智能车辆系统发展及其关键技术概述

介绍智能车辆系统的研究内容，研究与应用现状，智能车辆的使用可以改善道路安全状况，提高道路的利用率，智能车辆的行驶环境是很复杂的，为了得到一个可靠的决策，必须利用道路信息，其他车辆和目标的位置和动态信息和司机的状态信息等多源信息，智能车辆研究涉及的关键技术主要包括传感器技术，机器视角，GPS技术，通讯技术和数据融合技术等，尤其是数据融合技术中的多目标跟踪与匹配以及基于卡尔曼滤波器的状态估计技术等。     

基于雷达和视觉技术的车辆跟踪窗口

针对基于视觉技术的运动检测鲁棒性差、计算量大的缺点,提出一种融合雷达与视觉信息建立车辆跟踪窗口的方法。采用动力学模型描述车辆运动,通过基于雷达量测的扩展卡尔曼滤波(EKF)估计,确定目标初始位置,然后根据灰度信息自适应调整跟踪窗口的中心位置及尺寸,快速而准确地建立起以目标形心为中心且适合目标大小的跟踪窗口,缩小了后续图像处理区域。三维场景仿真实验证明,该融合方法能快速有效地建立起目标的跟踪窗口。     

汽车雷达多目标跟踪的模糊数据关联

介绍了一种量测(新测目标)到目标(已知目标)之间的模糊数据关联方法，将模糊聚类均值方法和决策逻辑方法相结合，利用Mahalanobis距离代替聚类运算中的欧氏距离，使量测与目标预测值之间的相似性度量更准确，应用决策逻辑确定量测与目标预测值的关联关系。仿真表明这种方法简单，在杂波环境下，有较高的跟踪精度，这种方法可以用于道路条件下，基于汽车雷达的多目标的可靠跟踪。     

Feature subset selection based on mahalanobis distance： a statistical rough set method

In order to select effective feature subsets for pattern classification, a novel statistics rough set method is presented based on generalized attribute reduction. Unlike classical reduction approaches, the objects in universe of discourse are signs of training sample sets and values of attributes are taken as statistical parameters. The binary relation and discernibility matrix for the reduction are induced by distance function. Furthermore, based on the monotony of the distance function defined by Mahalanobis distance, the effective feature subsets are obtained as generalized attribute reducts. Experiment result shows that the classification performance can be improved by using the selected feature subsets.     

一种基于模糊量相似度测量的模糊数据关联方法

介绍了一种用于汽车雷达多目标跟踪的模糊数据关联方法，这种基于模糊量相似度测量的方法简单，便于实现，首先将传感器的量测值与目标的估计值模糊化，然后计算两个模糊量之间的相似度，得到相似度矩阵，最后根据相似度的大小确定量测与目标之间的关系，蒙特卡洛仿真验证了这种方法的有效性。     

NEW HAUSDORFF DISTANCE-BASED VEHICLE LOCATION

Objective To realize accurate localization of moving vehicles from single monocular intensity image.Methods The new modified Hansdorff distance(M2HD) was adopted, which used dominant points instead of edge maps as features for measuring similarity between image and model projection. Modified simulated annealing (MSA) algorithm was used to find optimum localization parameters. Results M2HD reduces the computational complexity,and improves the matching precision. Furthermore, MSA can fast find global optimum instead of getting into partial one because of its high parallel and robust performance. Conclusion Experiments confirm that the combination of MSA and M^2 HD can effectively localize the vehicles that are changed both in translation and rotation     

基于扩展卡尔曼滤波的车道融合跟踪

车道检测算法的研究是智能车辆自动导航的首要环节。与目前基于视觉的车道检测与跟踪系统不同,本文提出一种基于扩展卡尔曼滤波的车道融合跟踪方法。该方法利用毫米波雷达探测到前方车辆的距离信息,并采用扩展卡尔曼滤波技术和图像处理技术,建立车道跟踪的动态视觉窗口,提取车道边界,并判断前方车辆相对于车道的位置。该方法大大缩减了处理时间,且增强了系统的鲁棒性。     

THE PARALLEL RECURSIVE AP ADAPTIVE ALGORITHM BASED ON VOLTERRA SERIES

Aiming at the nonlinear system identification problem, a parallel recursive affine projection （AP） adaptive algorithm for the nonlinear system based on Volterra series is presented in this paper. The algorithm identifies in parallel the Volterra kernel of each order, recursively estimate the inverse of the autocorrelation matrix for the Volterra input of each order, and remarkably improve the convergence speed of the identification process compared with the NLMS and conventional AP adaptive algorithm based on Volterra ,series. Simulation results indicate that the proposed method in this paper is efficient.