Abstract
Reliable detection of small, local changes in real airborne laser scanning data remains difficult with current 3D change-detection techniques. Off-the-shelf methods often overlook subtle modifications or flag too many false positives. By combining semantics with geometry-based and deep-learning methods, we aim to improve robustness in noisy, cluttered settings.
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 31-32 |
| Seitenumfang | 2 |
| Fachzeitschrift | ERCIM NEWS- European Research Consortium for Informatics and Mathematics |
| Volume | 143 |
| Publikationsstatus | Veröffentlicht - 30 Jan. 2026 |
Research Field
- Responsive Sensing & Analytics
Fingerprint
Untersuchen Sie die Forschungsthemen von „Detecting Small Changes in 3D Aerial Scans: A Hybrid Approach for Real Urban Environments“. Zusammen bilden sie einen einzigartigen Fingerprint.Diese Publikation zitieren
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver