Machine Vision Cherry Picking via Stem Detection and Size Sorting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic picking technologies are inadequate for cherries, which are small spherical-like fruits with long stems and grow in dense clusters, leading to low picking efficiency and a lack of automated classification methods.
Innovation Solution
A cherry picking and classifying method based on machine vision that includes image processing to extract stem features, determine a picking point, and classify cherries by size using pixel-based contour analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If existing automatic picking technologies are used for cherries, then picking can be automated, but picking efficiency remains low due to the unique characteristics of cherries (small size, long stems, dense clusters)
Solution Approach 1:
The image processing is divided into multiple sequential stages: noise filtering, stem feature extraction, picking point determination, and classification. This segmentation allows each stage to focus on specific characteristics of cherries, improving overall automation effectiveness despite the challenging fruit characteristics
Solution Approach 2:
Machine vision serves as an intermediary between the picking system and the cherries. The vision system captures images, extracts stem features, and determines optimal picking points, enabling automated decision-making that accounts for the unique morphology of cherries with long stems and dense cluster growth
2Measurement precision
If manual classification is used for cherries, then classification accuracy is maintained, but labor costs and time consumption increase
Solution Approach 1:
The manual classification process is replaced with an automated image processing system that extracts contour features and calculates cherry sizes based on pixel analysis. This substitution maintains classification accuracy while eliminating the time loss associated with manual sorting
Solution Approach 2:
The physical classification process is replaced by creating digital copies (images) of cherries and analyzing them through image processing algorithms. The contour extraction and pixel-based size calculation provide accurate classification without requiring physical handling and measurement
3Productivity
If cherries are picked independently without the stem, then picking speed increases, but fruit damage occurs easily
Solution Approach 1:
The system performs preliminary analysis of the stem structure and determines the optimal picking point before execution. By pre-identifying the correct location on the stem for cutting, the system ensures that cherries are detached at the proper position, preventing damage while maintaining efficient automated operation
Data Source
AI summary
The present disclosure provides a cherry picking and classifying method based on machine vision, including: acquiring an image for a cherry with a stem hung on a branch, filtering the image to remove noise, and taking a resulting image as an original image; processing the original image to extract a stem feature of the cherry, and determining a picking point for picking; acquiring an image for a picked cherry to obtain a classification image; processing the classification image to extract a contour feature of the cherry, and calculating a size of the cherry according to the contour feature; and classifying the cherry according to size data of the cherry. The present disclosure further provides a picking and classifying device, including: an acquisition module, a classifying transmission module, a connection module; and a control module.