Shared-memory parallelization of a local correlation multi-reference CI program

We present a shared-memory parallelization of our open-source, local correlation multi-reference framework, TigerCI. Benchmarks of the total parallel speedup show a reasonable scaling for typical modern computing system setups. The efficient use of available computing resources will extend simulations on this high level of theory into a new size regime. We demonstrate our framework using local-correlation multireference computations of alkyl-substituted dioxirane and solvated methyl nitrene as examples.     

An efficient track association algorithm for the multitarget tracking problem

A new and extremely promising approach is presented for the solution of the multitarget tracking problem for an important class of targets. For the class of targets that can be described as a linear, time-invariant system, it appears that this approach may be considerably more efficient, computationally, than existing procedures. A survey of approaches to the solution of the multitarget tracking problem has been presented in Ref. [2]. As indicated there, most algorithms require the use of the Kalman filter to provide state estimation for data association and track assignment. In this report, the need for state estimation to identify feasible tracks is eliminated. The use of simpler input-output models for track prediction results in a very substantial reduction in computational burden when compared with methods requiring state estimation.The utility of the method presented here depends, as do Kalman-filter-based methods, upon the definition of data windows that permit the identification of feasible tracks and the elimination of infeasible tracks in a timely manner and according to statistically meaningful criteria. After identifying feasible tracks, the Kalman filter can be utilized to obtain the required state estimates and to analyze and refine the information in the feasible track files.     

多传感器多目标联合概率数据关联研究

提出改进联合概率数据关联算法对多传感器、多目标量测进行同源划分及单一传感器测量数据转换,并采用联合概率数据关联算法求解空间目标轨迹交叉时的数据关联.仿真结果表明,改进联合概率数据关联算法提高了成功关联概率,降低了求解数据关联概率的难度,可以解决密集目标的正确跟踪问题.     

Multiple hypothesis tracking for data association in vehicular networks

The introduction of Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communications in Intelligent Transportation Systems of the future brings new opportunities and new challenges into the automotive scene. Vehicular communications broaden the information spectrum that is available to each vehicle, allowing the enhancement of existing applications and the introduction of new ones. Undoubtedly, the impact of this new technology in transportation safety, efficiency and infotainment is expected to be very important.A significant part of research in vehicular networks (VANETs) is dedicated to networking issues like routing and safety. However, perception systems which until now were based on onboard sensors only, need to incorporate the wirelessly received information in order to extend the situation awareness of the vehicle and the driver. This paper presents an algorithm for associating targets tracked from an onboard radar sensor with the position and motion data received from the VANET. The core of the algorithm is a track oriented multiple hypothesis tracker that is modified for incorporating information included in VANET messages. The algorithm is tested in real scenarios using two experimental vehicles and then compared with two other algorithmic approaches. One is using a simpler single hypothesis algorithm for association of VANET messages and the second is using only the onboard sensors for environment perception. As a result, the advantages of the Multiple Hypothesis Algorithm regarding association performance and the added value of wireless information in the perception system are highlighted.     

Overlapping Mixtures of Gaussian Processes for the data association problem

In this work we introduce a mixture of GPs to address the data association problem, i.e., to label a group of observations according to the sources that generated them. Unlike several previously proposed GP mixtures, the novel mixture has the distinct characteristic of using no gating function to determine the association of samples and mixture components. Instead, all the GPs in the mixture are global and samples are clustered following “trajectories” across input space. We use a non-standard variational Bayesian algorithm to efficiently recover sample labels and learn the hyperparameters. We show how multi-object tracking problems can be disambiguated and also explore the characteristics of the model in traditional regression settings.     

On single-walk parallelization of the job shop problem solving algorithms

New parallel objective function determination methods for the job shop scheduling problem are proposed in this paper, considering makespan and the sum of jobs execution times criteria, however, the methods proposed can be applied also to another popular objective functions such as jobs tardiness or flow time. Parallel Random Access Machine (PRAM) model is applied for the theoretical analysis of algorithm efficiency. The methods need a fine-grained parallelization, therefore the approach proposed is especially devoted to parallel computing systems with fast shared memory (e.g. GPGPU, General-Purpose computing on Graphics Processing Units).     

Efficient GPU-based parallelization of solvation calculation for the blind docking problem

The Journal of Supercomputing - Molecular docking techniques are widely used in computational drug discovery. Most of these techniques simulate the way that a ligand interacts with a protein target...     

On the singular tracking problem

In this paper we continue the analysis of the problem of output tracking in the presence of singularities, whose study was begun by R. Hirschorn and J. Davis. We introduce further structure which is important in quantifying the multiplicity and smoothness of solutions to the problem. The paper is motivated by the analysis of those singular ordinary differential equations whose structure ultimately governs solutions to the singular tracking problem. In the particular case of time-varying linear systems, it is shown how the structure of their solutions in the case of regular and irregular singularities affects solutions to the tracking problem. Less specific results are also obtained in the full nonlinear case. P. E. Crouch and I. Ighneiwa were partially supported by N.S.F. Contract No. ECS 8703615.     

