Multiple Hypothesis Tracking Research Articles

Detection of Multiple Maneuvering Extended Targets by Three-Dimensional Hough Transform and Multiple Hypothesis Tracking

Existing extended target probability hypothesis density (ET-PHD) filters are insufficient in tracking weak extended targets. Hough transform-based track-before-detect methods are designed to detect the weak targets in a straight-line constant-velocity model. Therefore, this paper presents a novel method for detecting and tracking multiple maneuvering weak extended targets by a 3-dimensional Hough transform (3DHT) and multiple hypothesis tracking (MHT). The proposed method consists of two stages. In stage 1, the measurements in multiple scans are partitioned into overlapped time windows. The tracklets in each window can be detected by the 3DHT. In stage 2, the tracklets are associated to get the entire trajectories by the MHT. The tracklets of weak targets can be detected by the 3DHT in stage 1. Association in stage 2 is designed to detect maneuvering targets. Some false alarm tracklets could be built in stage 1. However, the false alarm tracklets are independent and unlikely to form a sequential trajectory in stage 2. Merely, the trajectories whose target likelihood ratio larger than a detection threshold can be confirmed as a target. Both the real data and the synthetic data are performed with the proposed approach and several existing algorithms. The result infers that the proposed approach is superior to the others with much less prior information that is necessary.

A Geometric Model based 2D LiDAR/Radar Sensor Fusion for Tracking Surrounding Vehicles

Abstract This paper presents a novel and efficient sensor fusion system for tracking multiple moving vehicles over Light Detection and Ranging (LiDAR) and Radar in autonomous vehicles. What is important in the sensor fusion using LiDAR and Radar is how well they utilize the characteristics of each sensor. The proposed fusion system improves the estimating accuracy and maximum perception distance for the target vehicles by utilizing LiDAR which has high distance accuracy and Radar which has wide Field of View (FOV) and observability of relative speed. In addition, multiple hypothesis tracking (MHT) based track management and extended Kalman filtering (EKF) based filtering enable multitarget tracking with less computational complexity than particle filter-based methods. Three measurement models are designed according to the types of measurement assigned to each track, and the tracks were updated optimally according to each model. The proposed fusion system is evaluated through the real vehicle test with RT-range.

Underwater Bearings-Only Multitarget Tracking Based on Modified PMHT in Dense-Cluttered Environment

Underwater bearings-only multitarget tracking has many advantages, and the probabilistic multiple hypothesis tracking (PMHT) is an elegant algorithm for multitarget tracking problem. However, the basic PMHT has following weakness: 1) the targets' posterior probability may convergent to the local maximum, which would degrade the tracking accuracy and 2) the tracking performance is sensitive to the targets' initialization. In order to overcome these weaknesses, this paper proposes a modified PMHT algorithm. The key idea of the modified PMHT algorithm is that it allows the bearings measurements at one scan come from any Gaussian density, which has the same mean and different covariance with the same target. In addition, the modified PMHT algorithm uses the deterministic annealing to reduce the dependence on the targets' initialization. To deal with the nonlinear bearings measurements, the paper uses the unscented Kalman smoother to update the target states. The simulation treats the cross moving targets and closely spaced targets for both multiple stationary sensors and single maneuvering sensor scenarios in a dense clutter environment. The simulation results show the superiority of the modified PMHT algorithm over the basic PMHT algorithm respect to accuracy and robustness for underwater bearings-only multitarget tracking problem when setting a relatively bad initialization value.

