CRL-2001-1

运用计算机图形学的知识，采用4阶B样条基函数，节点向量取为[0,0,0,0,1/4,2/4,3/4,1,1,1,1] 先绘制控制多边形，再用分段直线段绘制B样条曲线(Using the knowledge of computer graphics, the 4 order B spline basis function is used, and the node vector is taken as [0,0,0,0,1/4,2/4,3/4,1,1,1,1]. First, draw the control polygon and draw the B spline curve by piecewise straight line segments.)

一个自己编的解码jpeg格式图片的VC++程序的源代码。()

利用opencv高斯混合背景建模，并进行开闭运算滤波， 提取视频监控中的车辆(Using opencv Gaussian mixture background modeling and opening and closing operation filtering to extract vehicles in video surveillance)

说明：  facet边缘检测的matlab源代码,是基于二阶模型，只要运行最后一个hhh.m就可以了(facet Edge Detection Matlab source code is based on second-order model, as long as the last one run on the hhh.m)

yuv格式的视频分解成每一帧图像，使用的是matlab语言(yuv format video into each frame, using matlab language)

鱼眼图像校正并将校正后的图像转换成鸟瞰图，即俯视图，纯C代码，没有调用其它库(fish eye image correction,then change it to bird s eye view)

用vc实现图像选块的拖拽和融合,通过对窗口的拖动实现图像选块的拖拽,,(Using vc realize image selected block drag and fusion, by dragging the window to realize image choose a drag and drop,,)

说明：  UNet最早发表在2015的MICCAI上，短短3年，引用量目前已经达到了4070，足以见得其影响力。而后成为大多做医疗影像语义分割任务的baseline，也启发了大量研究者去思考U型语义分割网络。而如今在自然影像理解方面，也有越来越多的语义分割和目标检测SOTA模型开始关注和使用U型结构，比如语义分割Discriminative Feature Network(DFN)(CVPR2018)，目标检测Feature Pyramid Networks for Object Detection(FPN)(CVPR 2017)等。(Its influence has reached 70% in 2015. Then it became the baseline that most of the medical image semantic segmentation tasks, and inspired a large number of researchers to think about the U-shaped semantic segmentation network. In the aspect of natural image understanding, more and more SOTA models of semantic segmentation and object detection begin to pay attention to and use U-shaped structure, such as semantic segmentation, discriminative feature network (DFN) (cvpr2018), feature pyramid networks for object detection (FPN) (CVPR 2017), etc.)

说明：  dct域的图像数字水印，将水印图像信息隐藏在DCT系数的中频部分。(DCT domain image watermarking, the watermark image information hidden in the intermediate frequency part of DCT coefficients.)

说明：  一个去除恶略天气状况的去噪程序，可以去除大雨中的雨点，还原原图像(A slightly weather conditions to the evil forces of the de-noising procedure, can remove heavy rain in the rain, to restore the original image)