Deep learning network-based paddy field waterlogging severity early warning method and system
By building a rice field waterlogging early warning system based on the YOLOv8 neural network, the time-consuming and labor-intensive problem of traditional manual monitoring has been solved, and real-time and accurate monitoring and early warning of rice field waterlogging have been achieved, ensuring the safety of rice growth.
CN120689811APending Publication Date: 2025-09-23HOHAI UNIV
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202510789184.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-13
- Publication Date
- 2025-09-23
AI Technical Summary
Technical Problem
Traditional manual monitoring of farmland waterlogging is time-consuming and labor-intensive, making it difficult to accurately grasp the waterlogging situation in real time, leading to hindered rice growth, reduced yields, and even total crop failure.
Method used
A rice field waterlogging severity early warning method based on deep learning networks was adopted. By building a YOLOv8 neural network model, video images captured by surveillance cameras were analyzed in real time, waterlogging conditions were labeled and classified, and early warning signals were issued.
Benefits of technology
It improves the real-time and accuracy of waterlogging warning, realizes efficient and automated monitoring of waterlogging in rice fields, and ensures food security.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN120689811A_ABST
Abstract
The invention discloses a paddy field waterlogging severity early warning method and system based on a deep learning network. The method comprises the steps that a video image shot by a paddy field monitoring camera is acquired, and a single-frame image is intercepted; marking the paddy field planting area of each image, evaluating the waterlogging condition of each marked area, and constructing a paddy field waterlogging severity data set; a neural network model based on a YOLOv8 network structure is constructed and trained, and model parameters are adjusted; accessing the trained neural network model into a monitoring device, sampling a monitoring image according to the severity of the paddy field waterlogging in a time-sharing manner, evaluating the severity of the paddy field waterlogging, giving out an early warning according to an evaluation result, adjusting a sampling interval according to the severity, and storing and recording the image and the corresponding severity; the system can better capture the change of the water accumulation amount of the paddy field, and can automatically monitor the waterlogging condition of the paddy field, thereby improving the waterlogging treatment speed of the paddy field, and guaranteeing the food safety.
Need to check novelty before this filing date? Find Prior Art