|
DF Level 0. Level 0
functions operate on sensor data to produce (extract) features using
inference models. For the imaging sensors, Object classification
(labeling) is inferable using inference models developed by Deep Learning
(DL) processes trained in the mission planning phase on targets and
environments representative of those expected in the ATO area. The Level 0
outputs are Object and Event detections such as radar “contacts” (reflected
and received power exceeds some Constant False Alarm Rate (CFAR) threshold)
and image bounding boxes about some object type of interest. For
Electro-Magnetic (EM) sensors, the C-ATA UAV can come near to the targets
to detect and triangulate intentional and non-intentional EM emissions
from, e.g., Low Probability of Intercept (LPI) emissions, site motor
generators, and computer networks. In this modality, the Level 0 outputs
are estimated waveform parameters like carrier frequency and modulation
along with Lines of Bearing (LOB). DF Level 0 often includes knowledge
bases of a priori data drawn from an ontology resulting from an Intelligence
Preparation of the Operational Environment (IPOE)
including target and confounder Characteristics and Performance (C&P),
other Scientific and Technical Intelligence (S&TI), Order-of-Battle
(OB), terrain data, ambient objects, man-made structures, avoidance areas,
and other GEOspatial INTelligence
(GEOINT). This data is structured into a formal ontology
to support processing by DF functions.
DF Level 1.
Level 1 processes estimate properties of Events and Objects, where Position,
Identification, Classification, and Composition properties (PICC) are
developed from Level 0’s extracted features using, typically, statistical
estimation (e.g., Kalman filter) and probabilistic inference (e.g., Bayesian,
Dempster-Shafer, fuzzy) algorithms.
As part of Level 1
fusion, Classification processes estimate that an object is a type of a
class, e.g., SA-2 missile launcher or Spoon Rest acquisition radar.
Classification is about “what”. Identification says the object is a
member-of or belongs-to an Organization, e.g.,
NATO, Al Qaeda. Identification is about “who”, involving estimation of
attribution/ownership. Organization here is in a general sense and can
include not just nationalities but also alliances or subdivisions or
groupings thereof.
DF Level 2.
Level 2 is concerned about linkages between Objects and Events. When the linkages are about wholes and
their parts, it is Composition. An example is the Composition of an SA-2
SAM site consisting of parts, such as missile launchers, radars,
generators, command and control trailers, arranged in some standard
layouts. This can be represented as a graph where the nodes are the Objects
and Events and the edges are the type of relationships between them, e.g.,
whole-part, distance-from. Similarly, the a priori data, structured
into a formal ontology, can be formed into graphs. Directed Attributed Relational Graphs (DARG) and
associated graph association methods (see, e.g., ) have high potential for this type
of Level 2 DF. The DARG
analytical processes involve representation of layered data, cross-layer
(graph) association, and associated evidence-to-situation information by
graph-matching. In recent work, an inexact subgraph matching algorithm was
developed as a variation of the subgraph isomorphism approach for situation
assessment.
DF Level 3. Level 3 is concerned with
prediction. In this example, this
means inferring the Tactics, Techniques, and Procedures (TTP) being used by
the adversary and then the adversary’s possible and probable Courses of
Action (CoA). In this C-ATA example
it could be the air defense TTP and the Position of Intended Movement (PIM)
of the targets.
DF Level 4.
Level 4 is concerned with Information-optimizing resource
management. Each C-ATA UAV’s DF estimation process is
coupled with a sensor/source management process. An integrated approach to
sensor management is based on an embedded scheme for trading off mission
objectives with optimal sensor data acquisition and is integrated into the
real-time DF processes.
Gross, G., Nagi, R. and Sambhoos, K.
"Continuous Preservation of Situational Awareness through
Incremental/Stochastic Graphical Methods," 14th International
Conference on Information Fusion, Chicago, IL, 26-29 July 2011.
|
