基于相似性测度的异类传感器的数据融合算法

雷达具有较好的测距性能,红外传感器具有高精度的测角性能。雷达和红外传感器是异类传感器系统的一个典型组合,但是异类传感器信息融合因没有现成的数学工具和方法而面临诸多困难。提出一种基于相似性测度的数据融合方法,能够有效提高数据正确关联概率和多目标跟踪的精度。     

综合利用各类信息的红外/雷达数据关联

异类传感器数据关联是数据融合中的一个难点,综合利用角度和其他特征信息是改善异类传感器数据关联的一个重要途径.对于雷达在直角坐标系对目标进行跟踪、红外传感器在修正的球坐标系对目标进行跟踪情况,文章综合利用角度、角度变化率和ITG(Inverse-Time-to-Go)信息,构建了新的关联统计量,并进行了计算机仿真.结果表明,所给出的新关联统计量较之只利用角度或角度变化率的关联统计量有更好的关联性能.     

一种新的异类传感器信息融合算法

针对典型的雷达和红外异类传感器信息融合系统,提出了一种新的雷达和红外信息融合算法。对雷达和红外传感数据进行了预处理,分别滤波得到各自的局部航迹,基于线性最小均方误差准则（Linear Minimum Mean Square Error,LMMSE）对局部航迹进行融合以得到最终航迹。仿真结果表明：该算法可以对雷达和红外传感器进行有效融合并大幅提高航迹跟踪精度。     

雷达与红外传感器数据关联及融合算法研究

多传感器信息融合技术在目标跟踪领域已经得到了广泛的应用,末制导融合技术是多传感器跟踪系统中的关键技术之一,而主动雷达、红外传感器的数据融合问题是研究的热点。由于主动雷达发射电磁波容易暴露,红外传感器隐蔽性好,但只能测角,不能测距,采用主动雷达为主、红外探测为辅的数据融合系统进行目标跟踪有利于充分地发挥红外、雷达2种传感器的互补性,使其相得益彰。基于卡尔曼滤波的预测、修正的思想,提出了一种新的融合算法,仿真结果和实验表明:利用此方法可使雷达、红外传感器达到较好的数据融合效果。     

基于红外相机和毫米波雷达融合的夜间行人检测

为了提升夜间环境行人检测的能力,使用红外相机和毫米波雷达进行信息融合.对两传感器数据进行时间配准并分别进行处理,利用改进YOLO算法处理红外图像得到目标类别特征,处理毫米波雷达数据获得目标的距离和速度特征,再建立空间对准模型对两传感器进行目标匹配,最后利用基于特征的融合算法完成夜间行人多模态信息输出.两传感器检测目标首次匹配之后,可以将类别信息反馈给雷达数据处理单元进行记录,当红外图像检测算法漏检时,利用雷达记录的信息补充输出类别特征.通过实验证明该融合算法提升了单一传感器行人检测成功率,在夜间场景具有良好的应用效果.     

异类传感器集中式扩维融合无迹卡尔曼滤波融合算法

雷达和红外传感器是异类传感器系统的一个典型组合,但是异类传感器系统的状态方程和测量方程存在较大的非线性特征,使得此类系统无法应用现有算法进行信息融合。将UKF引入到异类传感器,并利用集中式观测融合UKF,解决同步配置、同步采样的异类传感器的信息融合问题。仿真结果表明,该算法的SMSE比其他方法的要小得多。     

多传感器多目标跟踪及航迹融合系统

多传感器数据融合能够实现信息互补以提高目标跟踪精度、识别能力以及增强系统的抗干扰性,因此受到广泛关注。本文主要针对雷达和红外跟踪及航迹融合的体系结构,对目标跟踪、航迹关联和航迹融合的各个算法进行详细描述及仿真。仿真结果表明,基于雷达和红外传感器数据融合跟踪相对于单传感器的跟踪,性能有所提高。      

