搜索资源列表
VideoProj
- OpenCV 人脸识别示例，请将源码拷贝至E盘（具体路径，参见编译后提示） 请使用Debug模式编译-OpenCV Face Recognition sample, please copy the source code to the E site (the specific path, see the compiled tips), please use the Debug mode compilation
opencv
- this contains many tutorials and e-books related to openCv for beginners-this contains many tutorials and e-books related to openCv for beginners...
OpenCV
- opencv教程，经典著作《学习opencv》的中文版电子书-opencv tutorial, classic " learning opencv" the Chinese version of e-books
twarz2.tar
- Face detection app, using OpenCV modyficated by me for tracing face coordinates on video screen. You can use std output to using them for other purposes, i.e. for tracing face by webcam positioner.
CamFromAVI
- 在VC++环境下，利用OpenCV现有的函数针对DIVX格式的视频进行播e放，播放过程中按动Grab键可以获取当时那一帧图片-Play the camero by OpenCV which base on VC++,you can get a image if you push the "Grab" during the process.
opencvshouce
- opencv的教程和使用手册，非常全面，非常好用-The e-book to learn opencv, it is very good, I have used it for 1 year
OpenCV-Computer-Vision-
- This OpenCV e-Book-This is OpenCV e-Book...
Opencv_tutorial
- OpenCV 的範例介紹，從安裝說明到圖形使用的英文電子書。-OpenCV sample introduction, from the installation instructions to the graphics used in English e-books.
pictureChanger
- 给定两幅尺寸一样的彩色图片（e.g. 640X480）,实现从一副图片到另一副图片的渐进变化-Given two color pictures of the same size (eg 640X480), a picture from a picture to a gradual change in the other vice
Cookbook-CODE
- Introduction to COmputer vision library i.e. OpenCv
find_obj
- 在box_in_scene图片中找到box，即已知图像在目标图像中的定位检测-Found box_in_scene picture box, i.e. a known image in the target image, the location detection
5-21
- 基于OPENCV的车辆检测，采用画出虚拟线圈的方法实现车辆的检测，定位，触发-Intelligent transport system(ITS)is currently being studied and the subject of widespread concern in the area of the world transport．These years，the great economic benefit has been gained through ITS，At the
Motion_detect2
- 基于opencv的移动监测，基于TTX引擎的语音报警， 可以讲监测的图片发至邮箱，可以通过飞信发送短信-based on the opencv, based on the TTX, send picture to you e-mail, send message to your phone by fetion.
onling_tracker
- 采用在线学习跟踪方式，对物体进行跟踪，代码用c++编写，库用的Opencv库，程序中包括了3个.h，3个.cpp，一个.main程序。-We have added two new state-of-the-art object tracking algorithms to OpenCV which can robustly track images patches across a video sequence and learn online (i.e., on-the-fly) as the
CTFromCam
- 基于网络摄像头的压缩感知人脸识别跟踪算法 压缩感知（Compressive Sensing）理论是近年来信号处理领域诞生的一种新的信号处理理论，由D. Donoho、E. Candes及华裔科学家T. Tao等人提出，自诞生之日起便极大地吸引了相关研究人员的关注。-Face recognition based on compressed sensing tracking algorithm Compressive Sensing (Compressive Sensing) signal
cars3
- Vehicle detection, its an opensource code and works well with opencv and boost, === === === === === === === ==== = multi-target tracking method by Wongun Choi === === === === === === === ==== Compile * Require opencv and boost library to b
e
- 用OPENCV实现支持向量机的源代码，运行于VS2010环境下运行通过-Support vector machine (SVM) to implement in OPENCV source code, run run through in VS2010 environment
HOG_OpenCV
- HOG即histogram of oriented gradient, 是用于目标检测的特征描述子，该技术将图像局部出现的方向梯度次数进行计数，该方法和边缘方向直方图、scale-invariant feature transform类似，不同的是hog的计算基于一致空间的密度矩阵来提高准确率。Navneet Dalal and Bill Triggs首先在05年的CVPR中提出HOG，用于静态图像or视频的行人检测。-HOG i.e. histogram of oriented gradien
surfmex-opencv
- SURF,huan jing,xia ,keyi yunxing qieyou ceshi shuju d e.
MTF
- Kal man 滤波是一种应用非常广泛的状态估计算法 基于信息融合的 Kal man 滤波包 括状态向量融合和测量融合两种方法 传统的 Kal man 方法 TTF 具有较低的估计误差和很长的计算时间 提出的状态向量和测量向量的融合模型 MTF 利用局部融合信息给出一种更好的状态估计 计算时间短 性能也比 TTF 高-Conventi onal Kal man filt er TTF based on i nf or mati on f usi on i ncl udes t Wo