Multiple Hypothesis Semantic Mapping for Robust Data Association

In this paper, we present a semantic mapping approach with multiple hypothesis tracking for data association. As semantic information has the potential to overcome ambiguity in measurements and place recognition, it forms an eminent modality for autonomous systems. This is particularly evident in urban scenarios with several similar looking surroundings. Nevertheless, it requires the handling of a non-Gaussian and discrete random variable coming from object detectors. Previous methods facilitate semantic information for global localization and data association to reduce the instance ambiguity between the landmarks. However, many of these approaches do not deal with the creation of complete globally consistent representations of the environment and typically do not scale well. We utilize multiple hypothesis trees to derive a probabilistic data association for semantic measurements by means of position, instance and class to create a semantic representation. We propose an optimized mapping method and make use of a pose graph to derive a novel semantic SLAM solution. Furthermore, we show that semantic covisibility graphs allow for a precise place recognition in urban environments. We verify our approach using real-world outdoor dataset and demonstrate an average drift reduction of 33 % w.r.t. the raw odometry source. Moreover, our approach produces 55 % less hypotheses on average than a regular multiple hypotheses approach.

Robust and Real-Time Detection and Tracking of Moving Objects with Minimum 2D LiDAR Information to Advance Autonomous Cargo Handling in Ports.

Detecting and tracking moving objects (DATMO) is an essential component for autonomous driving and transportation. In this paper, we present a computationally low-cost and robust DATMO system which uses as input only 2D laser rangefinder (LRF) information. Due to its low requirements both in sensor needs and computation, our DATMO algorithm is meant to be used in current Autonomous Guided Vehicles (AGVs) to improve their reliability for the cargo transportation tasks at port terminals, advancing towards the next generation of fully autonomous transportation vehicles. Our method follows a Detection plus Tracking paradigm. In the detection step we exploit the minimum information of 2D-LRFs by segmenting the elements of the scene in a model-free way and performing a fast object matching to pair segmented elements from two different scans. In this way, we easily recognize dynamic objects and thus reduce consistently by between two and five times the computational burden of the adjacent tracking method. We track the final dynamic objects with an improved Multiple-Hypothesis Tracking (MHT), to which special functions for filtering, confirming, holding, and deleting targets have been included. The full system is evaluated in simulated and real scenarios producing solid results. Specifically, a simulated port environment has been developed to gather realistic data of common autonomous transportation situations such as observing an intersection, joining vehicle platoons, and perceiving overtaking maneuvers. We use different sensor configurations to demonstrate the robustness and adaptability of our approach. We additionally evaluate our system with real data collected in a port terminal the Netherlands. We show that it is able to accomplish the vehicle following task successfully, obtaining a total system recall of more than 98% while running faster than 30 Hz.

Multi-appearance segmentation and extended 0-1 programming for dense small object tracking.

Aiming to address dense small object tracking, we propose an image-to-trajectory framework including tracking and detection, where Track-Oriented Multiple Hypothesis Tracking(TOMHT) is revised for tracking. Unlike common cases of multi-object tracking, merged detections and the greater number of objects make dense small object tracking a more challenging problem. Firstly, we handle frequent merged detections through the aspects of detection and hypothesis selection. To tackle merged detection, we revise Local Contrast Method(LCM) and propose a multi-appearance variant, which exploits tree-like topological information and realizes one threshold for one object. Meanwhile, one-to-many constraint is employed via the proposed extended 0-1 programming, which enables hypothesis selection to handle track exclusions caused by merged detections. Secondly, to alleviate the high complexity caused by dense objects, we consider batch optimization and more rigorous and precise pruning technologies. Specifically, we propose autocorrelation based motion score test and two-stage hypotheses pruning. Experimental results are presented to verify the strength of our methods, which indicates speed and performance advantages of our tracker.

Dynamic Obstacle Detection and Tracking Based on 3D Lidar

Detection and tracking of dynamic obstacle is one of the research hotspot in autonomous vehicles. In this paper, a dynamic obstacle detection and tracking method based on 3D lidar is proposed. The nearest neighborhood method is used to cluster the data obtained by the laser lidar. The characteristic parameters of the clustering obstacles are analyzed. Multiple hypothesis tracking model (MHT) algorithm and the nearest neighbor association algorithm are used for data association of two consecutive frames of obstacle information. The dynamic and static state of obstacles are analyzed through the temporal and spatial correlation of the obstacle. Finally, we use linear Kalman filter to predict the movement state of the obstacle. The experimental results on a low-speed driverless vehicle “small whirlwind” which is an autonomous sightseeing vehicle show that the method can accurately detect the dynamic obstacles in unknown environment with effectiveness and real-time performance.

