Sequential Monte Carlo Probability Hypothesis Research Articles

SA-HPMHT for Maritime Dim Targets Tracking With Sensor Location Uncertainty

To address the problem of tracking low signal-to-clutter ratio (SCR) maritime targets with sensor location uncertainty, an effective track-before-detect (TBD) method, called the state augmentation histogram probabilistic multihypothesis tracking (SA-HPMHT) algorithm, is proposed in this article. In this algorithm, the initialization of new tracks is realized based on the constant false alarm rate (CFAR) detector with a low threshold and the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -means clustering algorithm. The target and sensor states are then simultaneously estimated in an iterative manner via a synthetic histogram and state augmentation (SA) method. In each iteration, we update the estimated sensor state and yield more accurate measured images, allowing for improved performance of detection and tracking targets. Finally, an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${M}/{N}$ </tex-math></inline-formula> logic technology is invoked to confirm or terminate the tracks. The results of simulation and real dataset verification show that the SA-HPMHT algorithm has a better performance compared with the histogram probabilistic multihypothesis tracking (H-PMHT) algorithm and the sequential Monte Carlo probability hypothesis density (SMC-PHD) algorithm.

Scene-Specialized Multitarget Detector with an SMC-PHD Filter and a YOLO Network.

You only look once (YOLO) is one of the most efficient target detection networks. However, the performance of the YOLO network decreases significantly when the variation between the training data and the real data is large. To automatically customize the YOLO network, we suggest a novel transfer learning algorithm with the sequential Monte Carlo probability hypothesis density (SMC-PHD) filter and Gaussian mixture probability hypothesis density (GM-PHD) filter. The proposed framework can automatically customize the YOLO framework with unlabelled target sequences. The frames of the unlabelled target sequences are automatically labelled. The detection probability and clutter density of the SMC-PHD filter and GM-PHD are applied to retrain the YOLO network for occluded targets and clutter. A novel likelihood density with the confidence probability of the YOLO detector and visual context indications is implemented to choose target samples. A simple resampling strategy is proposed for SMC-PHD YOLO to address the weight degeneracy problem. Experiments with different datasets indicate that the proposed framework achieves positive outcomes relative to state-of-the-art frameworks.

Underwater Multitarget Tracking With Sonar Images Using Thresholded Sequential Monte Carlo Probability Hypothesis Density Algorithm

This letter presents a multi-target tracking algorithm—thresholded Sequential Monte Carlo probability hypothesis density (TH-SMC-PHD) algorithm. The TH-SMC-PHD aims to overcome the problem that underwater multi-target tracking is prone to missing tracking on sonar images, resulting in the breakage of trajectories. First, CA-CFAR and K-means are employed to detect potential underwater targets from sonar images, respectively. Then TH-SMC-PHD is applied to the detection results for tracking, using a continuously lost frame threshold to reduce the missing tracking rate and the Minimum-Sampling-Variance (MSV) resampling to improve tracking accuracy. An actual underwater multi-target tracking experiment using a forward-looking sonar was contracted in a water tank to evaluate the tracking performance. Compared with the other two PHD tracking algorithms, the results demonstrate that the proposed algorithm achieves high-precision, non-fracture, non-missing tracking of three targets. In addition, the TH-SMC-PHD is more stable and less affected by different detection algorithms, which has the potential for practical applications.

A Robust SMC-PHD Filter for Multi-Target Tracking with Unknown Heavy-Tailed Measurement Noise.

In multi-target tracking, the sequential Monte Carlo probability hypothesis density (SMC-PHD) filter is a practical algorithm. Influenced by outliers under unknown heavy-tailed measurement noise, the SMC-PHD filter suffers severe performance degradation. In this paper, a robust SMC-PHD (RSMC-PHD) filter is proposed. In the proposed filter, Student-t distribution is introduced to describe the unknown heavy-tailed measurement noise where the degrees of freedom (DOF) and the scale matrix of the Student-t distribution are respectively modeled as a Gamma distribution and an inverse Wishart distribution. Furthermore, the variational Bayesian (VB) technique is employed to infer the unknown DOF and scale matrix parameters while the recursion estimation framework of the RSMC-PHD filter is derived. In addition, considering that the introduced Student- t distribution might lead to an overestimation of the target number, a strategy is applied to modify the updated weight of each particle. Simulation results demonstrate that the proposed filter is effective with unknown heavy-tailed measurement noise.

Automated extraction of dolphin whistles-A sequential Monte Carlo probability hypothesis density approach.

