Multiple Hypothesis Tracking Research Articles

Modified multi-hypothesis tracking algorithm based on radar target appearance features

The marine radars are widely used in surveillance system for its convenience and cost-effectiveness, but it always suffers from the sea clutters and other inferences, and there are multiple maneuvering targets in the surveillance area. In these complex scenes, the traditional radar detector and tracker can result high false alarm and target loss. Especially the high false alarm scenes can bring an unacceptable computational burden. In this paper, we propose a practice tracking-by-detection method composed by a convolutional neural network (CNN) detector and a multiple hypothesis tracking (MHT) tracker. In order to deal with complex scenes efficiently and accurately, it utilize modified pruning strategies and multiple data information, such as the kinematic and appearance features. And the experiments on the self-designed simulation radar datasets prove that this method has the ability to reach a good performance with both accuracy and a low computational cost.

Improved N - Best Multiple Hypothesis Tracking Algorithm

In the tracking process of the multi-hypothesis tracking algorithm, many hypothesis are made about the correlation between the track and the measured values. Although its tracking performance is better than other tracking algorithms, it needs a lot of computation time and memory resources when tracking multiple targets or in environments with large clutter due to exponential growth of hypothesis. In view of this situation, an improved N-Best algorithm is proposed to be applied to MHT. The simulation results show that this method can reduce the computation time and realize the track correlation, so it has certain practicability.

Comparing accuracy of fish sperm motility measurements obtained from two computational extremes in tracking approaches: Nearest neighbor and multiple hypothesis tracking.

We conducted a study to assess the accuracy of nearest neighbour (NN) and multiple hypothesis tracking (MHT) methods-which are opposite extremes in computational complexity-in determining the percentage of motile sperms and the number of sperms tracked in simulated data of fish sperm movements, and to evaluate the resulting number of tracking errors and analysis duration. Sperm tracking and swimming path assembly were assessed in 36 video clips (1s length at 100 fps) of emulated Rhamdia quelen sperm kinetics at different densities (50, 100, 200 or 300 spermatozoa in the field of view) and motility rates (30, 60 or 90%). The MHT method accurately estimated the percentage of motile sperms, whereas NN underestimated it by up to 6.59%. Increase in sperm density reduced the number of sperms tracked from both trackers. With more than 50 sperms in the field of view, NN and MHT tracked 73% and 92% of the ground-truth sperm count, respectively. Both trackers showed a quadratic increase in tracking errors with increasing sperm density. The maximum percentage of errors at 90% motility was 12% for NN and 4.7% for MHT. The MHT tracker required up to 150s to track 300 sperms, whereas NN completed the tracking procedure in less than 0.5s. On maintaining a density of up to 100 sperms in the field of view, it was possible to obtain high accuracy, low number of tracking errors and an acceptable analysis duration with both tracking methods.

Overlapping Speaker Segmentation Using Multiple Hypothesis Tracking of Fundamental Frequency

This paper demonstrates how the harmonic structure of voiced speech can be exploited to segment multiple overlapping speakers in a speaker diarization task. We explore how a change in the speaker can be inferred from a change in pitch. We show that voiced harmonics can be useful in detecting when more than one speaker is talking, such as during overlapping speaker activity. A novel system is proposed to track multiple harmonics simultaneously, allowing for the determination of onsets and end-points of a speaker's utterance in the presence of an additional active speaker. This system is bench-marked against a segmentation system from the literature that employs a bidirectional long short term memory network (BLSTM) approach and requires training. Experimental results highlight that the proposed approach outperforms the BLSTM baseline approach by 12.9% in terms of HIT rate for speaker segmentation. We also show that the estimated pitch tracks of our system can be used as features to the BLSTM to achieve further improvements of 1.21% in terms of coverage and 2.45% in terms of purity.

