CN117274816A - Maize tassel identification system - Google Patents
Maize tassel identification system Download PDFInfo
- Publication number
- CN117274816A CN117274816A CN202311316557.1A CN202311316557A CN117274816A CN 117274816 A CN117274816 A CN 117274816A CN 202311316557 A CN202311316557 A CN 202311316557A CN 117274816 A CN117274816 A CN 117274816A
- Authority
- CN
- China
- Prior art keywords
- tassel
- detection module
- corn
- detection
- module
- 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
- 240000008042 Zea mays Species 0.000 title claims abstract description 57
- 235000002017 Zea mays subsp mays Nutrition 0.000 title claims abstract description 57
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 title claims abstract description 15
- 235000009973 maize Nutrition 0.000 title claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 65
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 claims abstract description 42
- 235000005822 corn Nutrition 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000011161 development Methods 0.000 claims abstract description 15
- 230000000694 effects Effects 0.000 claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 230000008901 benefit Effects 0.000 claims abstract description 9
- 238000011160 research Methods 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 235000013339 cereals Nutrition 0.000 abstract description 6
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 241000238631 Hexapoda Species 0.000 abstract description 3
- 241000607479 Yersinia pestis Species 0.000 abstract description 3
- 201000010099 disease Diseases 0.000 abstract description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 9
- 230000009471 action Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 2
- 241001024327 Oenanthe <Aves> Species 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009396 hybridization Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/34—Graphical or visual programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a maize tassel identification system. According to the invention, the image recognition technology is adopted, so that farmers can be helped to recognize the situation of corn tassel more quickly and accurately, and measures can be taken timely, and the spread and damage of diseases and insect pests are avoided. Meanwhile, the system can realize real-time monitoring and early warning, helps farmers to know the growth condition of crops in time, and improves the production efficiency of the crops. The system has the advantages of simple operation, powerful function, high reliability and the like, can be used as an early-stage basis for corn mechanized emasculation research, can detect the quantity and growth condition of corn tassel, and promotes the development of agriculture to an intelligent and large-scale direction. The corn tassel detection device can realize real-time identification of the corn tassel by pictures, videos and cameras, rapidly and accurately detect the phenotype characteristics of the corn tassel, and provide references for agricultural condition monitoring in the corn tassel stage. Meanwhile, the method is beneficial to farmland management personnel to master the growth condition of crops in the area, and the method establishes a grain policy and has a certain guiding effect on yield estimation.
Description
Technical Field
The invention belongs to the technical field of corn tassel identification, and particularly relates to a corn tassel identification system.
Background
Corn is one of the most important cereal crops in the world. The corn emasculation period is the most critical period for determining corn yield, and tassel is the main basis for judging whether corn enters the emasculation period. Meanwhile, the corn planting relates to emasculation in the seed production and field production processes. The research shows that the emasculation of the corn can bring various advantages such as hybridization advantages, yield increase, lodging resistance and the like. Therefore, the safety, quality and unit yield of corn can be ensured by continuously monitoring the growth of corn tassel. In traditional breeding, tassel mainly relies on artificial identification, and is low in efficiency, high in subjective component and limited in sample size. The unmanned aerial vehicle remote sensing has the characteristics of strong maneuverability, high imaging resolution and the like, and provides an effective way for detecting the stamens of the corn in the emasculation period. Deep learning algorithms have been widely used to count stems, seedlings and wheat ears. The early detection algorithm of the maize tassel is to divide images by using a support vector machine method.
However, the throughput of the image capturing process is low, and the labor intensity is high, so that the image capturing process cannot be applied to a larger field. The former develops mASSLE software to monitor different stages of corn tassel traits by an automatic fine-grained machine vision system, and proposes that tasselNet counts corn tassel, but the number of samples is still limited, and the problem of measuring the performance of different models is always forgotten.
Thus, rapid and accurate identification is important for better understanding of the phenotypic characteristics of corn. Meanwhile, the method can predict the grain yield timely and accurately, and has important significance for grasping the growth condition of crops in the area, guiding agricultural production and formulating grain policies.
Disclosure of Invention
The invention aims at: in order to solve the above-mentioned problem, a maize tassel identification system is provided.
