The methods of data association and tracking beginning and ending to single and multiple targets tracking in the multi - echo environment is listed . at the end of the thesis , a method is introduced , which is that based on the most closed principle , without the chosen echo , the current forecasting values added yawp based upon the former state values is considered as the target state estimated value . the value is an input of observation equation , the output of the observation equation is considered a chosen echo . and the method is validated in the simulation results 针对多目标跟踪问题,首先对多目标跟踪的原理和跟踪门的形成方法进行了概述,并对多回波环境下单目标跟踪和多目标跟踪的常用的数据关联方法和跟踪起始、跟踪终结方法进行了介绍,在本文的后半部分,对多目标的运动状态进行了仿真研究,提出了一种目标状态估计方法,该种方法的思想是当前时刻如果目标跟踪门内没有所期望的候选回波,首先计算出目标在前一时刻的运动状态下对当前时刻的预测值,并将该值叠加上系统噪声作为量测方程输入值,然后将观测值作为候选回波对目标进行状态估计。
On the foundation of past research , author put forward a single - object tracking and detection algorithm based on background subtraction algorithm and a multi - object cooperative tracking and detection algorithm based on three layers dynamic interaction system , to implement credible unmanned active - scene detection and consecutive , real - time , concerted multiple active object tracking 在前人研究的基础上,引入了基于背景差分算法的单目标入侵检测及跟踪算法和基于三层动态交互体系的多目标协调跟踪算法,真正实现在无人状态下对运动场景进行可靠的监控,对多运动目标进行连续、实时、协调的跟踪。
The new ways that solve multiple objectives decision making under risk into probability permanent type : decision making diagram method , matrix analysis method , multiple objectives markov method , the shortest distance method , successive type variation multiple objectives decision making under risk method and fuzzy analysis decision making method . 3 . the new modes that solve multiple objectives decision making under risk into probability interval type and uncharted type : weighted method and sorting method 4 the new repent average value criterion that handle multiple objectives decision making under risk into probability uncharted type and generalizing the criterions that have been used into one objective decision making under probability into uncharted type to multiple objectives decision making under probability into uncharted type . 5 . giving the error analyses method and decision result regulating method that been used into multiple objectives decision making under risk 2 、探讨了‘决策图法’ 、 ‘矩阵法’ 、 ‘多目标马尔科夫法’ 、 ‘最小距离法’ 、 ‘连续型变量的多目标风险型决策法’和‘模糊分析决策法’等解决概率固定型的多目标风险型决策的新方法。 3 、探讨了‘加权法’ 、 ‘排序法’两种解决概率区间型和未知型的多目标风险型决策的方法； 4 、在概率未知型的多目标风险型决策中改进了‘后悔值准则’ ，提出了‘后悔均值准则’ ；并将单目标概率未知型风险型决策的准则推广运用到多目标概率未知型的风险型决策中去； 5 、探讨了多目标风险型决策方法误差分析及决策结果值调整的方法。
The ga is extended for the optimal design of packing mechanism in this study . some key techniques for solving single object with multi parameters were " investigated . finally the original iterative method of ga was improved , therefore , the convergence to local optimal solution can be avoided but the convergence to global optimal solution can be accelerated 本文将遗传算法推广应用于包装机械的机构优化设计，研究应用遗传算法求解多参数单目标优化的关键技术，并通过采用改进了的遗传算法迭代方案，避免了标准遗传算法在搜索最优解时过早收敛于局部最优解，加快了全局最优解的收敛速度，有效的解决了机械优化设计中求解多参数单目标优化的问题。
In a word , this paper puts forward a multiobjective risky decision model in view of the present incomplete decision indexes and methods in investment with the switch from the mono - objective determinate decision to the multiobjective risky one , which leads to more scientific investment decision 概而言之，本文在评述现行投资决策指标和方法不足的基础上，提出了多目标风险型决策模型，从而把决策分析从单目标确定型转向了多目标风险型，使投资决策朝更科学的方向迈进了一步。
The thesis proposes to solve such kinds of hev propulsion system optimization problems using the evolutionary computation techniques . single objective optimization and multi - objective optimization will be both explored based on the hev propulsion system simulation software advisor by treating the typical performance parameters of the components and the major control strategy parameters as optimization variables together 本文提出用演化计算来求解这类hev的驱动系统优化问题，将各部件典型的性能参数和主要的控制策略参数同时作为优化变量基于hev驱动仿真软件advisor进行单目标优化和多目标优化。
In part two of this dissertation , a general interaction programming of interactive system which has m subsystems is introduced according to the productions and resources distribution model ( prdm ) . also , we define three kinds of solutions of it . after transforming the ipp into a single - level and single - object optimum problem , the relation between their solutions > s discussed 第三章针对资源?产品分配模型( prdm )给出了数学模型? ?一个有多个子系统的一般交又规划模型，提出了较为合理的几种解的定义，并利用加权的方法将交叉规划转化为一单层单目标问题，然后讨论了他们的解之间的关系
The experiments show that this method has great performance of single target tracking in sequence images on the sea . considering the correlation between the frames of sequence , we research the tracking methods which take advantage of both the intra - frame and inter - frame information , including predicting tracking machine based on kalman filtering algorithm and matching tracking machine based on mean - shift algorithm 实验表明,该方法对海上单目标跟踪具有很好的稳定性;然后,针对序列图象具有帧间相关性的特点,研究了基于帧内? ?帧间信息的自动跟踪方法,即同时利用帧内信息和帧间相关性信息,设计了基于kalman滤波的预测跟踪器和基于mean - shift算法的匹配跟踪器。
Then a model was established for solving the problem of hybrid power unit matching by connecting optimization design with vehicle simulation , and the problem of power matching of hybrid power unit was solved with evolutionary algorithm according to single - object optimization and multi - object optimization separately 然后，将优化设计与汽车仿真结合，建立了混合动力系统优化匹配问题的求解模型，并利用遗传算法对混合动力系统的功率匹配问题进行了单目标和多目标优化求解。