Relationship Between Finite Set Statistics and the Multiple Hypothesis Tracker

The multiple hypothesis tracker (MHT) and finite set statistics (FISST) are two approaches to multitarget tracking, which both have been heralded as optimal. In this paper, we show that the multitarget Bayes filter with basis in FISST can be expressed in terms the MHT formalism, consisting of association hypotheses with corresponding probabilities and hypothesis-conditional densities of the targets. Furthermore, we show that the resulting MHT-like method under appropriate assumptions (Poisson clutter and birth models, no target death, linear-Gaussian Markov target kinematics) only differs from Reid's MHT with regard to the birth process.

Particle filter for multipath time delay tracking from correlation functions in deep water.

This paper presents a particle filtering-based approach for tracking multipath time delays from correlation function, such as autocorrelation, cross-correlation, and matched-filter output. The proposed approach exploits the continuous evolution with time of the correlations between multipath arrivals masked by the background noise to track time delays. The prominent feature of this approach is tracking the signal-related peaks (single points) instead of correlation pulses adopted in conventional approaches. To do so, the correlation function with only local peaks is introduced in the model of the measurement equation. This allows no assumption on the reference signal used to match the correlation pulse and no a priori knowledge of the covariance of the background noise. The time-evolving marginal posterior probability densities are also extracted by filtering to reveal the uncertainty of the time delays in every step of tracking. The approach is performed on both simulated data in reliable acoustic path propagation and experimental data collected during two deep water experiments; the results demonstrate significant advantages of the proposed method over a conventional state-space approach, the multiple hypothesis tracking, and a modified peak amplitude detection method.

Multiple hypothesis tracking algorithm for multi‐target multi‐camera tracking with disjoint views

In this study, a multiple hypothesis tracking (MHT) algorithm for multi-target multi-camera tracking (MCT) with disjoint views is proposed. Our method forms track-hypothesis trees, and each branch of them represents a multi-camera track of a target that may move within a camera as well as move across cameras. Furthermore, multi-target tracking within a camera is performed simultaneously with the tree formation by manipulating a status of each track hypothesis. Each status represents three different stages of a multi-camera track: tracking, searching, and end-of-track. The tracking status means targets are tracked by a single camera tracker. In the searching status, the disappeared targets are examined if they reappear in other cameras. The end-of-track status does the target exited the camera network due to its lengthy invisibility. These three status assists MHT to form the track-hypothesis trees for multi-camera tracking. Furthermore, they present a gating technique for eliminating of unlikely observation-to-track association. In the experiments, they evaluate the proposed method using two datasets, DukeMTMC and NLPR-MCT, which demonstrates that the proposed method outperforms the state-of-the-art method in terms of improvement of the accuracy. In addition, they show that the proposed method can operate in real-time and online.

A Novel Ship-Tracking Method for GF-4 Satellite Sequential Images.

The geostationary remote sensing satellite has the capability of wide scanning, persistent observation and operational response, and has tremendous potential for maritime target surveillance. The GF-4 satellite is the first geostationary orbit (GEO) optical remote sensing satellite with medium resolution in China. In this paper, a novel ship-tracking method in GF-4 satellite sequential imagery is proposed. The algorithm has three stages. First, a local visual saliency map based on local peak signal-to-noise ratio (PSNR) is used to detect ships in a single frame of GF-4 satellite sequential images. Second, the accuracy positioning of each potential target is realized by a dynamic correction using the rational polynomial coefficients (RPCs) and automatic identification system (AIS) data of ships. Finally, an improved multiple hypotheses tracking (MHT) algorithm with amplitude information is used to track ships by further removing the false targets, and to estimate ships’ motion parameters. The algorithm has been tested using GF-4 sequential images and AIS data. The results of the experiment demonstrate that the algorithm achieves good tracking performance in GF-4 satellite sequential images and estimates the motion information of ships accurately.