The technical scheme adopted by the invention is as follows: the corn tassel identification system comprises a system software main interface module, a system login interface module, a comprehensive detection module and an output folder opening module;
the inside of the comprehensive detection module is provided with: the device comprises a picture detection module, a camera detection module and a video detection module;
the system login interface module opens software to enter a login interface;
when the picture detection module is used, after successful login, the system automatically jumps to the main page. Clicking a 'selection model', selecting a 'yolov5s' or 'yolov5x' trained model for target detection, clicking 'loading data' to jump to file management, and selecting a picture to be identified to obtain an identified effect;
clicking the upper left corner of the camera detection module to detect the camera when the camera detection module is used, opening the configured camera, and aligning the camera to the corn tassel to be identified, so that the identified effect can be obtained;
when the video detection module is used, firstly clicking a 'selection model', selecting a model trained by 'yolov5s' or 'yolov5x' to carry out target detection, clicking 'loading data' to jump to file management, and selecting a video to be identified, thereby obtaining an identified effect;
when the output folder opening module is used, after the identification of pictures, cameras or videos is finished, clicking the lower left corner to open the output folder can jump to a file management interface, and the result can be checked
In a preferred embodiment, the system software main interface module develops a graphical interface of the present software using a qdesigner;
qt is a cross-platform C++ application development framework and has strong graphical interface development capability. Qt is used to develop applications with graphical user interfaces, qtDesigner is one of the many tools it provides, and the process of creating user interfaces for Qt-based applications can be simplified. Qt provides rich graphical interface elements and widgets, from basic buttons, text boxes and labels to advanced charts, tables and drawing tools, and supports 3D graphics and OpenGL. These widgets can help developers create a variety of complex user interfaces. QtDesigner is part of the Qt application development framework and is a design tool for creating Graphical User Interfaces (GUIs). PySide2 can let us use Qt through Python language. The PySide2 library is a main development tool of the software 'corn tassel identification system', and after the environment is installed and configured, a graphical interface of the software can be developed by using QtDesigner.
In a preferred embodiment, the system login interface module is developed using the OpenCV open source computer vision library, with the aim of providing a set of tools and functions that are widely used for image processing and computer vision tasks. OpenCV was originally developed by intel and later becomes an open source project, now maintained and developed by an active community. It supports various programming languages including C++, python and Java, and can run on operating systems such as Windows, linux and Mac OS.
In a preferred embodiment, the OpenCV library provides a number of functions and algorithms including image processing, feature detection, object recognition, object tracking, face detection and recognition, machine learning, and the like. It also supports various computer vision tasks such as feature detection, feature matching, object recognition, object tracking, face recognition, gesture recognition, etc. This makes OpenCV very useful in the fields of image recognition, machine vision, and automation.
In a preferred embodiment, the OpenCV has the advantage that it is an open source software library with a high degree of flexibility and customizable. Its community support and contribution is also very active, continually pushing new functions and improvements, its open source nature and rich functionality make it the first choice tool in research, education and business projects.
In a preferred embodiment, YOLOv5 within the video detection module is a deep learning algorithm for object detection that can detect multiple objects in an input image and provide its location and category information. YOLOv5 has real-time performance while maintaining accuracy, can perform target detection at a very high frame rate, and is suitable for real-time applications such as automatic driving, real-time video monitoring and the like. Moreover, YOLOv5 supports a variety of different model sizes (e.g., YOLOv5s, YOLOv5m, YOLOv5l, YOLOv5 x) so that a developer can select an appropriate model according to the needs of the application. The algorithm can detect targets at different scales, which is helpful for detecting targets with different sizes and improves detection performance;
YOLOv5 is a high-performance, real-time target detection algorithm, has a lightweight design, is suitable for various application fields, and is easy to deploy. Its real-time performance and accuracy make it a powerful tool for many computer vision and deep learning projects. The system is designed based on the Yolov5 algorithm.
In a preferred embodiment, the video detection module will use MySQL database; mySQL is an open-source relational database management system, which is one of the most popular and widely used databases. MySQL is a relational database management system that uses tables (tables) to store data, and relationships can be established between tables to facilitate association and querying between data. In addition, mySQL is highly optimized, has excellent performance, and is capable of handling large data sets and high concurrent access. It supports multithreading, cache management, and query optimization to improve performance.
