MPS-based information extraction method for remotely sensed imagery: a comparison of fusion methods
Bibliographic record
Abstract
Recently, multiple-point simulation (MPS) was introduced to increase the accuracy of information extraction from remotely sensed imagery by incorporating structural information through a training image. An important procedure in the MPS-based information extraction method is the fusion of two probability fields from two different classifiers, extracting spectral and spatial structure information. In previous studies the fusion process was accomplished using the theory of evidence and the theory of consensus. It has been shown that these fusion methods each have their own capabilities and characteristics for different data under different circumstances. This paper investigates primarily the advantages and disadvantages of three different types of fusion methods: evidence-based, consensus-based, and probability-based, and then compares the fusion results through an accuracy assessment. For validation purposes, we selected two remotely sensed images taken in different areas and with distinct structural characteristics of roads. Both images, from Satellite Pour l'Observation de la Terre 5 (SPOT5) with spatial resolution of 10 m, were used to investigate the performance of the three fusion methods in extracting road information with distinct structural characteristics from the images. A comparison of the different fusion methods can assist users in selecting the appropriate fusion method for the given data characteristics. Based on the results of two experiments, the relationships between these fusion methods are further investigated.
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 | 0.008 | 0.021 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.002 | 0.002 |
| 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".