SEMANTIC INFORMATION EXTRACTION FROM MULTISPECTRAL GEOSPATIAL IMAGERY VIA A FLEXIBLE FRAMEWORK

Conference · Fri Jan 01 00:00:00 EST 2010

OSTI ID:991189

Gleason, Shaun Scott ^[1]; Ferrell, Regina Kay ^[1]; Cheriyadat, Anil M ^[1]; Vatsavai, Raju ^[1]; De, Soumya ^[2]

---

1. ORNL
2. Missouri University of Science and Technology

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.

• Research Organization: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE National Nuclear Security Administration (NNSA)
• DOE Contract Number: DE-AC05-00OR22725
• OSTI ID: 991189
• Resource Relation: Conference: IGARSS 2010, Honolulu, HI, USA, 20100724, 20100730
• Country of Publication: United States
• Language: English

Related Subjects

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL PROTECTION
ALGORITHMS
CLASSIFICATION
MONITORING
PROLIFERATION
QUANTIZATION
SATELLITES
VECTORS