SFS_3

前景检测 对动态背景进行多角度监测 动态背景检测(Foreground detection is used to monitor dynamic background from different angles)

背景建模和前景分割的方式把运动车辆提取出来。并进行最近临关联，输出目标轨迹。 MeanShift运动目标跟踪 matlab程序 1.截取跟踪目标矩阵rect 2.求取跟踪目标的加权直方图hist1 3.读取视频序列中的一帧， 先随机取一块与rect等大的矩形，计算加权直方图hist2。 4.计算两者比重函数，如果后者差距过大， 更新新的矩阵中心Y，进行迭代（MeanShift是一种变步长可以迅速接近概率密度峰值的方法），直至一定条件后停止。 这两种算法为处理图像跟踪的基本方法 (Background modeling and foreground segmentation the extracted moving vehicles. Pro associated output and the target locus. Target tracking matlab program MeanShift movement. Interception tracking the target matrix rect strike a tracking target weighted histogram hist1 3. Reads a video sequence, randomly take a with the rect large rectangular, calculate the weighted histogram hist2. 4. Calculate both the proportion of function, if the latter gap is too large to update the new center of the matrix Y conducted the iteration (MeanShift is a variable step size can be rapidly approaching the peak of the probability density) until certain conditions to stop. The basic method of these two algorithms for processing the image tracking)

实现SURF特征点描述子算法，并使用Oxford Dataset图像自动进行精度评价(SURF feature descriptor and matching precision evaluation)

数字全息分区算法模拟，用于从一副同轴全息图中恢复出物体的像(digital holography)

APG算法，加速近端临近点算法，通过对子问题的调整，计算速度很快(APG algorithm, accelerated near the proximal point algorithm, by adjusting the sub-problems, fast calculation)

自主选择性的查看一幅图像中的部分区域的颜色直方图：允许用户在一幅图像中选择一个矩形区域，通过按住鼠标键画一个矩形，当鼠标放开是，高亮显示矩形框，同时在另一个独立的窗口中，使用画图函数画一个图表（选定区域的颜色直方图），分别用蓝，绿，红表示选中区域中每种颜色的像素数量。(Self-selective color in an image to view a partial area of ​ ​ the histogram: Allows the user to select a rectangular area in an image by holding down the mouse button to draw a rectangle when the mouse is released, the highlighted rectangle, Meanwhile in a separate window, using the drawing functions to draw a chart (selected color histogram region), respectively, with blue, green, red indicates the number of pixels in the selected area of ​ ​ each color.)

需安装Halcon

2015年最新国外算法，基于加权视觉词典的人群密度估计(crowd entimatin by a weighted bag of visual word model)

图像处理领域最新的K-L变换后求主成分的程序。matlab文件。(image processing latest K-L transform PCA for the procedure. Matlab document.)

对叶片进行预处理和提取部分特征：1.均值去噪 2.k均值聚类提取复杂背景下的叶子图片 3.填充孔洞 4.去叶柄 5.提取轮廓 6计算纵横轴比、面积凹凸比、周长凹凸比、球形性、圆形性、偏心率、形状参数和矩形度等特征值并进行画图。( Pretreatment of leaves and extract some of the characteristics: a mean denoising 2.k means clustering leaf extract complex background picture fill holes 3 4 5 contour extraction petiole 6 to calculate the vertical and horizontal axis ratio, convex area ratio.. convex perimeter than spherical, circularity, eccentricity, and rectangular shape parameter values ​ ​ and other characteristics of the drawing.)