Neural-network calibration of a multiple-line laser-camera range sensor for 3D surface-geometry measurement
Bibliographic record
Abstract
Single-line laser-camera range sensors require scanning over the object surface to measure three-dimensional (3D) surface geometry. Full-field 3D surface measurement techniques typically require more than one pattern to be projected and captured by camera. This paper presents a method to calibrate a multiple-line laser-camera range sensor using an artificial neural network (NN) to enable capture of full-field 3D surface geometry using a single projected pattern. The range sensor projects nineteen laser lines onto a surface. During calibration, points in 2D images are extracted from the intersections of nineteen laser profiles and horizontal lines marked on a calibration plate, for several calibration plate positions. A mapping of 2D image coordinates to 3D object coordinates is performed separately for each laser-line projection using a multi-layer perceptron (MLP) neural network. Experiments using different NN configurations found a network with two hidden layers of 43 nodes per layer using the sigmoidal activation function to generate the lowest 3D reconstruction errors. Errors were consistent errors over all calibration positions. Calibration with an acceptable error for many applications can be achieved without knowledge of the camera pose. The fast 3D reconstruction by the trained system may permit low resolution full-field 3D surface-geometry measurement in real-time.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".