MySQL provides powerful security functions including user authentication, rights management, and data encryption to help protect sensitive data. The system is a database management system with strong functions, high reliability and good cost effectiveness, and is suitable for application programs and projects of various scales. Its open source nature and broad support make it the database of choice for many developers and organizations.
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
1. according to the invention, the image recognition technology is adopted, so that farmers can be helped to recognize the situation of corn tassel more quickly and accurately, and measures can be taken timely, and the spread and damage of diseases and insect pests are avoided. Meanwhile, the system can realize real-time monitoring and early warning, helps farmers to know the growth condition of crops in time, and improves the production efficiency of the crops.
2. The system has the advantages of simplicity in operation, powerful functions, high reliability and the like, can be used as a preliminary basis for the mechanized emasculation research of corn, can detect the quantity and growth condition of corn tassel, reduces labor cost, and promotes the development of agriculture to an automatic, intelligent and large-scale direction.
3. According to the invention, the picture, the video and the camera can be used for identifying the corn tassel in real time, so that the phenotype characteristics of the corn tassel can be rapidly and accurately detected, and a reference is provided for agricultural condition monitoring in the corn tassel stage. Meanwhile, the method is beneficial to farmland management personnel to master the growth condition of crops in the area, and the method establishes a grain policy and has a certain guiding effect on yield estimation.
Drawings
FIG. 1 is a schematic diagram of a system software main interface of the present invention;
FIG. 2 is a schematic diagram of a system login interface according to the present invention;
FIG. 3 is a schematic image detection diagram of a maize tassel identification system according to the present invention;
FIG. 4 is a schematic diagram of camera detection of a maize tassel identification system of the present invention;
FIG. 5 is a schematic diagram of a video detection of a maize tassel identification system of the present invention;
FIG. 6 is a diagram of an output folder interface in accordance with the present invention;
FIG. 7 is a schematic diagram of a program interface according to the present invention;
FIG. 8 is a schematic diagram of a final interface for operation in accordance with the present invention
Fig. 9 is a schematic diagram of a CVAT data annotation interface according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The data set used for training the system model is from a forest starting area test field of the southern agricultural university in Guangzhou, guangdong, and the test field is planned by an unmanned aerial vehicle, and the weather with clear weather and moderate illumination is selected for photographing. The aircraft adopts the straight-line path flight, considers unmanned aerial vehicle duration and the resolution ratio on ground, sets the unmanned aerial vehicle flight height to be about 12m from ground, adjusts camera resolution ratio, ground resolution ratio to suitable parameter, and the experiment is through the video of camera recording, carries out screenshot saving to every 25 frames of video, and to the screening of photo, we will shoot the dataset that acquires and sample every interval 2 to reject the relatively poor image of quality in the sample, with this 643 pictures that have been comparatively fit for as the dataset.
After screening the data set, uploading the data set to a CVAT image marking system, setting parameters such as segment size, chunk size and the like to be of proper sizes, and marking the screened data set (as shown in figure 9). The team divides the training set, the verification set and the test set into 8:1:1, selects proper weight files, modifies training parameters and optimizes the model, so as to obtain the model of the system.
With reference to figures 1-8 of the drawings,
the corn tassel identification system comprises a system software main interface module, a system login interface module, a comprehensive detection module and an output folder opening module;
the inside of the comprehensive detection module is provided with: the device comprises a picture detection module, a camera detection module and a video detection module;
the system login interface module opens software to enter a login interface;
when the picture detection module is used, after successful login, the system automatically jumps to the main page. Clicking a 'selection model', selecting a 'yolov5s' or 'yolov5x' trained model for target detection, clicking 'loading data' to jump to file management, and selecting a picture to be identified to obtain an identified effect;
clicking the upper left corner of the camera detection module to detect the camera when the camera detection module is used, opening the configured camera, and aligning the camera to the corn tassel to be identified, so that the identified effect can be obtained;
when the video detection module is used, firstly clicking a 'selection model', selecting a model trained by 'yolov5s' or 'yolov5x' to carry out target detection, clicking 'loading data' to jump to file management, and selecting a video to be identified, thereby obtaining an identified effect;
when the output folder opening module is used, after the identification of pictures, cameras or videos is finished, clicking the 'open output folder' at the lower left corner can jump to a file management interface, and then the result can be checked.
