given a frame sequence from a fixed camera, detecting all the foreground objects : the detection of the foreground objects is obtained by the difference between the current frame and an image of the scene’s static background

My implementation of Stauffer & Grimson's GMM(Background subtraction Drawbacks of Stauffer & Grimson's GMM Since its pixel based model fitting, a) lots of unwanted small blobs are scattered all over the frame. e.g. UCSD demo b) main blobs

利用ML算法对训练集进行学习，利用多维高斯进行判断后对输入图片进行前景后景判断(The training set for learning to use ML algorithm to judge on the input image foreground & background)

实现图像的前景与背景分割，设定三个不同阈值，直接观察分割结果或者利用统计直方图，得到一个自适应的阈值，再观察实验结果；(Segmentation of foreground and background of image, threshold segmentation method)