The system can accurately identify and distinguish different paddy pest types. It supports detection through pictures, picture sets, video files, and real-time cameras. Features include columnar graph analytics, identification markers, class counting, adjustable confidence, IOU threshold, and result display. In addition, a user management system based on SQLite has been developed
The Data Transmission Service we rely on is the cornerstone of accuracy and practicality. The dataset used in this study not only performs well in scale, covering a total of 5,229 images, including 4,178 training images, 546 validation images, and 505 test images, but also strictly checks the quality to ensure the reliability of the experimental results and the practicality of the system.
System interface effect
The system uses PySide6 as a GUI library, providing an intuitive and user-friendly interface. Below, I will introduce the functions and design of each main interface in detail
The system provides SQLite-based sign-up and login management functions. Users need to register through the registration interface when they use it for the first time. After entering the username and password, the system will store this information in the SQLite database. After successful registration, users can enter the username and password through the login interface to log in. This design ensures the security of the system and provides the possibility to add more personalized functions in the future.
If you have any questions or need the full code or data or need customized development requirements, you can contact me Email Mail me : slowlon@foxmail.com
On the main interface, the system provides functions to support the input of pictures, videos, real-time cameras and batch files. Users can select the pictures or videos to be detected for paddy pest detection by clicking the corresponding buttons, or start the camera for real-time detection. During detection, the system will display the detection results in real time and store the detection records in the database.
In addition, the system also provides the function of changing the YOLOv8 model with one click. Users can select a different YOLOv8 model for detection by clicking the “Change Model” button on the interface. At the same time, the dataset attached to the system can also be used to retrain the model to meet the user’s detection needs in different scenarios.
The image file will resize the image to 850x500, and preprocess the image, you can use the model to make predictions.
In our paddy pest detection system study, we compared the performance of four different versions of the YOLO family: YOLOv5nu, YOLOv6n, YOLOv7-tiny, and YOLOv8n. By conducting rigorous experiments on the same data set and using two key metrics, F1-Score and mAP, we analyzed the performance of each model in detail.
