Mobile Image Analysis of Harvested Material for Processing Quality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the processing quality of agricultural harvested materials, such as corn silage, are cumbersome, expensive, and lack precision, particularly in the manual separation and analysis of grain components using dedicated cameras or smartphones.
Innovation Solution
A method utilizing a mobile device with a computing unit and a trained machine learning model to analyze image data of agricultural harvested material samples, enabling automated classification and geometric analysis of grain components without manual separation, thereby determining an indicator of processing quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual separation and analysis of grain components is performed using dedicated cameras or smartphones, then measurement precision can be achieved, but device complexity and ease of operation deteriorate
Solution Approach 1:
The patent replaces manual mechanical separation and physical analysis of grain components with an automated optical imaging system using a camera and machine learning algorithm. The system captures images of grain components in the harvested material and automatically determines processing quality indicators through image analysis, eliminating the need for manual separation and physical measurement while maintaining or improving measurement precision.
Solution Approach 2:
The system enables the harvested material itself to provide the measurement information through its visual characteristics. By analyzing images of the grain components directly in the context of the harvested material, the system allows the material to 'self-report' its processing quality without requiring external manual intervention or complex sample preparation procedures.
2Measurement precision
If manual separation and analysis of grain components is performed, then measurement precision can be achieved, but loss of time increases
Solution Approach 1:
The patent replaces time-consuming manual separation and analysis procedures with automated optical imaging and machine learning-based image analysis. The system captures images of grain components and automatically processes them through algorithms that rapidly determine processing quality indicators, reducing analysis time from minutes or hours of manual work to seconds of automated processing while maintaining measurement precision.
3Measurement precision
If dedicated cameras are used for analysis, then measurement precision improves, but ease of operation and device complexity worsen
Solution Approach 1:
The patent employs a camera, which is a universal device already commonly available in smartphones and other mobile devices, to perform the specialized function of grain component analysis. This multi-functional approach allows the same device to serve both as a general-purpose camera and as a precision measurement instrument for determining processing quality indicators, thereby improving ease of operation without sacrificing measurement precision.
4Measurement precision
If corn grains are washed out and manually separated, then measurement precision improves, but loss of time and ease of operation worsen
Solution Approach 1:
The patent extracts only the essential visual information needed for measurement from the harvested material, rather than requiring physical extraction and separation of grain components. By capturing images that directly show the grain components in their natural context within the harvested material, the system eliminates the time-consuming washing and manual separation steps while maintaining the ability to accurately determine the corn silage processing score through image analysis.
Data Source
AI summary
A method and a system for determining an indicator of processing quality of an agricultural harvested material using a mobile device is disclosed. A computing unit analyzes image data of a prepared sample of harvested material containing grain components and non-grain components in an analytical routine to determine the indicator of the processing quality of the agricultural harvested material. Further, the computing unit uses a trained machine learning model in the analytical routine to perform at least one step of determining the indicator of the processing quality of the agricultural harvested material.