Coordinating high-resolution hyperspectral and RGB video acquisition of dynamic natural water scenes
Bibliographic record
Abstract
A bimodal video imaging platform combining 371-band hyperspectral and red-green-blue (RGB) video acquisition systems was constructed and used to collect video imagery of the Lake Ontario shoreline at Hamlin Beach State Park in Rochester, New York, United States. We designed a video processing workflow to correlate video reflectance data collected by a line-scanning imaging spectrometer and a traditional RGB video camera for hyperspectral imagery prediction. Using the relationship between the hyperspectral video (HSV) data and RGB video, we tested our workflow by predicting hyperspectral image frames of dynamic natural water scenes from the RGB imagery at times prior to and following a time segment where we had developed a correlative model between the two imagery data streams. We acquired HSV using a Headwall Hyperspec micro-high efficiency visible and near-infrared imaging spectrometer in the low-rate video mode of our configuration and RGB data with a low-cost consumer GoPro Hero 8 Black. Hyperspectral image band predictions used distributions of absolute and normalized residuals in radiometrically calibrated reflectance spaces. Within visible wavelengths, 95% of the scene was predicted to within 2% absolute reflectance, which translates to ∼30% of signal level for water spectra. In the near-infrared regime, the normalized error percentage of the residuals sharply increased to ∼90% for 95% of the scene due to lack of band information from the RGB video imagery of our shallow water scene.
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) | 0.000 | 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 | 0.000 | 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".