The system software main interface module develops a graphical interface of the software by using a QtDesigner;
qt is a cross-platform C++ application development framework and has strong graphical interface development capability. Qt is used to develop applications with graphical user interfaces, qtDesigner is one of the many tools it provides, and the process of creating user interfaces for Qt-based applications can be simplified. Qt provides rich graphical interface elements and widgets, from basic buttons, text boxes and labels to advanced charts, tables and drawing tools, and supports 3D graphics and OpenGL. These widgets can help developers create a variety of complex user interfaces. QtDesigner is part of the Qt application development framework and is a design tool for creating Graphical User Interfaces (GUIs). PySide2 can let us use Qt through Python language. The PySide2 library is a main development tool of the software 'corn tassel identification system', and after the environment is installed and configured, a graphical interface of the software can be developed by using QtDesigner.
The system login interface module is developed by using an OpenCV open source computer vision library, and aims to provide a set of tools and functions widely used for image processing and computer vision tasks. OpenCV was originally developed by intel and later becomes an open source project, now maintained and developed by an active community. It supports various programming languages including C++, python and Java, and can run on operating systems such as Windows, linux and Mac OS.
The OpenCV library provides a number of functions and algorithms including image processing, feature detection, object recognition, object tracking, face detection and recognition, machine learning, and the like. It also supports various computer vision tasks such as feature detection, feature matching, object recognition, object tracking, face recognition, gesture recognition, etc. This makes OpenCV very useful in the fields of image recognition, machine vision, and automation.
: the advantage of OpenCV is that it is an open source software library with a high degree of flexibility and customizable. Its community support and contribution is also very active, continually pushing new functions and improvements, its open source nature and rich functionality make it the first choice tool in research, education and business projects.
YOLOv5 inside the video detection module is a deep learning algorithm for object detection, which can detect multiple objects in an input image and provide its location and category information. YOLOv5 has real-time performance while maintaining accuracy, can perform target detection at a very high frame rate, and is suitable for real-time applications such as automatic driving, real-time video monitoring and the like. Moreover, YOLOv5 supports a variety of different model sizes (e.g., YOLOv5s, YOLOv5m, YOLOv5l, YOLOv5 x) so that a developer can select an appropriate model according to the needs of the application. The algorithm can detect targets at different scales, which is helpful for detecting targets with different sizes and improves detection performance.
YOLOv5 is a high-performance, real-time target detection algorithm, has a lightweight design, is suitable for various application fields, and is easy to deploy. Its real-time performance and accuracy make it a powerful tool for many computer vision and deep learning projects. The system is designed based on the Yolov5 algorithm.
The video detection module can use a MySQL database; mySQL is an open-source relational database management system, which is one of the most popular and widely used databases. MySQL is a relational database management system that uses tables (tables) to store data, and relationships can be established between tables to facilitate association and querying between data. In addition, mySQL is highly optimized, has excellent performance, and is capable of handling large data sets and high concurrent access. It supports multithreading, cache management, and query optimization to improve performance.
MySQL provides powerful security functions including user authentication, rights management, and data encryption to help protect sensitive data. The system is a database management system with strong functions, high reliability and good cost effectiveness, and is suitable for application programs and projects of various scales. Its open source nature and broad support make it the database of choice for many developers and organizations.
The main interface function code is as follows:
main.py (Main interface function code)
According to the invention, the image recognition technology is adopted, so that farmers can be helped to recognize the situation of corn tassel more quickly and accurately, and measures can be taken timely, and the spread and damage of diseases and insect pests are avoided. Meanwhile, the system can realize real-time monitoring and early warning, helps farmers to know the growth condition of crops in time, and improves the production efficiency of the crops.
The system has the advantages of simplicity in operation, powerful functions, high reliability and the like, can be used as a preliminary basis for the mechanized emasculation research of corn, can detect the quantity and growth condition of corn tassel, reduces labor cost, and promotes the development of agriculture to an automatic, intelligent and large-scale direction.
