子波变换是目标特征抽取和模式识别的有效方法。
Wavelet transform is a very useful method for image features extraction and pattern recognition.
通过对目标特征的分析比较，选取不变矩作为识别特征。
By the analysis and comparison of target characteristics, invariant moments are chosen as recognition characteristics.
像素标记算法是图像处理中提取目标特征量的一种有效方法。
The pixel labeled algorithm is an effective method to obtain the objects s feature in image processing.
在雷达目标识别研究中，获取有效的雷达目标特征信号非常重要。
In radar target recognition research, it is very important to obtain effective radar target signature signal.
提出一种二值分割图像目标描述的实现方法，用以获取目标特征量。
A practical approach of object description after image segmentation to obtain objects' features is introduced in this paper.
提出了基于目标回波自相关矩阵本征值分解提取多目标特征的新方法。
A method extracting multiple target feature by the eigenvalues decomposition of target echo autocorrelation matrix is presented.
本文重点分析了摄像机镜头径向畸变对立体表面目标特征检测精度的影响；
The effect on inspecting precision of object feature on solid surface caused by camera radial distortion has been analyzed.
相关测量方法与最优搜索方法结合，可以测量表征被测目标特征的物理量。
Combining correlation measurement and optimized searching method, some physical parameters is easy to measure.
提出了一种基于目标特征的航天器间相对位置和相对姿态单目视觉测量方法。
The paper poses a measure method of relative position and attitude between spacecrafts based on monocular computer vision and feature points on the target.
来自多传感器的目标特征往往是高维数的，并且包含了更多的冗余信息和噪声。
The features of target from multi_sensor system are generally high dimensional, redundant and noisy.
常见的目标特征可分为灰度(密度、颜色)特征、纹理特征和几何形状特征等。
Usually, object features include gray-scale (density, colour), feature, geometry shape, and so on.
感兴趣区域定位是提取目标特征，进行目标识别与跟踪等后续处理的重要基础。
Detecting regions of interest(ROIs) is the base step for object's feature extraction, identification and tracking.
提出了对回波信号逆滤波以恢复目标特征及采用匹配滤波来抑制成像旁瓣的方法。
An inverse filter for return signal to restore target signature and a restraining image sidelobe method used matched filter are provided.
本文主要研究了复信号双谱分析方法及其在常规低分辨雷达目标特征分析中的应用。
This paper mainly deals with the bispectrum of complex-valued signals analysis techniques as well as their applications to conventional radar target signature analysis.
特征关联就是从复杂背景中筛选与发现目标特征，揭示目标与背景之间的特征模式。
Feature association rule mining is filtering and finding characteristic patterns between object and background.
在分析研究空中目标特征指标的基础上，提出并建立了基于灰色关联的目标识别模型。
After analyzing the feature indexes of air targets, a target identification model based on grey relation is presented.
提出了一种新目标特征构型下基于单帧图像的航天器间相对位置和相对姿态测量方法。
The paper presents an optical method based-on a new target feature structure and single-image for testing the relative position and attitude between spacecrafts.
针对现有方法目标特征信息考虑不足的缺陷，提出一种基于特征匹配的目标跟踪方法。
The existed methods of object tracking can not use character information sufficiently, so this paper proposes an object tracking method based on character matching.
利用小波空间的多种特征作为目标特征，提高特征空间的维数，增加目标识别的可靠性。
Using the multi-character of the wavelet space as the characters of a target to increase the dimension of the character space of the target and to increase the reliability of identifying the target.
目标的最佳描述区域对于建立目标特征、目标跟踪、目标轮廓求取具有非常重要的意义。
Since the best description of the target is very important to the target feature, the target tracking and the target contour acquisition, a new ellipse description method is proposed.
在跟踪算法上采用了直方图作为目标特征，使用直方图后向投影方法实现对动态目标的跟踪。
The histogram is selected as the object characteristic, and is compared with histogram back-projection for object tracking.
将外力设计成GVF场的形式，可扩大图像的映射范围，使模型更好地向所期望的目标特征拟合。
Designing external force in the form of GVF can expand the scope of mapping to make Snake model towards to expected image features.
融合后的图像不仅较好地保持了可见光图像的线条及边缘特征，还融合了SAR图像的点目标特征。
The fused images show the contribution of the optical image for discriminating lines and edges, while the SAR image provides an information on the detection of point targets.
前者用于评价轮廓分段所描述目标特征的重要性，后者用于评价轮廓分段相对目标整体轮廓的比例。
The former evaluates the importance of the local feature, and the latter evaluates the proportion of contour fragment to the whole contour.
在二值边缘图像中应用双窗口分别选定目标和要去除的噪声，在各窗口中采用双向扫描提取目标特征。
Choose the target and the noise that will be removed in two Windows, then extract target with dual-direction scan in each window.
利用单个特征识别强噪声中的弱小运动目标，常因所提取的目标特征与噪声特征易混淆而导致高的虚警率。
Recognition algorithms for small moving target in strong noise based on single feature has a high false alarm. Sometimes the features of target and noise are very alike.
采用了短时傅里叶变换方法对仿真信号进行了时频分析，得到了能够较好地反映目标特征的微多普勒图像。
Short time Fourier transform was used to analyze the simulated signal in the time-frequency domain, a micro-Doppler image that can demonstrate the target characteristics was generated.
为了满足目标特征点的空间匹配一致性要求，提出了一种基于外极线约束条件新的视频图像判读处理模式。
In order to satisfy the consistency of the feature point spatial matching, a novel algorithm for video interpretation based on constraint of epipolar line is proposed.
利用单个特征识别强噪声中的弱小运动目标，常因所提取的目标特征与噪声特征易混淆而导致高的虚警率。
Recognition algorithms for small moving target in strong noise based on single feature has a high false alarm.
提出了一种基于机器视觉与离散傅里叶变换的目标特征识别方法。利用计算机图像技术采集和处理图像信号；
A identifying image methods based on machine vision and DFT are studied, The images are collected and video signal is processed using computer technology.
应用推荐