Abstract | ||
---|---|---|
One of the central problems in Automated Target Recognition is to accommodate the infinite variety of clutter in real military environments. The principle focus of our paper is on the construction of metric spaces where the metric measures the distance between objects of interest invariant to the infinite variety of clutter. Such metrics are formulated using second-order random field models. Our results indicate that this approach significantly improves detection/classification rates of targets in clutter. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/TPAMI.2005.97 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
clutter invariant atr,central problem,metric space,metric measure,second-order random field model,real military environment,interest invariant,automated target recognition,infinite variety,classification rate,principle focus,context modeling,cluster analysis,indexing terms,layout,random field,object recognition,stochastic processes,principal component analysis,photometry,algorithms,robustness,computer simulation,second order,statistics,image classification,strontium,clutter,artificial intelligence | Computer vision,Object detection,Random field,Pattern recognition,Clutter,Computer science,Stochastic process,Artificial intelligence,Invariant (mathematics),Metric space,Contextual image classification,Cognitive neuroscience of visual object recognition | Journal |
Volume | Issue | ISSN |
27 | 5 | 0162-8828 |
Citations | PageRank | References |
0 | 0.34 | 9 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dmitri Bitouk | 1 | 238 | 9.65 |
Michael I Miller | 2 | 3123 | 422.82 |
Laurent Younes | 3 | 1490 | 120.48 |