基于矩不变理论的车型识别技术研究

车型识别是智能交通系统中的一个关键技术。采用二值数学形态学对目标图像腐蚀、区域填充，得到仅含“0”、“1”的二值车型图像，其中“1”即亮点对应全部车体，而背景为暗点“0”，然后提取车体内部图像七个不变矩的特征值，使用欧氏距离法进行车型的特征匹配。通过实验证明，该方法优于其它的常用算法。     

Experimental verification of robustness in a semi-autonomous heavy vehicle platoon

Novel numerical methods for analyzing robust peak-to-peak performance of heterogeneous vehicle platoons are presented. The goal is to compute worst-case spacing error peaks in terms of platoon heterogeneity, communication delays, disturbances and uncertainties in the vehicle dynamics. First, a convex set of parametric linear vehicle models is employed to analyze the effect of platoon heterogeneity. Then, a data-driven uncertainty modeling algorithm is developed that computes the least conservative spacing error bound for a given disturbance model class. The methods are demonstrated on three platoon controllers. One of them is a new constant spacing controller receiving control information from both the platoon leader and the immediate preceding vehicle.     

Vehicle positioning in cell manufacturing systems via robust optimization

Numerous manufacturing companies are taking advantage of material handling systems due to their flexibility, reliability, safety and contribution to the increase of productivity. However, several uncertain parameters such as types of cost, availability of vehicle etc., influence the performance of the material handling system greatly. In recent years, robust optimization has proven to be an effective methodology permitting overcoming uncertainty in optimization models. Robust optimization models work well even when probabilistic knowledge of the phenomenon is incomplete. This paper thus proposes two new zero-one programming (ZOP) models for vehicle positioning in multi-cell automated manufacturing system. Uncertain parameters in these models include cost parameters, travel time between each pair of centers of cells and location of machines, average time required for performing all transports from location of machines and availability of the vehicle. Then, the robust counterpart of the proposed ZOP models is presented by using the recent extensions in robust optimization theory. Eventually, to verify the robustness of the solutions obtained by the novel robust optimization model, they are compared to those generated by the deterministic ZOP model for different test problems.     

基于字符纹理特征的快速定位算法

针对现代(智能)交通中的车牌自动识别系统给出了一种快速的车牌定位算法。该算法结合有效的图像预处理增强方法,通过对车牌一维字符特征搜索,能够快速地定位车牌。大量实验结果证明本算法定位速度快(<50ms, PII300),准确率较高(>95%)。     

基于无人机高光谱数据的玉米叶面积指数估算

无人机高光谱遥感是低成本、高精度获取精细尺度农作物生物物理参数和生物化学参数的新型手段，以此快速反演叶面积指数（Leaf Area Index, LAI）对作物长势评价、产量预测具有重要意义。以山东禹城市玉米为研究对象，利用PROSAIL辐射传输模型模拟玉米冠层反射率获取LAI特征响应波段结合相关性定量分析获取对LAI变化最为敏感的波段，并以此计算6种植被指数（Vegetation Index,VI），利用6种回归模型分别对单一特征波段和VI进行反演建模，以实测LAI评定模型精度。研究表明，光谱反射率中516、636、702、760和867 nm等波段对LAI变化最为敏感，以此建立的单一特征波段反演模型预测LAI精度R2为0.44~0.58；RMSE为0.16~0.18，其中636 nm建立的模型(LAI=21.86exp(-29.47R₆₃₆))相比其他反演模型预测精度较高（R2=0.58，RMSE=0.16）；6种植被指数与LAI高度相关，相关性系数R ²为0.85~0.86，以此建立的反演模型相比单一特征波段反演模型精度有所提高，R2为0.66~0.72，RMSE为0.12~0.14；其中mNDVI构建的LAI估算模型（LAI=exp(2.76~1.77/mNDVI))精度最高（R2=0.72，RMSE=0.13）。无人机高光谱遥感是快速、无损监测农作物生长信息的有效手段，为指导精细化尺度作物管理提供依据。     

坦克动力机械传动系统稳态随机扭转振动研究

论述了坦克动力传动系统扭转振动的性质;建立了稳态随机扭转振动时激励的统计特性、系统的频率响应函数、响应的统计特性三者之间的关系;编制了计算程序;通过计算与试验,得到了某中型坦克动力传动系统扭转振动的统计特性。     

磁县浮实验列车模型的解耦控制系统

本文主要讨论磁悬浮实验列车模型的解耦控制问题.在分析列车动力学模型的基础上, 利用信号变换技巧,实现了系统的解耦,对解耦系统根据性能要求配置了闭环系统的极点,通 过状态反馈给出了反馈阵F,应用Pearson动态补偿器理论设计了补偿器,研究了磁悬浮控 制系统的具体实现问题.     

车辆号牌识别中车辆速度的估计

光照不足导致了运动物体图像出现运动模糊。为提高图像质量,对多种算法方案进行了分 析,提出了一种稳健实用计算量少的新方法。在车辆号牌识别的实际例子里利用图像中运动物体的特征点估算出运动物体的运动速度从而对图像进行修正处理,成功地得到满意的图像。     

商务用车车身有限元建模及分析

以某一商务用车为例,利用MSC.Nastran分析软件对其白车身进行有限元建模计算,并对计算结果给出了合理的评价。验证新设计出的各零部件能否满足各种恶劣工况的使用要求,找到车身薄弱环节,为产品定型或设计改进提供依据。