多光谱图像

多光谱图像数据压缩技术的发展与现状

Developments and Recent Trends in the Compression of Multispectral Imagery

基于红外多光谱图像相关性的自动目标识别算法

An automatic target recognition algorithm based on correlation of infrared multispectral imagery

SAR图像与多光谱图像融合方法研究

The Research on the Method of Fusion for SAR and Multi-spectrum Images

基于运动估计和ROI编码的干涉多光谱图像压缩

An Algorithm for Multi-spectral Image Compression Based on Motion Estimation and ROI

多光谱图像的增强是其识别和判读的重要技术基础，传统的Pal算法运算量大，不便操作。

Multi-spectrum image enhancement is the important technical basis of identification and interpretation .

基于改进的FCM和KPCA的多光谱图像特征提取方法

Feature Extraction for Multispectral Images Based on Improved FCM and KPCA

本文将二维离散余弦变换（DCT）应用于多光谱图像与全色光学图像融合问题的研究中。

This paper applies 2-D DCT to the remote sensing image fusion between panchromatic and multi-spectral images .

将DCT应用于遥感图像中全色光学图像和多光谱图像的融合上。

Applies DCT to the remote sensing image fusion between the panchromatic image and the multi spectral image .

CCD图像传感器是相机中最重要的部件之一。本论文主要针对多光谱图像传感器数据与全色图像传感器数据进行双源融合。

A key part in the camera is its CCD sensor . This paper focuses on image fusion between multi-spectral images and panchromatic images .

本文提出了两种基于Vega平台红外多光谱图像仿真方法，均能得到不同季节、天气、时间等不同成像条件下的红外多光谱图像。

This thesis presented two infrared multispectral image simulation methods based on Vega platform .

对TM多光谱图像和SPOT高分辨率图像进行融合实验，并从主观和客观两方面对融合结果进行了比较分析。

The experiments on TM multi-spectral image and SPOT high-resolution image were carried out , and the fusion results were analyzed from both subjective and objective perspectives .

文中首先讨论了多光谱图像分类前需要进行的图像几何配准和大气辐射校正等预处理方法，然后根据kmeans算法的数理模型，重点讨论了分类的技术过程。

The preprocessing method of geometrical image match and atmospherical image correction for multispectral image classification was briefly introduced , with the emphasis on image classification based on the mathematical and physical model of K-means .

图像融合技术是当前的研究热点，本文的工作对于多光谱图像的配准和融合方法，基于DSP平台的图像处理系统及软件优化等方面的研究，具有一定的参考价值。

The work of this paper is valuable to the research field of multispectral image registration and fusion , the image processing system based on DSP and its software optimization .

实验结果表明，该图像融合方法在保留TM多光谱图像光谱分辨率的同时，通过融合SPOT全色图像提高了空间分辨率，丰富了图像细节信息。

Experiment results show that image details are enriched while spectral solution of TM image is reserved by fusing TM image with SPOT image with the image fusion method .

在对提升机制小波变换的原理和特点研究的基础上，结合SAR图像与多光谱图像不同成像特性，提出了一种基于提升小波变换区域融合的SAR与多光谱图像融合方法。

The paper presents a region-fused image fusion algorithm , according to the different imagery characteristic between the SAR and multi-spectral images based on studying the lifting scheme wavelet transform .

提出了基于特征标度核Fisher判别分析和特征提取的多光谱图像分类方法。

We propose a classification method for hyperspectral images based on feature scaling for kernel fisher discriminant analysis ( FS-KFDA ) and feature extraction .

研究了高维多光谱图像分类中SVM的分类性能与训练样本数目和数据维数之间的关系。

So the classification accuracy of SVM is better than traditional ones . The relationship between the classification performance of SVM and training set , data dimension is studied .

在分辨率为10m和20m的多光谱图像上，无法辨别出长城。

The Great Wall can ′ t be seen in SPOT-5 multi-spectral image with spacial resolution of 10m and 20m .

该算法采用NMF算法对多光谱图像进行预处理，以获得较高的图像质量。

The algorithm uses the NMF algorithm for multi-spectral image pre-processing to obtain high image quality .

在分析多光谱图像小波变换后系数特点的基础上，提出了一种基于整数小波变换的3维集合分裂嵌入块编码（3DSPECK）压缩方法。

3D SPECK compression of multispectral remote sensing image is presented , which is based on integer wavelet transform ( IWT ) by analyzing the characteristics of transformed wavelet coefficient .

为有效存储MODIS多光谱图像数据，该文提出一种基于谱间预测和整数小波变换的多光谱图像压缩算法。

In order to store MODIS multispectral images effectively , a new hybrid compression algorithm based on optimal inter-band prediction and integer wavelet transform is proposed .

本文提出的基于Vega与ANSYS的红外多光谱图像仿真采用三维热导方程，使得红外仿真结果更加逼近真实情况。

The proposed approach applied a three-dimensional heat conduction function based on Vega and ANSYS infrared multispectral imagery simulation , and produced a superior infrared simulation result in terms of simulation accuracy .

针对多光谱图像配准问题，利用了基于边缘特征的的相关匹配算法，设计了由可编程逻辑门阵列FPGA和多处理器DSP板构建的通用性高速实时信号处理硬件体系结构。

Aiming at the question of multispectral image matching , correlation matching algorithm based on edge character is adopted and a general-purpose high speed real time signal processing hardware architecture using FPGA and multi-DSP as its key processors is designed .

基于Karhunen-Loeve和小波变换的多光谱图像三维集合嵌入块编码压缩算法

Compression of Multispectral Image Using Three-Dimensional Embedded Block Coding Algorithm Based on Karhunen-Loeve and Wavelet Transforms

高光谱遥感（HyperspectralRemoteSensing）与多光谱图像相比的突出特点是谱分辨力的提高，这对于利用遥感图像进行目标分类、识别与跟踪等都具有重要的研究价值和应用意义。

The outstanding characteristic of compared hyperspectral remote sensing image with multispectral image is the improvement of the resolving power . This for utilize remote sensing image carry on goal classify , discern and with importance value of research of following etc.

文章根据多光谱图像数据维数高的特点，以像素各个波段的灰度值为特征，采用支持向量机（SVM）方法为核心来分割多光谱显微细胞图像。

According to the high-dimension data of multi-spectral microscope cell image , an image segmentation method based on Support Vector Machines ( SVM ) is presented , which uses gray values of the pixel 's bands as features .

由于采用了QPSO算法，使最后变换后的图像与多光谱图像和全色图像都有很强的相关性。

Because of the use of QPSO , the fused image is more relative with the multi-spectral and panchromatic imagery .

接着论述了红外多光谱图像仿真中几个重要环节实现过程，主要利用Vega平台进行红外多光谱图像仿真，这是一种便捷手段。

Several core steps in the implementation process of infrared imagery simulation were also discussed . Due to its conveniences , Vega platform was mainly utilized for infrared multispectral imagery simulation .

对多光谱图像进行IHS变换，利用变换后得到的强度分量和高分辨图像具有较强的相关性，在小波变换域进行图像融合。

The high correlation between high resolution image and spectral intensity component by means of the IHS transform , makes it easy to perform images fusion in wavelet transform domain .

文章提出一种基于KarhunenLoeve变换（KLT）和小波量化编码的多光谱图像压缩方法。

An approach for compression of multi-spectral images is proposed based on Karhunen-Loeve transform and wavelet trellis-coded quantization .