这个是Dr. Juergan Gall写的检测识别图片中的物体，有关的文章名字是Class-specific Hough Forests for Object detection. hough森林方法结合了随机森林和Hough选票去估计物体中心的可能。-A method for the detection of instances of an object class.A class-specific Hough forest is a random forest that maps image

QBC算法，即投票委员会程序算法，是一种以投票进行表决的算法，用Matlab实现。-QBC algorithm, the program algorithm committee vote is a vote to vote algorithm, using Matlab achieve.

Hough-based Tracking of Non-Rigid Objects-extend the idea of Hough-Forests to the online domain and couple the center vote based detection and back-projection with a rough segmentation based on graph-cuts.

可以画圆，椭圆，直线。圆或椭圆的直径不要选的太小，否则画好的圆或直径可能不会停留在工作区间-You can draw a circle, ellipse, straight line。Round or oval diameter is too small not to vote for, or draw a good circle or diameter may not stay in the work area