Greenhouse Cucumber Detection and Characterization for Harvesting Framework Implementation
Bibliographic record
Abstract
Cucumbers constitute a significant portion of greenhouse vegetables cultivated in southern Ontario. The human labour shortage and potential injuries associated with manual labour in cucumber harvesting highlight the need to explore automation as a viable solution. The proposed automated system in this study comprises two key components: an image processing unit and a cutting robotic arm. The image processing phase involves the identification of cucumbers using six models using shape and colour features. Four models are successfully employed in YOLOv8, yielding results in the form of bounding boxes and keypoints, with no false positives. Near-real-time cucumber detection is also achieved using YOLO. One model has been successfully tested in RoboFlow. Finally, one new model is being initially investigated for the direct management of raw RGB-XYZ data in Python. About harvesting unit, a robotic arm equipped with a cutting tool is programmed to move to specific positions and perform cutting tasks. To enable this functionality, a 3D camera and cutter are integrated into the TCP of a UR3e robot. The 3D camera installed on TCP of the robot can move at angles and positions to capture cucumbers hidden from view. Additionally, analyses of cucumber geometry and force are carried out to improve the understanding of cucumber properties. Finally, initial cost and OEE analyses are conducted to assess the potential improvement resulting from transitioning from manual harvesting to automation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".