Perform Data Association Research Articles

Simultaneous Localization and Layout Model Selection in Manhattan Worlds

In this paper, we will demonstrate how Manhattan structure can be exploited to transform the Simultaneous Localization and Mapping (SLAM) problem, which is typically solved by a nonlinear optimization over feature positions, into a model selection problem solved by a convex optimization over higher order layout structures, namely walls, floors, and ceilings. Furthermore, we show how our novel formulation leads to an optimization procedure that automatically performs data association and loop closure and which ultimately produces the simplest model of the environment that is consistent with the available measurements. We verify our method on real world data sets collected with various sensing modalities.

δ-Generalized Labeled Multi-Bernoulli Filter Using Amplitude Information of Neighboring Cells

The amplitude information (AI) of echoed signals plays an important role in radar target detection and tracking. A lot of research shows that the introduction of AI enables the tracking algorithm to distinguish targets from clutter better and then improves the performance of data association. The current AI-aided tracking algorithms only consider the signal amplitude in the range-azimuth cell where measurement exists. However, since radar echoes always contain backscattered signals from multiple cells, the useful information of neighboring cells would be lost if directly applying those existing methods. In order to solve this issue, a new δ-generalized labeled multi-Bernoulli (δ-GLMB) filter is proposed. It exploits the AI of radar echoes from neighboring cells to construct a united amplitude likelihood ratio, and then plugs it into the update process and the measurement-track assignment cost matrix of the δ-GLMB filter. Simulation results show that the proposed approach has better performance in target’s state and number estimation than that of the δ-GLMB only using single-cell AI in low signal-to-clutter-ratio (SCR) environment.

Probabilistic multihypothesis trackerwith an evolving poisson prior

The probabilistic multihypothesis tracker (PMHT) is an efficient multitarget tracking algorithm that performs data association under a conditional independence assumption. A key part of the measurement model is the data-association prior, which can be used as a track quality measure for track management decisions. The original PMHT makes this prior an unknown fixed parameter. The PMHT with hysteresis extended the measurement model by adding a Markov chain hyperparameter to the prior, but this came at the cost of exponential complexity in the number of targets. This complexity comes as a consequence of the normalization of the prior. This article shows that the PMHT data-association model is equivalent to assuming that targets create a Poisson-distributed number of measurements; an alternative PMHT is derived that deals directly with the Poisson model parameters and retains linear complexity in the number of targets.

A joint possibilistic data association technique for tracking multiple targets in a cluttered environment

Multitarget tracking in a cluttered environment is a significant issue with a wide variety of applications. A typical approach to address this issue is the joint probabilistic data association (JPDA) technique. This technique determines joint probabilities over all targets and hits and updates the predicted target state estimate using a probability-weighted sum of innovations. This paper proposes a new joint possibilistic data association technique for tracking multiple targets. Unlike the JPDA technique, the proposed technique determines joint possibilities over all targets and hits and updates the predicted target state estimate using a possibility-weighted sum of innovations. The possibility weights are determined using the noise covariance matrices and the current received measurements such that the total sum of the distances between all measurements and targets is minimized. The proposed technique performs data association based on a possibility matrix of measurements to trajectories; thus, it highly reduces the computational complexity compared to conventional data association techniques. The proposed association technique is applied to examples of multitarget tracking in a cluttered environment, and the results demonstrate its efficiency.

Two Measures for Enhancing Data Association Performance in SLAM

Data association is one of the key problems in the SLAM community. Several data association failures may cause the SLAM results to be divergent. Data association performance in SLAM is affected by both data association methods and sensor information. Two measures of handling sensor information are introduced herein to enhance data association performance in SLAM. For the first measure, truncating strategy of limited features, instead of all matched features, is used for observation update. These features are selected according to an information variable. This truncating strategy is used to lower the effect of false matched features. For the other measure, a special rejecting mechanism is designed to reject suspected observations. When the predicted robot pose is obviously different from the updated robot pose, all observed sensor information at this moment is discarded. The rejecting mechanism aims at eliminating accidental sensor information. Experimental results indicate that the introduced measures perform well in improving the stability of data association in SLAM. These measures are of extraordinary value for real SLAM applications.

