Crop Growth Stage Imaging for Nutrient Deficiency Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for diagnosing nutrient deficiencies in crops are inaccurate, time-consuming, and limited to indoor conditions, failing to account for full plant image analysis across different growth stages and lacking comprehensive morphological feature analysis, which hinders precise nutrient deficiency detection.
Innovation Solution
A system utilizing a trained single shot deep learning network to analyze crop images from multiple views, segmenting plant regions, and computing a balanced plant nutrition index (BPNI) to identify nutrient deficiencies based on morphological features, calculating deficiency scores, and recommending nutrient adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing image processing methods are used to analyze plant morphological features, then the analysis can be performed, but the accuracy of identifying macronutrients and micronutrients deficiency is insufficient
Solution Approach 1:
The system segments the plant into multiple regions (upper leaves, middle leaves, lower leaves, terminal buds) and analyzes each region separately. This segmentation allows the system to identify nutrient deficiencies more accurately by examining specific morphological features in different plant zones, resolving the contradiction between general analysis capability and specific nutrient identification accuracy.
Solution Approach 2:
The system transitions from traditional 2D image analysis to 3D spatial analysis by capturing images from multiple viewpoints (top view, front view, right side view, left side view) and integrating them. This multi-dimensional approach enables comprehensive extraction of morphological features including leaf area, length, width, thickness, and curvature, significantly improving nutrient deficiency detection accuracy and reliability.
2Area of stationary object
If full plant image analysis is performed without considering growth stages, then the analysis covers the entire plant, but the accuracy of deficiency detection is reduced
Solution Approach 1:
The system performs preliminary classification of the plant's growth stage (vegetative, flowering, or maturity stage) before conducting nutrient deficiency analysis. This preliminary action allows the system to apply growth stage-specific morphological feature extraction and evaluation criteria, thereby maintaining high detection accuracy across the entire plant area by adapting the analysis method to the appropriate growth phase.
3Reliability
If traditional nutrient diagnosis methods are used, then comprehensive analysis can be performed, but the process is very expensive and time consuming
Solution Approach 1:
The system replaces traditional manual or laboratory-based nutrient diagnosis methods with an automated computer vision system using deep learning. The trained single shot deep learning network automatically extracts morphological features from multi-view images and identifies nutrient deficiencies, providing comprehensive diagnosis results in seconds without the time-consuming and expensive procedures of traditional methods.
Solution Approach 2:
The system enables farmers to perform self-diagnosis of nutrient deficiencies using the automated image analysis system. By capturing images with a mobile device or camera and processing them through the deep learning model, farmers can independently identify nutrient deficiencies and receive recommendations without requiring external expert intervention, significantly reducing both time and cost while maintaining diagnostic comprehensiveness.
4Area of stationary object
If aerial photographs are used for nutrient deficiency identification, then large area coverage is achieved, but top to bottom scanning of plants is lacking causing ineffective diagnose
Solution Approach 1:
The system employs asymmetric multi-view imaging by capturing images from four different perspectives (top view, front view, right side view, left side view) rather than uniform aerial photography. This asymmetric approach ensures that the system can scan the plant from top to bottom and extract comprehensive morphological features including leaf curvature, thickness, and regional variations, thereby maintaining both field coverage capability and diagnostic effectiveness.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
This disclosure relates generally to system and method to determine crop growth stage nutrient deficiencies. Diagnosing correct nutrient deficiencies in the plant is very challenging based on plant image analysis during the cropping season. The method of the present disclosure enables assessing nutrient deficiency using image processing techniques according to current crop growth stage. The method receives from an image capturing device a plurality of crop images of one or more crop fields. Further, trained single shot deep learning network determines a crop growth stage from a plurality of crop growth stages for each crop by extracting a plurality of morphological features. Then, the health state of the crop is determined based on a balanced plant nutrition index (BPNI) value. Further, a plurality of nutrient deficiencies corresponding to the current crop growth stage of the unhealthy crop. Further, a total nutrient deficiency score for deficient nutrients of the unhealthy crop.