-DOA

使用GDAL库，用于遥感影像的特征点提取(Using the GDAL library, used for remote sensing image feature point extraction)

说明：  基于各种算法的运动视频背景消除。使用opencv工具库，通过读取视频文件，处理视频，最后存储。(Background Subtract Algorithm)

打开一个图像或者视频文件，相应的轮廓检测功能，视频运动物体的跟踪功能(applications on image，tracking objects in the video)

使用VC++编程，自动检测角点，实现图像配准，代码可用。(Automatically detect the corner points, for image registration, the code is available.)

对灰度和真彩色位图实现了多种边缘提取算法(Of gray-scale and true color bitmaps to achieve a variety of edge detection algorithm)

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.)

图像的分割处理，可以将图像中的数字分割找出(IMAGE division)

Shap Context based Shape recognition

FDK重建算法 希望对其他人能有帮助 用C和cuda 实现的(fdk reconstrcution algorithm using cuda and c source code hope to help others it may be usefull. it is implented by c and cuda)

特征点匹配时，采用构造KD-tree，用最优节点优先法寻找最佳匹配点(Matching feature points, the tectonic KD-tree, with the optimal node is preferred method to search for the optimal matching point)