Title :
Semantic information extraction from multispectral geospatial imagery via a flexible framework
Author :
Gleason, Shaun ; Ferrell, Regina ; Cheriyadat, Anil ; Vatsavai, Raju ; De, Soumya
Author_Institution :
Oak Ridge Nat. Lab., Oak Ridge, TN, USA
Abstract :
Identification and automatic labeling of facilities in high-resolution satellite images is a challenging task as the current thematic classification schemes and the low-level image features are not good enough to capture complex objects and their spatial relationships. In this paper we present a novel algorithm framework for automated semantic labeling of large image collections. The framework consists of various segmentation, feature extraction, vector quantization, and Latent Dirichlet Allocation modules. Initial experimental results show promise as well as the challenges in semantic classification technology development for nuclear proliferation monitoring.
Keywords :
feature extraction; image classification; satellite communication; automated semantic labeling; current thematic classification scheme; feature extraction; high resolution satellite image; image collection; multispectral geospatial imagery; nuclear proliferation monitoring; semantic information extraction; vector quantization; Feature extraction; Image segmentation; Pixel; Satellites; Semantics; Tiles; Visualization; Latent Dirichlet Allocation; Satellite image analysis; invariant features; semantic classification;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2010 IEEE International
Conference_Location :
Honolulu, HI
Print_ISBN :
978-1-4244-9565-8
Electronic_ISBN :
2153-6996
DOI :
10.1109/IGARSS.2010.5649141