基于多源信息融合的潜艇目标识别方法研究

提出一种基于多信息源的潜艇目标识别系统原理模型,介绍了证据理论在潜艇目标识别中的应用方法,给出了针对潜艇装备情况,建立各种识别信息源的方法,初步探讨了该识别系统的实现方法,并给出了有效的决策规则,为解决潜艇目标识别难题提供了一种新的解决方案.     

无人飞机在交通信息采集中的研究进展和展望

以无人飞机多次试飞试验和相关研究成果为基础,分析了无人飞机在交通信息采集、处理与应用中的可能性及主要挑战,从不同角度展望了无人飞机在交通规划与仿真、道路监控、应急调度和城市交通拥堵分析等领域的应用前景。分析结果表明:应用无人飞机可以弥补现有交通信息采集技术的不足,是有效采集连续交通信息的新手段;随着动态交通视频处理技术的发展,从无人飞机采集的视频中可以自动提取交通信息;应用无人飞机采集的交通信息可用于应急调度、车辆跟驰、换道行为与交通拥挤等方面的研究;无人飞机动态交通视频处理技术的适应性还有待提高;利用无人飞机信息的车辆跟驰、换道行为与交通拥挤尚缺乏实证研究;建立无人飞机与地面应急系统的通讯和协调系统及无人飞机-车-路协调通信系统是未来重要的研究方向。     

基于多尺度Kalman滤波的多传感器数据融合

通过分析多尺度动态系统模型,提出了一种基于小波变换的Kalman多传感器数据融合算法。该算法结合了Kalman滤波的实时性、递归性和小波变换的多尺度特性,能对多传感器的观测数据有效地融合。算法首先将最细尺度上观测数据滤波后得到的估计序列小波分解到各尺度上;然后在各尺度上,利用该尺度上的传感器观测数据对小波分解系数进行更新;最后利用小波重构,达到更新原始估计序列的目的。仿真实验表明,该算法具有很好的数据融合效果。     

一种列车完整性监测系统的设计

本文设计了一种风压传感器、GPS定位模块和加速度传感器相结合的列车完整性监测系统,通过采集多源传感器信息,进行决策级信息融合,监测列车完整性状态与GSM-R无线通信技术实现车地双向通信.文中对系统的组成、工作原理及关键技术进行阐述.测试结果表明该系统能够有效监控列车分离,具有较高的应用价值.     

基于融合模型动态权值的短期客流预测方法

针对传统交通系统中短期客流预测精度低的问题,考虑城市交通站点客流数据在横纵向时间序列的规律性,基于卡尔曼滤波算法和K近邻（K-Nearest Neighbor, ANN）算法,分别根据当日数据和历史数据对客流量进行预测,然后利用权重系数方程对两个预测值加以融合,从而构建基于融合模型动态权值的短期客流预测方法。以某城市的某公交站点客流数据为研究对象,对所建融合模型短期客流预测的准确性和适用性加以验证。结果表明,新建模型、单一的卡尔曼滤波模型和KNN模型的平均相对误差分别为3.6%, 9.0%和7.7%,可见新建模型能更好地拟合客流变化趋势且评价效率更高。     

基于组合赋权理论的高速公路多源信息融合算法

智慧高速信息化系统的多元信息采集系统提供了大量的多源异构交通数据.对这些数据进行分类识别与融合分析,并获得精度更高、可靠性能更好的数据尤为迫切.为更好地研究该问题,笔者分析了手机、卫星定位和路侧交调信息采集手段的技术特点,构建多源采集数据的融合环境,利用主、客观赋权法分别对3种采集手段进行赋权.在此基础上,采用Kendall一致性系数判断主、客观赋权法的一致性,并利用Spearman等级相关系数修正主、客观赋权法之间的不一致性,以组合主、客观赋权法的思想构建高速公路区间行程车速融合算法,兼顾主客观信息对权值的影响.通过案例分析,发现融合车速计算误差在土10 km/h内的精度可达96%,保证了多源信息融合后的高速公路区间行程车速的准确性与可靠性.      

引入轨道特征的北斗列车定位方法研究

列车定位是轨道交通众多应用的基础条件,北斗卫星导航用于列车定位能够有效提升我国轨道交通装备的自主性.针对列车北斗定位性能对运行条件的适应性需求,本文提出一种引入轨道特征的北斗列车定位方法,该方法从轨道电子地图中提取轨道特征参数,在列车状态预测的系统模型中增加轨道约束,并利用一维地图位置预测拓展北斗导航卫星的伪距测量.利用现场实测数据构建场景进行仿真.所得结果表明,本文提出的方法能够提高列车定位解算对卫星可视条件的鲁棒性,有效拓展北斗列车定位在恶劣观测条件下的可用水平,具有较高的实际应用价值.     

Probabilistic Tracking of Objects with Adaptive Cue Fusion Mechanism

A tracking method based on adaptive multiple cue fusion mechanism was presented,where particle filter is used to integrate color and edge cues.The fusion mechanism assigns different weights to two cues according to their importance,thus improving the robustness and reliability of the tracking algorithm.Moreover,a multi-part color model is also invoked to deal with the confliction among similar objects.The experimental results on two real image sequences show the tracking algorithm with adaptive fusion mechanism performs well in the presence of complex scenarios such as head rotation,scale change and multiple person occlusions.     

Collection Cost Screening Mechanism in a Closedloop Supply Chain

Recently, the product remanufacturing has been a hot topic in the field of operational management, and more manufacturers are beginning to recover the value in their end-of-life (EOL) products by remanufacturing. This paper focuses on the closed-loop supply chain where the retailer takes charge of not only retail, but also collection. There are two possible types of the retailer's collection cost as an assumption, i.e. high cost or low cost, and the retailer knows his type, whereas the manufacturer only has a prior probability over the two possible cost types. This paper deploys the contracts with which the manufacturer can screen the type of the retailer to improve her profit under incomplete information. As a result, the pooling contract can perfectly coordinate the decentralized system under incomplete information, but the manufacturer obtains the lower profit; nevertheless, with the separating contracts the manufacturer obtains the larger profits though the system profit is lower.     

A Robust Interacting Multisensor State Fusion Based on Adaptive Outlier Controlling Multirate Model

An adaptive outlier controlling multirate model based on Hong’s multirate kinetic model was represented in order to resist the outliers and utilize their useful information. Wavelet transform was introduced to detect and control the outliers. The multirate information extraction and the controlling of outliers were properly integrated to establish an adaptive outlier controlling multirate model. The proposed model was applied to multisensor state fusion with interacting multiple model (IMM), and a robust interacting multisensor state fusion algorithm was established based on adaptive outlier controlling multirate model. The Monte-Carlo simulation shows that it could improve the accuracy of fusion estimation by 70% compared to Hong’s algorithm and at least 14% to Xiao’s algorithm.