Z源逆变器开路三相SVPWM调制

使用cnn提取图像特征，然后用SVM分类，此处没有给出训练集，另外imagenet-caffe-alex部分代码需要注意，需要下载的话把注释掉的代码打开(Using CNN image feature extraction, and then use the SVM classification, there were no given training set, also need to pay attention to imagenet-caffe-alex part of the code, you need to download the commented code open)

采用曲率的方法，等间隔三点的大小计算夹角的大小，根据阈值标记指尖指根区域。(Curvature of the methods used, such as the size of three intervals calculated the size of the angle, according to the threshold refers to the root area marked fingertips.)

目前已有的手部运动跟踪系统大多在一定程度上限制了人体运动自由. 基于此, 提出一种无线、 可穿戴、 无障碍的腕关节、 指关节运动跟踪系统. 在人体每个手指甲上粘贴一轻小永磁体, 用以产生标示腕关节、指关节运动的信号 若干磁传感器置于手腕处的电子腕带上, 作为标示信号( 磁信号) 检测器. 当腕关节、 指关 节运动时, 永磁体在各传感器所在位置处的合成磁场发生变化, 传感器对该磁场信号进行测量, 所检测到的磁场信号送入手部姿势估计器, 估计器基于系统数学模型计算手部姿势, 从而实现对手部运动的跟踪.(Most of the existing hand movement tracking system to a certain extent limited the freedom of human motion. This paper presents a wireless, wearable, accessible wrist, knuckles motion tracking system. In each fingernail on the human body Paste a light small permanent magnet to produce marked the wrist, referring to the signal of the joint movement the number of magnetic sensors placed in the wrist at the electronic wristband, as marked signal (magnetic signal) detector. when the wrist, knuckles campaign , the permanent magnet in the magnetic field of the sensor location at changes in the sensors of the magnetic signal measurement, the detected magnetic field signal sent from the start with the Ministry of posture is estimated, the estimator based on the mathematical model to calculate the hand position in order to achieve of hand movement tracking.)

基于sift算法的图像匹配。并用RANSEC算法去除错误匹配。最后还给出了sift算法的图像拼接。(Sift-based image matching algorithm. And use RANSEC algorithm to remove false matches. Finally, given the sift algorithm for image stitching.)

随机过程实验（研一）包含的程序：离散时间马尔可夫链、连续时间马尔科夫链、布朗运动。(Random process experiments (yanyi) program included: discrete time Markov chains, continuous-time Markov chains, Brownian motion.)

说明：  在图像恢复技术中，总变分最小化是一种以保存图像细节为目标的规整化复原方法。本算法基于总变分最小化的思想，采取交替最小化的精确迭代策略来对图像和点扩展函数同时进行恢复。实验表明，该算法在噪声水平较高的情况下仍能对图像进行稳健的恢复。(Total variation image restoration techniques is a goal to save the image detail regularization recovery method. Algorithm based on total variation minimization thinking, take the alternating minimization accurate iteration strategy to simultaneously restore the image and point spread function. The experiments show that the algorithm in the case of high noise levels can still robust recovery image.)

说明：  裁剪图像为固定大小，非常简单，只需要设定图像裁剪起始位置以及图像裁剪大小即可，非常方便。(It is very simple to crop the image to a fixed size. It is very convenient to set the starting position and size of the image clipping)

图像融合工具包：包含多种基本图像融合方法 开发环境：matlab(Image Fusion tool kits : a mixture of basic image fusion method development environment : Matlab)

能实现VFW编程，调用本地视频设备，实现视频捕捉和RGB-YUV颜色空间转换。 (To achieve VFW programming, call the local video equipment, the implementation of video capture and RGB-YUV color space conversion.)

Susan算法，用于角点检测。很先进的方法，国内有人改进过，这是原来的方法。(Susan algorithm for corner detection. The most advanced methods, there are those who improved, this is the original method.)