figure4_41

图像保重要特征扩散滤波方法之 -非线性扩散,不错的(Image confirmed important feature of diffusion filter method nonlinear diffusion, pretty good)

我写的基于bandelet域的spiht图像压缩算法。效果比经典的SPIHT好。文章已发，希望代码对大家有用。(I wrote bandelet domain-based SPIHT image compression algorithm. SPIHT is better than a good classic. Article has been distributed, I hope the code useful for everyone.)

使用matlab调用opencv做成的adaboost人脸检测DLL模块，在usb摄像头采集的视频序列中检测人脸并实时显示， 实时性比C低。 下载后可以直接在matlab运行，不要改动文件夹内的文件相对位置。(Opencv matlab call made using adaboost face detection DLL module, usb camera capture video sequences of face detection and real-time display, real-time lower than C. Download can be run directly in matlab, do not change the file folder relative position.)

迭代法阈值分割，迭代法自动计算最优阈值。已经写成函数形式，输入灰度图，输出分割好后的阈值图。(Threshold segmentation iterative method, iterative method for automatically calculating the optimal threshold. Function has been written in the form of input grayscale output partition threshold after a good map.)

基于颜色来检测火焰，将是频频分帧，然后逐帧检测，碧昂切将火焰全画出来，基础编程。(Based on color to test the flame, basic programming )

说明：  这个压缩包里只要给出了边缘保持系数和等效视数的计算方法(This compression is given as long as the edge of the bag to maintain the equivalent depending on the number of coefficients and the calculation of)

基于mean-shift的动态目标跟踪算法，简单有效，另附图库(Based on mean-shift of the dynamic target tracking algorithm, simple and effective, attach library)

逆透视变换的算法,先生成一个图像 然后将图像坐标系和世界坐标系进行转换 最后将消除透视效果的图像显示出来(inverse perspective transformation algorithm Mr. images into one image will then coordinate system and the world coordinate system conversion for the final elimination of the effects of lens images show to)

用自适应阈值法二值化图像，首先将图像分为几个子图像，在每个子图像中求得均值，用此均值二值化本子图(err)

在本文件中，我主要研究通过行人的表观特征进行识别，例如颜色、纹理等等。用matlab GUI 编写了程序，对行人进行匹配 (Pedestrian recognition of the inter-camera is intelligent surveillance camera network a key research direction. Match the pedestrian different camera, you can cross the pedestrian track of the camera, the expansion of the monitoring horizon, at the same time can have a clearer grasp of the behavior of pedestrians in the entire surveillance area. Different cameras, different lighting conditions, the pedestrian position and a different scale, shelter, etc., making the pedestrian match challenging. In this document, I study to identify by pedestrian apparent characteristics such as color, texture, and so on.)