Cyclist detection and tracking based on multi-layer laser scanner

The technology of Artificial Intelligence (AI) brings tremendous possibilities for autonomous vehicle applications. One of the essential tasks of autonomous vehicle is environment perception using machine learning algorithms. Since the cyclists are the vulnerable road users, cyclist detection and tracking are important perception sub-tasks for autonomous vehicles to avoid vehicle-cyclist collision. In this paper, a robust method for cyclist detection and tracking is presented based on multi-layer laser scanner, i.e., IBEO LUX 4L, which obtains four-layer point cloud from local environment. First, the laser points are partitioned into individual clusters using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) method based on subarea. Then, 37-dimensional feature set is optimized by Relief algorithm and Principal Component Analysis (PCA) to produce two new feature sets. Support Vector Machine (SVM) and Decision Tree (DT) classifiers are further combined with three feature sets, respectively. Moreover, Multiple Hypothesis Tracking (MHT) algorithm and Kalman filter based on Current Statistical (CS) model are applied to track moving cyclists and estimate the motion state. The performance of the proposed cyclist detection and tracking method is validated in real road environment.

A message passing approach for multiple maneuvering target tracking

This paper considers the problem of detecting and tracking multiple maneuvering targets, which suffers from the intractable inference of high-dimensional latent variables that include target kinematic state, target visibility state, motion mode-model association, and data association. A unified message passing algorithm that combines belief propagation (BP) and mean-field (MF) approximation is proposed for simplifying the intractable inference. By assuming conjugate-exponential priors for target kinematic state, target visibility state, and motion mode-model association, the MF approximation decouples the joint inference of target kinematic state, target visibility state, motion mode-model association into individual low-dimensional inference, yielding simple message passing update equations. The BP is exploited to approximate the probabilities of data association events since it is compatible with hard constraints. Finally, the approximate posterior probability distributions are updated iteratively in a closed-loop manner, which is effective for dealing with the coupling issue between the estimations of target kinematic state and target visibility state and decisions on motion mode-model association and data association. The performance of the proposed algorithm is demonstrated by comparing with the well-known multiple maneuvering target tracking algorithms, including interacting multiple model joint probabilistic data association, interacting multiple model hypothesis-oriented multiple hypothesis tracker and multiple model generalized labeled multi-Bernoulli.

Underwater Bearing-Only Multitarget Tracking in Dense Clutter Environment Based on PMHT

Underwater bearing-only multitarget tracking in clutter environment is challenging because of the measurement nonlinearity, range unobservability, and data association uncertainty. In terms of the principle of expectation maximization, combining the extended Kalman filter (EKF) and unscented Kalman filter algorithm(UKF), a new bearing-only multi-sensor multitarget tracking via probabilistic multiple hypothesis tracking(PMHT) algorithm is proposed. The PMHT algorithm introduces an association variable to deal with the data association uncertainty problem between the measurements and the targets. Furthermore, the EKF-based PMHT for multi-sensor multitarget system is simplified, which obviate the need to "stack" the synthetic measurements and can reduce the computation cost. The estimation accuracy of the EKF based on PMHT approach and UKF based on PMHT approach in simulation experiments for underwater bearing-only cross-moving targets and closely spaced targets for the case of stationary multiple observations and maneuvering single observation under dense clutter environment is analyzed. The experimental results demonstrate that the present algorithm is very well in a highly clutter environment and its computational load is low, which confirms the effectiveness of the algorithm to the bearing-only multitarget tracking in dense clutter.

Iterative Multiple Hypothesis Tracking With Tracklet-Level Association

This paper proposes a novel iterative maximum weighted independent set (MWIS) algorithm for multiple hypothesis tracking (MHT) in a tracking-by-detection framework. MHT converts the tracking problem into a series of MWIS problems across the tracking time. Previous works solve these NP-hard MWIS problems independently without the use of any prior information from each frame, and they ignore the relevance between adjacent frames. In this paper, we iteratively solve the MWIS problems by using the MWIS solution from the previous frame rather than solving the problem from scratch each time. First, we define five hypothesis categories and a hypothesis transfer model, which explicitly describes the hypothesis relationship between adjacent frames. We also propose a polynomial-time approximation algorithm for the MWIS problem in MHT. In addition to that, we present a confident short tracklet generation method and incorporate tracklet-level association into MHT, which further improves the computational efficiency. Our experiments on both MOT16 and MOT17 benchmarks show that our tracker outperforms all the previously published tracking algorithms on both MOT16 and MOT17 benchmarks. Finally, we demonstrate that the polynomial-time approximate tracker reaches nearly the same tracking performance.