Real-Time Computer Vision/DGPS-Aided Inertial Navigation System for Lane-Level Vehicle Navigation

Many intelligent transportation system (ITS) applications will increasingly rely on lane-level vehicle positioning that requires high accuracy, bandwidth, availability, and integrity. Lane-level positioning methods must reliably work in real time in a wide range of environments, spanning rural to urban areas. Traditional positioning sensors such as the Global Navigation Satellite Systems may have poor performance in dense urban areas, where obstacles block satellite signals. This paper presents a sensor fusion technique that uses computer vision and differential pseudorange Global Positioning System (DGPS) measurements to aid an inertial navigation system (INS) in challenging environments where GPS signals are limited and/or unreliable. To supplement limited DGPS measurements, this method uses mapped landmarks that were measured through a priori observations (e.g., traffic light location data), taking advantage of existing infrastructure that is abundant within suburban/urban environments. For example, traffic lights are easily detected by color vision sensors in both day and night conditions. A tightly coupled estimation process is employed to use observables from satellite signals and known feature observables from a camera to correct an INS that is formulated as an extended Kalman filter. A traffic light detection method is also outlined, where the projected feature uncertainty ellipse is utilized to perform data association between a predicted feature and a set of detected features. Real-time experimental results from real-world settings are presented to validate the proposed localization method.

Smoothing innovations and data association with IPDA

Surveillance sensors return detections from targets as well as the clutter measurements. Data association algorithms often use innovations to discriminate between the target and the clutter measurements. Reducing the covariance of innovations reduces the surveillance area from which measurements are used, reducing the number of clutter measurements. This paper introduces smoothing innovations which reduce innovation covariance, and improve the data association performance. This concept is applied to the Integrated Probabilistic Data Association (IPDA) to produce a Smoothing IPDA (sIPDA). sIPDA trajectory estimation errors are reduced with a smoothing delay. A surprising outcome is that sIPDA improves the false track discrimination in real time (without the smoothing delay).

An Optimization-Based Parallel Particle Filter for Multitarget Tracking

Particle filters are used in state estimation applications because of their capability to solve nonlinear and non-Gaussian problems effectively. However, they have high computational requirements, especially in the case of multitarget tracking, where data association is the bottleneck. In order to perform data association and estimation together, an augmented state vector, whose dimensions depend on the number of targets, is typically used in particle filters. With data association, the computational load increases exponentially as the number of targets increases. In this case, parallelization is a possibility for achieving real-time feasibility in large-scale multitarget tracking applications. In the work presented here, an optimization-based scheduling algorithm, that is suitable for parallel implementation of particle filter, is presented. This proposed scheduling algorithm minimizes the total computation time for the bus-connected heterogeneous primary-secondary architecture. Further, this scheduler is capable of selecting the optimal number of processors from a large pool of secondary processors and mapping the particles among the selected ones. A new distributed resampling algorithm suitable for parallel computing is also proposed. Furthermore, a less communication-intensive parallel implementation of the particle filter without compromising tracking accuracy using an efficient load balancing technique, in which optimal particle migration among secondary processors is ensured, is presented. Simulation results demonstrate the tracking effectiveness of the new parallel particle filter and the speedup achieved using parallelization.

A novel all-neighbor fuzzy association approach for multitarget tracking in a cluttered environment

This paper proposes a novel all-neighbor fuzzy association approach for multitarget tracking in a cluttered environment. It performs data association with a little prior knowledge and updates the predicted target state estimate using a fuzzy weighted sum of innovations. Unlike the joint probabilistic data association filter, in which the similarity measures are determined in terms of the conditional probability for all feasible data association hypothesis, the proposed fuzzy association approach determines the similarity measures between measurements and tracks in terms of possibility weights based on a partition matrix. The possibility weights are determined according to the fuzzy clustering algorithm. The proposed approach is able to perform all-neighbor association with a lower computational complexity in the expense of a little lower performance compared to the standard joint probabilistic data association filter. Computer simulation shows the feasibility and the efficiency of the proposed all-neighbor fuzzy association approach.

