elman

高光谱图像的解译是遥感图像应用的一个重要环节。基于线性光谱混合模型的光谱解译技术正在越来越广泛地应用。仿真结果表明，当部分端元参与解译和分区域进行解译时，高光谱图像的解译效果会得到较显著改善。(The unmixing of Hyperspectral imagery is a critical link of the application of remote sensing imagery. Based on linear spectral mixture model, spectral unmixing technology now is being increasingly used. On the basis of it,studying unmixing ways engaged by endmembers in different conditions, comparing and discussing a more effective expression mode of endmembers.)

混合高斯(Mixture of Gaussian, MOG) 背景建模算法和Codebook 背景建模算法被广泛应用于监控视频的运动目标检测问题, 但混合高斯的球体模型通常假设RGB 三个分量是独立的, Codebook 的圆柱体模型假设背景像素值在圆柱体内均匀分布且背景亮度值变化方向指向坐标原点, 这些假设使得模型对背景的描述能力下降. 本文提出了一种椭球体背景模型, 该模型克服了混合高斯球体模型和Codebook 圆柱体模型假设的局限性, 同时利用主成分分析(Principal components analysis, PCA) 方法来刻画椭球体背景模型, 提出了一种基于主成分分析的Codebook 背景建模算法. 实验表明, 本文算法不仅能够更准确地描述背景像素值在RGB 空间中的分布特征, 而且具有良好的鲁棒性.(The background modeling algorithm of mixture of Gaussian (MOG) and codebook is widely used in moving object detection of surveillance video. However, the ball model of MOG usually assumes that the three components of RGB are independent, while the cylinder model of codebook assumes that the value of background pixel is distributed uniformly within the cylinder and the changing direction of brightness points to the origin of the coordinate system. These assumptions reduce the descriptive capability for background modeling. Therefore, the paper proposes an ellipsoid- based background model, which overcomes the MOG and codebook0s limitations. By using principal component analysis to depict the ellipsoid background model, a novel PCA-based codebook background modeling algorithm is proposed. Experiments show that this algorithm can not only give more accurate description of the distribution of background pixels but also have a better robustness.)

基于opencv的图像灰度化，将24位彩色图像重新量化为8位灰度图像(gray image)

说明：  基于自组织神经网络数据及图像处理，在图像分割中应用极强。很好的源程序。 (Self-organizing neural network-based data and image processing, image segmentation in the application of highly. Very good source.)

用matlab实现levelset水平集分割图像！(levelset to fen ge Image ag dag gf a ga ga h agr d we v g)

非常完整的帧差法多目标跟踪Matlab代码，并提供了完整的文档介绍，非常适合初学者学习。注：运行时要改一下文件路径，以及把视频文件转成图像序列输入。(Very complete frame difference method, multi-target tracking Matlab code, and provides a complete documentation, very suitable for beginners to learn. Note: at run time, you change the file path, and the video file is converted to an image sequence)

利用边缘检测及梯度信息进行图像分割的源码(Using edge detection and gradient information source for Image Segmentation)

LabWindows /CVI 大学实验指导书，难度循序渐进，一套下来，基本操作都会了。推荐一下(LabWindows/CVI University experiment instructions, the difficulty of step-by-step, set down, the basic operation will be. You recommend)

该代码用于实现视觉目标跟踪研究中的协方差跟踪，能够把多种时空特征融合于统一的模型中，在实现视觉目标跟踪时具有较好的鲁棒性，而且其维数等于使用特征的数量，与各个特征的维数无关，因此，其计算复杂度较小，实时性较好。(This code is used to realize covariance tracking in the research field of visual object tracking of computer vision. It enables fusion of various spatial-temporal features into an unified object feature model, hence robust to noise. In addition, its dimension is equal to the number of the features used and independent of the dimensions of the features used. Therefore, it satisfies the requirement of real-time application due to its low computation cost.)

CNN中的手写识别LeNet5实现，用python，进行了中文注释(CNN handwritten recognition LeNet5 implementation, using python, carried out in Chinese Notes)