Semiautomatic Road Extraction From VHR Images Based on Multiscale and Spectral Angle in Case of Earthquake
Bibliographic record
Abstract
Road extraction offers great potential for research initiatives because of the complexity due to its great topological variability. The use of remote sensing imagery to accomplish this mapping is an interesting option. Indeed, satellite images can be acquired shortly after the event, and cover a large area of territory. We hope to produce a mapping of the present facilities from very high resolution images shortly after a disaster. This availability of very high spatial resolution images brings added value to the study in urban areas and their mapping. Increasing the spatial resolution generates noise, which makes extraction difficult, especially in the event of an earthquake in an urban context. This problem increases false alarm rates and generally affects the performance of road extraction algorithms in detecting linear features used to locate and extract roads on such images. During major disasters, short deadlines demand an effective response in terms of updating the mapping of affected areas. Our aim is to improve the road extraction quality after adaptation of Lowe's scale-invariant features transform descriptors jointly with spectral angle algorithms. An illustration is performed on three high-resolution images, respectively, representing a rural, suburban, and urban disaster area, captured by the Quickbird satellite. Our approach significantly reduces the false detection rate and shows an increase in overall quality of up to nearly 30% in some cases as compared to what obtain in the literature.
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 | 0.001 |
| Bibliometrics | 0.002 | 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".