Efficient and Enhanced Multi-Target Tracking with Doppler Measurements

In many radar and sonar tracking systems, the target state typically includes target position and velocity components that are estimated from a time sequence of target position and Doppler measurements. The use of measured Doppler information directly in the target trajectory estimation leads to a nonlinear filter implementation such as the extended Kalman filter (EKF), particle filter etc. We investigate a method for including Doppler measurements as part of the data association process and then assess the benefits of this approach. It is well understood that data association performance can dominate the total performance of a tracker that is designed to track targets in the presence of clutter. In this case, the Doppler component of the measurements may be used in combination with the target position measurement as an additional discriminant of measurement origin. We have developed a simple but efficient Doppler data association (DDA) method which utilises both position and Doppler measurements for single and multi-target tracking. If the Doppler measurements are not used in trajectory state estimation, then the nonlinear filters for the incorporation of Doppler measurements are not required, however a significant improvement in tracking performance is still observed. The proposed DDA method is demonstrated using both the linear multi-target integrated probabilistic data association algorithm (LMIPDA) and the linear multi-target integrated track splitting algorithm (LMITS) in an active sonar underwater multi-target tracking scenario.

Extending the Limits of Feature-Based SLAM With B-Splines

<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> This paper describes a simultaneous localization and mapping (SLAM) algorithm for use in unstructured environments that is effective regardless of the geometric complexity of the environment. Features are described using B-splines as modeling tool, and the set of control points defining their shape is used to form a complete and compact description of the environment, thus making it feasible to use an extended Kalman-filter (EKF) based SLAM algorithm. This method is the first known EKF-SLAM implementation capable of describing general free-form features in a parametric manner. Efficient strategies for computing the relevant Jacobians, perform data association, initialization, and map enlargement are presented. The algorithms are evaluated for accuracy and consistency using computer simulations, and for effectiveness using experimental data gathered from different real environments. </para>

New data association technique based on ACO with directional information considered

Due to the advantages of ant colony optimization (ACO) in solving complex problems, a new data association algorithm based on ACO in a cluttered environment called DACDA is proposed. In the proposed method, the concept for tour and the length of tour are redefined. Additionally, the directional information is incorporated into the proposed method because it is one of the most important factors that affects the performance of data association. Kalman filter is employed to estimate target states. Computer simulation results show that the proposed method could carry out data association in an acceptable CPU time, and the correct data association rate is higher than that obtained by the data association (DA) algorithm not combined with directional information.

Energy-based video tracking using joint target density processing with an application to unmanned aerial vehicle surveillance

Successfully tracking targets in a video sequence has many important applications, including unmanned aerial vehicle (UAV) surveillance. A robust and efficient video tracking algorithm based on the continuous wavelet transform (CWT) is presented, which has been proven to be effective in capturing motion information over multiple frames and excellent in velocity selectivity. The CWT converts target trajectories in a spatio-temporal domain into target energy volumes in a wavenumber–frequency domain. By integrating over different motion parameters, three target energy densities are obtained, which then serve as cost functions for estimating target trajectories and sizes. Because of excellent velocity selectivity, the energy-based tracker has the capability of detecting and tracking targets with a particular velocity range. To best handle target interferences among multiple nearby or crossing targets, a novel joint processing technique using expectation-maximization-based Gaussian mixture estimation is developed. A global nearest neighbourhood algorithm is employed to perform data association and maintain continuous kinematic trajectories. In addition to computer simulations, the developed energy-based algorithm is applied to a UAV surveillance application where multiple vehicles move closely to each other on a multi-lane road.

Multiple-Target Tracking with Competitive Hopfield Neural Network Based Data Association

Data association which obtains relationship between radar measurements and existing tracks plays one important role in radar multiple-target tracking (MTT) systems. A new approach to data association based on the competitive Hopfield neural network (CHNN) is investigated, where the matching between radar measurements and existing target tracks is used as a criterion to achieve a global consideration. Embedded within the CHNN is a competitive learning algorithm that resolves the dilemma of occasional irrational solutions in traditional Hopfield neural networks. Additionally, it is also shown that our proposed CHNN-based network is guaranteed to converge to a stable state in performing data association and the CHNN-based data association combined with an MTT system demonstrates target tracking capability. Computer simulation results indicate that this approach successfully solves the data association problems.