Multi-target tracking with hierarchical data association using main-parts and spatial-temporal feature models

Multimedia Tools and Applications - Multi-target tracking in complex scenes is challenging because target appearance features generate partial or significant variations frequently. In order to...     

SVM在多目标跟踪中的回波分类及并行化研究

在蒙特卡罗联合概率数据关联滤波(MC-JPDAF)算法基础上提出了SVM-MC-JPDAF算法,采用支持向量机(SVM)分类技术,针对跟踪门交叉区域的有效回波进行特别分类。通过仿真实验,算法有效地降低了失跟率以及目标估计值的均方根误差(RMSE),并且对算法实现了并行化,在提高性能的同时控制了算法的执行负担。     

Multiple target tracking using cognitive data association of spatiotemporal prediction and visual similarity

Object tracking is crucial to surveillance systems, which provide target information including position, size, and velocity. This paper presents a data association process combining two primary components of visual features and spatiotemporal prediction. In addition, the change perception and the visual distinguishability are utilized to adaptively combine the two primary components. The proposed spatiotemporal prediction is performed on several consecutive frames in order to cover the irregular motion of targets. The prediction is then filtered with a change perception mask to determine whether the candidate observations have motion or not. In addition, the level of contribution of a visual feature is adjusted by the proposed distinguishability to maintain a reward-penalty balance. The proposed method is applied to various video sequences having small targets and abrupt motions, and the experimental results show consistent tracking performance.     

A novel multiple maneuvering targets tracking algorithm with data association and track management

A novel multiple maneuvering targets tracking algorithm with data association and track management is presented in this paper. First, the variation of the generalized pseudo-Bayesian estimator of first order is designed. Then, the data association and track management via handling two matrices are given, which reflect the relationships between target trajectory and the output of the Gaussian mixture probability hypothesis density (PHD) filter for jump Markov system models (JMS-GM-PHD) filter. The tracking performance of the proposed algorithm is compared with two conventional algorithms. One is JMS-GM-PHD filter, the other is algorithm entitled hybrid algorithms for multi-target tracking using MHT and GM-CPHD which is denoted as hybrid method hereinafter. The results of Monte Carlo simulation show that the proposed filter has overall performance than the conventional.     

An interacting multi-pattern probabilistic data association(IMP-PDA) algorithm for target tracking

A theoretical development of a novel approach for target tracking based on multiple patterns extracted from measurement sequences is presented in this paper. The introduction of patterns leads to a new paradigm for developing high performance algorithms. An interacting multi-pattern probabilistic data association (IMP-PDA) algorithm is developed, taking the advantage of clever formulation of the interacting multiple model approach. The IMP-PDA algorithm employs distance, directional and maneuver information for data association, which enhances significantly the capability of discriminating correct measurements from false measurements     

Joint probabilistic data association for multitarget tracking with possibly unresolved measurements and maneuvers

In a multitarget environment, when tracking crossing targets, a model is needed for the situation where the measurements from two targets are merged into one due to an inherent resolution threshold. A multidimensional model for the merged measurements is proposed and the resulting pdf is presented. This model is applied to augment the Joint Probabilistic Data Association (JPDA) algorithm used for tracking multiple targets in a cluttered environment, so that it can handle, in a more realistic manner, the situation of crossing targets. An extension to maneuvering targets is also presented.     

程序并行化中基于暴露集生成数据分布代码

在并行化编译中,代码生成属于编译器的后端,决定着并行程序的执行效率.数据划分将计算循环中被重定义或没被读引用的数据映射到处理器,按照数据划分生成通信代码会产生冗余通信.提出了利用数组数据流分析求解暴露集,并建立计算划分、循环迭代以及暴露集的不等式限制系统,最后通过FME(fourier Motzkin elimination)消元生成数据分布代码的优化算法.测试结果表明该算法对数据分布的优化效果明显.     

Extending parallelization of the self-organizing map by combining data and network partitioned methods

High-dimensional data is pervasive in many fields such as engineering, geospatial, and medical. It is a constant challenge to build tools that help people in these fields understand the underlying complexities of their data. Many techniques perform dimensionality reduction or other “compression” to show views of data in either two or three dimensions, leaving the data analyst to infer relationships with remaining independent and dependent variables. Contextual self-organizing maps offer a way to represent and interact with all dimensions of a data set simultaneously. However, computational times needed to generate these representations limit their feasibility to realistic industry settings. Batch self-organizing maps provide a data-independent method that allows the training process to be parallelized and therefore sped up, saving time and money involved in processing data prior to analysis. This research parallelizes the batch self-organizing map by combining network partitioning and data partitioning methods with CUDA on the graphical processing unit to achieve significant training time reductions. Reductions in training times of up to twenty-five times were found while using map sizes where other implementations have shown weakness. The reduced training times open up the contextual self-organizing map as viable option for engineering data visualization.