Building Detection from Pan-Sharpened GeoEye-1 Satellite Imagery Using Context Based Multi-Level Image Segmentation
Bibliographic record
Abstract
Availability of high resolution satellite imageries has increased its applications in the areas of aerial imageries. Few noted examples are update of GIS database of urban city, change detection and urban monitoring. Building detection is one of the most basic tasks in most of the aforementioned urban applications. This research is focused on automatic building detection from pan-sharpened very high spatial resolution satellite imagery. Building detection results are also used for subsequent evaluation of UNB pansharpening algorithm. The building detection utilizes shadow context, color tone, size, edge features, structural and geometric features, and prior knowledge in a multi-level segmentation based building detection. It first finds shadows using both pixels based and shadow region based analysis. In the next step, multi-resolution segmentation is performed using eCognition software with Sobel edge gradient image and principal component image as additional layers. Then, shadow geometry, according to Sun's azimuth angle, is utilized to detect the positions of buildings. Finally, spurious buildings are eliminated based on prior knowledge of objects which surround the buildings e.g., bare lands and roads. The performance is evaluated by both qualitative and quantitative analysis. The detection results are promising but still need modifications for real applications. Further, it also shows that UNB pansharpening performs well in applications utilizing spectral and spatial features.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".