Tracking highly maneuverable targets with unknown behavior
Stephen Linder2004, Proceedings of The IEEE
Sign up for access to the world's latest research
checkGet notified about relevant papers
checkSave papers to use in your research
checkJoin the discussion with peers
checkTrack your impact
Abstract
Tracking of highly maneuvering targets with unknown behavior is a difficult problem in sequential state estimation. The performance of predictive-model-based Bayesian state estimators deteriorates quickly when their models are no longer accurate or their process noise is large. A data-driven approach to tracking, the segmenting track identifier (STI), is presented as an algorithm that operates well in environments where the measurement system is well understood but target motion is either or both highly unpredictable or poorly characterized. The STI achieves improved state estimates by the least-squares fitting of a motion model to a segment of data that has been partitioned from the total track such that it represents a single maneuver. Real-world STI tracking performance is demonstrated using sonar data collected from free-swimming fish, where the STI is shown to be effective at tracking highly maneuvering targets while relatively insensitive to its tuning parameters. Additionally, an extension of the STI to allow its use in the most common multiple target and cluttered environment data association frameworks is presented, and an STI-based joint probabilistic data association filter (STIJPDAF) is derived as a specific example. The STIJPDAF is shown by simulation to be effective at tracking a single fish in clutter and through empirical results from video data to be effective at simultaneously tracking multiple free-swimming fish.
Related papers
Bayesian tracking of two possibly unresolved maneuvering targets
IEEE Transactions on Aerospace and Electronic Systems, 2000
Knowledge area(s) Advanced (sensor-) information processing Descriptor(s) Bayesian estimation Descriptor system False measurements Formation flight Markov chain Missing measurements Multitarget tracking Stochastic hybrid system Sudden maneuvers Unresolved measurements Bayesian tracking of two possible unresolved maneuvering Bayesian tracking of two possible unresolved maneuvering Bayesian tracking of two possible unresolved maneuvering Bayesian tracking of two possible unresolved maneuvering targets targets targets targets Problem area This report studies the problem of maintaining tracks of two targets that maneuver in and out formation flight, whereas the sensor and measurement extraction chain produces false and possibly unresolved and missing measurements. If the possibility of unresolved measurements is not modeled then one of the tracks may diverge on false measurements, or the two tracks may coalesce. In order to improve this situation, during a series of studies we have developed exact and novel approximate Bayesian filtering approaches to address this problem. First, we developed a combination of a joint IMM for the joint target maneuver modes with an enhanced version of JPDA that takes coupling between target state estimates into account. We refer to this algorithm as Joint IMM Coupled PDA (JIMMCPDA). Subsequently, for this JIMMCPDA filter we developed an enhanced version which addresses track coalescence avoidance yielding the JIMMCPDA* filter, where the * stands for avoiding track coalescence. Description of work The aim of the work is to effectively enhance the IMM/JPDA paradigm to situations of possibly unresolved measurements from two targets that maneuver in and out a formation amidst false measurements. This is accomplished by combining a Gaussian shaped two-target resolution model with a descriptor system approach towards tracking multiple targets from missing and false measurements. First the considered two target track maintenance problem is defined and formulated as a problem of filtering for a jump-linear descriptor system with identically independently distributed (i.i.d.) stochastic coefficients. Next the exact Bayesian filter recursion is derived. Subsequently equations for the mode-conditional mean and covariance are developed. These equations are on their turn used for the development of the Joint interacting Multiple Model Coupled Probabilistic Data Association with Resolution (JIMMCPDAR) filter and a track-coalescence-avoiding version, which is referred to as the JIMMCPDAR*.
Adaptive joint probabilistic data association algorithm for tracking multiple targets in cluttered environment
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.
Monte Carlo filtering for multi-target tracking and data association
IEEE Transactions on Aerospace and Electronic Systems, 2005
We present Monte Carlo methods for multi-target tracking and data association. The methods are applicable to general nonlinear and non-Gaussian models for the target dynamics and measurement likelihood. We provide efficient solutions to two very pertinent problems: the data association problem that arises due to unlabelled measurements in the presence of clutter, and the curse of dimensionality that arises due to the increased size of the state-space associated with multiple targets. We develop a number of algorithms to achieve this. The first, which we refer to as the Monte Carlo joint probabilistic data association filter (MC-JPDAF), is a generalisation of the strategy proposed in [1] and [2]. As is the case for the JPDAF, the distributions of interest are the marginal filtering distributions for each of the targets, but these are approximated with particles rather than Gaussians. We also develop two extensions to the standard particle filtering methodology for tracking multiple targets. The first, which we refer to as the sequential sampling particle filter (SSPF), samples the individual targets sequentially by utilising a factorisation of the importance weights. The second, which we refer to as the independent partition particle filter (IPPF), assumes the associations to be independent over the individual targets, leading to an efficient component-wise sampling strategy to construct new particles. We evaluate and compare the proposed methods on a challenging synthetic tracking problem.
