▍1. Shadow-Detection
阴影检测,基于OpenCV用于对图像中阴影的检测(Shadow detection, OpenCV for image shadow detection)
阴影检测,基于OpenCV用于对图像中阴影的检测(Shadow detection, OpenCV for image shadow detection)
说明: RGB-IHS变换:图像进行 RGB-HIS 正变换,分别对明度、饱和度、色调进行线性 拉伸显示;然后再进行反变换 (RGB-IHS transformation: the image is RGB-HIS transformation, respectively, lightness, saturation, hue, a linear stretch display then the inverse transform)
在GPU-CUDA平台上进行SIFT特征提取,加快提取速度(On GPU-CUDA platform SIFT feature extraction, speeding up the extraction rate)
包括基于SIFTGPU的sift特征提取,sift匹配,基于ransac误匹配点剔除等(SIFTGPU based sift feature extraction, sift matching, mismatching points based ransac removed, etc.)
VC和OpenGL实现的点云读取界面,需要的朋友可以下载参考(VC and OpenGL realize the point cloud to read interface, the need for a friend can download the reference)
说明: 基于Kmeans算法的图像分割,一般Kmeans是数据挖掘中用来聚类的,本试验利用图像中的灰度值作为Kmeans算法的原始点,进行图像分割(Kmeans algorithm based on image segmentation, data mining in general Kmeans is used to clustering, the trial use of the image gray value as the original algorithm Kmeans spots for Image Segmentation)
说明: k-svd算法用于稀疏表示的图像去噪,字典学习算法,去噪效果良好(k-svd algorithm for image denoising of sparse representation)
通过数字图像相关的方法计算两幅图像之间的位移,计算时间较长,是最基础的DIC,没有优化。(Digital image correlation method to calculate the displacement between the two images, the time is longer, is the most basic DIC, no optimization.)
实现凸多边形排样,使用临界多边形NFP判断两个凸多边形形是否相交,使用启发式算法提高效率, (Convex polygon nesting, polygon NFP to determine whether two convex polygon-shaped intersection, the use of heuristic algorithms to improve efficiency,)
利用四参数随机生成法生成三维多孔介质,以研究黏土、页岩等的微观流动机制(Using QSGS to construct 3D porous media)
DOG检测算子,能够构造高斯尺度空间,并检测其中的极值,从而得到有价值的特征点位置(DOG detection operator, the Gaussian scale space can be constructed, and tested one of the extremes, resulting in valuable feature position)
matlab下图文并茂的分析了fft算法,分析了如何从频谱如何看频率,相位,幅值(Here to enter through the abundant of matlab analyzed fft, and analyzed from the frequency spectrum how to see that phase, should be translated text)
零相位带通滤波源代码,可以对信号进行滤波处理提高信噪比.(Zero-phase band-pass filtering the source code, you can filter the signal-noise ratio improve treatment.)
该程序是发表在IEEE上的经典直线提取论文“Extracting Straight Lines”的源代码实现,对计算机视觉、模式识别和信息提取等领域的科学研究人员具有极其重要的参看意义。建议下载学习和适用。(The program is published in the IEEE paper on the classic straight-line extraction " Extracting Straight Lines" the source code implementation of computer vision, pattern recognition and information extraction and other areas of scientific researchers see an extremely important significance. Recommended to download to learn and to apply.)
RLE压缩算法,对.bmp格式文件进行操作。使用MFC编制界面,可读入位图,压缩后保存位图并显示。(RLE compression algorithm, bmp format file operation. Use the MFC preparation interface, readable into the bitmap compressed to save a bitmap display.)
基于格子玻尔兹曼方法模拟泊肃叶流,边界条件用非平衡格式(Poiseuille flow based on the lattice Boltzmann method to simulate the boundary conditions with unbalanced format )
基于侧抑制的图像分割,在PCNN分割的基础上实现(failed to translate)
CZT变换进行信号频谱分析,解决了FFT法频域分辨不高的问题,源码开发,特别适用(Chirp Z Transform)
一个简单的HALCON计算圆心坐标的例子,C++代码格式,初学者适用!(A simple example of calculating coordinates HALCON, c++ code format, for beginners!)
基于opencv的Kinect深度图像的去噪,滤波(Opencv based Kinect depth image denoising, filtering)