Agricultural Image Normalization Without Reference Strips
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for characterizing agricultural field variability using aerial images and sensors face challenges in comparing fields due to variability in sensor outputs and crop conditions, and the need for high nitrogen reference strips, which are difficult to establish and maintain.
Innovation Solution
A method for normalizing image data by identifying and segregating areas with unusual development patterns, using color infrared and NDVI layers to select a best representative pixel value, allowing for precise application rates of agricultural compounds without requiring high nitrogen reference strips.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If high nitrogen reference strips are used for normalization, then consistency of parameter relationships is improved, but device complexity and ease of operation deteriorate due to the difficulty of establishing and maintaining these strips
Solution Approach 1:
The system automatically identifies and selects the best representative pixel values from the image data itself, without requiring external reference strips. The normalization process serves itself by using intrinsic field characteristics (best pixels) rather than requiring separately established reference standards, thereby eliminating the complexity of creating and maintaining high nitrogen reference strips while maintaining normalization consistency
Solution Approach 2:
The invention extracts the normalization reference directly from the image data by identifying best representative pixels within the field boundaries. Instead of relying on external reference strips that must be established separately, the system extracts the necessary normalization information from the actual field imagery, simplifying the overall process while maintaining reliability
2Stability of the object's composition
If equal area classification is used, then distribution of high and low zones is improved, but relationship to actual crop conditions deteriorates
Solution Approach 1:
The system applies different classification approaches to different parts of the data distribution. Rather than forcing all fields into equal area classes, the methodology uses best pixel normalization to preserve local variations in crop conditions while still providing structured classification. This allows each region to be classified according to its actual characteristics rather than a uniform distribution scheme
3Manufacturing precision
If equal increment classification is used, then class definition is improved, but representation in some fields deteriorates
Solution Approach 1:
The system uses best pixel normalization to ensure that classification thresholds are set appropriately for each field's actual range of values. Rather than applying fixed equal increment classes that may not represent all fields, the methodology adjusts the classification action to match the partial needs of each specific field, ensuring all fields have adequate representation while maintaining precise class definitions
Data Source
AI summary
A method of processing vegetation data including the steps of identifying data relating to an agricultural field, segregating areas of predetermined development patterns and prescribing application rates of an agricultural compound. The identifying step includes identifying data relating to an agricultural field representative of areas of predetermined development patterns of vegetation in the field. The segregating step includes segregating the areas of the predetermined development patterns thereby defining segregated areas, other areas in the field being non-segregated areas. The prescribing step including prescribing application rates of an agricultural compound to the non-segregated areas dependent on at least one attribute determined from the data.