Abstract | ||
---|---|---|
Ground Penetrating Radar (GPR) is a widely used technique for detecting buried objects in subsoil. Exact localization of buried objects is required, e.g. during environmental reconstruction works to both accelerate the overall process and to reduce overall costs. Radar measurements are usually visualized as images, so-called radargrams, that contain certain geometric shapes to be identified. This paper introduces a component-based image reconstruction framework to recognize overlapping shapes spanning over a convex set of pixels. We assume some image to be generated by interaction of several base component models, e.g., handmade components or numerical simulations, distorted by multiple different noise components, each representing different physical interaction effects. We present initial experimental results on simulated and real-world GPR data representing a first step towards a pluggable image reconstruction framework. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-319-01595-8_35 | Studies in Classification Data Analysis and Knowledge Organization |
Field | DocType | ISSN |
Radar,Iterative reconstruction,Computer vision,Physical interaction,Ground-penetrating radar,Computer science,Convex set,Artificial intelligence,Pixel,Geometric shape | Conference | 1431-8814 |
Citations | PageRank | References |
2 | 0.44 | 4 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andre Busche | 1 | 32 | 4.31 |
Ruth Janning | 2 | 45 | 7.88 |
Tomás Horváth | 3 | 122 | 18.50 |
Lars Schmidt-Thieme | 4 | 3802 | 216.58 |