资源列表
Untitled2
- BP神经网络基本原理概述:这种网络模型利用误差反向传播训练算法模型,能够很好地解决多层网络中隐含层神经元连接权值系数的学习问题,它的特点是信号前向传播、误差反向传播,简称BP(Back Propagation)神经网络。BP学习算法的基本原理是梯度最快下降法,即通过调整权值使网络总误差最小,在信号前向传播阶段,输入信号经输入层处理再经隐含层处理最后传向输出层处理;在误差反向传播阶段,将输出层输出的信号值与期望输出信号值比较得到误差,若误差较大则把误差信号传回隐含层直至输入层,在各层神经元中使用
AtmCor
- 本代码基于IDL语言开发,以我国环境一号(HJ-1)卫星影像为例,实现了HJ-1 CCD影像的大气校正。压缩包中包括了HJ-1 CCD影像的定标系数(可以根据资源卫星应用中心发布的最新系数进行替换)和查找表。供遥感初学者参考(This code is developed based on IDL language, taking the environmental satellite I (HJ-1) satellite image as an example to realize the at
chengxu
- 用于高光谱图像处理的matlab程序,包括图像融合,降维和图像的极大似然分类程序(Matlab program for hyperspectral image processing, including image fusion, dimension reduction, and maximum likelihood classification of images)
颜色识别 - 图像(普通轮廓)
- 基于opencv的简单颜色识别,载入图像进行识别,可识别出图像中的红色物体并画出物体轮廓(Opencv based simple color recognition, loading image recognition, can identify the red object in the image and draw the outline of the object.)
INface_tool
- 可用于图片的预处理,去除光照、噪音等影响(used for pre-processing pictures, removing the effect of light, noise, etc.)
MATLAB
- 课堂中的小练习,其中使用MATLAB涉及霍夫变换、旋转(Small exercises in the classroom, where using MATLAB involves Hough transformation, rotation)
programe
- 使用MATLAB进行高光谱数据显示(显示分类后图像)(Hyperspectral data display using MATLAB (displaying the classified image))
3DpcaPlot
- PCA主成分分析,基于R语言平台的pca分析和绘制三维图像(PCA principal component analysis, based on R language platform PCA analysis and rendering 3d images.)
PCA
- 使用matlab自带的函数princomp()计算主成分,当维数很高时通常会出现内存耗尽的错误,即使内存足够也非常耗时。快速pca能加快计算进程且减小内存占用,更容易计算较大尺寸的图像主成分。(Use MATLAB's own function princomp () to calculate the principal component. When the dimension is very high, the memory exhaustion error usually occurs,
zhenjiancha
- 对视频中的运动目标进行检测与跟踪,采用帧间差法跟踪结果用矩形框表示。(The moving objects in video are detected and tracked, and the result of tracking by frame difference method is represented by rectangle box.)
test2
- 对视频序列中的运动目标进行检测与跟踪,动目标检测部分采用背景差分法,跟踪部分采用卡尔曼滤波,检测结果用红色外接矩形框表示,跟踪结果用绿色矩形框表示 2、采用平均背景法更新背景图像。(The moving target in the video sequence is detected and tracked, the moving target detection part uses the background difference method, the tracking part uses
26个字母识别 用matlab实现的
- 用matlab实现的26个字母识别。基于BP算法的字母识别其容错性和识别率相对较高,在有噪声的情况下训练其识别出错率也相应增加,许进一步改进。(26 letter recognition implemented with MATLAB.The letter recognition based on BP algorithm has a relatively high fault tolerance and recognition rate, and the error rate of recog