CN112116595A - End-to-end automatic plant root system characteristic segmentation system - Google Patents
End-to-end automatic plant root system characteristic segmentation system Download PDFInfo
- Publication number
- CN112116595A CN112116595A CN202011160899.5A CN202011160899A CN112116595A CN 112116595 A CN112116595 A CN 112116595A CN 202011160899 A CN202011160899 A CN 202011160899A CN 112116595 A CN112116595 A CN 112116595A
- Authority
- CN
- China
- Prior art keywords
- root system
- image
- segmentation
- plant root
- display screen
- 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.)
- Pending
Links
- 241000196324 Embryophyta Species 0.000 title claims abstract description 62
- 230000011218 segmentation Effects 0.000 title claims abstract description 54
- 240000007651 Rubus glaucus Species 0.000 claims abstract description 19
- 235000011034 Rubus glaucus Nutrition 0.000 claims abstract description 19
- 235000009122 Rubus idaeus Nutrition 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 19
- 239000002689 soil Substances 0.000 claims description 10
- 230000007246 mechanism Effects 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 230000003321 amplification Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims description 2
- 230000002787 reinforcement Effects 0.000 claims description 2
- 238000003709 image segmentation Methods 0.000 abstract description 4
- 238000000034 method Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 abstract 1
- 238000011160 research Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 101100243951 Caenorhabditis elegans pie-1 gene Proteins 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 235000016709 nutrition Nutrition 0.000 description 2
- 230000035764 nutrition Effects 0.000 description 2
- 230000008261 resistance mechanism Effects 0.000 description 2
- 229920000742 Cotton Polymers 0.000 description 1
- 244000299507 Gossypium hirsutum Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- 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
- G06T2207/10004—Still image; Photographic image
- G06T2207/10008—Still image; Photographic image from scanner, fax or copier
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Abstract
The invention discloses an end-to-end automatic plant root characteristic segmentation system which comprises a scanning camera, a USB (universal serial bus) connecting line, a raspberry group, an HDMI (high-definition multimedia interface) connecting line and a display screen. The scanning camera is used for collecting images of plant roots in the cultivation container, the scanning camera is placed beside the cultivation container, and the scanning camera is connected to the USB interface of the raspberry pie through the USB connecting line. And burning the deep learning semantic segmentation algorithm finished by iterative training into the raspberry group. The scanning camera transmits root system images of different growth periods of plants into the raspberry group for pixel segmentation through the root system image acquisition based on the time sequence nodes, a display screen is connected to the HDMI interface of the raspberry group, and the segmentation result is directly output to the display screen for display and storage. The automatic plant root characteristic segmentation system provided by the invention is simple in structure and easy to realize, and compared with the traditional root segmentation method, the system can acquire a larger area of root system visual images on the premise of ensuring the segmentation precision and realize end-to-end plant root image segmentation.
Description
Technical Field
The invention relates to the field of root system morphology, in particular to an end-to-end automatic plant root system characteristic segmentation system.
Background
The plant root system is the main organ for fixing plants and obtaining water and nutrient substances, and is used as a hub for connecting plant bodies and the soil environment, and the development condition of the root system is directly related to the morphological construction of the overground part. However, the root system is complicated, many morphological characteristics are difficult to extract, the traditional manual extraction is time-consuming and labor-consuming, and the root is easy to be damaged to a certain degree. The existing image segmentation technology is to input an image into a traditional convolution neural network, extract a feature map of the image through convolution operation, and restore the extracted feature map to obtain a segmentation result. However, the accuracy and efficiency of a segmented image obtained by segmenting an image based on a conventional convolutional neural network are not high. In order to solve the problems, the invention provides an end-to-end automatic plant root system characteristic segmentation system, which can realize rapid and lossless acquisition of root system images by adopting a scanning camera, segment the scanned root system images into plant root systems through a semantic segmentation model, and introduce an attention mechanism into the semantic segmentation model, so that more weights can be replayed on the segmentation and identification of the root systems, the information extraction on the soil environment is reduced, the segmentation efficiency is improved, an end-to-end automatic plant root system characteristic segmentation technology is realized, and more powerful data support and observation means are provided for rapid agricultural development.