Improved Multiple Hypothesis Tracker for Joint Multiple Target Tracking and Feature Extraction

Feature-aided tracking can often yield improved tracking performance over the standard multiple target tracking (MTT) algorithms. However, in many applications, the feature signal of the targets consists of sparse Fourier-domain signals. It changes quickly and nonlinearly in the time domain, and the feature measurements are corrupted by missed detections and misassociations. In this paper, we develop a feature-aided multiple hypothesis tracker for joint MTT and feature extraction in dense target environments. We use the atomic norm constraint to formulate the sparsity of feature signal and use the ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -norm to formulate the sparsity of the corruption induced by misassociations. Based on the sparse representation, the feature signal are estimated by solving a semidefinite program. With the estimated feature signal, refiltering is performed to estimate the kinematic states of the targets, where the association makes use of both kinematic and feature information. Simulation results are presented to illustrate the performance of the proposed algorithm.

A New Multiple Hypothesis Tracker Integrated with Detection Processing.

In extant radar signal processing systems, detection and tracking are carried out independently, and detected measurements are utilized as inputs to the tracking procedure. Therefore, the tracking performance is highly associated with detection accuracy, and this performance may severely degrade when detections include a mass of false alarms and missed-targets errors, especially in dense clutter or closely-spaced trajectories scenarios. To deal with this issue, this paper proposes a novel method for integrating the multiple hypothesis tracker with detection processing. Specifically, the detector acquires an adaptive detection threshold from the output of the multiple hypothesis tracker algorithm, and then the obtained detection threshold is employed to compute the score function and sequential probability ratio test threshold for the data association and track estimation tasks. A comparative analysis of three tracking algorithms in a clutter dense scenario, including the proposed method, the multiple hypothesis tracker, and the global nearest neighbor algorithm, is conducted. Simulation results demonstrate that the proposed multiple hypothesis tracker integrated with detection processing method outperforms both the standard multiple hypothesis tracker algorithm and the global nearest neighbor algorithm in terms of tracking accuracy.

A Novel Global Localization Approach Based on Structural Unit Encoding and Multiple Hypothesis Tracking

In this paper, we present a novel 2-D laser-based global localization approach for mobile robots, which is composed of geometrical relationship construction, a new structural unit encoding scheme (SUES), and an extended multiple hypothesis tracking (MHT) algorithm. Different from existing methods, we construct a 3-D “directional endpoint” feature encapsulating both the endpoint and the direction of a line segment; on this basis, a novel and efficient online structural unit encoding scheme (SUES) is proposed to describe the geometric relationship between the two directional endpoint features with some robustness to dynamic disturbances. Note that SUES presented in this paper is different from the bag-of-words scheme in two aspects: 1) SUES quantizes the geometrical relationship without offline training for vocabulary and 2) SUES is independent of the quality of the vocabulary. By factoring the global localization problem into a discrete pose estimation problem, the MHT is extended on the basis of SUES and odometry information to gradually restore the global robot pose. Different from the classical MHT framework, the extended MHT takes the independent observation results as the a priori , while the likelihood term is composed of consecutive candidate poses and the odometry information. Evaluations are carried out by using both publicly available data sets and self-recorded data sets. Comparative experimental results with respect to the adaptive Monte Carlo localization are presented to show the superior performance of the proposed approach in terms of success ratio and efficiency.

