Abstract
A novel roof-top extraction method for satellite images based on probabilistic topic model is presented. We model roof-top as the connected structural elements. The proposed method contains two major steps: 1) Detect structural elements, different from earlier structure detector, the proposed method automatically learn the types of elements from unlabeled samples; 2) Connect these elements to form roof-top boundary, where the relationships between elements are estimated by hierarchical topic model. This approach belongs to generative method where only a small number of roof-top samples are required. The experimental results demonstrate the effectiveness of the proposed approach.
| Original language | English |
|---|---|
| Pages | 2213-2216 |
| Number of pages | 4 |
| DOIs | |
| State | Published - 2012 |
| Externally published | Yes |
| Event | 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 - Munich, Germany Duration: 22 Jul 2012 → 27 Jul 2012 |
Conference
| Conference | 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 |
|---|---|
| Country/Territory | Germany |
| City | Munich |
| Period | 22/07/12 → 27/07/12 |
Keywords
- LDA
- remote sensing
- roof-top detection
- topic model
Fingerprint
Dive into the research topics of 'Roof-top detection based on structural elements combination'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver