Digital Detection of Transgenic Maize Drug Resistance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting drug resistance in transgenic maize are time-consuming and inefficient, relying on manual measurement of morphological features which do not accurately reflect a plant's resistance under changing environmental conditions.
Innovation Solution
A digital detection method using RGB images, three-dimensional point cloud data, and chlorophyll relative content, combined with convolutional neural networks and long-short term memory networks to predict drug resistance by calculating pixel ratios and morphological features, and distinguishing between transgenic and non-transgenic maize varieties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual measurement of morphological features is used for drug resistance detection, then the detection can be performed on maize plants, but the detection process is time-consuming and inefficient
Solution Approach 1:
The patent replaces manual mechanical measurement with an automated digital detection system that captures images of maize plants and uses image processing algorithms to automatically extract morphological features. This substitution eliminates time-consuming manual operations while maintaining measurement accuracy, directly resolving the contradiction between detection reliability and productivity.
Solution Approach 2:
The detection system enables the maize plants to 'self-report' their morphological characteristics through automated image capture and analysis. The system automatically processes images, extracts features such as plant height and leaf area, and generates detection results without requiring manual intervention, thereby significantly improving detection efficiency while preserving accuracy.
2Device complexity
If morphological feature parameters are measured manually, then the detection method is simple, but the detection period is long and the process is inefficient
Solution Approach 1:
The patent implements preliminary automated image capture and processing steps that prepare detection data in advance. The system pre-processes images, automatically identifies plant features, and calculates morphological parameters before final analysis, thereby shortening the overall detection period while maintaining methodological simplicity through automation.
Solution Approach 2:
Manual measurement operations are replaced with automated digital image processing systems that rapidly analyze plant morphology. This substitution dramatically reduces the detection period by eliminating time-consuming manual measurements while keeping the detection approach conceptually simple through automated workflows.
3Loss of time
If seed-based drug resistance testing is performed, then the test period is short and environmental requirements are low, but the final drug resistance performance of maize plants does not completely match that of seeds
Solution Approach 1:
The patent transitions from seed-based testing to plant-based digital phenotyping, adding the dimension of actual plant growth observation. By capturing and analyzing morphological features of growing plants, the system bridges the gap between seed potential and actual plant performance, providing more reliable drug resistance assessment that reflects real-world conditions while maintaining efficiency through automated detection.
Solution Approach 2:
The system implements continuous monitoring and feedback by repeatedly capturing images of maize plants during growth and tracking changes in morphological features. This feedback mechanism allows the system to assess actual drug resistance performance in real-time, ensuring that the detected resistance characteristics accurately reflect the plant's true performance rather than just seed potential.
Data Source
AI summary
A digital detection method and system for predicting drug resistance of transgenic maize are disclosed. The method includes acquiring an RGB image, three-dimensional point cloud data and chlorophyll relative content of a maize plant after medicament spraying at a current moment; calculating a pixel ratio and morphological feature according to the RGB image and three-dimensional point cloud data; inputting a detection parameter of the maize plant at the current moment into a series model to predict the detection parameter of the maize plant at a next moment to obtain a graph of change in the detection parameter in a next period; estimating a drug resistance characteristic according to the graph of the change in the detection parameter of the maize plant; and inputting the detection parameter of the maize plant at the current moment into a parallel model to predict the variety of the maize plant.