Hu_MV_Nicolas

利用GPU加速的SIFT算法，实现影像匹配，并利用RANSAC进行粗差的剔除(GPU-accelerated use SIFT algorithm to achieve image matching, and use RANSAC removing coarse poor)

说明：  最近一直在看matlab仿真WSN的资料，今天找到一个仿真LEACH协议的。其主要是为了仿真他自己提出来的分簇协议，并给出了matlab代码，同时给出leach的代码。有兴趣的可以研究一下leach 协议和deec的协议对比(I've been looking at the MATLAB simulation WSN recently, and today I've found a simulation LEACH protocol. The main purpose is to simulate the clustering protocol proposed by himself, and give the matlab code, and give leach code at the same time. Interested can study the LEACH protocol and DEEC protocol comparison)

空间光通信中的信标光探测器非均匀性校正，使用matlab进行仿真，得到探测器非均匀性校正前后的光斑位置探测情况(Nonuniformity correction of beacon photodetectors in space optical communication)

基于ESS303开发板的OV7670_VGA拍照功能实现(Implementation of OV7670_VGA camera function based on ESS303 development board)

首先将非平稳的故障振动信号进行双树复小波包分解，得 到不同频带的分量；然后对每个分量求其峭度值和相关系数并进行比较；最后选取峭度值和相关系数较大的分量 进行软阈值降噪和双树复小波包重构，即可有效地消除振动信号中噪声的干扰，同时保留信号中的有效信息即实 现了故障特征信息的提取。(In view of the above situation, a new fault diagnosis method is proposed based on dual-tree complex wavelet packet transform and threshold de-noising. Firstly, the non-stationary fault signal is decomposed into several different frequency band components through dual-tree complex wavelet packet decomposition. Secondly, Kurtosis and the cross-correlation coefficient of each component are obtained and compared. Due to the kurtosis reflecting the signal variations, if the kurtosis value is bigger, the degree of the change of signal is bigger too. The correlation coefficient can reflect the proximity between the component and the original signal at the same time, the correlation coefficient is bigger, the more similar with the original signal. Finally, the components that have a bigger value are chosen to be de-noised by a soft threshold and reconstructed by dual-tree complex wavelet packet transform. The noise interference was eliminated effectively, and the effective si)

该程序是我多年的经验总结以及代码，实现了全景目标跟踪、火焰识别、烟雾识别、起立坐下行为判断、越界闯入、徘徊、违规停车等多种智能功能一体化，粒子滤波、贝叶斯分类器、随机森林等多种在线学习机制，还有传统的camshift、meanshift、光流法、卡尔曼滤波、struck、KCF、TLD、CT、区域匹配，相位相关、轮廓跟踪等多种算法(The program is my many years of experience and code, the realization of the panorama target tracking, flame detection, smoke detection, standing up sitting judge, cross-border intrusion, wandering, illegal parking and other various intelligent functions integration, particle filter, Bayesian classifier, random forest variety of online learning mechanism, and the traditional CAMSHIFT, meanshift, optical flow method, Kalman filter, the, KCF, regional matching, phase correlation, contour tracking and other several algorithms)

说明：  用simulink进行的有源电力滤波器的仿真，波形清晰(Simulation of active power filter with clear waveform)

在自适应中值滤波的基础上，采用均值与方差得到一个阈值，来判断极值点是不是噪声点！(On the basis of adaptive median filtering, a threshold is obtained by means of mean and variance to determine whether the extreme point is a noise point!)

此为人工智能中的简单遗传算法的实现,使用的开发工具为c#()

Packet matching code.