Extended smoothing joint data association for multi‐target tracking in cluttered environments
IET Radar, Sonar & Navigation, 2019
In heavily cluttered environments, it is difficult to estimate the uncertain motion of an unknown number of targets with low detection probabilities. In particular, for tracking multiple targets, standard multi-target data association algorithms such as joint integrated probabilistic data association (JIPDA), face complexity and severely limited applicability due to a combinatorially increasing number of possible measurement-to-track associations. Smoothers refine the target estimates based on future scan information. However, in this complex surveillance scenario, existing smoothing algorithms often fail to track the true target trajectories. To overcome such difficulties, this study proposes a new smoothing joint measurement-to-track association algorithm called fixed-interval smoothing JIPDA for tracking extended target trajectories (FIsJIPDA). The algorithm employs two independent JIPDA filters: forward JIPDA (fJIPDA) and backward JIPDA (bJIPDA). fJIPDA tracks the target state forward in time and is computed after the smoothing is achieved. bJIPDA estimates the target state in the backward time sequence. The numerical simulation is performed in a heavily populated cluttered environment with low target-detection probabilities. The results show better target trajectory accuracy and false-track discrimination performance of FIsJIPDA compared with that of existing algorithms for tracking multiple extended targets.
Smoothing data association for target trajectory estimation in cluttered environments
EURASIP Journal on Advances in Signal Processing
For heavily cluttered environments with low target detection probabilities, tracking filters may fail to estimate the true number of targets and their trajectories. Smoothing may be needed to refine the estimates based on collected measurements. However, due to uncertainties in target motions, heavy clutter, and low target detection probabilities, the forward prediction and the backward prediction may not be properly matched in the smoothing algorithms, so that the smoothing algorithms may fail to detect the true target trajectories. In this paper, we propose a new smoothing algorithm to overcome such difficulties. This algorithm employs two independent integrated probabilistic data association (IPDA) tracking filters: one running forward in time (fIPDA) and the other running backward in time (bIPDA). The proposed algorithm utilizes bIPDA multi-tracks in each fIPDA path track for fusing through data association to obtain the smoothing innovation in a fixed-lag interval. The smoothing innovation is used to obtain the smoothing data association probabilities which update the target trajectory state and the probability of target existence. The fIPDA tracks are updated after smoothing using the smoothing data association probabilities, which makes the fIPDA path tracks robust for maneuvering target tracking in clutter. This significantly improves the target state estimation accuracy compared to the IPDA. The proposed algorithm is called fixed-lag smoothing data association based on IPDA (FLIPDA-S). A simulation study shows that the proposed algorithm improves false track discrimination performance for maneuvering target tracking in clutter.
Joint probabilistic data association-feedback particle filter for multiple target tracking applications
2012 American Control Conference (ACC), 2012
This paper introduces a novel feedback-control based particle filter for the solution of the filtering problem with data association uncertainty. The particle filter is referred to as the joint probabilistic data association-feedback particle filter (JPDA-FPF).
Bayesian multiple target tracking in forward scan sonar images using the PHD filter
2005
A multiple target tracking algorithm for forward-looking sonar images is presented. The algorithm will track a variable number of targets estimating both the number of targets and their locations. Targets are tracked from range and bearing measurements by estimating the first-order statistical moment of the multitarget probability distribution called the Probability Hypothesis Density (PHD). The recursive estimation of the PHD is much less computationally expensive than estimating the joint multitarget probability distribution. Results are presented showing a variable number of targets being tracked with targets entering and leaving the Field of View. An initial implementation is shown to work on a simulated sonar trajectory and an example is shown working on real data with clutter.
A non-Bayesian segmenting tracker for highly maneuvering targets
IEEE Transactions on Aerospace and Electronic Systems, 2005
The Segmenting Track Identifier (STI) is introduced as a new methodology to tracking highly maneuvering targets. This non-Bayesian approach dynamically partitions a target track into a sequence of track segments, making hard estimates of when the target's maneuvering mode transitions occur, and then estimates the parameters of the target model for each segment. STI is compared to two VS IMM algorithms through simulations, where it is shown to have a three fold performance advantage in median absolute turn rate estimation errors, as well as better position estimation for very highly maneuvering targets. STI performance is also shown to increase substantially if small delays in output can be tolerated.
