feature-tracking

2d convolution on image

本设计是基于超像素的图像分割代码，可以实现图像前景和后景的分割。没有人机交互界面GUI。( U672C u8BB u8B1 u662F u57FA u5FF u524F u5BF u5BF u5DF u7D0 u7R0 u7684 u56FE u50CF u5206 u5272 u4EE3 u7801 uFF0C u53EF u4E5 u5B9E u73B0 u56FE u50CF u524D u666F U548C u540E u666F u7684 u5206 u5272 u3002 u6CA1 u6709 u4EBA u673A u4EA4 u4E92 u754C u9762GUI u3002)

计算机图形学基础算法z-buffer， 实现隐藏面消除(Computer graphics based algorithm z-buffer, to achieve hidden surface removal)

K均值聚类算法对图像进行分割，实验用程序，亲测可用。(K-means clustering algorithm for image segmentation, experimental procedures, pro-test is available.)

图像逆透视变换的示例，用于合成360度全景俯视图。(An example realizes the image processing of Inverse Perspective Mapping, which is used in composing 360 panorama planform.)

用大整数乘法来计算两个n位二进制数相乘(With large integer multiplication to calculate the multiplication of two n-bit binary number)

采用多成分分析算法进行图像分解，并对该算法进行评价(MCA picture dissolution)

针对粒子概率假设密度(PH D)滤波算法在虚警、漏检情况下，b标状态估计不稳定和b标可观测性车弱的问题，提出了一种基于序贯融合的粒子PH D滤波方法，利用雷达和红外传感器多目标进行融合跟踪杏基本思想是先对红外传感器进行粒子PH D滤波，丙将红外传感器滤波结果作为雷达的预测值，然后利用P达观测的数据进行更新，这样通过雷达和红外传感器交替上作保证目标状态的可观测性，从滤波器输出结身即可得到目标的状态信息仿真结果表明，在虚警、漏检和密集目标环境下，该方法是有效的和稳健的(The problem of target state estimation instability and observability weakerin the presence offalse alarms and missed detection was deal with. On the basis of sequential fusion, a particleprobabil- ity hypothesis density(PHD) filter for multrsensor multrtarget tracking was proposed. Observed da to collected from the infrared sensor was estimated with the particle PHD filter. Then the results from the filter were set as the radar predicted value by the radar observations. The multrtarget state can be updated to guarantee observing the target state. In this way, the global state is updated at the fusion center. Simulation results show that the proposed algorithm is effective and robust under the false warning, omission and concentrated target environment. )

这是一个数字图像处理常用的功能的集成软件，用VC++ 编写，可以对图像进行一些常见的操作，也可以自己扩展功能(This is a common feature of digital image processing integrated software, images can perform basic operations)

用Matlab写的投影法提取嘴唇 输入图像必须是规定大小的人脸(Written using Matlab projection extraction lips input image must be provided for the size of face)