Disclosure of Invention
The invention aims to provide an end-to-end automatic plant root characteristic segmentation system.
In order to achieve the purpose, the invention provides the following scheme:
an end-to-end plant root system feature automatic segmentation system, comprising: the device comprises a scanning camera, a USB connecting line, a raspberry group, an HDMI connecting line and a display screen; the scanning camera is arranged beside the cultivation container and used for scanning the plant root system in the cultivation container to obtain image data of the plant root system; the scanning camera is connected to a USB interface of the raspberry pi through the USB connecting line; recording a written semantic segmentation program in advance in the raspberry pie, and segmenting a morphological distribution image of a plant root system; the HDMI of the raspberry pie is connected with the display screen through the HDMI connecting line, and the segmented plant root system image is fed back to the display screen; the display screen is used for displaying and storing the root system images after being divided, so that the automatic division of the end-to-end plant root system characteristics is realized.
Optionally, the scanning camera scans two side surfaces of the long edge of the cultivation container in turn each time of scanning so as to acquire an image of the plant root system to form a data set.
Optionally, the root system image acquired by the scanning camera is divided into a training set and a test set according to a ratio of 8:2, the training set is used for training the root system segmentation model, and the test set is used for testing the performance of the model after training. And performing data amplification on the data in each training set, training network parameters, analyzing the root system image by using the trained network, predicting the category of each pixel in the root system image, outputting a semantic segmentation image, and displaying and storing the semantic segmentation image by the display screen.
Optionally, the image processing method used in the raspberry group is a semantic segmentation algorithm, and the distribution position of the root system in the complex soil environment can be automatically and accurately segmented.
Optionally, an attention mechanism is introduced into the semantic segmentation algorithm, continuous iteration and reinforcement learning of the root system features are performed, pixel point classification in the root system image is classified one by one, pixel level detection is performed on the root system image, and the image features are stably segmented.
Optionally, the segmented root system image is stored in the display screen, wherein the white part is the distribution form of the plant root system, and the black part is other uninteresting features except the root system.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the end-to-end automatic plant root characteristic segmentation system provided by the invention is simple in structure and easy to realize, and can obtain a root observation image with a large area; in the research of root system image segmentation, a semantic segmentation algorithm is adopted, and an attention mechanism is introduced into a semantic segmentation model, wherein the attention mechanism can integrate context information of a plant root system target and information input by all sequences, so that a specific filter is trained, information extraction on a soil environment is reduced, model precision is increased, and overall training efficiency is improved, thereby meeting the requirement of accurate segmentation of the plant root system; the system is used for researching the shape distribution of the plant root system, particularly the research on the deep root property of the plant, and has important application value in the research on the aspects of plant moisture and nutrition absorption, stress resistance mechanism and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a top view of an end-to-end automatic plant root system feature segmentation system according to an embodiment of the present invention;
FIG. 2 is an image of a plant root system captured by a scanning camera according to an embodiment of the present invention;
FIG. 3 is a plant root segmentation image according to an embodiment of the present invention.
Reference numerals: 1. a raspberry pie; 2. a USB connection line; 3. a scanning camera; 4. a display screen; 5. HDMI connecting wire.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide an end-to-end automatic segmentation system for plant root system characteristics, which is simple in structure and easy to realize, can obtain a large-area root system observation image, reduces information extraction on a soil environment, not only increases model precision, but also improves overall training efficiency, and realizes end-to-end accurate segmentation of the root system image.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, an end-to-end automatic segmentation system for plant root system features provided in an embodiment of the present invention includes: a scanning camera 3 is arranged beside the cultivation container and used for scanning the plant root system in the cultivation container to obtain image data of the plant root system; the scanning camera 3 is connected to the USB interface of the raspberry pi 1 through the USB connecting line 2; a written semantic segmentation program is recorded in advance in the raspberry pie 1, and a morphological distribution image of a plant root system is segmented; the HDMI of the raspberry pie 1 is connected with the display screen 4 through the HDMI connecting line 5, and the segmented plant root system image is fed back to the display screen 4; the display screen 4 is used for displaying and storing the root system images after being divided, so that the automatic division of the end-to-end plant root system characteristics is realized.
