Vision Sensor Billet Disease Detection in Harvesters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current disease detection methods in agricultural harvesting are inefficient, as they rely on manual inspections pre- or post-harvesting, leading to delayed detection and missed diseased areas within fields, particularly for crops like sugarcane where diseases like 'red rot' can spread quickly.
Innovation Solution
A system and method that uses a vision-based sensor on an agricultural harvester to capture images of chopped billets and analyze them for disease indications, such as discolorations, allowing for real-time detection and initiation of control actions like operator notifications or field mapping to mitigate disease spread.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual inspection is performed pre-harvesting or post-harvesting at offsite locations, then disease detection can be conducted, but detection is delayed and specific disease areas within the field cannot be identified
Solution Approach 1:
The system performs disease detection during the harvesting operation itself, before the crops are fully processed and transported. The vision sensor captures images of harvested material on the harvester, enabling disease identification to occur preliminarily during harvesting rather than after transport to offsite locations, thus eliminating detection delays.
Solution Approach 2:
The patent replaces manual inspection with an automated vision-based detection system. The vision sensor and image processing system automatically detect disease symptoms in harvested material, substituting the slow manual inspection process with rapid automated analysis that provides immediate feedback during harvesting operations.
2Measurement precision
If manual inspection is performed in the field pre-harvesting, then some disease areas can be identified, but the inspection is limited to a very small area of the field
Solution Approach 1:
The vision-based detection system on the harvester serves multiple functions: it detects diseases in harvested material while the harvester moves through the entire field, providing both comprehensive field coverage and continuous monitoring. This multi-functional approach allows the system to inspect the entire harvested area rather than being limited to small pre-harvest inspection zones.
Solution Approach 2:
The system performs detection during harvesting, capturing images of material as it is being processed. This preliminary detection during the harvesting process itself allows coverage of the entire field area that is being harvested, rather than being limited to small pre-harvest inspection areas.
3Productivity
If vision-based sensors are deployed on the harvester to capture images of billets, then real-time disease detection is enabled, but the system complexity increases
Solution Approach 1:
The vision sensor system is integrated with the existing harvester operations, utilizing the harvester's movement through the field and its harvesting function to enable disease detection. The system leverages the harvester's existing infrastructure and operational flow, adding detection capability without requiring separate dedicated detection equipment, thus managing complexity while maintaining high productivity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables rapid and accurate detection of diseases during harvesting, allowing for timely action to prevent crop loss and disease spread by identifying diseased areas within the field as sugarcane is processed.
Implementation Method 1
a vision-based sensor supported on or within the agricultural harvester. The vision-based sensor is configured to capture images of the billets created by the chopper assembly
Data Source
AI summary
In one aspect, a method for detecting diseases within harvested materials during operation of an agricultural harvester includes receiving, with a computing system, an image of billets created by a chopper assembly of the agricultural harvester; analyzing, with the computing system, the image to identify indications of disease in association with one or more of the billets contained within the image; and initiating, with the computing system, a control action in response to the identification of indications of disease in association with the one or more billets contained within the image.