Real-Time Point Recognition for Seedlings Using Kernel Density Estimators and Pyramid Histogram of Oriented Gradients
Bibliographic record
Abstract
This paper introduces a new real-time method based on a combination of kernel density estimators and pyramid histogram of oriented gradients for identifying a point of interest along the stem of seedlings suitable for stem–stake coupling, also known as the ‘clipping point’. The recognition of a clipping point is a required step for automating the stem–stake coupling task, also known as the clipping task, using the robotic system under development. At present, the completion of this task depends on the expertise of skilled individuals that perform manual clipping. The robotic stem–stake coupling system is designed to emulate human perception (in vision and cognition) for identifying the clipping points and to replicate human motor skills (in dexterity of manipulation) for attaching the clip to the stem at the identified clipping point. The system is expected to clip various types of vegetables, namely peppers, tomatoes, and cucumbers. Our proposed methodology will serve as a framework for automatic analysis and the understanding of the images of seedlings for identifying a suitable clipping point. The proposed algorithm is evaluated using real-world image data from propagation facilities and greenhouses, and the results are verified by expert farmers indicating satisfactory performance. The precise outcomes obtained through this identification method facilitate the execution of other autonomous functions essential in precision agriculture and horticulture.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".