifying the number of ears of plant as claimed in any one of claims 1-6, further comprising the steps of, before the extracting the contour map of the ear-bearing plant by using the visible side view of the ear-bearing plant:
and collecting a visible light side view of the plant with the ear and an infrared imaging side view of the plant with the ear from a preset angle.
8. An apparatus for automatically identifying the number of plant ears is applied to the method for automatically identifying the number of plant ears of any one of claims 1 to 7, and comprises:
the outline extraction module is used for extracting an outline drawing of the plant with the ear by utilizing the visible light side view of the plant with the ear;
the preprocessing module is used for carrying out noise reduction preprocessing on the infrared imaging side view of the plant with the ear to generate a primary infrared imaging side view;
the matching module is used for matching and fusing the contour map of the plant with the ear to the primary infrared imaging side view to generate a secondary infrared imaging side view;
and the identification module is used for extracting the ear information through the deep processing of the secondary infrared imaging side view so as to identify the number of ears of the plant.
9. An electronic device, characterized in that the electronic device comprises:
a processor; and a memory storing computer executable instructions which, when executed, cause the processor to perform a method of automatically identifying ears of plants according to any one of claims 1-7.
10. A storage medium having stored therein at least one instruction, which is loaded and executed by a processor to perform the operations according to the method for automatically identifying ears of plants as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010870458.8A CN112001910A (en) | 2020-08-26 | 2020-08-26 | Method and device for automatically identifying number of plant ears, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010870458.8A CN112001910A (en) | 2020-08-26 | 2020-08-26 | Method and device for automatically identifying number of plant ears, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112001910A true CN112001910A (en) | 2020-11-27 |
Family
ID=73471003
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010870458.8A Withdrawn CN112001910A (en) | 2020-08-26 | 2020-08-26 | Method and device for automatically identifying number of plant ears, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112001910A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117274812A (en) * | 2023-10-08 | 2023-12-22 | 北京香田智能科技有限公司 | Tobacco plant counting method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989585A (en) * | 2015-03-05 | 2016-10-05 | 深圳市朗驰欣创科技有限公司 | Method and system for fusing infrared image and visible light image |
| CN106548467A (en) * | 2016-10-31 | 2017-03-29 | 广州飒特红外股份有限公司 | The method and device of infrared image and visual image fusion |
| US20180227509A1 (en) * | 2015-08-05 | 2018-08-09 | Wuhan Guide Infrared Co., Ltd. | Visible light image and infrared image fusion processing system and fusion method |
| CN108694709A (en) * | 2017-04-12 | 2018-10-23 | 深圳市朗驰欣创科技股份有限公司 | A kind of image interfusion method and device |
| CN109389581A (en) * | 2018-09-10 | 2019-02-26 | 江苏大学 | The method of wheat leaf rust classification based on infrared thermal imaging edge detection process |
| CN109410159A (en) * | 2018-09-11 | 2019-03-01 | 上海创客科技有限公司 | Binocular visible light and infrared thermal imaging complex imaging system, method and medium |
-
2020
- 2020-08-26 CN CN202010870458.8A patent/CN112001910A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989585A (en) * | 2015-03-05 | 2016-10-05 | 深圳市朗驰欣创科技有限公司 | Method and system for fusing infrared image and visible light image |
| US20180227509A1 (en) * | 2015-08-05 | 2018-08-09 | Wuhan Guide Infrared Co., Ltd. | Visible light image and infrared image fusion processing system and fusion method |
| CN106548467A (en) * | 2016-10-31 | 2017-03-29 | 广州飒特红外股份有限公司 | The method and device of infrared image and visual image fusion |
| CN108694709A (en) * | 2017-04-12 | 2018-10-23 | 深圳市朗驰欣创科技股份有限公司 | A kind of image interfusion method and device |
| CN109389581A (en) * | 2018-09-10 | 2019-02-26 | 江苏大学 | The method of wheat leaf rust classification based on infrared thermal imaging edge detection process |
| CN109410159A (en) * | 2018-09-11 | 2019-03-01 | 上海创客科技有限公司 | Binocular visible light and infrared thermal imaging complex imaging system, method and medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117274812A (en) * | 2023-10-08 | 2023-12-22 | 北京香田智能科技有限公司 | Tobacco plant counting method |
| CN117274812B (en) * | 2023-10-08 | 2024-02-20 | 北京香田智能科技有限公司 | Tobacco plant counting method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| CN103955938B (en) | A kind of wheat growth method for diagnosing status based on mobile Internet pattern and leaf color analysis | |
| CN102495005B (en) | Method for diagnosing crop water deficit through hyperspectral image technology | |
| CN101692037B (en) | Method for analyzing chlorophyll distribution on surface of leaves of plant by hyperspectral image and independent component | |
| CN110082298B (en) | Hyperspectral image-based wheat variety gibberellic disease comprehensive resistance identification method | |
| Narvekar et al. | Grape leaf diseases detection & analysis using SGDM matrix method | |
| CN103278503B (en) | Multi-sensor technology-based grape water stress diagnosis method and system therefor | |
| Masood et al. | Plants disease segmentation using image processing | |
| CN113570538B (en) | Blade RGB image bias distribution parameter information acquisition and analysis method | |
| CN113963260A (en) | Extraction method and device for winter wheat planting area and computer equipment | |
| Kurniawati et al. | Texture analysis for diagnosing paddy disease | |
| CN115082451A (en) | Stainless steel soup ladle defect detection method based on image processing | |
| CN114612794A (en) | Remote sensing identification method for land covering and planting structure in finely-divided agricultural area | |
| CN112883987A (en) | Target extraction method, system, device and medium based on remote sensing spectral characteristics | |
| CN116559111A (en) | Sorghum variety identification method based on hyperspectral imaging technology | |
| Setyawan et al. | Comparison of hsv and lab color spaces for hydroponic monitoring system | |
| CN112001910A (en) | Method and device for automatically identifying number of plant ears, electronic equipment and storage medium | |
| CN107993243B (en) | Wheat tillering number automatic detection method based on RGB image | |
| CN117455828A (en) | Combustion quality detection method based on MLP neural network | |
| CN106951824A (en) | The method and system of plant leaf color are extracted based on unmanned aerial vehicle remote sensing images | |
| CN115049902B (en) | Visual prediction method, system, equipment and storage medium for water content of citrus blade | |
| CN110580495A (en) | automatic analysis method for leaf area and leaf surface anthracnose lesion number of pear | |
| Di et al. | The research on the feature extraction of sunflower leaf rust characteristics based on color and texture feature | |
| CN105628206A (en) | Method for measuring colors of tea leaves at different positions | |
| CN108982386B (en) | Multispectral image determination method and system for total iron content of sandalwood leaves |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201127 |
|
| WW01 | Invention patent application withdrawn after publication |