Geo-Based Vector Joining for High-Resolution Agricultural Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The increasing computational resource requirements for processing high-quality agricultural image data, such as for crop yield predictions, necessitate significant data storage and processing resources due to the inefficiencies of raster data representation.

Innovation Solution

Implementing a system that converts contiguous groups of cells in agricultural image data to vector data representation, indexed using R-trees, and aggregates data using user-defined functions, reducing storage and processing needs by replacing large groups of cells with compact vector representations and utilizing tile maps for navigation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high-quality agricultural image data is processed using raster data representation, then measurement precision is improved, but computational resource requirements increase

Engineering Contradiction:
Improveimage data qualityVSAvoidcomputational resource requirement
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent segments the raster data processing by identifying contiguous groups of cells with the same value and separating them as distinct vector objects. This segmentation allows the system to process only the boundaries of homogeneous regions rather than every individual cell, reducing computational load while preserving the precision needed for agricultural analysis.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the data representation parameter from raster (grid-based) to vector (geometry-based) for contiguous regions. This parameter change transforms the fundamental structure of data storage and processing, enabling more efficient computational operations while maintaining the ability to represent agricultural features with high precision.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If high-quality agricultural image data is processed using raster data representation, then measurement precision is improved, but data storage resources increase

Engineering Contradiction:
Improveimage data qualityVSAvoiddata storage requirement
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent merges contiguous cells with the same value into single vector objects representing entire regions. Instead of storing data for each individual cell, the system stores geometric representations of merged regions, significantly reducing storage requirements while preserving the ability to analyze agricultural data at the required precision level.

Inventive Principle:
Principle #5Merging (Combining)

3Productivity

If vector data representation is used to replace raster data, then processing efficiency is improved, but data structure complexity increases

Engineering Contradiction:
Improveprocessing efficiencyVSAvoiddata structure complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent implements a dynamic system that automatically selects between raster and vector representations based on the characteristics of the data being processed. The system dynamically converts raster data to vector format when beneficial for processing efficiency, while maintaining the ability to switch back or use hybrid approaches, thus managing complexity adaptively rather than statically.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS12493656B2Geo-based vector data and raster data joining and/or aggregation using user defined function(s)
Publication Date: 2025.12.09 DEERE & CO
  • US12493656B2 patent drawing
  • US12493656B2 patent drawing
  • US12493656B2 patent drawing

AI summary

Techniques are disclosed herein that enable the generation and processing of user defined functions for customized aggregation and/or joining of instances of agricultural data. Various implementations include agricultural image data which includes one or more high elevation images that capture an agricultural plot. Additional or alternative implementations include transmitting the user defined function to a remote computing device for processing. In some implementations, the user defined function can be processed in tandem with additional user defined functions, where processing of instructions occurring in multiple user defined functions are not repeated.