Simultaneous feature-based identification and track fusion

Proceedings of the IEEE 2010 National Aerospace & Electronics Conference, 2010

Airborne tracking and identification (ID) of high value ground targets is a difficult task impacted by sensor, target, and environmental conditions. Layered sensing, using a combination of standoff and short-range sensors, maintains target track and identification in cluttered environments such as cities or densely vegetated areas through sensor diversity. Data, feature, decision, or information fusion is necessary for high confidence target classification to be achieved using multiple sensors and sensor modalities. Target identification performance is improved by exploiting the extra information gained from independent sensing modalities through information fusion for automatic target recognition (ATR). Increased target ID has been demonstrated using spatial-temporal multi-look sensor fusion and decision level fusion. To further enhance target ID performance and increase decision confidence, feature level fusion techniques are being investigated. A fusion performance model for feature level fusion was applied to a combination of sensor types and features to provide estimates of a fusion gain. This paper presents a fusion performance gain for Synthetic Aperture Radar (SAR), electro-optical (EO), and infrared (IR) video stationary target identification.

IEEE Aerospace and Electronic Systems Magazine, 2000

Target tracking using multiple sensors can provide better performance than using a single sensor. One approach to multiple target tracking with multiple sensors is to first perform single sensor tracking and then fuse the tracks from the different sensors. Two processing architectures for track fusion are presented: sensor to sensor track fusion, and sensor to system track fusion. Technical issues related to the statistical correlation between track estimation errors are discussed. Approaches for associating the tracks and combining the track state estimates of associated tracks that account for this correlation are described and compared by both theoretical analysis and Monte Carlo simulations.

This paper presents an online adaptive multiple feature fusion and template update mechanism for kernel-based target tracking. According to the discrimination between the object and background, measured by two-class variance ratio, the multiple features are combined by linear weighting to realize kernel-based tracking. An adaptive model-updating mechanism based on the likelihood of the features between successive frames is addressed to alleviate the mode drifts. In this paper, RGB colour features, Prewitt edge feature and local binary pattern (LBP) texture feature are employed to implement the scheme. Experiments on several video sequences show the effectiveness of the proposed method.

2011

Performance evaluation of simultaneous tracking and identification (STID) systems consists of measures of performance, measures of effectiveness, and measures of force effectiveness. To investigate the capability of STID, we extend track purity to a current assignment ratio. Track purity determines the correctly associated measurements for a given scan where as the Current Assignment Ratio (CAR) determines the correct measurements for a given track. Using the CAR aids sensor management algorithms in determining which targets have robust features for target identification in clutter, such that the target can be tracked. The CAR enables effectiveness evaluation of STID systems for mission success. In the paper, we review the fusion performance evaluation literature, outline STID metrics, and demonstrate the use of the CAR in a scenario.

2012

Multiple target tracking that integrates target model estimation and data association steps is described. The integration allows successive refinement of the models while reducing the uncertainty in data association. Each target is described by "weak" models of kinematics, shape and appearance. The target models are refined in a two-stage process: imagebased tracklets of high purity and accuracy are generated, and geospatial tracks are extended from these tracklets. During each stage of tracking, observation data of reduced uncertainties are associated with the refined tracks in a probabilistic manner. We describe our approach in the context of a real time system that has been tested and evaluated for vehicle and human tracking in sparse, medium, and dense clutter using aerial EO/IR video.

2006

The objective of this chapter is to present and compare different fusion rules which can be used for Generalized Data Association (GDA) for multitarget tracking (MTT) in clutter. Most of tracking methods including Target Identification (ID) or attribute information are based on classical tracking algorithms such PDAF, JPDAF, MHT, IMM, etc. and either on the Bayesian estimation and prediction of target ID, or on fusion of target class belief assignments through the Dempster-Shafer Theory (DST) and Dempster’s rule of combination. The main purpose of this study is to pursue our previous works on the development of a new GDA-MTT based on Dezert-Smarandache Theory (DSmT) but compare it also with standard fusion rules (Dempster’s, Dubois & Prade’s, Yager’s) and with the new fusion rules: Proportional Conflict Redistribution rule No.5(PCR5), fusion rule based on T-Conorm and T-Norm Fuzzy Operators(TCN rule) and the Symmetric Adaptive Combination (SAC) rule. The goal is to assess the effici...

IEEE Transactions on Signal Processing, 2021

2006 9th International Conference on Information Fusion, 2006

In many useful video tracking situations, targets move through repeated mutual occlusions. As targets undergo occlusions , the feature subsets and combinations of those features that are effective in identifying the target and improvin g tracking performance may change. We use Combinatorial Fusion Analysis to select and evaluate criteria by which to identify the combination of features that will produce the most accurate tracking.

Iee Proceedings-radar Sonar and Navigation, 1997

A joint probabilistic data association filter that uses adaptive update times for tracking targets in a cluttered environment is presented and compared with the joint probabilistic data association filter that uses a constant update time. The tracking performance of the algorithm is assessed by Monte Carlo simulations on different target trajectories.

IEEE Transactions on Aerospace and Electronic Systems, 2001

We present the development of a multisensor fusion algorithm using multidimensional data association for multitarget tracking. The work is motivated by a large scale surveillance problem, where observations from multiple asynchronous sensors with time-varying sampling intervals (electronically scanned array (ESA) radars) are used for centralized fusion. The combination of multisensor fusion with multidimensional assignment is done so as to maximize the "time-depth,'' in addition to "sensor-width" for the number S of lists handled by the assignment algorithm. The standard procedure, which associates measurements from the most recently arrived S -I frames to established tracks, can have, in the case of S sensors, a time-depth of zero. A new technique, which guarantees maximum effectiveness for an S-dimensional data association (S 2 3), i.e., maximum time-depth (S -I) for each sensor without sacrificing the fusion across sensors, is presented.