SEAMLESS CO-REGISTRATION OF IMAGES FROM MULTI-SENSOR MULTISPECTRAL CAMERAS
Bibliographic record
Abstract
Abstract. Small-format, consumer-grade multi-camera multispectral systems have gained popularity in recent years. This is specifically due to the simplicity of their integration onboard platforms with limited payload capacity, such as Unmanned Aerial Vehicles (UAVs). Commercially available photogrammetric software can process the image data collected by these cameras to create multispectral ortho-rectified mosaics. However, misalignments of several pixels between spectral bands have been observed to be a common issue when employing these solutions, which can undermine the spectral and geometric integrity of the data. Besides, in advanced processing workflows such as object detection and classification with deep learning algorithms, band-to-band co-registered images are needed rather than one mosaic. We propose a two-fold solution for seamless band-to-band registration of images captured by five cameras integrated into a miniature multispectral camera system. This approach consists of 1) a robust self-calibration of the multispectral camera system to accurately estimate the intrinsic calibration parameters and relative orientation parameters of all cameras; 2) a single capture, band-to-band co-registration method based on trifocal constraints. This approach differs from existing literature since it is fully automatic, does not make any assumptions about the scene, does not use any best-fit projective or similarity transformations, and does not attempt cross-spectral feature-point matching. Our experiments confirm that the proposed co-registration method can accurately fuse multispectral images from a miniature multi-camera system and is invariant to large depth-variations in the captured 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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".