Local-Diffusion-based Distributed SMC-PHD Filtering Using Sensors with Limited Sensing Range Tiancheng Li ; Víctor Elvira ; Hongqi Fan ; Juan M. Corchado IEEE Sensors Journal Abstract: We investigate the problem of distributed multitarget tracking by using a set of spatially dispersed, 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 scheme, 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. T. Li, V. Elvira, H. Fan and J. M. Corchado, Local-Diffusion-Based Distributed SMC-PHD Filtering Using Sensors With Limited Sensing Range, in IEEE Sensors Journal , vol. 19, no. 4, pp. 1580-1589, 15 Feb.15, 2019. doi: 10.1109/JSEN.2018.2882084 @ARTICLE{Li2019local, author={T. Li and V. Elvira and H. Fan and J. M. Corchado}, journal={IEEE Sensors Journal}, title={Local-Diffusion-Based Distributed \\cal{SMC-PHD} Filtering Using Sensors With Limited Sensing Range}, year={2019}, volume={19}, number={4}, pages={1580-1589}, doi={10.1109/JSEN.2018.2882084}, ISSN={1530-437X}, month={Feb.},}
( 复杂 ) 网络涉及到一个基础的信息分享问题，即网络节点之间通过信息分享与融合，最终达成“一致” /Consensus ，及网络一致性。特别是相比于基于含有一个网络中间节点的中心式 /Centralized 网络，分布式网络中只通过节点与节点连接（相互称为邻居节点）进行通信，而没有中心节点，所以网络结构更为稳定（不会因为某一节点的破坏等而造成网络瘫痪），易于扩展（网络节点的性质一致，所以任何节点都可以再增加邻居节点）等，也实际上是很多物理网络（如监控传感网、社交网络等）的本质特征。 然而，在多目标跟踪多传感器信息融合里面却存在一个有趣的发现：传感器邻居节点相互之间分享的信息并不一定越多对于大家越有利，这里的“利”特指提高传感器节点估计的精度。这一点初感违背我们的直觉，因为一般的来讲：信息越多（应该）越有利。 那么为什么呐？ 物理传感器往往都遭受两类问题：一类是漏检，一类是虚警。前者是传感器没能获得目标的观测数据所造成，即 missingdata 问题。而后者是传感器遭遇干扰，获得观测数据不属于任何目标，是假信号，即 falsedata 问题。如此情况下，信息的分享就不见得越多越好，因为有些信号可能是 falsedata 相关，其对于邻居节点没有益处，反而可能造成误导。 这一现象可称之为： Many Could Be Better Than All ，或者 Less-is-More 。实际这一现象并不罕见，如在认知科学/cognitive science （Gigerenzer, G., Brighton, H., 2009. Homo heuristicus: Why biased minds make better inferences. Topics in Cognitive Science, 1(1):107–143.） 和神经网络/neural networks（ Zhi-Hua Zhou, Jianxin Wu, Wei Tang, Ensembling neural networks: Many could be better than all, In Artificial Intelligence, Vol. 137, Issues 1–2, 2002, Pages 239-263。 ） 因此适当的控制信息分享量（更宽泛的是，只分享有利的信息，而尽量减少误导性或者干扰性的信息），不但显然有利于降低通讯开支（这一点在现实中往往很重要，甚至是网络的重要限制。特别是分布式传感器网络往往都是 low-powered/ 低耗的传感器构成，以减少通讯和造价开支等） , 反而还可能更利于获得更高估计精度。 如下两篇论文分别基于高斯混合 /Gaussian Mixtures 和 序贯蒙特卡洛 /Sequential Monte Carlo( 也称粒子滤波 ) 实现 PHD 滤波进行多目标探测估计揭示这一发现，提出了“部分一致性” Partial Consensus 的概念。同时在随机集 PHD 一致性信息融合方式上给出了一些探索性思考，特别明确和比较了（简单却被忽视的）算术平均 ArithmeticAverage 和（当前主流）几何平均 GeometricAverage 的区别和相比优势，提出了实时一致性 RealTime Consensus （即网络通信在理论上不对滤波器造成延迟，两者在一定程度上可以实现并行进行）的概念。 T. Li, J.M. Corchado and S. Sun, Partial Consensus and Conservative Fusion of Gaussian Mixtures for Distributed PHD Fusion, IEEE Trans. Aeros. Electr. Syst., 2018, DOI: 10.1109/TAES.2018.2882960. 连接：https://ieeexplore.ieee.org/document/8543158 Partial Consensus and Conservative Fusion of Gaussian Mixtures for Distributed PHD Fusion Tiancheng Li , Juan M Corchado , Shudong Sun Link : arXiv:1711.10783 We propose a novel consensus notion, called partialconsensus, for distributed GM-PHD (Gaussian mixture probabilityhypothesis density) fusion based on a peer-to-peer (P2P) sensor network, inwhich only highly-weighted posterior Gaussian components (GCs) are disseminatedin the P2P communication for fusion while the insignificant GCs are notinvolved. The partial consensus does not only enjoy high efficiency in both network communication and local fusion computation but also significantly reduces the effect of potential false data (clutter) to the filter, leading to increased signal-to-noise ratio at local sensors. Two conservative mixture reduction schemes are advocated for fusing the shared GCs in a fully distributed manner. One is given by pairwise averaging GCs between sensorsbased on Hungarian assignment and the other is merging close GCs based a new GMmerging scheme. The proposed approaches have a close connection to theconservative fusion approaches known as covariance union and arithmetic meandensity. In parallel, average consensus is sought on the cardinalitydistribution (namely the GM weight sum) among sensors. Simulations for tracking either a single target or multiple targets that simultaneously appear are presented based on a sensor network where each sensor operates a GM-PHD filter, in order to compare our approaches with the benchmark generalized covariance intersection approach. The results demonstrate that the partial, arithmeticaverage, consensus outperforms the complete, geometric average, consensus. 上文正式发表在 : IEEE Transactions on Aerospace and Electronic Systems DOI: 10.1109/TAES.2018.2882960 Distributed SMC-PHD Fusion for Partial, Arithmetic Average Consensus Tiancheng Li Link : arXiv:1712.06128 We propose an average consensus approach for distributed SMC-PHD(sequential Monte Carlo-probability hypothesis density) fusion, in which local filters extract Gaussian mixtures (GMs) from their respective particle posteriors, share them (iteratively) with their neighbors and finally use the disseminated GM to update the particle weight. There are two distinguishable features of our approach compared to existing approaches. First, a computationally efficient particles-to-GM (P2GM) conversion scheme is developed based on the unique structure of the SMC-PHD updater in which the particle weight can be exactly decomposed with regard to the measurements and misdetection. Only significant components of higher weight are utilized for parameterization. The consensus, conditioned on partial information dissemination over the network, is called partial consensus.Second, importance sampling (IS) is employed to re-weight the local particles for integrating the received GM information, while the states of the particles remain unchanged. By this, the local prior PHD and likelihood calculation can be carried out in parallel to the dissemination \\ fusion procedure. To assess the effectiveness of the proposed P2GM parameterization approach and IS approach, two relevant yet new distributed SMC-PHD fusion protocols are introduced for comparison. One uses the same P2GM conversion and GMdissemination schemes as our approach but local particles are regenerated from the disseminated GMs at each filtering iteration - in place of the IS approach. This performs similar to our IS approach (as expected) but prevents any parallelization as addressed above. The other is disseminating the particles between neighbors - in place of the P2GM conversion. This avoids parameterization but is communicatively costly. The state-of-the-art exponential mixture density approach is also realized for comparison.
标签: 分布式网络
