GMM

transeint behavior in induction generator during grid fault

说明：  DensePose用深度学习把2D图像坐标映射到3D人体表面上，再加上以每秒多帧的速度处理密集坐标，最后实现动态人物的精确定位和姿态估计。该技术集目标检测、姿态估计、目标部分/实例分割等多种计算机视觉任务于一身的一个综合问题。(DensePost maps 2D image coordinates to 3D human body surface by in-depth learning, and processes dense coordinates at the speed of multiple frames per second. Finally, it realizes precise positioning and attitude estimation of dynamic characters. This technology integrates many kinds of computer vision tasks, such as target detection, attitude estimation, target part/instance segmentation, etc.)

三相不平衡的补偿方法,simulink环境下实现,不错(The compensation method of three-phase imbalance is realized in simulink environment, which is good.)

基于Hessian矩阵增强提取二维或三维医学图像中的血管(Vessel enhancement and extraction from 2D or 3D medical images)

说明：  对脑肿瘤进行分割 基于3dunet(Brain tumors were segmented based on 3dunet)

说明：  数字图像处理 小波处理 ，去噪音，比基于傅里叶变换的去噪方法好。 含噪信号经过预处理，然后利用小波变换把信号分解到各尺度中，在每一尺度下把属于噪声的小波系数去掉，保留并增强属于信号的小波系数，最后再经过小波逆变换恢复检测信号。(The noisy signal is pre-processed, then the signal is decomposed into different scales by wavelet transform. The wavelet coefficients belonging to noise are removed at each scale, and the wavelet coefficients belonging to the signal are retained and enhanced. Finally, the detected signal is restored by inverse wavelet transform. It is better than the denoising method based on Fourier transform.)

读取jpeg图片数据并输出到txt文本中，再从txt文本中读取数据生成图片(Reading image data and outputs to txt, and then read the data generated image txt text)

绘制一个小房子，并演示透视变换。(drawing a small house, and demonstrated perspective transformation.)

车牌矫正,对于一写不够标准的车牌进行矫正，让车牌更容易被分割(Plate correction, not enough for a standard license plate write to correct, so more likely to be split plate)

vtk碰撞检测程序，基于obb包围盒的碰撞检测程序，需要用cmake进行编译(vtk collision detection procedure, based on obb bounding box collision detection program needs to be compiled with cmake)