Multicell migration tracking within angiogenic networks by deep learning-based segmentation and augmented Bayesian filtering.

.Cell migration is a key feature for living organisms. Image analysis tools are useful in studying cell migration in three-dimensional (3-D) in vitro environments. We consider angiogenic vessels formed in 3-D microfluidic devices (MFDs) and develop an image analysis system to extract cell behaviors from experimental phase-contrast microscopy image sequences. The proposed system initializes tracks with the end-point confocal nuclei coordinates. We apply convolutional neural networks to detect cell candidates and combine backward Kalman filtering with multiple hypothesis tracking to link the cell candidates at each time step. These hypotheses incorporate prior knowledge on vessel formation and cell proliferation rates. The association accuracy reaches 86.4% for the proposed algorithm, indicating that the proposed system is able to associate cells more accurately than existing approaches. Cell culture experiments in 3-D MFDs have shown considerable promise for improving biology research. The proposed system is expected to be a useful quantitative tool for potential microscopy problems of MFDs.

Multiple-Hypothesis Tracking for Targets Producing Multiple Measurements

This paper extends the multiple-hypothesis tracking (MHT) recursion to allow for multiple detections per target, per scan of data. We show that the generalized recursion admits the factorization of global-hypothesis probabilities, enabling track-oriented MHT. We propose a two-stage MHT implementation that allows tractable processing in this setting, and explore performance with respect to classical track-oriented MHT processing.

Joint Kinematic and Feature Tracking of Ships with Satellite Electronic Information

To track multiple ships and estimate the feature parameters of multiple emitters on board using electronic intelligence satellites under clutter interference, a long and random revisit time, and other complex conditions, a novel tracking algorithm using both kinematic (position and velocity) and feature information based on an improved Multiple Hypothesis Tracking (MHT) approach is proposed in this paper. Firstly, the characteristics of multi-ship tracking with multiple emitters using satellite electronic information are analysed, and a new model of an emitter is built as an extended target in geographical coordinates. Secondly, a pre-processing of measurements is utilised via hierarchical clustering using the location and feature information of emitters. Thirdly, feature information is incorporated into the MHT framework using Jensen-Shannon divergence distance and fuzzy C-means clustering to calculate track scores. Finally, we present the prediction and update of target states, especially the update of feature parameters, to realise joint kinematic and feature tracking of ships. The results of the simulation show that the proposed method has much better tracking performance than the standard MHT algorithm.

Ship target tracking based on a low-resolution optical satellite in geostationary orbit

ABSTRACTBased on the low-resolution geostationary optical satellite for maritime surveillance, a complete processing algorithm including ship detection and ship tracking is proposed. Potentially ships are first detected by a constant false alarm rate processing and a morphological filter from the area of water. Image coordinates of ships are then corrected and transformed by using rational polynomial coefficients and high-resolution shoreline database. In the ship-tracking procedure, a convenient motion model based on geographical coordinates is established, and the multiple hypothesis tracking method is used to track ships for further removing false targets and getting motion states of targets ultimately. Our algorithm has been tested using GaoFen-4 (GF-4) satellite image sequences and the automatic identification system messages of ships. The results of the experiment show that the proposed algorithm can effectively detect and track ships in complex scenes and estimate ships’ motion information accurately with the help of a low-resolution geostationary optical satellite.

