Segmentation of planar surfaces in LiDAR point clouds of an electrical substation by exploring the structure of points neighbourhood
Bibliographic record
Abstract
Abstract. According to the Department of Energy of the USA, today’s electrical distribution system is 97.97% reliable. However, power outages and interruptions still impact many people. Many power outages are caused by animals coming into contact with the conductive elements of the electrical substations. This can be prevented by covering the conductive electrical objects with insulating materials. The design of these custom-built insulating covers requires a 3D as-built plan of the substation. This research aims to develop automated methods to create such a 3D as-built plan using terrestrial LiDAR data for which objects first need to be recognized in the LiDAR point clouds. This paper reports on the application of a new algorithm for the segmentation of planar surfaces found at electrical substations. The proposed approach is a region growing method that aggregates points based on their proximity to each other and their neighbourhood dispersion direction. PCA (principal components analysis) is also employed to segment planar surfaces in the electrical substation. In this research two different laser scanners, Leica HDS 6100 and Faro Focus3D, were utilized to scan an electrical substation in Airdrie, a city located in north of Calgary, Canada. In this research, three subsets incorporating one subset of Leica dataset with approximately 1.7 million points and two subsets of the Faro dataset with 587 and 79 thousand points were utilized. The performance of our proposed method is compared with the performance of PCA by performing check point analysis and investigation of computational speed. Both methods managed to detect a great proportion of planar points (about 70%). However, the proposed method slightly outperformed PCA. 95% of the points that were segmented by both methods as planar points did actually lie on a planar surface. This exhibits the high ability of both methods to identify planar points. The results also indicate that the computational speed of our method is superior to that of PCA by 50%. It is concluded that our proposed method achieves better results with higher computational speed than PCA in the segmentation of planar surfaces.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".