Powerline Detection in Aerial Images Using Neural Networks
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
<p>This study builds a machine learning (ML) model to identify the components of a powerline. The power infrastructure is subject to extreme weather conditions, wear, and environment changes. Power structures require routine maintenance to provide reliable power to the community. Inspections are often done by humans, requiring special equipment to climb up to great heights. This can be dangerous as there is electricity, and the risk of falling. This is a time-consuming process which can be streamlined with the use of drones. Drone-acquired images can be used where a ML model processes the data and finds all the issues present. Using an existing dataset a YOLOv8 deep neural network model was developed to identify the different components on a powerline. The developed model quickly unveiled the challenges of creating an accurate model for powerline inspection. It was found that the components on a powerline are very small and look so similar to each other, making accurate classifications very difficult. There were problems within the dataset identified such as the data disparity between classes. Overall, the model developed is a good starting point for further development, and much information was gained which will be used to further improve the model.</p>
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it