As shown in fig. 2-3, the scanning camera 3 scans the root system image and the well-segmented root system shape distribution image obtained by scanning, the scanning camera 3 scans two side surfaces of the long side of the cultivation container at intervals to obtain the plant root system image shown in fig. 2, the semantic segmentation algorithm is used to segment the plant root system image collected by the scanning camera 3, and the display screen 4 displays the plant root system image shown in fig. 3.
The root system images acquired by the scanning camera 3 are selected from 80% of training sets and 20% of testing sets. And performing data amplification on the data in each training set, training network parameters, analyzing the root system image by using the trained network, predicting the category of each pixel in the root system image, outputting a semantic segmentation image, and displaying and storing the semantic segmentation image by the display screen 4. Wherein the white part is the distribution form of the plant root system, and the black part is other uninteresting characteristics except the root system.
For the low precision of the traditional convolution neural network segmentation image, the semantic segmentation network based on deep learning provided by the invention can be used for finely segmenting the cotton root system from end to end. Due to the problem of low contrast between soil and root systems, the network effectively enlarges the filtering receptive field by adopting cavity convolution so as to obtain richer root system context information; the pooling layer fusion adopts a spatial pyramid method with holes to stably divide fine roots and root hairs on multiple scales; and the simple and effective decoding module is added to refine the root system segmentation result, especially the boundary part of the root system; furthermore, the Xscene architecture is used for helping the model to improve the segmentation performance and quicken the calculation speed. And a space attention module is added in the latter half of the model, and the space attention module obtains the root system dimension reduction characteristics by using the convolutional layer so as to better extract target characteristics to obtain an attention weight matrix and reduce the calculation amount, retain the plant root system characteristics, filter unimportant information in the soil environment and improve the processing efficiency.
The end-to-end automatic plant root characteristic segmentation system provided by the invention is simple in structure and easy to realize, a large-area root observation image can be obtained, and the scanning camera scans the plant root in the cultivation container once every a period of time, so that a distribution image of the whole plant root in the cultivation container is obtained, the growth condition of the plant root image can be monitored in real time, and the plant root morphological distribution in the soil can be obtained without destructive sampling; in the research of root system image segmentation, a semantic segmentation algorithm is adopted, and an attention mechanism is introduced into a semantic segmentation model, wherein the attention mechanism can integrate context information of a plant root system target and information input by all sequences, so that a specific filter is trained, information extraction on a soil environment is reduced, model precision is increased, and overall training efficiency is improved, thereby meeting the requirement of accurate segmentation of the plant root system; the system is used for researching the shape distribution of the plant root system, particularly the research on the deep root property of the plant, and has important application value in the research on the aspects of plant moisture and nutrition absorption, stress resistance mechanism and the like.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (6)
1. An end-to-end automatic plant root system feature segmentation system, comprising: the device comprises a scanning camera, a USB connecting line, a raspberry group, an HDMI connecting line and a display screen; the scanning camera is arranged beside the cultivation container and used for scanning the plant root system in the cultivation container to obtain image data of the plant root system; the scanning camera is connected to a USB interface of the raspberry pi through the USB connecting line; recording a written semantic segmentation program in advance in the raspberry pie, and segmenting a morphological distribution image of a plant root system; the HDMI of the raspberry pie is connected with the display screen through the HDMI connecting line, and the segmented plant root system image is fed back to the display screen; the display screen is used for displaying and storing the root system images after being divided, so that the automatic division of the end-to-end plant root system characteristics is realized.