Optimised multi‐hypothesis tracking algorithm based on the two‐dimensional constraints and manoeuvre detection

With the increase of target mobility and environment complexity, highly reliable single-period statistical judgments become more and more difficult. The multiple hypothesis tracking (MHT) algorithm is a method based on delay logic, and can effectively solve the problem of data association in the course of tracking. However, the number of hypotheses generated by the MHT algorithm is exponentially related to the false alarm rate and the number of targets. Therefore, the hypotheses reduction techniques are required for the implementation of the algorithm. The N-scan-back method and K-best method are often used. On the basis of understanding the K-Best method and the N-Scan-back method, this study proposes the two-dimensional constraints by the K-Best method and the N-Scan-back method, and besides adds the target manoeuvre detection method to jointly manage the hypotheses based on the mean of the filter residual. According to the manoeuvre detection results, the optimised MHT algorithm can adjust the likelihood probability calculation model of the plot-track association and the posterior probability calculation model of the hypothetical branch track, and shorten the decision depth N in the N-Scan-back method. Through simulation, it is proved that the optimised algorithm can reduce the calculation amount and improve the tracking accuracy.

Joint Target Detection and Tracking in Multipath Environment: A Variational Bayesian Approach

We consider multitarget detection and tracking problem for a class of multipath detection system where one target may generate multiple measurements via multiple propagation paths, and the association relationship among targets, measurements, and propagation paths is unknown. In order to effectively utilize multipath measurements from one target to improve detection and tracking performance, a tracker has to handle high-dimensional estimation of latent variables including target existence state, target kinematic state, and multipath data association. Based on variational Bayesian inference, we propose a novel joint detection and tracking algorithm that incorporates multipath data association, target detection, and target state estimation in a unified Bayesian framework. The posterior probabilities of these latent variables are derived in a closed-form iterative manner, which is effective for reducing the performance deterioration caused by the coupling between estimation errors and identification errors. Loopy belief propagation is exploited to approximately calculate the probability of multipath data association, saving the computational cost significantly. Simulation results of over-the-horizon radar multitarget tracking show that the proposed algorithm outperforms multihypothesis multipath track fusion and multidetection (hypothesis-oriented) multiple hypothesis tracker, especially under low signal-to-noise ratio circumstance.

Extracting tree structures in CT data by tracking multiple statistically ranked hypotheses.

In this work, we adapt a method based on multiple hypothesis tracking (MHT) that has been shown to give state-of-the-art vessel segmentation results in interactive settings, for the purpose of extracting trees. Regularly spaced tubular templates are fit to image data forming local hypotheses. These local hypotheses are then used to construct the MHT tree, which is then traversed to make segmentation decisions. Some critical parameters in the method, we base ours on, are scale-dependent and have an adverse effect when tracking structures of varying dimensions. We propose to use statistical ranking of local hypotheses in constructing the MHT tree which yields a probabilistic interpretation of scores across scales and helps alleviate the scale dependence of MHT parameters. This enables our method to track trees starting from a single seed point. The proposed method is evaluated on chest computed tomography data to extract airway trees and coronary arteries and compared to relevant baselines. In both cases, we show that our method performs significantly better than the Original MHT method in semiautomatic setting. The statistical ranking of local hypotheses introduced allows the MHT method to be used in noninteractive settings yielding competitive results for segmenting tree structures.

Improved converted measurement Kalman filter for satellite‐borne multi‐target tracking

This study introduces a special converted measurement Kalman filter (CMKF) algorithm which apply to satellite for tracking target. Typical CMKF applies to radar which measures targets in spherical coordinate system. The new algorithm can be used by satellite which measures target's latitude and longitude. Improved CMKF algorithm tracks target in simple situation but is not able to deal with multi-target and information missing situation. Multiple hypothesis tracking (MHT) can track multi-target accurately and has the ability to initial track and end track at all times. For satellite, MHT use improved CMKF to calculate cost matrix and update the state estimate and estimate covariance. In the simulation, tracking process is simulated by MATLAB. Single target measured by satellite can be tracked accurately by CMKF algorithm. MHT can track multi-target accurately and distinguish the information missing rightly.

