<title>Improved state estimation through use of roads in ground tracking</title>

Abstract

The ability to provide an accurate view of a region of interest is standard among existing tracking systems. The extension of this capability to include accurate projections of the targets to future times increases the complexity of the problem. However, this ability to predict future locations is an important problem due to the inherent time latency that is present from "sensor to shooter." Because of this, a major requirement of the tracking system is that it must be able to use available information to accurately predict future target locations. The focus of this paper is to describe an improved state estimation technique that incorporates road information by using a Variable Structure 1MM. Furthermore, this approach will identify and account for stopped or stationary moving targets. Finally, some preliminary performance results will be presented.

Ground target tracking and road map extraction

“…Such road maps provide valuable context information which can be used for improving the quality of GMTI tracking (Shea et al, 2000;Agate and Sullivan, 2003;Arulampalam et al, 2002;Ulmke, 2003;Pannetier et al, 2005;Ulmke and Koch, in press). This does not only affect the achievable track accuracy but also the weighting factors for association hypotheses in MHT techniques (Multi-Hypotheses Tracking) or, more generally, the problem of track continuity and track separation.…”

Road Map Extraction using GMTI Tracking

“…Such road maps provide valuable context information which can be used for improving the quality of GMTI tracking [4,5,6,7,8]. This does not only affect the achievable track accuracy but also the weighting factors for association hypotheses in Multiple Hypothesis Tracking (MHT) or, more generally, the problem of track continuity and track separation.…”

Improved target tracking with road network information

“…The classical framework for handling such problems is the so-called jump-Markov (non)linear systems. Early studies dealing with the problem used the interacting multiple model (IMM) algorithm [1,2] with extended Kalman filters (EKFs) as sub-blocks [3][4][5]. Since the different road segments corresponded to different modes in these IMM algorithms, there were too many of them to be considered at a single step of the multiple model filter.…”