Bibliographic record
Abstract
Design, implementation and performance verification of an affordable field-based high-throughput plant phenotyping platform for monitoring Canola plants, including both data acquisition/visualization software and measurement system, was the main objective of this research. The primary motivation for this research is the fact that breeders need a well-organized approach and efficient tool to monitor and analyze a number of plant traits to achieve a higher yield. At the moment, manual measurement is a conventional approach to gather the required information for plant analysis. Nevertheless, manual measurement has many limitations especially to study a large-scale field. To address this bottleneck, a high-throughput plant phenotyping platform (HTPP) was developed which consists of a data acquisition system, a data storage unit, and a data visualization and analysis software. Such an HTPP will be an essential asset for breeders to conveniently gather a comprehensive database which contains various information such as a plant height, temperature, Normalized Difference Vegetation Index (NDVI), etc. To develop and implement such an HTPP, first, the overall system block diagram and required algorithms were drawn. Then to find the optimum set of equipment according to the requirement of this application, the performance of different sensors and devices were examined using literature search and experimental examinations in the laboratory setting. Then a mechanical boom was attached to the rear of a farm vehicle (a Swather) to carry different sensors, cameras and other measurement equipment (mechanical development of the boom structure was carried out by other members of the research team). A control box containing power supplies, safety fuses, and a data logger unit was attached to the farm vehicle, and a program was developed for data logger to read sensors signals as well as GPS data for data geo-referencing and future retrieval purposes. The efficiency of different system architecture including different data transmission networks was examined by conducting several field tests to minimize existing errors such as delays in synchronizing different steps. Three programs were developed in MATLAB GUI for image acquisition via webcam and DSLR cameras as well as a central program for data processing and interactive data visualization. The indoor tests were performed at the Robotics laboratory, University of Saskatchewan and outdoor experiments were performed on a Canola nursery at Cargill Canada, Aberdeen, SK, throughout spring-summer 2016 and 2017. Finally, the performance and effectiveness of the developed field-based phenotyping platform was validated by various measures such as conducting some manual measurements and comparing the results with the values given by the platform. According to the achieved results, both hardware and software components of the proposed system meet the requirements of a field-based plant phenotyping platform as an essential asset for breeders for comprehensive study of Canola plants or any other cultivars as a result of some minor design modifications. The main contributions of this study to plant phenotyping research are autonomous image acquisition capability, enhancement of the data acquisition cycle to minimize data geo-referencing error, development of a modular program for data visualization in MATLAB, and faster data collection in a high-throughput fashion (almost 125 times faster).
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".