Analytic Implementations of the Cardinalized Probability Hypothesis Density Filter

The probability hypothesis density (PHD) recursion propagates the posterior intensity of the random finite set (RFS) of targets in time. The cardinalized PHD (CPHD) recursion is a generalization of the PHD recursion, which jointly propagates the posterior intensity and the posterior cardinality distribution. In general, the CPHD recursion is computationally intractable. This paper proposes a closed-form solution to the CPHD recursion under linear Gaussian assumptions on the target dynamics and birth process. Based on this solution, an effective multitarget tracking algorithm is developed. Extensions of the proposed closed-form recursion to accommodate nonlinear models are also given using linearization and unscented transform techniques. The proposed CPHD implementations not only sidestep the need to perform data association found in traditional methods, but also dramatically improve the accuracy of individual state estimates as well as the variance of the estimated number of targets when compared to the standard PHD filter. Our implementations only have a cubic complexity, but simulations suggest favorable performance compared to the standard Joint Probabilistic Data Association (JPDA) filter which has a nonpolynomial complexity.

COOPERATIVE EXPLORATION FOR USAR ROBOTS WITH INDIRECT COMMUNICATION

To coordinate a team of robots for exploration is a challenging problem, particularly in unstructured areas, as for example post-disaster scenarios where direct communication is severely constrained. Furthermore, conventional methods of SLAM, e.g. those performing data association based on visual features, are doomed to fail due to bad visibility caused by smoke and fire. We use indirect communication (based on RFIDs), to share knowledge and use a gradient-like local search to direct robots towards interesting areas. To share a common frame of reference among robots we use a feature based SLAM approach (where features are RFIDs). The approach has been evaluated on a 3D simulation based on USARSim.

Fuzzy Data Association Filter (FDAF) For Maneuvering Multitarget Tracking.

This paper presents a new algorithm for Manoeuvring Multitarget Tracking. The suggested algorithm solves the interrelated tasks of data association and state estimation in one combined algorithm. The new algorithm is based on fuzzy cluster means algorithm to solve the data association problem, and an adaptive Kalman filter for maneuvering multitaget tracking. To demonstrate the effectiveness of the proposed algorithm to perform data association and state estimation in multitarget tracking in high noisy measurement, an example of four-dimensional tracking system is considered. A scenario of two targets moving together at near distance and then making high maneuver is considered. The performance is evaluated using Monte Carlo simulations and the results are reasonable.

MULTI-CRITERIA FUSION FOR THE SELECTION OF ROADS OF AN ACCURATE MAP

To localize a vehicle on a map, a reliable road selection system is essential. For this purpose, the article presents a credibilist multi-criteria association algorithm that performs data association between the infrastructure information (the map) and the noisy measurements of two sensors (DGPS, Odometer). The algorithm takes into account the inaccuracy, the uncertainty and the redundancy of the data. The multi-criteria fusion process is realized using Belief Theory and Dempster-Shafer's rule. A local strategy is developed to allot believes to two criteria. Experimental results show that the credibilist roads around an estimated position are well selected.

Multiple target detection using modified high order correlations

This work is concerned with the problem of multiple target track detection in heavy clutter. Using the "modified high order correlation" (HOC) process and a track scoring mechanism a new method is developed to perform data association and track identification in the presence of heavy clutter. Using this new scheme any number of very close, crossing or splitting target tracks can be resolved without increasing the computational complexity of the algorithm. The applicability of the method for continuous detection of target tracks that can originate and terminate at any scan is also demonstrated, In addition, the operating characteristics as a function of the clutter density are also provided. Simulation results on all the cases are presented.

Performance of neural data associator

The paper presents the performance of neural data association based on a mean field Hopfield network. The authors create a new energy function for measurement data association (MDA) that consists of assigning radar plots to predicted track positions which plays a key role in all track-while-scan systems. The network presented in the paper in combination with the new energy function can minimise a global cost, which is a function of the distances between the plots in a given scan of data and the predicted track positions. The data association capacities of the neural network have been studied in different environments, and the results are presented. The authors also give the results of tracking trials based on neural data association.