2. The system as claimed in claim 1, wherein the scanning camera scans the two sides of the long side of the cultivation container to collect the image of the plant root system to form a data set.
3. The system of claim 1, wherein the root system image acquired by the scanning camera is divided into a training set and a testing set according to a ratio of 8:2, the training set is used for training the root system segmentation model, and the testing set is used for testing the performance of the model after training. And performing data amplification on the data in each training set, training network parameters, analyzing the root system image by using the trained network, predicting the category of each pixel in the root system image, outputting a semantic segmentation image, and displaying and storing the semantic segmentation image by the display screen.
4. The system of claim 1, wherein the image processing method used in the raspberry group is a semantic segmentation algorithm, and can automatically and precisely segment the distribution position of the root system in a complex soil environment.
5. The system of claim 4, wherein an attention mechanism is introduced into the semantic segmentation algorithm, the continuous iteration and reinforcement learning of the root system features are performed, the pixel point classification in the root system image is classified one by one, the pixel level detection is performed on the root system image, and the image features are stably segmented.
6. The system of claim 1, wherein the image of the root system after the segmentation is completed is stored in the display screen, wherein white parts are the distribution of the plant root system, and black parts are other uninteresting features except the root system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011160899.5A CN112116595A (en) | 2020-10-27 | 2020-10-27 | End-to-end automatic plant root system characteristic segmentation system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011160899.5A CN112116595A (en) | 2020-10-27 | 2020-10-27 | End-to-end automatic plant root system characteristic segmentation system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112116595A true CN112116595A (en) | 2020-12-22 |
Family
ID=73794547
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011160899.5A Pending CN112116595A (en) | 2020-10-27 | 2020-10-27 | End-to-end automatic plant root system characteristic segmentation system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112116595A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112686261A (en) * | 2020-12-24 | 2021-04-20 | 广西慧云信息技术有限公司 | Grape root system image segmentation method based on improved U-Net |
CN113985438A (en) * | 2021-11-12 | 2022-01-28 | 河北农业大学 | Plant three-dimensional model reconstruction system and method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106981238A (en) * | 2017-03-20 | 2017-07-25 | 南昌大学 | A kind of sign language ac equipment based on computer vision |
CN109544554A (en) * | 2018-10-18 | 2019-03-29 | 中国科学院空间应用工程与技术中心 | A kind of segmentation of plant image and blade framework extracting method and system |
CN109614973A (en) * | 2018-11-22 | 2019-04-12 | 华南农业大学 | Rice seedling and Weeds at seedling image, semantic dividing method, system, equipment and medium |
CN109635811A (en) * | 2018-11-09 | 2019-04-16 | 中国科学院空间应用工程与技术中心 | The image analysis method of spatial plant |
CN110245665A (en) * | 2019-05-13 | 2019-09-17 | 天津大学 | Image, semantic dividing method based on attention mechanism |
CN110705395A (en) * | 2019-09-18 | 2020-01-17 | 北京邮电大学 | Detection system based on raspberry group |
CN111476310A (en) * | 2020-04-16 | 2020-07-31 | 中国科学院半导体研究所 | Image classification method, device and equipment |
CN111652292A (en) * | 2020-05-20 | 2020-09-11 | 贵州电网有限责任公司 | Similar object real-time detection method and system based on NCS and MS |
-
2020
- 2020-10-27 CN CN202011160899.5A patent/CN112116595A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106981238A (en) * | 2017-03-20 | 2017-07-25 | 南昌大学 | A kind of sign language ac equipment based on computer vision |