According to the invention, the picture, the video and the camera can be used for identifying the corn tassel in real time, so that the phenotype characteristics of the corn tassel can be rapidly and accurately detected, and a reference is provided for agricultural condition monitoring in the corn tassel stage. Meanwhile, the method is beneficial to farmland management personnel to master the growth condition of crops in the area, and the method establishes a grain policy and has a certain guiding effect on yield estimation.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A maize tassel identification system which characterized in that: the corn tassel identification system comprises a system software main interface module, a system login interface module, a comprehensive detection module and an output folder opening module;
the inside of the comprehensive detection module is provided with: the device comprises a picture detection module, a camera detection module and a video detection module;
the system login interface module opens software to enter a login interface;
when the picture detection module is used, after successful login, the system automatically jumps to the main page; clicking a 'selection model', selecting a 'yolov5s' or 'yolov5x' trained model for target detection, clicking 'loading data' to jump to file management, and selecting a picture to be identified to obtain an identified effect;
clicking the upper left corner of the camera detection module to detect the camera when the camera detection module is used, opening the configured camera, and aligning the camera to the corn tassel to be identified, so that the identified effect can be obtained;
when the video detection module is used, firstly clicking a 'selection model', selecting a model trained by 'yolov5s' or 'yolov5x' to carry out target detection, clicking 'loading data' to jump to file management, and selecting a video to be identified, thereby obtaining an identified effect;
when the output folder opening module is used, after the identification of pictures, cameras or videos is finished, clicking the 'open output folder' at the lower left corner can jump to a file management interface, and then the result can be checked.
2. The maize tassel identification system of claim 1, wherein: the system software main interface module develops a graphical interface of the software by using a QtDesigner;
qt is a cross-platform C++ application development framework and has strong graphical interface development capability; qt is used to develop applications with graphical user interfaces, qtDesigner is one of the many tools it provides, which can simplify the process of creating user interfaces for Qt-based applications; qt provides rich graphical interface elements and widgets, from basic buttons, text boxes and labels to advanced charts, tables and drawing tools, and supports 3D graphics and OpenGL; these widgets can help developers create a variety of complex user interfaces; qtDesigner is part of the Qt application development framework, a design tool for creating Graphical User Interfaces (GUIs); pySide2 can let us use Qt through Python language; the PySide2 library is a main development tool of the software 'corn tassel identification system', and after the environment is installed and configured, a graphical interface of the software can be developed by using QtDesigner.
3. The maize tassel identification system of claim 1, wherein: the system login interface module is developed by using an OpenCV open source computer vision library, and aims to provide a set of tools and functions widely used for image processing and computer vision tasks; openCV was originally developed by intel and later becomes an open source project, now maintained and developed by an active community; it supports various programming languages including C++, python and Java, and can run on operating systems such as Windows, linux and Mac OS.
4. The maize tassel identification system of claim 3, wherein: the OpenCV library provides a number of functions and algorithms including image processing, feature detection, object recognition, object tracking, face detection and recognition, machine learning, and the like; it also supports various computer vision tasks such as feature detection, feature matching, object recognition, target tracking, face recognition, gesture recognition, etc.; this makes OpenCV very useful in the fields of image recognition, machine vision, and automation.
5. The maize tassel identification system of claim 3, wherein: the advantage of OpenCV is that it is an open source software library with a high degree of flexibility and customizable; its community support and contribution is also very active, continually pushing new functions and improvements, its open source nature and rich functionality make it the first choice tool in research, education and business projects.
6. The maize tassel identification system of claim 1, wherein: YOLOv5 inside the video detection module is a deep learning algorithm for object detection, and can detect a plurality of objects in an input image and provide position and category information thereof; YOLOv5 has real-time performance while maintaining accuracy, can perform target detection at a very high frame rate, and is suitable for real-time applications such as automatic driving, real-time video monitoring and the like; moreover, YOLOv5 supports a variety of different model sizes (e.g., YOLOv5s, YOLOv5m, YOLOv5l, YOLOv5 x) so that a developer can select an appropriate model according to the needs of the application; the algorithm can detect targets at different scales, which is helpful for detecting targets with different sizes and improves detection performance;
YOLOv5 is a high-performance real-time target detection algorithm, has a light-weight design, is suitable for various application fields, and is easy to deploy; its real-time performance and accuracy make it a powerful tool for many computer vision and deep learning projects; the system is designed based on the Yolov5 algorithm.
