loci

基于区域的稠密立体匹配方法（论文） 关键词：种子点；区域增长；稠密匹配(Based on Region Dense Three—dimensional Match Method)

N年前上数字图像课时写的实验报告和程序，用滤波反投影（Filter Back Project，FBP)法重建图像。(Report and source code for data image restore experiment, using FBP.)

通过GDAL读取常用遥感影像，如img，tiff，可实现读取显示和雷达影像处理的一些基本算法(Read through GDAL common remote sensing images, such as img, tiff, read the display and radar can achieve some of the basic image processing algorithms)

采用了Harrtraining和离子滤波算法实现了拥挤人群人头计数，非常有用。VC++和Opencv开发，采用Oepncv中的Harrtraining训练一个分类器即可运行(Human detection and tracking in high density crowds is an unsolved problem. Standard preprocessing techniques such as background modeling fail when most of the scene is in motion. We integrate human detection and tracking into a single framework, and in- troduce a conrmation-by-classication method to estimate condence in a tracked trajectory, track humans through occlusions, and eliminate false positive detections.)

双目立体视觉，采用两张图像恢复三维形状，外国人的一个开源项目。(System Prototype to make 3D reconstruction solution using stereo images. It works with common cameras and not require large amount of memory during the images processing. It provides a low cost solution to educational environments with low budgets. )

摄影测量学 通过迭代法求解五个相对定向元素(Relative orientation)

ostu二值化算法vc实现，基于MIL图像处理软件包将图像解析，通过ostu求取二值化阈值，实现二值化算法(ostu binarization algorithm to achieve vc, MIL image processing software package based on the image resolution, strike through ostu binarization threshold binarization algorithm to achieve)

2009年CVPR最佳论文《Single image haze removal using dark channel prior》暗原色图像去雾的算法实现。与原文不同的是本程序没有完成最后matting细化效果的部分，但仍能够达到视觉上可以接受的去雾效果。计算机视觉课程作业。工程运行于VS2008环境，需要OpenCV支持。Debug目下exe文件可以直接双击运行查看结果。(CVPR 2009 Best Paper " Single image haze removal using dark channel prior" to the dark fog of the primary image algorithm. The difference is that with the original program did not complete the final matting refinement part，yet haze-removal result is visually acceptable. Visual course work. This project runs under VS2008 with OpenCV. Double click the exe file under Debug folder to check the final result.)

人脸检测与跟踪，我的毕业论文，使用我自己改进的ADABOOST和CAMSHIFT算法,附带我的毕业论文,opencv1.0或以上自己配置(face detection use adaboost and camshift algorithm，relevant paper enclosed，OPENCV1.0 is necessary)

VC编写的位图图像处理的源代码，包括了增强、变换等内容(VC prepared bitmap images deal with the source code, including the enhanced transformation, etc.)