异类传感器时间配准技术研究

在多传感器信息融合系统中，异类传感器之间由于异步采样及传输延迟，数据之间存在时间不匹配的问题。时间配准是把关于同一个目标的各传感器的不同步测量信息同步到某一时刻，是信息融合前的数据预处理步骤之一。如果不经过时间配准这一步骤，那么信息融合会产生较大误差，甚至无法有效进行，因此，时间配准是多传感器信息融合中不可或缺的部分。针对异步采样这一时间配准的问题来源，通过Matlab验证了最小二乘法和内插外推法两种经典算法的有效性，并将卡尔曼（Kalman）滤波引入时间配准，将插值法与卡尔曼滤波相结合，提出了一种改进的时间配准算法，提高了信息融合的精度。     

基于新型AFCM的多传感器目标跟踪航迹融合

多目标跟踪是多传感器系统信息融合中的核心技术之一.采用新型的AFCM模糊算法实现对多目标交叉状态下航迹数据关联.该算法定义了一种新的度量空间中的距离,通过新的距离定义有效抑制含有噪声点的样本及目标航迹交叉在迭代中对数据关联聚类中心点的大幅偏差.同时应用改进带加权的航迹融合算法对红外和毫米波雷达传感器测量的航迹数据进行融合.仿真试验证明,新的算法在综合多传感器探测优势的基础上,对航迹的融合结果优于SF算法.新的数据关联算法和改进的加权航迹融合算法为多源信息融合提供了一种可靠有效的多目标跟踪技术.     

基于改进加权航迹关联的异步融合算法与仿真

在分布式多传感器信息融合系统中,来自各传感器的局部航迹往往是不同步的。针对分布式多传感器异步航迹关联与融合问题,文中提出一种基于改进加权航迹关联的异步航迹顺序融合算法。把多传感器异步航迹外推校准到同一时刻,实现异步航迹的同步化,再用改进的加权航迹关联算法进行航迹关联,并利用顺序融合算法对已关联航迹进行融合。仿真结果表明了该算法的有效性。     

Data fusion based coverage optimization in heterogeneous sensor networks: A survey

Sensor networks, as a promising network paradigm, have been widely applied in a great deal of critical real-world applications. A key challenge in sensor networks is how to improve and optimize coverage quality which is a fundamental metric to characterize how well a point or a region or a barrier can be sensed by the geographically deployed heterogeneous sensors. Because of the resource-limited, battery-powered and type-diverse features of the sensors, maintaining and optimizing coverage quality includes a significant amount of challenges in heterogeneous sensor networks. Many researchers from both academic and industrial communities have performed numerous significant works on coverage optimization problem in the past decades. Some of them also have surveyed the current models, theories and solutions on the problem of coverage optimization. However, most of the existing surveys and analytical studies ignore how to exploit data fusion and cooperation of the deployed sensors to enhance coverage performance. In this paper, we provide an insightful and comprehensive summarization and classification on the data fusion based coverage optimization problem and techniques. Aiming at overcoming the shortcomings existed in current solutions, we also discuss the future issues and challenges in this area and sketch a general research framework in the context of reinforcement learning.     

Combining Intelligent Techniques for Sensor Fusion

Mobile robots rely on sensor data to build a representation of their environment. However, sensors usually provide incomplete, inconsistent or inaccurate information. Sensor fusion has been successfully employed to enhance the accuracy of sensor measures. This work proposes and investigates the use of Artificial Intelligence techniques for sensor fusion. Its main goal is to improve the accuracy and reliability of the distance measure between a robot and an object in its work environment, based on measures obtained from different sensors. Several Machine Learning algorithms are investigated to fuse the sensors data. The best model generated by each algorithm is called estimator. It is shown that the employment of estimators based on Artificial Intelligence can improve significantly the performance achieved by each sensor alone. The Machine Learning algorithms employed have different characteristics, causing the estimators to have different behaviors in different situations. Aiming to achieve an even more accurate and reliable behavior, the estimators are combined in committees. The results obtained suggest that this combination can further improve the reliability and accuracy of the distances measured by the individual sensors and estimators used for sensor fusion.     