Track-Oriented Multiple Hypothesis Tracking Based on Tabu Search and Gibbs Sampling

In order to circumvent the curse of dimensionality in multiple hypothesis tracking data association, this paper proposes two efficient implementation algorithms using Tabu search and Gibbs sampling. As the first step, we formulate the problem of generating the best global hypothesis in multiple hypothesis tracking as the problem of finding a maximum weighted independent set of a weighted undirected graph. Then, the metaheuristic Tabu search with two basic movements is designed to find the global optimal solution of the problem formulated. To improve the computational efficiency, this paper also develops a sampling based algorithm based on Gibbs sampling. The problem formulated for the Tabu search-based algorithm is reformulated as a maximum product problem to enable the implementation of Gibbs sampling. The detailed algorithm is then designed and the convergence is also theoretically analyzed. The performance of the two algorithms proposed are verified through numerical simulations and compared with that of a mainstream multiple dimensional assignment implementation algorithm. The simulation results confirm that the proposed algorithms significantly improve the computational efficiency while maintaining or even enhancing the tracking performance.

Group tracking algorithm for split maneuvering based on complex domain topological descriptions

A group tracking algorithm for split maneuvering based on complex domain topological descriptions is proposed for the tracking of members in a maneuvering group. According to the split characteristics of a group target, split models of group targets are established based on a sliding window feedback mechanism to determine the occurrence and classification of split maneuvering, which makes the tracked objects focus by group members effectively. The track of an outlier single target is reconstructed by the sequential least square method. At the same time, the relationship between the group members is expressed by the complex domain topological description method, which solves the problem of point-track association between the members. The Singer method is then used to update the tracks. Compared with classical multi-target tracking algorithms based on Multiple Hypothesis Tracking (MHT) and the Different Structure Joint Probabilistic Data Association (DS-JPDA) algorithm, the proposed algorithm has better tracking accuracy and stability, is robust against environmental clutter and has stable time-consumption under both classical radar conditions and partly resolvable conditions.

Multiple Extended Targets Tracking Algorithm Based on Generalized Labeled Multi-Bernoulli Filter

An extended target filter based on random finite sets (RFS) is proposed with modeling for Star-Convex. The proposed algorithms combine multiple hypotheses tracking (MHT) and labeled RFS to smooth the multiframe measurements. Experimental results show that the proposed algorithm is able to form the track and estimate the target state effectively, the tracking performance is better than that of the traditional extended target filter in the low signal-to-noise ratio (SNR) scenario.

Multi-sensor target tracking in the presence of clutter using game theory

The problem of multi-sensor target tracking in the presence of clutter has not been studied from a game theory point of view. This paper presents a game theory approach for such a problem. Fundamental sub-problems are state estimation and data association in multi-sensor target tracking systems. In this paper, the state estimation problem is formulated as zero-sum game and a minimax filter is developed to estimate the target characteristics, including its position, velocity, and acceleration. To extend the filter in the presence of clutter, a data association framework is proposed. In data association framework, set of new hypotheses in each step is produced from set of validated measurements and the ith global hypothesis is obtained from the previous step. Next, posteriori estimate of ith global hypothesis is updated based on the filter for each new hypothesis. To manage exponential growth of new hypotheses, a new k-best algorithm is implemented. Simulation results illustrate the improved performance of the proposed filter compared to multiple hypothesis tracking and nearest-neighbor fuzzy filters.

A novel fast target tracking method for UAV aerial image

Abstract Unmanned aerial vehicles (UAV) are able to achieve autonomous flight without drivers, and UAV has been a key tool to extract space data. Therefore, how to detect the trajectories of targets from UAV aerial image sequences is of great importance. Because local features are suitable to detect target tracking, we exploit scaleinvariant feature transform (SIFT) features to describe the interesting keypoints of targets. The main innovation of this paper is to utilize Multiple hypothesis tracking (MHT) algorithm to track an object (target) in a series of image sequences. Particularly, we develop a MHT framework based on a multidimensional assignment formulation and a sliding time window policy. To obtain target tracking from UAV aerial image sequences, three steps should be done, that is, 1) Breaking each track set into tracklet at a specific time, 2) Estimating the association cost of each track set, 3) Merging trajectory fragments to a longer one iteratively. Finally, we collect several UAV aerial image sequences with different target density to construct a dataset, and experimental results demonstrate the effectiveness of the proposed algorithm.