code_of_baijiaxing

用于求取三维点云数据的法向量，我的人脸建模就是用的这个，效果很好，但必须保证点云没有重叠的，否则会出现严重错误。(Strike a 3D point cloud data for normal vectors, and my face is to use this model, the effect is very good, but must ensure that there is no overlap of the point cloud, there would be a serious mistake.)

在有障碍的环境中，有效避障搜索，到达目标点。(In an obstacle environment, effective obstacle avoidance search can reach the target point.)

一个由matlab编写的从多视点拍摄的图像计算Visual Hull的简单的演示程序，基于空间体积的方法求物体的Visual Hull，对实现由多视点图像求Visual Hull的过程可以起到借鉴作用(Matlab prepared by a multi-viewpoint images of the Visual Hull calculate simple demo program, the method of space-based volume objects for Visual Hull, the realization of multi-viewpoint image for Visual Hull of the process can play a useful reference)

计算飞行器滚转角，俯仰角，偏航角变化对特征点在像平面的变化(Calculate the vehicle roll angle, pitch angle, yaw angle change of feature points in the image plane changes)

OSG中智能指针的使用。自己写了一个类，用来模仿OSG的智能指针。(The use of intelligent pointer in OSG. I wrote a class that mimics the intelligent pointer of OSG.)

说明：  这时一个delaunay三角网的程序，功能强大，并里面有详细说明和程序及原代码。能创建二维和三维的，且能生成模拟的3D图。(then a triangular network nodes procedures, powerful, and there are detailed procedures and the original code. To be able to create two-dimensional and three-dimensional and can generate simulated 3D map.)

基于2D轮廓的三维模型相似性比较研究 在游戏开发和机械建模 常用的方法

说明：  水平集（level set）中快进算法（fast marching）算法的matlab工具箱，内容很全面。(Level Set (level set), Fast Forward algorithm (fast marching) algorithm m atlab Toolbox, which is very comprehensive.)

一个比例和方向自适应均值漂移跟踪算法（SOAMST） 提出本文所要解决的问题，如何估计的规模和方向 改变均值漂移下的目标跟踪框架。在原来的均值偏移 跟踪算法，可以很好地估计目标的位置，规模的同时， 方向的变化，不能自适应估计。考虑到图像（重量） 是来自于目标运动模型和候选模型可以代表的可能性，一个 像素属于目标，我们证明了原来的均值漂移跟踪算法可以 推导出的重量图像的零阶和一阶矩。随着零阶 矩和目标模型和候选模型之间的Bhattacharyya系数， 提出了简单而有效的方法来估计的规模为目标。然后一种方法， 利用估计的区域和第二阶中心矩，提出 自适应地估计目标的宽度，高度和方向的变化。广泛 实验来证实所提出的方法，并验证其可靠性 规模和方向变化的目标。(A scale and orientation adaptive mean shift tracking (SOAMST) algorithm is proposed in this paper to address the problem of how to estimate the scale and orientation changes of the target under the mean shift tracking framework. In the original mean shift tracking algorithm, the position of the target can be well estimated, while the scale and orientation changes can not be adaptively estimated. Considering that the weight image derived from the target model and the candidate model can represent the possibility that a pixel belongs to the target, we show that the original mean shift tracking algorithm can be derived using the zeroth and the first order moments of the weight image. With the zeroth order moment and the Bhattacharyya coefficient between the target model and candidate model, a simple and effective method is proposed to estimate the scale of target. Then an approach, which utilizes the estimated area and the second order center moment, is proposed to adaptively e)

说明：  用LK光流算法实现视频跟踪的金字塔实现方法(Optical Flow Computation)