Detection of compound structures using multiple hierarchical segmentations
Date
2012Source Title
2012 IEEE International Geoscience and Remote Sensing Symposium
Print ISSN
2153-6996
Electronic ISSN
2153-7003
Publisher
IEEE
Pages
6833 - 6836
Language
English
Type
Conference PaperItem Usage Stats
146
views
views
115
downloads
downloads
Abstract
In this paper, our aim is to discover compound structures comprised of regions obtained from hierarchical segmentations of multiple spectral bands. A region adjacency graph is constructed by representing regions as vertices and connecting these vertices that are spatially close by edges. Then, dissimilarities between neighboring vertices are computed using statistical and structural features, and are assigned as edge weights. Finally, the compound structures are detected by extracting the connected components of the graph whose edges with relatively large weights are removed. Experiments using WorldView-2 images show that grouping of these vertices according to different criteria can extract high-level compound structures that cannot be obtained using traditional techniques. © 2012 IEEE.
Keywords
Object detectionCompound structures
Connected component
Edge weights
Graph-based representations
Hier-archical clustering
Hierarchical segmentation
Object Detection
Region adjacency graphs
Spectral band
Structural feature
Traditional techniques
Geology
Remote sensing