The need for automated methods to detect and extract marine mammal vocalizations from acoustic data has increased in the last few decades due to the increased availability of long-term recording systems. Automated dolphin whistle extraction represents a challenging problem due to the time-varying number of overlapping whistles present in, potentially, noisy recordings. Typical methods utilize image processing techniques or single target tracking, but often result in fragmentation of whistle contours and/or partial whistle detection. This study casts the problem into a more general statistical multi-target tracking framework and uses the probability hypothesis density filter as a practical approximation to the optimal Bayesian multi-target filter. In particular, a particle version, referred to as a sequential Monte Carlo probability hypothesis density (SMC-PHD) filter, is adapted for frequency tracking and specific models are developed for this application. Based on these models, two versions of the SMC-PHD filter are proposed and the performance of these versions is investigated on an extensive real-world dataset of dolphin acoustic recordings. The proposed filters are shown to be efficient tools for automated extraction of whistles, suitable for real-time implementation.

Audio–Visual Particle Flow SMC-PHD Filtering for Multi-Speaker Tracking

Sequential Monte Carlo probability hypothesis density (SMC-PHD) filtering is a popular method used recently for audio-visual (AV) multi-speaker tracking. However, due to the weight degeneracy problem, the posterior distribution can be represented poorly by the estimated probability, when only a few particles are present around the peak of the likelihood density function. To address this issue, we propose a new framework where particle flow (PF) is used to migrate particles smoothly from the prior to the posterior probability density. We consider both zero and non-zero diffusion particle flows (ZPF/NPF), and developed two new algorithms, AV-ZPF-SMC-PHD and AV-NPF-SMC-PHD, where the speaker states from the previous frames are also considered for particle relocation. The proposed algorithms are compared systematically with several baseline tracking methods using the AV16.3, AVDIAR and CLEAR datasets, and are shown to offer improved tracking accuracy and average effective sample size (ESS).

Local-Diffusion-Based Distributed SMC-PHD Filtering Using Sensors With Limited Sensing Range

We investigate the problem of distributed multitarget tracking by using a set of netted, collaborative sensors with limited sensing range (LSR), where each sensor runs a sequential Monte Carlo probability hypothesis density filter and exchanges relevant posterior information with its neighbors. The key challenge stems from the LSR of neighbor sensors whose fields of view (FoVs) are partially/non-overlapped, and therefore, they may observe different targets at the same time. With regard to the local common FoVs among neighbor sensors, the proposed distributed fusion approach, called local diffusion, performs one iteration of neighbor communication per filtering step in either of two means. One is given by immediate particle exchange, in which a reject-control operation is devised to reduce the number of communicating particles. The other is done by converting the particle distribution to Gaussian functions for parametric information exchange and fusion. The performance of both approaches has been experimentally investigated via simulation for different LSR situations and compared with cutting-edge approaches.

Particle PHD Filter Based Multiple Human Tracking Using Online Group-Structured Dictionary Learning

An enhanced sequential Monte Carlo probability hypothesis density (PHD) filter-based multiple human tracking system is presented. The proposed system mainly exploits two concepts: a novel adaptive gating technique and an online group-structured dictionary learning strategy. Conventional PHD filtering methods preset the target birth intensity and the gating threshold for selecting real observations for the PHD update. This often yields inefficiency in false positives and missed detections in a cluttered environment. To address this issue, a measurement-driven mechanism based on a novel adaptive gating method is proposed to adaptively update the gating sizes. This yields an accurate approach to discriminate between survival and residual measurements by reducing the clutter inferences. In addition, online group-structured dictionary learning with a maximum voting method is used to robustly estimate the target birth intensity. It enables the new-born targets to be automatically detected from noisy sensor measurements. To improve the adaptability of our group-structured dictionary to appearance and illumination changes, we employ the simultaneous code word optimization algorithm for the dictionary update stage. Experimental results demonstrate our proposed method achieves the best performance amongst state-of-the-art random finite set-based methods, and the second best online tracker ranked on the leaderboard of latest MOT17 challenge.

Kalman-Gain Aided Particle PHD Filter for Multitarget Tracking

We propose an efficient sequential Monte Carlo probability hypothesis density (PHD) filter which employs the Kalman-gain approach during weight update to correct predicted particle states by minimizing the mean square error between the estimated measurement and the actual measurement received at a given time in order to arrive at a more accurate posterior. This technique identifies and selects those particles belonging to a particular target from a given PHD for state correction during weight computation. Besides the improved tracking accuracy, fewer particles are required in the proposed approach. Simulation results confirm the improved tracking performance when evaluated with different measures.

A Novel Sequential Monte Carlo-Probability Hypothesis Density Filter for Particle Impoverishment Problem

As a typical implementation of the probability hypothesis density (PHD) filter, sequential Monte Carlo PHD (SMC-PHD) is widely employed in highly nonlinear systems. However, diversity loss of particles introduced by the resampling step, which can be called particle impoverishment problem, may lead to performance degradation and restrain the use of SMC-PHD filter in practical applications. In this paper, a novel SMC-PHD filter based on particle compensation is proposed to solve the problem. Firstly, based on an analysis of the particle impoverishment problem, a new particle compensatory method is developed to improve the particle diversity. Then, all the particles are integrated into the SMC-PHD filter framework. Compared with the SMC-PHD filter, simulation results demonstrate that the proposed particle compensatory SMC-PHD filter is capable of overcoming the particle impoverishment problem, which indicate good application prospects.

