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. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/IGARSS.2012.6351059 | IGARSS |
Keywords | Field | DocType |
remote sensing,roof-top detection,remote sensing image,structural element detection combination,structural engineering computing,image sensors,image sampling,roof-top sample detection,lda,hierarchical topic estimation model,object detection,satellite imaging,topic model,roofs,roof-top extraction method,probability,probabilistic topic model,computational modeling,indexes,probabilistic logic,dictionaries,visualization | Small number,Object detection,Computer vision,Satellite,Image sensor,Computer science,Remote sensing,Artificial intelligence,Roof,Topic model,Probabilistic logic,Detector | Conference |
ISSN | ISBN | Citations |
2153-6996 E-ISBN : 978-1-4673-1158-8 | 978-1-4673-1158-8 | 0 |
PageRank | References | Authors |
0.34 | 3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hao Feng | 1 | 0 | 0.34 |
Zhiguo Jiang | 2 | 321 | 45.58 |
Jihao Yin | 3 | 90 | 12.18 |