Multiple Target Tracking Based on Multiple Hypotheses Tracking and Modified Ensemble Kalman Filter in Multi-Sensor Fusion.

In multi-sensor fusion (MSF), the integration of multi-sensor observation data with different observation errors to achieve more accurate positioning of the target has always been a research focus. In this study, a modified ensemble Kalman filter (EnKF) is presented to substitute the traditional Kalman filter (KF) in the multiple hypotheses tracking (MHT) to deal with the high nonlinearity that always shows up in multiple target tracking (MTT) problems. In addition, the multi-source observation data fusion is also realized by using the modified EnKF, which enables the low-precision observation data to be corrected by high-precision observation data, and the accuracy of the corrected data can be calibrated by the statistical information provided by the EnKF. Numerical studies are given to demonstrate the effectiveness of our proposed method and the results show that the MHT-EnKF method can achieve remarkable enhancement in dealing with nonlinear movement variation and positioning accuracy for MTT problems in MSF scenario.

Multiple hypothesis method for tracking move‐stop‐move target

This study presents a new approach to track the move-stop-move targets. In the presence of the radar Doppler blind area, a move-stop-move target may lead to track breakages, which has some adverse effects on estimating the number of targets in the surveillance area. The authors develop a mode switching-based multiple hypothesis tracking (MHT) method to solve this problem. In each association, MHT generates three types of hypotheses: moving and detected, moving and undetected and stopped. In the first two types of hypotheses, the target is in the mode of move and tracked with interacting multiple model (IMM)-extended Kalman filter (EKF) estimator, while in the third kind of hypotheses, the target is in the mode of stop and tracked by EKF with a stop model. The mode probabilities are calculated using the kinematic state statistics from the estimator and the Markov transfer probability of the target movement stage. The track discontinuity event in the classical log-likelihood ratio of MHT is modified as well. The results of simulation experiment show that the proposed MHT-based tracker outperforms the conventional MHT-based method when tracking move-stop-move target.

Moving Object Detection and Tracking with Doppler LiDAR

In this paper, we present a model-free detection-based tracking approach for detecting and tracking moving objects in street scenes from point clouds obtained via a Doppler LiDAR that can not only collect spatial information (e.g., point clouds) but also Doppler images by using Doppler-shifted frequencies. Using our approach, Doppler images are used to detect moving points and determine the number of moving objects followed by complete segmentations via a region growing technique. The tracking approach is based on Multiple Hypothesis Tracking (MHT) with two extensions. One is that a point cloud descriptor, Oriented Ensemble of Shape Function (OESF), is proposed to evaluate the structure similarity when doing object-to-track association. Another is to use Doppler images to improve the estimation of dynamic state of moving objects. The quantitative evaluation of detection and tracking results on different datasets shows the advantages of Doppler LiDAR and the effectiveness of our approach.

Online Appearance-Motion Coupling for Multi-Person Tracking in Videos

Multi-person tracking in videos is a promising but challenging visual task. Recent progress in this field is introducing deep convolutional features as appearance models, which achieves robust tracking results when coupled with proper motion models. However, model failures that often cause severe tracking problems, have not been well discussed and addressed in previous work. In this paper, we propose a solution by online detecting such failures and accordingly adjusting the coupling between appearance and motion models. The strategy is letting the functional models take over when certain model faces data association ambiguity, and at the same time suppressing the influence of inappropriate observations during model update. Experimental results prove the benefit of our proposed improvement. Multiple object tracking; deep neural network; online learning; tracking-by-detection; multiple hypothesis tracking (key words)

Multiple Hypothesis Tracking with Kinematics and Appearance Models on Traffic Flow for Wide Area Traffic Surveillance

AbstractThis paper presents a study of multiple hypothesis tracking (MHT) of vehicles recorded in wide area motion imagery (WAMI) that has persistent coverage. To take advantage of visual informati...