Multi-Target State Extraction for the SMC-PHD Filter.

The sequential Monte Carlo probability hypothesis density (SMC-PHD) filter has been demonstrated to be a favorable method for multi-target tracking. However, the time-varying target states need to be extracted from the particle approximation of the posterior PHD, which is difficult to implement due to the unknown relations between the large amount of particles and the PHD peaks representing potential target locations. To address this problem, a novel multi-target state extraction algorithm is proposed in this paper. By exploiting the information of measurements and particle likelihoods in the filtering stage, we propose a validation mechanism which aims at selecting effective measurements and particles corresponding to detected targets. Subsequently, the state estimates of the detected and undetected targets are performed separately: the former are obtained from the particle clusters directed by effective measurements, while the latter are obtained from the particles corresponding to undetected targets via clustering method. Simulation results demonstrate that the proposed method yields better estimation accuracy and reliability compared to existing methods.

Cubature Information SMC-PHD for Multi-Target Tracking.

In multi-target tracking, the key problem lies in estimating the number and states of individual targets, in which the challenge is the time-varying multi-target numbers and states. Recently, several multi-target tracking approaches, based on the sequential Monte Carlo probability hypothesis density (SMC-PHD) filter, have been presented to solve such a problem. However, most of these approaches select the transition density as the importance sampling (IS) function, which is inefficient in a nonlinear scenario. To enhance the performance of the conventional SMC-PHD filter, we propose in this paper two approaches using the cubature information filter (CIF) for multi-target tracking. More specifically, we first apply the posterior intensity as the IS function. Then, we propose to utilize the CIF algorithm with a gating method to calculate the IS function, namely CISMC-PHD approach. Meanwhile, a fast implementation of the CISMC-PHD approach is proposed, which clusters the particles into several groups according to the Gaussian mixture components. With the constructed components, the IS function is approximated instead of particles. As a result, the computational complexity of the CISMC-PHD approach can be significantly reduced. The simulation results demonstrate the effectiveness of our approaches.

SMC-PHD algorithm based on squared cubature particles

Most of the conventional sequential Monte Carlo probability hypothesis density( SMC-PHD)approaches adopt the state transition density as importance sampling function. When targets are with nonlinear motions,such a selection makes few particles with large weights,leading to inaccurate estimation and particle divergence. To avoid such problems,a novel importance sampling function approximation approach with the squared cubature Kalman filter( SCKF) and statistical gating method was proposed. To design such an importance sampling function,the mean and covariance of importance sampling function were predicted at first.Then,the statistical gating method were utilized to extract observations associated with the importance sampling particle from the current observation set. Merging the extracted observations with corresponding weights,the mean and covariance of importance sampling function were updated. Using the designed importance sampling function,the intensity of particles can be predicted and updated,according to the conventional SMCPHD method. At last,the states and number of multi-target can be approximated by the intensity of particles.The simulation results demonstrate that the proposed approach has the advantages of high accuracy and stable estimation in nonlinear target tracking.

Dolphin Whistle Track Estimation Using Sequential Monte Carlo Probability Hypothesis Density Filter

This article focuses on possible automation of dolphin whistle track estimation process within the context of Multiple Target Tracking (MTT). It provides automatic whistle track estimation from raw hydrophone measurements using the Sequential Monte Carlo Probability Hypothesis Density (SMC-PHD) filter. Hydrophone measurements for three different types of species namely bottlenose dolphin (Tursiops truncates), common dolphin (Delphinus delphis) and striped dolphin (Stenella coeruleoalba) have been used to benchmark the tracking performance of the SMC-PHD filter against three major challenges- the presence of multiple whistles, spontaneous death/birth of whistles and multiple whistles crossing each other. Quantitative analysis of the whistle track estimation accuracy is not possible since there is no ground truth type track for the dolphin whistles. Hence visual inspection of estimated tracks has been used corroborate the satisfactory tracking performance in the presence of all three challenges. DOI: http://dx.doi.org/10.3329/dujs.v62i1.21954 Dhaka Univ. J. Sci. 62(1): 17-20, 2014 (January)

Fast Gaussian Mixture Probability Hypothesis Density Filter

Although the Gaussian mixture probability hypothesis density (GMPHD) filter is a multi-target tracker that can alleviate the computational intractability of the optimal multi-target Bayes filter and its computational complex is lower than that of sequential Monte Carlo probability hypothesis density (SMCPHD), its computational burden can be reduced further. In the standard GMPHD filter, each observation should be matched with each component when the PHD is updated. In practice, time cost of evaluating many unlikely measurements-to-components parings is wasteful, because their contribution is very limited. As a result, a substantial reduction in complexity could be obtained by directly setting relative value associated with these parings. A fast GMPHD algorithm is proposed in the paper based on gating strategy. Simulation results show that the fast GMPHD can save computational time by 60%~70% without any degradation in performance compared with standard GMPHD.

