A depth-based land-use semantic extraction method for landscape images
Bibliographic record
Abstract
Integrated aerial and ground-based observations are essential for rapid land-use classification in modern land surveys, requiring efficient analysis of large volumes of landscape images. These images often contain background noise that impedes classification accuracy and exhibit spatial compression of the main scene, which causes semantic spatial distortion as depth increases. To address these challenges, this paper proposes a depth-based land-use semantic extraction (DLSE) method that effectively reduces background noise and corrects spatial distortions. The DLSE method follows three main steps: (1) depth estimation per pixel using a multi-resolution neural network to delineate the main scene range, filtering semantic noise; (2) conversion of perspective projection to orthographic projection per pixel to correct spatial distortion; and (3) improved land-use semantic extraction through MobileViT-enhanced feature extraction in SegNet. Experimental results demonstrate that DLSE achieves a 96.84 % accuracy with more detailed outputs and operates at 23 fps, positioning it as an efficient tool for automated land surveys and land-use decision-making. • Projection Transformation: Converts perspective projection to orthographic projection, reducing spatial distortion in land-use semantics. • Enhanced Segmentation: Integrates MobileViT into SegNet, optimizing feature extraction for better efficiency and accuracy in segmentation. • Accurate Depth Estimation: Uses multi-resolution deep neural networks for precise pixel depth estimation, filtering background noise. • High Performance Metrics: Achieves 96.84 % accuracy in land-use semantic extraction with a processing speed of 23 fps on mobile devices.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".