Agricultural Item Quality Screening for Selective HSI Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Agricultural systems using hyperspectral imaging (HSI) cameras are inefficient and unreliable when scanning multiple agricultural items, leading to inconsistent quality measurement results.
Innovation Solution
An agricultural system with a camera, controller, and quality measuring device that uses machine-learned-related data and detection data to determine the suitability of measuring each agricultural item's quality, prioritizing items based on scores derived from probability matching, depth, and size, and controlling a robotic arm to position the quality measuring device for accurate measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If hyperspectral imaging is used to scan each of the plurality of agricultural items, then measurement completeness is improved, but time consumption increases
Solution Approach 1:
The system performs preliminary actions by using a camera to capture images and extract machine-learned-related data and detection data (depth, size, color ratio, segment size) before actual quality measurement. This preliminary screening identifies suitable agricultural items for measurement, avoiding time-consuming HSI scanning of unsuitable items while ensuring complete measurement of suitable ones.
Solution Approach 2:
The system applies partial action by selectively measuring only the subset of agricultural items that meet the suitability criteria determined by machine-learned-related data and detection data. This partial measurement approach reduces overall time consumption while maintaining measurement completeness for the targeted subset, avoiding the excessive action of scanning all items with HSI.
2Productivity
If arbitrary selection of agricultural items for scanning is performed, then measurement speed is improved, but measurement reliability deteriorates
Solution Approach 1:
The system implements feedback mechanisms by using machine-learned-related data and detection data (depth, size, color ratio, segment size) to evaluate and determine the suitability of each agricultural item before measurement. This feedback loop ensures that only suitable items are selected for measurement, maintaining high reliability while achieving efficient processing speed through automated suitability determination.
3Measurement precision
If quality measurement is performed on all agricultural items, then measurement comprehensiveness is improved, but system efficiency deteriorates
Solution Approach 1:
The system applies segmentation by dividing the agricultural items into two categories: suitable items for quality measurement and unsuitable items. Using machine-learned-related data and detection data, the system segments the measurement process into selective measurement of suitable items only, improving system efficiency while maintaining comprehensiveness through thorough measurement of the identified suitable subset.
Data Source
AI summary
An agricultural system includes a camera to acquire an image including an agricultural item, a controller configured or programmed to, based on the image acquired by the camera, determine whether or not it is suitable to measure a quality of the agricultural item, and a quality measuring device to measure the quality of the agricultural item when the controller determines that it is suitable to measure the quality of the agricultural item. The controller is configured or programmed to determine whether or not it is suitable to measure the quality of the agricultural item based on machine-learned-related data of the agricultural item and detection data of the agricultural item determined based on the image acquired by the camera.