Data Association and Track Management for the Gaussian Mixture Probability Hypothesis Density Filter

Panta, K.; Clark, Dan E.; Vo, Ba-Ngu

doi:10.1109/taes.2009.5259179

Cited by 219 publications

(154 citation statements)

References 22 publications

Supporting

Mentioning

154

Contrasting

Order By: Relevance

“…As the label of an MC indicates the object which is represented by this MC, all MCs are grouped with respect to their label. Further, each group of MCs contributes its MC with the highest weight to the set of object tracks if its weight is at least 0.5 [PCV09]. Consequently, each element of the set of tracks features a state estimate with related covariances as well as an unique label that facilitates a continuous multi-object tracking.…”

Section: Gm-phd Filter Innovationmentioning

confidence: 99%

Intersection-Based Road User Tracking Using a Classifying Multiple-Model PHD Filter

Meißner

Reuter

Strigel

et al. 2014

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

Bibliografische Information der Deutschen NationalbibliothekDie Deutsche Nationalbibliothek verzeichnet diese Publikation in der Deutschen Nationalbibliografie; detaillierte bibliografische Daten sind im Internet über http://dnb.dnb.de abrufbar. AbstractDue to an increasing number of traffic accident fatalities at intersections, the prevention of traffic accidents at intersection attracts more and more attention in public as well as in research. One example therefore, is the joint-project Ko-PER of the research initiative Ko-FAS which aims to increase the preventive traffic safety. This is realized by an preferably exhaustive recognition of the vehicles' environments based on locally gathered and communicated perception data. Therefore, especially at urban intersections, an intersection-based perception system which communicates the current traffic situation to vehicles in the intersection's surrounding is essential. Thus, a busy public intersection in Aschaffenburg, Germany was equipped with an intersection perception system, which contains multiple laserscanners and video cameras as well as data processing units. Beside the planning of the perception system, the core of this thesis is the laserscanner-based detection and classification of road users and the tracking of them by fusing detections of the laserscanners and video cameras.Since the laserscanners at the intersection are mounted at posts of lamps, traffic-lights as well as surrounding buildings, segmentation algorithms are introduced which utilize the knowledge about the consistent environment to segment the laserscanner measurements in background and foreground. Subsequently, the object detection in the foreground data relies on position as well as motion information. The 3D measurement points are clustered with a real-time capable implementation of the density based spatial clustering for applications with noise (DBSCAN) algorithm. Nevertheless, particularly large objects are sometimes not entirely detected due to occlusions, poor reflection characteristics and measurement uncertainties. This may lead to the separation of one object in multiple clusters. To avoid the overclustering, a combination of 2D tracking and 3D clustering methods is proposed. Beside the benefit of the considerably more robust object detection, additionally the determination of the objects' orientations is improved. Finally, the detected objects are classified by means of features of their laserscanner point clusters.The focus of this thesis lays on the tracking of road users at traffic intersections. Thus, a tracking approach is required which is able to handle multiple objects detected by multiple classifying sensors with different field of views. Due to the topdown modeling of the multi-object tracking problem and the availability of efficient implementations, a Gaussian mixture probability hypothesis density (GM-PHD) filter is used. Based on this the classifying multiple-model probability hypothesis density (CMMPHD) filter is developed which facilitates to track road user...

show abstract

Section: Gm-phd Filter Innovationmentioning

confidence: 99%

Intersection-Based Road User Tracking Using a Classifying Multiple-Model PHD Filter

Meißner

Reuter

Strigel

et al. 2014

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

show abstract

“…For the PHD approach, methods performing these extra steps have been reported using particle PHD filters [26][27][28] or Gaussian mixture (GM)-PHD filters [29]. Target positions are typically identified by peak-picking the target intensity function being tracked, and the estimated target positions are treated as measurements for the ensuing data association and track recovery tasks.…”

Section: Position Estimation and Track Formationmentioning

confidence: 99%

Tracking target signal strengths on a grid using sparsity

Farahmand

Giannakis

Leus

et al. 2014

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Multi-target tracking is mainly challenged by the nonlinearity present in the measurement equation and the difficulty in fast and accurate data association. To overcome these challenges, the present paper introduces a grid-based model in which the state captures target signal strengths on a known spatial grid (TSSG). This model leads to linear state and measurement equations, which bypass data association and can afford state estimation via sparsity-aware Kalman filtering (KF). Leveraging the grid-induced sparsity of the novel model, two types of sparsity-cognizant TSSG-KF trackers are developed: one effects sparsity through 1 -norm regularization, and the other invokes sparsity as an extra measurement. Iterative extended KF and Gauss-Newton algorithms are developed for reduced-complexity tracking, along with accurate error covariance updates for assessing performance of the resultant sparsity-aware state estimators. Based on TSSG state estimates, more informative target position and track estimates can be obtained in a follow-up step, ensuring that track association and position estimation errors do not propagate back into TSSG state estimates. The novel TSSG trackers do not require knowing the number of targets or their signal strengths and exhibit considerably lower complexity than the benchmark hidden Markov model filter, especially for a large number of targets. Numerical simulations demonstrate that sparsity-cognizant trackers enjoy improved root-mean-square error performance at reduced complexity when compared to their sparsity-agnostic counterparts. Comparison with the recently developed additive likelihood moment filter reveals the better performance of the proposed TSSG tracker.

show abstract

“…With the use of the Bayesian framework to propagate the posterior intensity of multiple targets recursively, the probability hypothesis density (PHD) filter provides a numerically tractable solution to this problem [2,3]. Two numerical solutions, namely sequential Monte Carlo (SMC) [4][5][6][7][8][9] and Gaussian mixtures (GM) [10][11][12][13][14][15][16][17], have been developed for the PHD filter. Extensions of the PHD filter have also been proposed to improve its performance.…”

Section: Introductionmentioning

confidence: 99%

“…PHD filters with observation-driven birth intensity were independently proposed in [16,18,19] to eliminate the need for exact knowledge of birth intensity. Methods for maintaining track continuity were proposed in [4,20] for the SMC-PHD filter and in [21] for the GM-PHD filter. To improve the accuracy and stability of the target number estimate, the cardinalized PHD (CPHD) filter, which jointly propagates moment and cardinality, was proposed in [22].…”

Section: Introductionmentioning

confidence: 99%

Sequential measurement-driven multi-target Bayesian filter

Liu

Xie

et al. 2015

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Bayesian filter is an efficient approach for multi-target tracking in the presence of clutter. Recently, considerable attention has been focused on probability hypothesis density (PHD) filter, which is an intensity approximation of the multi-target Bayesian filter. However, PHD filter is inapplicable to cases in which target detection probability is low. The use of this filter may result in a delay in data processing because it handles received measurements periodically, once every sampling period. To track multiple targets in the case of low detection probability and to handle received measurements in real time, we propose a sequential measurement-driven Bayesian filter. The proposed filter jointly propagates the marginal distributions and existence probabilities of each target in the filter recursion. We also present an implementation of the proposed filter for linear Gaussian models. Simulation results demonstrate that the proposed filter can more accurately track multiple targets than the Gaussian mixture PHD filter or cardinalized PHD filter.

show abstract

Data Association and Track Management for the Gaussian Mixture Probability Hypothesis Density Filter

Cited by 219 publications

References 22 publications

Intersection-Based Road User Tracking Using a Classifying Multiple-Model PHD Filter

Intersection-Based Road User Tracking Using a Classifying Multiple-Model PHD Filter

Tracking target signal strengths on a grid using sparsity

Sequential measurement-driven multi-target Bayesian filter

Contact Info

Product

Resources

About