<title>Modeling intent for a target tracking and identification scenario</title>

Abstract

The tracking goal is to reduce positional uncertainty. There are many ways to reduce tracking uncertainty: including classification data, using trafficability maps, and employing behavior information. We seek to extend tracking and identification modeling by incorporating intent to update prediction velocity vectors. A hybrid state space approach is formulated to deal with continuous-valued kinematics and discrete-valued target type, pose (inherently continuous but quantized), and intent behavior. The coupled tracker design is illustrated within the context of using ground moving target indicator (GMTI) and high range-resolution (HRRR) measurements as well as digital terrain elevation data (DTED), road map, and estimated goal states. The resulting Intent Coupled Tracking and Identification (ICTI) system is expected to outperform separately designed systems particularly during target maneuvers and recovering from temporary data dropout.

Contextual Tracking Approaches in Information Fusion

“…Over the many issues for contextual target tracking, we looked at the variations in the themes and while there is discussion on context awareness (as situation awareness using ontologies and logical networks), there was limited analysis of connections to threat assessment [101] for context inference. Ideas exist for game-theoretic modeling of multiple affiliation entities being tracked [102]; however, there is a need for context-based human, social, cultural, and behavior (HSCB) modeling and assessment [103]. For example, HSCB can be used can be used with road information to isolate which pedestrians, how fast cars are moving on roads, and clutter mitigation that does not conform to social, cultural and behavioral norms which leads to human, animal, vehicle and clutter (HVAC) target categorization.…”

Overview of contextual tracking approaches in information fusion

“…Over the many issues for contextual target tracking, we looked at the variations in the themes and while there is discussion on context awareness (as situation awareness using ontologies and logical networks), there was limited analysis of connections to threat assessment [97] for context inference. Ideas exist for game-theoretic modeling of multiple affiliation entities being tracked [98]; however, there is a need for context-based human, social, cultural, and behavior (HSCB) modeling and assessment [99]. For example, HSCB can be used can be used with road information to isolate which pedestrians, how fast cars are moving on roads, and clutter mitigation that does not conform to social, cultural and behavioral norms which leads to human, animal, vehicle and clutter (HVAC) target categorization.…”

Dismount tracking and identification from electro-optical imagery

“…A target tracking system [45] of objects includes target identity (allegiance) [46], intent [47], and vehicles of use [48]. Additionally, modeling the dismount requires a threat analysis [49] and emotion state of the players [50].…”

“…electro-optical/ Infrared (EO/IR) [7], radar [8]), algorithms for simultaneous tracking and identification, [9,10] situational awareness (e.g. behavioral intent [11] and site security [12]), and databases for behavior tracking and forecasting. For successful dismount tracking, key developments necessitate use of contextual information as well as knowledge management for determining dismount activity in relation to the situation [13], user interaction with tracking algorithms to diagnose dismount suspicious (intended) but yet unobserved information [14], and understanding culture [15].…”