The Spline Probability Hypothesis Density Filter

The Probability Hypothesis Density (PHD) filter is a multitarget tracker that can alleviate the computational intractability of the optimal multitarget Bayes filter. The PHD filter recursively estimates the number of targets and their PHD from a set of observations and works well in scenarios with false alarms and missed detections. Two distinct PHD filter implementations are available in the literature: the Sequential Monte Carlo Probability Hypothesis Density (SMC-PHD) and the Gaussian Mixture Probability Hypothesis Density (GM-PHD) filters. While particle-based PHD implementations may suffer from degeneracy, GM-based methods may not be suitable for highly nonlinear non-Gaussian systems. This paper proposes a B-Spline based Spline Probability Hypothesis Density (SPHD) filter, which has the capability to better approximate any arbitrary probability density function. The resulting algorithm can handle linear, non-linear, Gaussian, and non-Gaussian models. The SPHD filter can provide continuous estimates of the probability density function of the system state and it is immune to the degeneracy problem. The SPHD filter can maintain highly accurate tracks by taking advantage of dynamic knot movement, but at the expense of higher computational complexity, which makes it suitable for tracking a few high-value targets under difficult conditions. The SPHD filter derivations and simulations are provided in this paper.

Gaussian mixture importance sampling function for unscented SMC-PHD filter

The unscented sequential Monte Carlo probability hypothesis density (USMC-PHD) filter has been proposed to improve the accuracy performance of the bootstrap SMC-PHD filter in cluttered environments. However, the USMC-PHD filter suffers from heavy computational complexity because the unscented information filter is assigned for every particle to approximate an importance sampling function. In this paper, we propose a Gaussian mixture form of the importance sampling function for the SMC-PHD filter to considerably reduce the computational complexity without performance degradation. Simulation results support that the proposed importance sampling function is effective in computational aspects compared with variants of SMC-PHD filters and competitive to the USMC-PHD filter in accuracy.

Track-before-detect for Infrared Maneuvering Dim Multi-target via MM-PHD

In this paper, we present a novel and efficient track-before-detect (TBD) algorithm based on multiple-model probability hypothesis density (MM-PHD) for tracking infrared maneuvering dim multi-target. Firstly, the standard sequential Monte Carlo probability hypothesis density (SMC-PHD) TBD-based algorithm is introduced and sequentially improved by the adaptive process noise and the importance re-sampling on particle likelihood, which result in the improvement in the algorithm robustness and convergence speed. Secondly, backward recursion of SMC-PHD is derived in order to ameliorate the tracking performance especially at the time of the multi-target arising. Finally, SMC-PHD is extended with multiple-model to track maneuvering dim multi-target. Extensive experiments have proved the efficiency of the presented algorithm in tracking infrared maneuvering dim multi-target, which produces better performance in track detection and tracking than other TBD-based algorithms including SMC-PHD, multiple-model particle filter (MM-PF), histogram probability multi-hypothesis tracking (H-PMHT) and Viterbi-like.

Tracking Partly Resolvable Group Targets Using SMC-PHDF

摘要: 提出一种基于粒子概率假设密度滤波器(Sequential Monte Carlo probability hypothesis density filter, SMC-PHDF)的部分可分辨的群目标跟踪算法. 该算法可直接获得群而非个体的个数和状态估计. 这里群的状态包括群的质心状态和形状. 为了估计群的个数和状态, 该算法利用高斯混合模型(Gaussian mixture models, GMM)拟合SMC-PHDF中经重采样后的粒子分布, 这里混合模型的元素个数和参数分别对应于群的个数和状态. 期望最大化(Expectation maximum, EM)算法和马尔科夫链蒙特卡洛(Markov chain Monte Carlo, MCMC)算法分别被用于估计混合模型的参数. 混合模型的元素个数可通过删除、合并及分裂算法得到. 100次蒙特卡洛(Monte Carlo, MC)仿真实验表明该算法可有效跟踪部分可分辨的群目标. 相比EM算法, MCMC算法能够更好地提取群的个数和状态, 但它的计算量要大于EM算法. 关键词: 群目标跟踪 / 粒子概率假设密度滤波器 / 高斯混合模型 / 期望最大化算法 / 马尔科夫链蒙特卡洛算法