bianxingguangshanOK

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.)

首先对车牌识别系统的现状和已有的技术进行深入的研究，然后开发出一个基于 Python 的车牌识别系统，文中先对车辆图像进行高斯去噪、灰度化和边缘检测等预处理方法，然后用颜色特征和形态特征相结合的方法来确定车牌位置，用彩色分割法来完成车牌分割，最后，运用 SVM 分类训练器完成字符识别并使用Python 软件环境进行车牌识别的仿真实验。(License plate recognition based on SVM)

三维模型的网格简化算法，通过删除边来减少面片个数，同时保留图形特征(Three-dimensional model of the mesh simplification algorithm to reduce the number of patches by removing the side, while retaining graphic features)

说明：  图像预处理以及提取图像的Tamura 纹理特征(Image preprocessing and Tamura texture feature extraction)

基于keystone变换校正距离走动的机载预警雷达高速运动目标动目标检测方法(High-speed moving target moving target detection method based on keystone correction transformation walking distance airborne early warning radar)

本人图像处理的期末课程作业，使用模式识别自动识别验证码。老师都给好评哦(I end image processing course work, the use of pattern recognition automatic identification code)

此jar包用于解析jbig格式文件的工具包，调用接口即可(This jar package is a toolkit for parsing JBIG format files and calling interfaces.)

说明：  这是一篇关于大气湍流退化图像复原的硕士论文，我用matlab对该论文中阐述的方法进行了仿真(This is a master's thesis on the restoration of atmospheric turbulence degraded images. I used Matlab to simulate the methods described in this paper.)

transeint behavior in induction generator during grid fault

Pcnn与otsu结合，自适应找出Pcnn点火次数！(It is pcnn base on OTSU,can stop the program adaptive.)