3D rock fragmentation analysis using lidar, based on point cloud deep learning segmentation and synthetic data
Bibliographic record
Abstract
Accurate online measurement of particle size distribution is crucial in mining, tunnelling , and mineral processing industries to enable intelligent process control and optimization, ultimately enhancing efficiency and productivity. The current method for rock fragmentation relies on 2D image analysis, which is highly dependent on optimal lighting conditions, limiting its applicability and robustness in the challenging lighting environments commonly found in mining. This study diverges from the prevalent 2D image and photogrammetry approaches in rock fragmentation analysis, and pioneers a novel approach by harnessing laser scanner data for point cloud segmentation, offering a promising solution to overcome the limitations of image analysis techniques. By leveraging laser scanner data, a robust framework for rock fragmentation analysis is developed that is tailored to the specific challenges related to lighting situations. To avoid the laborious task of collecting and labelling point cloud datasets, this research introduces an innovative approach of using synthetic labeled datasets of scanned rockpiles. A platform is developed to automatically create and scan labeled point clouds of rock piles, facilitating the utilization of transfer learning . The synthetic 3D dataset was used to train a deep learning model for precise segmentation of rock instances in three-dimensional coordinates, providing an accurate representation of the rock object in 3D. The accuracy of the developed predictive model was tested and validated on experimental laser scanning data of three different rock piles. The proposed method depends on coordinate data instead of RGB information, rendering it particularly applicable in challenging conditions such as underground mining, night shifts, or situations where maintaining optimal lighting conditions is difficult or costly. The findings present a significant leap forward in rock fragmentation analysis, opening avenues for enhanced practices in diverse mining environments.
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 | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".