A new multiple decisions fusion rule for targets detection in multiple sensors distributed detection systems with data fusion

Currently, multiple sensors distributed detection systems with data fusion are used extensively in both civilian and military applications. The optimality of most detection fusion rules implemented in these systems relies on the knowledge of probability distributions for all distributed sensors. The overall detection performance of the central processor is often worse than expected due to instabilities of the sensors probability density functions. This paper proposes a new multiple decisions fusion rule for targets detection in distributed multiple sensor systems with data fusion. Unlike the published studies, in which the overall decision is based on single binary decision from each individual sensor and requires the knowledge of the sensors probability distributions, the proposed fusion method derives the overall decision based on multiple decisions from each individual sensor assuming that the probability distributions are not known. Therefore, the proposed fusion rule is insensitive to instabilities of the sensors probability distributions. The proposed multiple decisions fusion rule is derived and its overall performance is evaluated. Comparisons with the performance of single sensor, optimum hard detection, optimum centralized detection, and a multiple thresholds decision fusion, are also provided. The results show that the proposed multiple decisions fusion rule has higher performance than the optimum hard detection and the multiple thresholds detection systems. Thus it reduces the loss in performance between the optimum centralized detection and the optimum hard detection systems. Extension of the proposed method to the case of target detection when some probability density functions are known and applications to binary communication systems are also addressed.     

基于环境监测的两级数据融合模型与算法

利用多源传感器采集的数据不仅存在大量冗余,而且会影响最终监测结果.为了提高监测的准确度,本文提出一种面向草原环境监测的两级数据融合模型.在一级数据融合中,首先采用自适应加权平均法对各区域内的同类传感器进行融合,然后利用BP神经网络对该区域内的异类传感器进行训练和融合,从而得到对各区域环境状况的初步判断.由于经BP神经网络融合的结果具有不确定性,因此,二级融合利用D-S证据理论对一级融合结果进行综合分析,从而得到对草原环境的决策判断.最后对模型及算法进行了有效性验证与分析,实验结果表明本文的方法能够较准确地监测草原环境状况,同时对草原环境的高效管理和科学养护等提供一些有价值的指导和决策依据.     

Estimation fusion with radar and ADS-B for air traffic surveillance

The surveillance sensor that has been mainly used for target tracking in air traffic control (ATC) environment is radar. The automatic dependent surveillance — broadcasting (ADS-B), which is based on the technologies of global navigation satellite systems, is recently participating in ATC systems. Although ADS-B provides more accurate measurements than does radar, it needs careful considerations for the application of the ATC systems. This is due to the fact that the reliability of ADS-B measurements is dependent upon each aircraft whereas that of radar is not. This study proposes a system for the estimation fusion of multiple heterogeneous sensors, which includes radar and ADS-B, whose measurements and sensor characteristics are different from one another. A centralized fusion architecture based on three-dimensional earth-centered earth-fixed (ECEF) common coordinate system is adopted to process the data received asynchronously from multiple heterogeneous sensors. In case of the ADS-B, the validity of the sensor data for each aircraft is checked using not only the accuracy and integrity information of the aircraft, but also a comparison of the ADS-B data with the radar data. This study also proposes variable-sized measurement vectors and matrices for the tracking filter in order to dynamically reflect the availability of the additional measurements from the downlinked aircraft parameters (DAP) which can be obtained from mode-S radar and ADS-B. The simulation results indicate that the proposed fusion system can improve the tracking performance with the advantages of different types of surveillance sensors.     

异类传感器实时信息融合的STMHM算法

异类传感器实时信息融合由于两类设备的数据率不同和数据误差的限制,一直未得到有效解决,提出一种空时二维多假设模型(STMHM)算法来解决该问题。设计的融合数据模型,将异类传感器的测量数据映射在二维直角坐标系下;按照新的融合数据模型分别构建两类传感器的目标量测空间和融合空间;设计量测空间时间初始化方法和目标实体空间的滤波算法;通过仿真验证表明:该算法能够实现异类传感器的信息融合,初次融合成功的确认时间在3～5个主动传感器扫描周期。     

一种结构模式可变的组合导航算法研究

根据毫米波/红外双导引头数据融合装置在工程应用中对性能指标的特殊要求,提出了一种新的组合导航算法。该算法根据各传感器的工作状态,自适应改变跟踪算法的结构模式,从而有效缩短目标截获时间、增长截获距离、提高跟踪精度。通过计算机仿真,验证了该算法的可行性。该算法也可以推广到其他异类传感器构成的组合导航系统中去。