7. The maize tassel identification system of claim 1, wherein: the video detection module can use a MySQL database; mySQL is an open-source relational database management system, which is one of the most popular and widely used databases; mySQL is a relational database management system that uses tables (tables) to store data, and relationships can be established between tables, making it easier to associate and query between data; in addition, mySQL is highly optimized, has excellent performance, and can process large data sets and high concurrent access; the system supports the functions of multithreading, cache management, query optimization and the like so as to improve the performance;
MySQL provides powerful security functions including user authentication, rights management, and data encryption to help protect sensitive data; the system is a database management system with strong functions, high reliability and good cost effectiveness, and is suitable for application programs and projects of various scales; its open source nature and broad support make it the database of choice for many developers and organizations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311316557.1A CN117274816A (en) | 2023-10-12 | 2023-10-12 | Maize tassel identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311316557.1A CN117274816A (en) | 2023-10-12 | 2023-10-12 | Maize tassel identification system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117274816A true CN117274816A (en) | 2023-12-22 |
Family
ID=89200682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311316557.1A Pending CN117274816A (en) | 2023-10-12 | 2023-10-12 | Maize tassel identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117274816A (en) |
-
2023
- 2023-10-12 CN CN202311316557.1A patent/CN117274816A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gutierrez et al. | A benchmarking of learning strategies for pest detection and identification on tomato plants for autonomous scouting robots using internal databases | |
| Dell et al. | Automated image-based tracking and its application in ecology | |
| US7136524B1 (en) | Robust perceptual color identification | |
| Alkhudaydi et al. | An exploration of deep-learning based phenotypic analysis to detect spike regions in field conditions for UK bread wheat | |
| Li et al. | Fast detection and location of longan fruits using UAV images | |
| Böckmann et al. | Rapid and low-cost insect detection for analysing species trapped on yellow sticky traps | |
| Huang et al. | YOLO-EP: a detection algorithm to detect eggs of Pomacea canaliculata in rice fields | |
| Morchid et al. | Intelligent detection for sustainable agriculture: A review of IoT-based embedded systems, cloud platforms, DL, and ML for plant disease detection | |
| Popescu et al. | New trends in detection of harmful insects and pests in modern agriculture using artificial neural networks. a review | |
| Lu et al. | Maize plant detection using UAV-based RGB imaging and YOLOv5 | |
| Rößle et al. | Efficient noninvasive FHB estimation using RGB images from a novel multiyear, multirater dataset | |
| Mitra et al. | aGRodet 2.0: An Automated Real-Time Approach for Multiclass Plant Disease Detection | |
| Dang et al. | Computer Vision for Plant Disease Recognition: A Comprehensive Review | |
| Yu et al. | Maize tassel number and tasseling stage monitoring based on near-ground and UAV RGB images by improved YoloV8 | |
| Tariq et al. | An image dataset of fruitfly species (Bactrocera Zonata and Bactrocera Dorsalis) and automated species classification through object detection | |
| Paiva-Peredo | Deep learning for the classification of cassava leaf diseases in unbalanced field data set | |
| CN117274816A (en) | Maize tassel identification system | |
| Mostafizur Rahman Komol et al. | Sugarcane diseases identification and detection via machine learning | |
| Altınbaş et al. | Detecting defected crops: Precision agriculture using haar classifiers and UAV | |
| Jing et al. | Sunflower-YOLO: Detection of sunflower capitula in UAV remote sensing images | |
| Liu et al. | Pear flower recognition based on yolo v5s target detection model in complex orchard scenes | |
| Lin et al. | A Framework for Single-Panicle Litchi Flower Counting by Regression with Multitask Learning | |
| Kwon et al. | Case study: things to be considered for high-throughput phenotyping in genomic studies | |
| Lunawat et al. | An Efficient Approach for Crop Disease Detection using Deep Learning | |
| Putra et al. | Vision-Based Object Detection for Efficient Monitoring in Smart Hydroponic Systems |
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 |