目标识别

The dissertation aims at automatic target recognition in images. For that purpose, a variety of algorithms proposed by the dissertation have been used in different stages of image recognition, which deal with image segmentation, boundary feature point extraction, curve feature extraction, object invariant representation and recognition.

本论文的研究目标是实现图象中目标的自动识别，为此，论文围绕图象识别的各阶段，研究了图象分割、轮廓特征点提取、曲线特征提取、物体的不变性表征及识别等。

Based on goal-scenario coupling and conception attribute, this paper presents a structured method of goal description and identification,constructs goal model, describes and identifies goals. Integrated with the goal-driven software architecture modeling method smoothly, the methodimproves the development quality and production efficiency of information system.

摘 要：基于Goal-scenario coupling 理念，提出了一种基于概念属性的结构化目标描述与识别方法，构造了目标模型，对目标进行了描述和识别，该方法可以与目标驱动的软件体系结构建模方法进行平滑集成，提高了信息系统的开发质量和生产效率。

In this way,at the beginning,pretreating the image of pointsman's gesture from the colour vidicon which includes the colour image smoothing and intensifying.Then using the way of edge checking and image segmentation to divide the target image,due to the image is interfered badly by noise,Sobel operator is used.

该方法首先对彩色摄影机采集的交警手势图像进行预处理，包括彩色图像平滑、彩色图像增强；其次利用边缘检测和图像分割方法对目标图像进行分割，由于图像受噪声干扰严重，采用Sobel算子消除噪声；再次将分割得到的目标轮廓进行表示与描述，为图像的识别作好准备；最后结合图像的轮廓特征对图像进行识别，采用了模糊模式识别方法。

The goal of this item is to improve the whole process of recognizing and extracting road layer from raster map, and to make the whole process as a closed feedback system with output measurable, state controllable and recognition subprocess optimally adaptable.

本研究目标为：改进对栅格交通地图道路信息的识别抽取全过程，使之成为一个输出可测、目标可控、识别过程可自适应优化的闭环反馈识别系统。把对不同图层的识别过程作为并联的子过程控制对象，所构建的整体系统实现了其道路网络输出成为可测变量。

The features are stable and discriminable. The invariants are semi-local rather than global, which promotes tolerance to occlusion. The considerable redundancy is possible for the object whose boundary has complex structure, which enhances the reliability of object recognition.

本方法提取特征不变量只需对待识别图像进行处理，不需要进行摄像机标定和目标空间姿态测量，特征不变量具有较好的稳定性和可分辨性，在目标被部分遮掩的情况下，仍然可能获得可靠的识别，另外，边界结构复杂的目标提供了冗余特征，增强了识别的可靠性。

In this paper, the authors apply this technique in target identification in battlefields.

文章摘要：近年来，多传感器信息融合技术已经在许多领域得到了广泛的应用，该技术也可以用于战场目标识别。

This system has the advantages of high operation speed and high discrimination. The cost will be low due to the betterment of missile inertial guidance system.

该系统具有光学系统运算速度快，对畸变目标识别能力高等优点，在导弹原有惯性制导系统上进行改进，成本低。

First of all, the color model is discussed to present the color recognising theory for robot.

本文的主要贡献是建立了一个基于全景视觉的机器人彩色目标识别、跟踪与搬运系统。

The real-time target track processing system is designed which is constructed by the high performance DSP chipset TMS320C6416 as the core digital processor, the huge reprogrammable logic chipset CPLD as the system logic control and the field reprogrammable array FPGA as the image preprocessing chipset to sampled video digital image.

为了解决算法复杂性及满足工程实时性，设计了以高性能的DSP芯片TMS320C6416为核心处理器，结合大规模可编程逻辑器件CPLD进行逻辑控制以及现场可编程门阵列FPGA对采集的视频数字图像做预处理的实时目标识别跟踪处理平台。

The real2time target t rack processing system is designed which is const ruc2 ted by t he high performance DSP chip set TMS320C6416 as the core digital p rocessor , t he huge rep rogrammable logic chip set CPLD as t he system logic cont rol and the field reprogrammable array FPGA as t he image p reprocessing chip set to sampled video digital image.

为了解决算法复杂性及满足工程实时性，设计了以高性能的DSP 芯片TMS320C6416 为核心处理器，结合大规模可编程逻辑器件 CPLD 进行逻辑控制以及现场可编程门阵列FPGA 对采集的视频数字图像做预处理的实时目标识别跟踪处理平台。

We have no common name for a mime of Sophron or Xenarchus and a Socratic Conversation; and we should still be without one even if the imitation in the two instances were in trimeters or elegiacs or some other kind of verse--though it is the way with people to tack on 'poet' to the name of a metre, and talk of elegiac-poets and epic-poets, thinking that they call them poets not by reason of the imitative nature of their work, but indiscriminately by reason of the metre they write in.

索夫农 、森那库斯和苏格拉底式的对话采用的模仿没有一个公共的名称；三音步诗、挽歌体或其他类型的诗的模仿也没有——人们把&诗人&这一名词和格律名称结合到一起，称之为挽歌体诗人或者史诗诗人，他们被称为诗人，似乎只是因为遵守格律写作，而非他们作品的模仿本质。

The relationship between communicative competence and grammar teaching should be that of the ends and the means.

交际能力和语法的关系应该是目标与途径的关系。