Data Association in Multi-target Tracking Using Belief Function
Journal of Intelligent & Robotic Systems, 2012
ABSTRACT In this paper, we present a new method for data association in multi-target tracking. The representation and the fusion of the information in our method are based on the use of belief function. The proposal generates the basic belief mass assignment using a modified Mahalanobis distance. While the decision making process is based on the extension of the frame of hypotheses. Our method has been tested for a nearly constant velocity target and compared with both the nearest neighbor filter and the joint probabilistic data associations filter in highly ambiguous cases. The results demonstrate the feasibility of the proposal and show improved performance compared to the aforementioned alternative commonly used methods.
Approximate Bayesian tracking of two targets that maneuver in and out formation flight
2006 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, 2006
Related papers
Augmented input estimation in multiple maneuvering target tracking
Journal of Systems Engineering and Electronics, 2019
This paper presents augmented input estimation (AIE) for multiple maneuvering target tracking. Multi-target tracking (MTT) is based on two main parts, data association and estimation. In data association (DA), the best observations are assigned to the considered tracks. In real conditions, the number of observations is more than targets and also locations of observations are often so scattered that the association between targets and observations cannot be done simply. In this case, for general MTT problems with unknown numbers of targets, we present a Markov chain Monte-Carlo DA (MCMCDA) algorithm that approximates the optimal Bayesian filter with low complexity in computations. After DA, estimation and tracking should be done. Since in general cases, many targets can have maneuvering motions, then AIE is proposed to cover both the non-maneuvering and maneuvering parts of motion and the maneuver detection procedure is eliminated. This model with an input estimation (IE) approach is a special augmentation in the state space model which considers both the state vector and the unknown input vector as a new augmented state vector. Some comparisons based on the Monte-Carlo simulations are also made to evaluate the performances of the proposed method and other older methods in MTT.
Feature aided probabilistic data association for multi-target tracking
2008 11th International Conference on Information Fusion, 2008
Feature aided tracking can often yield improved tracking performance over the standard radar tracking with positional measurements alone. However, the complexity of the tracker may dramatically increase due to the inclusion of the target feature state. In this paper, we study the situation where the target feature is a constant or slowly varying parameter with respect to the target state and can be observed together with the target position. We consider using such target feature data for data association which is a significant problem and dominates the outcomes of multi-target tracking in clutter. Extra target discrimination is obtained by computing a joint measurement likelihood which is typically used in a PDA framework. This idea is demonstrated via an example where the target down-range extent measurement is incorporated into a standard IPDA tracker to resolve closely spaced targets in clutter. A simple target extent model is therefore proposed. Our results indicate that when us...
Markov Chain Monte Carlo Data Association for General Multiple Target Tracking Problems
In this paper, we consider the general multiple target tracking problem in which an unknown number of targets appears and disappears at random times and the goal is to find the tracks of targets from noisy observations. We propose an efficient real-time algorithm that solves the data association problem and is capable of initiating and terminating a varying number of tracks. We take the data-oriented, combinatorial optimization approach to the data association problem but avoid the enumeration of tracks by applying a sampling method called Markov chain Monte Carlo (MCMC). The MCMC data association algorithm can be considered as a deferred logic since its decision about forming a track is based on the current and past observations. But, at the same time, it can be considered as an approximation to the optimal Bayesian filter. The algorithm shows remarkable performance compared to the greedy algorithm and the multiple hypothesis tracker (MHT) under the extreme conditions, such as a large number of targets in a dense environment, low detection probabilities, and a large number of false alarms.
Joint particle filtering of multiple maneuvering targets from unassociated measurements
Journal of Advances in Information Fusion, 2006
The problem of maintaining tracks of multiple maneuvering targets from unassociated measurements is formulated as a problem of estimating the hybrid state of a Markov jump linear system from measurements made by a descriptor system with independent, identically distributed (i.i.d.) stochastic coefficients. This characterization is exploited to derive the exact equation for the Bayesian recursive filter, to develop two novel Sampling Importance Resampling (SIR) type particle filters, and to derive approximate Bayesian filters which use for each target one Gaussian per maneuver mode. The two approximate Bayesian filters are a compact and a trackcoalescence avoiding version of Interacting Multiple Model Joint Probabilistic Data Association (IMMJPDA). The relation of each of the four novel filter algorithms to the literature is well explained. Through Monte Carlo simulations for a two target example, these four filters are compared to each other and to the approach of using one IMMPDA filter per target track. The Monte Carlo simulation results show that each of the four novel filters clearly outperforms the IMMPDA approach. The results also show under which conditions the IMMJPDA type filters perform close to exact Bayesian filtering, and under which conditions not.
