Discrimination gain to optimize detection and classification

A method for managing agile sensors to optimize detection and classification based on discrimination gain is presented. Expected discrimination gain is used to determine threshold settings and search order for a collection of discrete detection cells. This is applied in a low signal-to-noise environment where target-containing cells must be sampled many times before a target can be detected or classified with high confidence. The goal of sensor management is interpreted here to be to direct sensors to optimize the probability densities produced by a data fusion system that they feed. The use of discrimination is motivated by its interpretation as a measure of the relative likelihood for alternative probability densities. This is studied in a problem where a single sensor can be directed at any detection cell in the surveillance volume for each sample. Bayes rule is used to construct a recursive estimator for the cell target probabilities. The expected discrimination gain is predicted for each cell using its current target probability estimates. This gain is used to select the optimal cell for the next sample. The expected discrimination gains can be maintained in a binary search tree structure for computational efficiency. The computational complexity of this algorithm is proportional to the height of the tree which is logarithmic in the number of detection cells. In a test case for a single 0 dB Gaussian target, the error rate for discrimination directed search was similar to the direct search result against a 6 dB target     

Bias Estimation in an Association-Free Nonlinear Filter

Musick, S., and Kastella, K., Bias Estimation in an Association-Free Nonlinear Filter, Digital Signal Processing12 (2002) 484–493Previous nonlinear filtering research has shown that by directly estimating the probability density of a target state using a track-before-detect scheme, weak and densely spaced targets can be tracked, and data association (in which reports are associated with tracks) can be avoided. Data association imposes a heavy burden on tracking, both in its design, where complex data management structures are required, and in its execution, which often requires many computer cycles. Therefore, avoiding data association can have advantages. However, a concern exists that data association is essential for estimating and correcting additive sensor biases, which are nearly always present. This paper demonstrates that target tracks and sensor biases can be estimated simultaneously using association-free nonlinear methods. We begin by defining a state consisting of target locations and a slowly drifting sensor bias. Stochastic models for state dynamics and for the measurement function are presented. A track-before-detect nonlinear filter is constructed to estimate the joint density of the state variables. A simulation that emulates estimator behavior is exercised under low signal-to-noise conditions. Simulation results are presented and discussed. This work extends the useful range of nonlinear filtering methods in tracking applications.     

Event-averaged maximum likelihood estimation and mean-field theoryin multitarget tracking

This paper presents a novel type of Kalman filter for track maintenance in multitarget tracking using thresholded sensor data at high target/clutter densities and low detection levels. The filter is robust against tracking errors induced by crossing tracks, clutter, and missed detections, and the computational complexity of the filter scales well with problem size. There are two key features that differentiate this approach from earlier work. First, to reduce computational load, the filter exploits techniques from statistical field theory to simplify measurement to track association by using a mean-field approximation to sum over associations. Second, to enhance tracking of close together targets, the filter explicitly models the error correlations that occur between such target pairs. These error correlations are caused by measurement to track association ambiguities that arise when target separations are comparable to sensor measurement errors     

An Information-Based Approach to Sensor Management in Large Dynamic Networks

This paper addresses the problem of sensor management for a large network of agile sensors. Sensor management, as defined here, is the process of dynamically retasking agile sensors in response to an evolving environment. Sensors may be agile in a variety of ways, e.g., the ability to reposition, point an antenna, choose sensing mode, or waveform. The goal of sensor management in a large network is to choose actions for individual sensors dynamically so as to maximize overall network utility. Sensor management in the multiplatform setting is a challenging problem for several reasons. First, the state space required to characterize an environment is typically of very high dimension and poorly represented by a parametric form. Second, the network must simultaneously address a number of competing goals. Third, the number of potential taskings grows exponentially with the number of sensors. Finally, in low-communication environments, decentralized methods are required. The approach we present in this paper addresses these challenges through a novel combination of particle filtering for nonparametric density estimation, information theory for comparing actions, and physicomimetics for computational tractability. The efficacy of the method is illustrated in a realistic surveillance application by simulation, where an unknown number of ground targets are detected and tracked by a network of mobile sensors.