CN109544554A (en) * | 2018-10-18 | 2019-03-29 | 中国科学院空间应用工程与技术中心 | A kind of segmentation of plant image and blade framework extracting method and system |
CN109635811A (en) * | 2018-11-09 | 2019-04-16 | 中国科学院空间应用工程与技术中心 | The image analysis method of spatial plant |
CN109614973A (en) * | 2018-11-22 | 2019-04-12 | 华南农业大学 | Rice seedling and Weeds at seedling image, semantic dividing method, system, equipment and medium |
CN110245665A (en) * | 2019-05-13 | 2019-09-17 | 天津大学 | Image, semantic dividing method based on attention mechanism |
CN110705395A (en) * | 2019-09-18 | 2020-01-17 | 北京邮电大学 | Detection system based on raspberry group |
CN111476310A (en) * | 2020-04-16 | 2020-07-31 | 中国科学院半导体研究所 | Image classification method, device and equipment |
CN111652292A (en) * | 2020-05-20 | 2020-09-11 | 贵州电网有限责任公司 | Similar object real-time detection method and system based on NCS and MS |
Non-Patent Citations (3)
Title |
---|
刘媛媛等: "基于语义分割的复杂场景下的秸秆检测", 《光学精密工程》 * |
房若民等: "MobileNet算法的嵌入式农业病虫害识别系统", 《单片机与嵌入式系统应用》 * |
王惠等: "基于图像处理的烟草分级系统设计与实现", 《现代农业科技》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112686261A (en) * | 2020-12-24 | 2021-04-20 | 广西慧云信息技术有限公司 | Grape root system image segmentation method based on improved U-Net |
CN113985438A (en) * | 2021-11-12 | 2022-01-28 | 河北农业大学 | Plant three-dimensional model reconstruction system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108416353B (en) | Method for quickly segmenting rice ears in field based on deep full convolution neural network | |
CN112116595A (en) | End-to-end automatic plant root system characteristic segmentation system | |
CN113657326A (en) | Weed detection method based on multi-scale fusion module and feature enhancement | |
CN111429761B (en) | Artificial intelligent simulation teaching system and method for bone marrow cell morphology | |
CN114841961B (en) | Wheat scab detection method based on image enhancement and improved YOLOv5 | |
CN110610438B (en) | Crop canopy petiole included angle calculation method and system | |
CN115953402A (en) | Plant stress-strain measurement method and device based on machine vision | |
Lu et al. | Citrus green fruit detection via improved feature network extraction | |
CN110956178B (en) | Plant growth measuring method and system based on image similarity calculation and electronic equipment | |
CN112966698A (en) | Freshwater fish image real-time identification method based on lightweight convolutional network | |
Hong-Yu et al. | Ramie plant counting based on UAV remote sensing technology and deep learning | |
CN116883718A (en) | Sugarcane seedling missing detection positioning method based on improved YOLOV7 | |
CN110910403A (en) | Industrial hemp seed counting method based on image processing | |
CN115294448A (en) | Method, device and system for counting seedlings in crop breeding community | |
CN110580495A (en) | automatic analysis method for leaf area and leaf surface anthracnose lesion number of pear | |
CN112329697B (en) | Improved YOLOv 3-based on-tree fruit identification method | |
CN115272956A (en) | Chicken health degree monitoring method based on improved YOLOv5 | |
CN114120359A (en) | Method for measuring body size of group-fed pigs based on stacked hourglass network | |
Cao et al. | Vegetation phenology detection of deciduous broad-leaf forest using YOLOv3 from PhenoCam | |
CN115690585B (en) | Method and system for extracting wheat tillering number based on digital photo | |
Gao et al. | Plant Event Detection from Time-Varying Point Clouds | |
Li et al. | MCFF: Plant leaf detection based on multi-scale CNN feature fusion | |
CN112966579B (en) | Large-area camellia oleifera forest rapid yield estimation method based on unmanned aerial vehicle remote sensing | |
CN214591683U (en) | Embedded DSP image detector of banana disease | |
CN117152234A (en) | Multi-growth-period wheat lodging area extraction method |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201222 |