Multiple Target Tracking Using Cheap Joint Probabilistic Data Association Multiple Model Particle Filter in Sensors Array
International Journal of Artificial Intelligence & Applications, 2012
Joint multiple target tracking and classification is an important issue in many engineering applications. In recent years, multiple sensor data fusion has been extensively investigated by researchers in a variety of disciplines. Indeed, combining results issued from multiple sensors can provide more accurate information than using a single sensor. In the present paper we address the problem of data fusion for joint multiple maneuvering target tracking and classification in cluttered environment where centralized versus decentralized architectures are often opposed. The proposal advocates a hybrid approach combining a Particle Filter (PF) like method to deal with system nonlinearities and Fitgerald's Cheap Joint Probabilistic Data Association Filter CJPDAF for the purpose of data association and target estimation problems, yielding CJPDA-PF algorithm. While the target maneuverability is tackled using a combination of a Multiple Model Filter (MMF) and CJPDAF, which yields CJPDA-MMPF algorithm. Consequently, at each particle level (of the particle filter), the state of the particle is evaluated using the suggested CJPDA-MMF. In case of several sensors, the centralized fusion architecture and the distributed architecture in the sense of Federated Kalman Filtring are investigated and compared. The feasibility and the performances of the proposal have been demonstrated using a set of Monte Carlo simulations dealing with two maneuvering targets with two distinct operation modes and various clutter densities.
From target tracking to targeting track: A data-driven yet analytical approach to joint target detection and tracking
Signal Processing, 2023
This paper addresses the problem of real-time detection and tracking of a non-cooperative target in the challenging scenario with almost no a-priori information about target birth, death, dynamics and detection probability. Furthermore, there are false and missing data at unknown yet low rates in the measurements. The only information given in advance is about the target-measurement model and the constraint that there is no more than one target in the scenario. To solve these challenges, we model the movement of the target by using a trajectory function of time (T-FoT). Data-driven T-FoT initiation and termination strategies are proposed for identifying the (re-)appearance and disappearance of the target. During the existence of the target, real target measurements are distinguished from clutter if the target indeed exists and is detected, in order to update the T-FoT at each scan for which we design a least-squares estimator. Simulations using either linear or nonlinear systems are conducted to demonstrate the effectiveness of our approach in comparison with the Bayes optimal Bernoulli filters. The results show that our approach is comparable to the perfectly-modeled filters, even outperforms them in some cases while requiring much less a-prior information and computing much faster.
Multiple target tracking by integrating track refinement and data association
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.
Data Association and Track Management for the Gaussian Mixture Probability Hypothesis Density Filter
IEEE Transactions on Aerospace and Electronic Systems, 2009
The Gaussian Mixture Probability Hypothesis Density (GM-PHD) recursion is a closed-form solution to the probability hypothesis density (PHD) recursion, which was proposed for jointly estimating the time-varying number of targets and their states from a sequence of noisy measurement sets in the presence of data association uncertainty, clutter and miss-detection. However the GM-PHD filter does not provide identities of individual target state estimates, that are needed to construct tracks of individual targets. In this paper, we propose a new multi-target tracker based on the GM-PHD filter, which gives the association amongst state estimates of targets over time and provides track labels. Various issues regarding initiating, propagating and terminating tracks are discussed. Furthermore, we also propose a technique for resolving identities of targets in close proximity, which the PHD filter is unable to do on its own.
Multiple target tracking using Sequential Monte Carlo Methods and statistical data association
International Conference on Intelligent RObots and Systems - IROS, 2003
This paper presents two approaches for the problem of Multiple Target Tracking (MTT) and specifically people tracking. Both filters are based on Sequential Monte Carlo Methods (SMCM) and Joint Probability Data Association (JPDA). The filters have been implemented and tested on real data from a laser measurement system. Experiments show that both approaches are able to track multiple moving persons. A comparison of both filters is given and the advantages and disadvantages of the two approaches are presented.
Monte Carlo Algorithm for Maneuvering Target Tracking and Classification
Lecture Notes in Computer Science, 2004
This paper considers the problem of joint maneuvering target tracking and classification. Based on the recently proposed particle filtering approach, a multiple model particle filter is designed for two-class identification of air targets: commercial and military aircraft. The classification task is implemented by processing radar (kinematic) measurements only, no class (feature) measurements are used. A speed likelihood function for each class is defined using a priori information about speed constraints. Class-dependent speed likelihoods are calculated through the state estimates of each class-dependent tracker. They are combined with the kinematic measurement likelihoods in order to improve the process of classification. The performance of the suggested multiple model particle filter is evaluated by Monte Carlo simulations.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.