这是修改之后的系统，主要用支持向量机SVM和水平方向梯度HOG特征进行特征目标识别分类-This is a system modifications, mainly with support vector machines SVM and horizontal direction gradient the HOG feature characteristic target recognition classification

视频镜头分割，能有效检测突变与渐变，可能机器配置不一样，换机器程序可能会出错，但是程序相对好调-Video shot segmentation,mutations and the gradient can be detected effectively.

corner finder from gradient and laplacian

采用梯度分布直方图的算法，自动识别视频文件中的人体，并通过蓝色方框标识出，能够实时识别，追踪显示-Gradient histogram algorithm that automatically identify video files in the human body, and identified by a blue box, real-time identification, tracking display