The unique heat radiation of infrared image is generated from subcomponents . this paper analyses the natural feature of infrared image and the relationship between the shape and orientation with eigen vectors , gives the measure to classify infrared image based on object position to improve ability of compatibility in object recognition , moreover , applies the independent component for sub - region segmentation to construct new infrared image eigen vectors . the image features are processed by a support vector machine , and transform the binary svm to multi - object classifier 文中在传统红外热图像特征量的基础之上，通过分析红外热图像自身特性以及它的形成与其自身姿态的关系，提出了对目标物体红外热图像基于目标姿态的子分类，来提高目标识别中对姿态的容忍度；同时根据红外目标子部件对图像影响的统计独立性，使用独立元的方法对目标红外热图像进行了子区域分割，形成了新的红外图像特征量。
Besides asm , a general approach towards object location using active appearance model ( aam ) is presented . aam measures the current texture residuals and uses the model to predict changes to the current parameters , leading to a better fit . at last , the independent component analysis is used in the building procedure of active shape model 在asm模型的基础上，本文还简要探讨了主动表观模型( aam )的定位方法， aam可以根据当前合成图象同目标图象之间的表面灰度差异逐步调整统计模型参数，使得合成模型更加逼近目标物体。
It is demonstrated by simulations that the control method is efficient and the fully cartesian coordinates is practically efficient . then the inverse kinematics of dual free flying space manipulator are mainly discussed in the third chapter , and the jacobean matrix for dual manipulator space robot is derived by fully cartesian coordinates , a control method for space manipulator based on the resolved motion rate control concept is proposed . then , the computer simulation verifies the effectiveness of the algorithm 首先，分析了闭环双臂空间机器人捕捉目标物体时的运动学关系，给出了以完全笛卡尔坐标表示的系统运动jacobi关系；然后，以此为基础研究了空间机器人双臂协调操作的分解运动速度控制方法和协调操作问题；最后应用matlab语言对平面双臂空间机器人系统进行了计算机模拟、仿真，仿真运算证实了上述方法的有效性。
By the software platform , figuring out the objects and the robotics projection according to the kinematics model and the coordinate transform and t our software platform is to test the validity of the arithmetic according to adjusting the distance between the two vidicons and vidicons ’ poses in the descartes space . , 设计的软件仿真算法验证平台中,通过运动学模型、坐标转换等计算出目标物体、机器人本体的视觉投影,在一定范围内调节目标对象在笛卡儿空间中的位姿,模拟现场工作环境。
Feature graphs , linear forms of skeletons , are introduced to guide the construction of intermediate skeleton . if the topologies of the source object and the target one are different , their feature graphs will be automatically extended with equivalent topologies . then the technique of intrinsic shape parameters is applied to the smooth transition of the extended feature graphs , which will guide the metamorphosis of the skeletons 为了指导骨架的变动顺利完成，引入骨架特征图的概念;当源物体与目标物体拓扑结构不一致时，特征图会根据特征顶点的对应函数(由用户定义)自动扩充为具有相同结构的扩展特征图;然后采用内在量的方法，实现源物体骨架的扩展特征图向与目标物体骨架的扩展特征图的光滑变形，从而转化为骨架的变形。
Single mode optical fiber laser confocal scanning microscopy is a new technology in microstructure studying . the speciality of the system is limiting the out - of - focus light reflected from out - of - focus plane in object to restrict the blur of image . therefore , the plane resolution and axial resolution of the system could be improved to sub - micron grade 单模光纤激光共焦扫描显微成像系统是研究微观结构的一种新技术，其本质是抑制目标物体离焦面所反射的光线进入系统，从而抑制这些离焦光线造成像点弥散斑增大的影响，使系统的横向与轴向分辨率得到大幅度的提高，能实现亚微米级的层析。
The paper recounts implementing thoughts of this system and advances some improved algorithm in pretreating image , for example image enforce , segmentation of image and so on . we get rather satisfying effect by using these algorithms . in initial phase of the system , in order to get the information of field and automobile " s edge , the paper introduces detecting algorithm to confirm end - points of field , improved hough algorithm , and worm - following algorithm to pick up edge . in real - time checking phase , the most importance aim is to identify sign circles , so we advance a qiuck searching algorithm based on threshold 文中详叙了系统的实现思路，对于预处理阶段采用的图像处理技术，如图像增强、图像分割等，提出了一些相应的改进算法，取得了较满意的处理效果；在系统初始化阶段，为了获取场地的端点信息和汽车边缘信息，分别介绍了自动确定场地端点位置的检测算法、改进的hough变换算法和提取区域边缘的“虫随法” ；在系统的实时检测阶段，最主要的目的是识别检测标志圆，为此，文中提出了基于阈值的快速搜索算法，有效的提高了目标物体区域的提取和识别速度。
