Improvements and Evaluation of an In-Field Bin Filler for Apple Bruising and Distribution
Bibliographic record
Abstract
Abstract. Automatic bin filling is needed for apple harvest and in-field sorting. A commercially viable bin filler for in-field use should be simple, compact, low in cost, and be able to distribute apples evenly in the bin without causing bruising damage. An innovative bin filling technology was developed for incorporation with the new apple harvest and in-field sorting machine recently developed by our group. Field tests of the first version of the bin filler in the 2016 harvest season showed relatively high bruising rates and uneven fruit distributions. Subsequently, a second version of the bin filler was developed with several major improvements. A new pair of foam rollers for better control of apples exiting the sorting system and avoiding fruit collisions during free falling was added below the sorter. An improved pinwheel with nine longer soft pads, instead of four short pads as in the original version, was installed for better fruit distribution. Foam guides, attached to the long pads, reduced the rolling speed of fruit from the pads into the bin. Field tests conducted in the 2017 harvest season showed that the second, improved version of the bin filler achieved superior performance in reducing bruise damage, with 99% of ‘Gala’ apples and 98% ‘Blondee’ of apples graded Extra Fancy. Furthermore, a depth imaging method, using a Kinect-v2 camera, was proposed to quantitatively compare the performance of the two bin fillers for distribution of fruit in the bin under uniform and non-uniform feeding conditions. Analysis of the fruit height data showed that the apple distributions were not significantly affected by feeding method for both bin fillers. Overall, the second version of the bin filler resulted in better distributions of apples in the bin, compared to the first version, and uneven distributions mainly occurred in the corners of the bin, which could not be reached by the bin filler’s pinwheel. The improved bin filler meets the requirements for apple harvest and in-field sorting, and it has potential for use with other harvest platforms. Keywords: 3D imaging, Apple, Bin filling, Bruising, Harvest, Sorting.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".