Affinity Propagation Clustering of Measurements for Multiple Extended Target Tracking

Abstract

More measurements are generated by the target per observation interval, when the target is detected by a high resolution sensor, or there are more measurement sources on the target surface. Such a target is referred to as an extended target. The probability hypothesis density filter is considered an efficient method for tracking multiple extended targets. However, the crucial problem of how to accurately and effectively partition the measurements of multiple extended targets remains unsolved. In this paper, affinity propagation clustering is introduced into measurement partitioning for extended target tracking, and the elliptical gating technique is used to remove the clutter measurements, which makes the affinity propagation clustering capable of partitioning the measurement in a densely cluttered environment with high accuracy. The Gaussian mixture probability hypothesis density filter is implemented for multiple extended target tracking. Numerical results are presented to demonstrate the performance of the proposed algorithm, which provides improved performance, while obviously reducing the computational complexity.

A box-particle implementation of standard PHD filter for extended target tracking

“…In [30] and [31] , distance partition and distance partition with sub-partition were adopted. In addition, in order to handle a densely cluttered environment with high accuracy, Zhang and Wu suggested an affinity propagation clustering method for the measurement partitioning [4] . Distance partition is mainly used to the separated extended targets, however, the filters using it will lead to the problem with underestimation of target number (i.e., the cardinality underestimation problem) in situations where two or more extended targets are spatially close.…”

“…However, with increased resolution of modern and more accurate sensors (e.g., phased array radar), the target may occupy the sensor's multiple resolution cells, thus potentially generating a strongly fluctuating number of measurements at a given time step. In this case, this target is preferably defined as an extended target [4] , which provides not only the target's kinematic information but also the target-extension information as the size, shape and orientation of the target. Extended target tracking is valuable for many actual applications including ground-based radar stations tracking airplanes in the near field of the radar, vehicles tracking other road-users using radar sensors, and mobile robotics tracking pedestrians using laser range sensors.…”

An Improved Interacting Multiple Model Filtering Algorithm Based on the Cubature Kalman Filter for Maneuvering Target Tracking

“…Bayes filtering algorithms have been broadly used in target tracking systems [ 1 , 2 , 3 , 4 ], while a large number of Gaussian approximation filters and Monte Carlo filters have been introduced to solve target tracking problems [ 5 ]. Although the particle filter (PF) can deal with non-linear and non-Gaussian systems, the computational complexity always makes its use prohibitive [ 6 ].…”

Energy Efficient Moving Target Tracking in Wireless Sensor Networks

“…Keeping the cost and size of these sensors small, they are equipped with low computation capability, small amounts of memory, and limited energy resources. Wireless sensor networks (WSN) must rely on these sensors and collaborative signal processing to dynamically manage node resources and effectively process distributed information [5,6,7]. Along this direction, moving target tracking will be considered in WSN.…”