Tracking and identification of multiple targets

Iee Proceedings-radar Sonar and Navigation, 2002

The paper describes an algorithm to jointly form a track and assign an identity flag to a target on the basis of measurements provided by a suite of sensors: surveillance radar, high resolution radar and electronic support measures. The algorithm is built around Bayes' inference and Kalinan filters with the interacting multiple model. The improved performance in the track formation and identity estimation, which accrues by the joint tracking and identification algorithm, is evaluated by Monte Carlo simulation and compared to the performance of filters that process the data provided by each single sensor. The joint tracking and identification algorithm plays an important role in modem surveillance systems with non-cooperative target recognition capabilities.

2005 7th International Conference on Information Fusion, 2005

In this paper we propose a method for solving the data association problem within the framework of multi-target tracking, given a set of environmental measurements obtained by complementary and redundant sensors. The proposed method exploits belief theory, which is a powerful tool for handling imperfect data. We applied the method to situations where colored moving targets emit an audio signal. The basic belief assignment is computed using a confidence measure between targets and incoming measurements based on multi-modal attributes. This allows the ambiguity in association between measurements and targets to be reduced especially for targets that come closely spaced. The proposed method has been tested using different sets of simulated data. The results obtained are very satisfactory and show that the method provides a useful mechanism for data association.

2016 19th International Conference on Information Fusion (FUSION), 2016

We propose a multisensor method for tracking an unknown number of targets. Low computational complexity and very good scalability in the number of targets, number of sensors, and number of measurements per sensor are achieved by running a belief propagation (BP) message passing scheme on a suitably devised factor graph. Using a redundant formulation of data association uncertainty and “augmented target states” including target indicators allows the proposed BP method to leverage statistical independencies for a drastic reduction of complexity. The proposed method is shown to outperform previously proposed multisensor methods for multitarget tracking, including methods with a less favorable scaling behavior.

Lecture Notes in Computer Science, 2004

This paper describes a real-time system for multi-target tracking and classification in image sequences from a single stationary camera. Several targets can be tracked simultaneously in spite of splits and merges amongst the foreground objects and presence of clutter in the segmentation results. In results we show tracking of upto 17 targets simultaneously. The algorithm combines Kalman filter-based motion and shape tracking with an efficient pattern matching algorithm. The latter facilitates the use of a dynamic programming strategy to efficiently solve the data association problem in presence of multiple splits and merges. The system is fully automatic and requires no manual input of any kind for initialization of tracking. The initialization for tracking is done using attributed graphs. The algorithm gives stable and noise free track initialization. The image based tracking results are used as inputs to a Bayesian network based classifier to classify the targets into different categories. After classification a simple 3D model for each class is used along with camera calibration to obtain 3D tracking results for the targets. We present results on a large number of real world image sequences, and accurate 3D tracking results compared with the readings from the speedometer of the vehicle. The complete tracking system including segmentation of moving targets works at about 25Hz for 352×288 resolution color images on a 2.8 GHz pentium-4 desktop.

2005

In this paper we present our findings of investigating non-linear multi-target tracking techniques when jointly used with object classification. The Transferable Belief Model (TBM) is utilised in the multitarget evaluation, data association and target classification stages. A particle filter is used to track each of the targets and uses a motion model that is relevant to the classification given to that target. The targets are classified based upon their motion throughout the scene and their land based position. We show how this system can deal with prior knowledge and lack of knowledge. Situations, with data of this type, regularly occur in real world scenarios and we think it is very important that any system must be able to cope well to such situations. Bayesian and regular DST methods have shortcomings when dealing with such scenarios. We show that the TBM approach can be generally more computational tractable and more robust.

1999

2020

Robotic technology is advancing out of the laboratory and into the everyday world. This world is less ordered than the laboratory and requires an increased ability to identify, target, and track objects of importance. The Bayes filter is the ideal algorithm for tracking a single target and there exists a significant body of work detailing tractable approximations of it with the notable examples of the Kalman and Extended Kalman filter. Multiple target tracking also relies on a similar principle and the Kalman and Extended Kalman filter have multi-target implementations as well. Other method include the PHD filter and Multiple Hypothesis tracker. One issue is that these methods were formulated to only track one classification of target. With the increased need for robust perception, there exists a need to develop a target tracking algorithm that is capable of identifying and tracking targets of multiple classifications. This thesis examines two of these methods: the Probability Hypot...

2013 Workshop on Sensor Data Fusion: Trends, Solutions, Applications (SDF), 2013

Multi-target tracking using multiple sensors is an important research field in application areas of mobile systems and military applications. This paper proposes a decentralized multi-sensor, multi-target tracking and belief (credal) based classification approach, applied to maritime targets. A given number of sensors, considered as unreliable, are designed to locally predict and update targets states using Interacting Multiple Model (IMM) algorithms (one IMM for one target). Targets IMMs are updated by sequentially acquired measurements. The measurements are assigned to the targets by the means of a generalized Global Nearest Neighbor (GNN) algorithm. The generalized GNN algorithm is able to provide information on the newly detected or non-detected targets and these information is used by score functions which manage the targets appearances and disappearances. In addition to the tracking task of multiple targets, each sensor performs a local classification of each one of the targets. The unreliability of the sensors makes the local classifications weak. In this article, a global classification method is shown to improve the sensors classification performances.

In this paper, two novel angle tracking algorithms are proposed for tracking multiple targets using an array of sensors with known locations. First, we present an extended Kalman particle filter (EKPF) which is capable of determining the direction-of-arrival (DOA) angles using a single snapshot of data during the interval between each time step. The proposed EKPF algorithm combines particle filtering with the extended Kalman filter (EKF) in order to prevent sample impoverishment during its resampling process. Next, we present a robust Kalman filter (RKF) tracking algorithm intended to improve tracking success rates of other existing algorithms for the case of multiple snapshots of data within each time increment. In the proposed RKF algorithm, a robust decision mechanism is proposed and incorporated into the Kalman filter (KF), leading to a much better tracking success rate. Because KF (or EKF) is able to offer the predictability of DOA angles, the proposed EKPF and RKF algorithms can avoid the data association problem that usually occurs in multitarget tracking. The effectiveness of the proposed algorithms are demonstrated via computer simulations in scenarios involving targets with crossing trajectories.

IET Radar, Sonar & Navigation, 2011

Probabilistic Multiple Hypothesis Tracking (PMHT) is an algorithm for multi-target tracking in clutter with computational requirements, which are linear in the number of targets and the number of measurements. In order to achieve this, the PMHT removes the point target constraint, and uses the expectation maximisation procedure to optimise both data association probabilities and the target trajectory state estimates. However, PMHT is known to have high track-loss percentage in comparison with Probabilistic Data Association, at least in point target tracking. The authors propose a new PMHT-like algorithm to solve some problems of PMHT. In this study they revert the point target constraint. The authors call the new algorithm Point target PMHT. Simulation results show the efficiency of this method.