Location:
Search - OpenCV 3.1
Search list
Description: OpenCV 同时3视频显示，有进度条可调整时间点位置
-OpenCV the 3 video display, a progress bar to adjust point position
Platform: |
Size: 1024 |
Author: 周易 |
Hits:
Description: 基于opencv的帧率提升算法，可实现超低帧率（3~5帧）的视频插帧，速度达到应用标准，六边形搜索块匹配-Opencv based on frame rate to enhance algorithm can achieve ultra-low frame rate (3 to 5) of the video frame interpolation, speed of application standards, hexagon search block matching
Platform: |
Size: 4096 |
Author: 廖琦宇 |
Hits:
Description: 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 be installed
- sudo apt-get install libboost-dev or see http://www.boost.org/
- refer to http://opencv.willowgarage.com/wiki/InstallGuide
1. move into the standalone_tracker directory : cd standalone_tracker
2. cmake .
3. make
Run
1. How to run
1) Download/prepare a video to be processed : e.g. wget http://www.vision.ee.ethz.ch/~aess/cvpr2008/seq02-img-left.tar.gz
2) unzip the images.
3) generate imagelist file using following command : ls seq02-img-left/*.jpg > seq02_imlist.txt
4) run detector to get detection bboxes and confidence map
5) generate conflist file : ls seq02-img-left/*.conf > seq02_conflist.txt
6) try tracking with track.sh
-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 be installed
- sudo apt-get install libboost-dev or see http://www.boost.org/
- refer to http://opencv.willowgarage.com/wiki/InstallGuide
1. move into the standalone_tracker directory : cd standalone_tracker
2. cmake .
3. make
Run
1. How to run
1) Download/prepare a video to be processed : e.g. wget http://www.vision.ee.ethz.ch/~aess/cvpr2008/seq02-img-left.tar.gz
2) unzip the images.
3) generate imagelist file using following command : ls seq02-img-left/*.jpg > seq02_imlist.txt
4) run detector to get detection bboxes and confidence map
5) generate conflist file : ls seq02-img-left/*.conf > seq02_conflist.txt
6) try tracking with track.sh
Platform: |
Size: 15360 |
Author: Khushwant |
Hits:
Description: 对OpenCV1.0与OpenCV高版本之间的Mat与IplImage做了详细对比，并做了相关实验。编译时候，需要至少使用CMake2.8.3-Mat and IplImage OpenCV1.0 for high versions with OpenCV to do a detailed comparison and do experiments. Compile time, you need to use at least CMake2.8.3
Platform: |
Size: 517120 |
Author: Scott |
Hits:
Description: 导向滤波中关键算法boxFilter算法C++代码，该代码在opencv-2.4.3支持下可以直接用matlab编译成boxFilter_c.mexw32实现混合编程。
-boxFilter for C++ based on opencv-2.4.3
Platform: |
Size: 6144 |
Author: hujunyi |
Hits:
Description: opencv 代码，运动物体检测的3帧差分算法，对于初学者来说还挺好用的-moving object using opencv
Platform: |
Size: 2048 |
Author: heyunlei |
Hits:
Description: 双边滤波
VS2010 + OpenCV 2.4.3-Bilateral Filtering
Platform: |
Size: 12907520 |
Author: 毕自强 |
Hits:
Description: 本文档是利用opencv实现的边缘检测代码，包括3个算子：canny算子，laplace算子和sobel算子-This document is to use the opencv implementation of edge detection code, including three operator, canny operator, Laplace operator and sobel operator
Platform: |
Size: 2048 |
Author: 宋宋 |
Hits:
Description: 应用在计算机视觉方面，结合CMAKE应用，还有OPENCV。-*** With CMake***
yaml-cpp uses CMake to support cross-platform building. In a UNIX-like system, the basic steps to build are:
1. Download and install CMake (if you don t have root privileges, just install to a local directory, like ~/bin)
2. From the source directory, run:
mk build
cd build
cmake ..
and then the usual
make
make install
3. To clean up, just remove the build directory.
*** Without CMake***
If you don t want to use CMake, just add all .cpp files to a makefile. yaml-cpp does not need any special build settings, so no configure file is necessary.
(Note: this is pretty tedious. It s sooo much easier to use CMake.)
Platform: |
Size: 2326528 |
Author: 琦肖 |
Hits:
Description: mastering opencv 第三章 源代码-mastering opencv chapter 3 source code
Platform: |
Size: 9857024 |
Author: 李鹏 |
Hits:
Description: 对输入的一张彩色图像，自己写代码实现Harris Corner 检测算法：
1. 不能直接调用OpenCV 里面与Harris 角点检测相关的一些函数；
2. 只能用C/C++，不能用其他语言；
3. GUI 只能用自带的HighGUI，不能用QT 或其他的；
4. 平台可以用Windows， Linux, MacOS；
5. 显示中间的处理结果及最终的检测结果，包括最大特征值图，最小特征值图，R 图（可以考虑彩色
展示），原图上叠加检测结果等，并将这些中间结果都输出成图像文件；
6. 命令格式： “xxx.exe 图片文件 k 参数(=0.04) Aperture_size(=3)”。-The input of a color image, write your own code to achieve Harris Corner Detection Algorithm: 1. Can not be called directly inside OpenCV some functions associated with the Harris corner detection 2. To only use C/C++, can not be used in other languages 3. GUI only with their own HighGUI, can not use QT or other 4. The platform can be used Windows, Linux, MacOS 5. Display intermediate and final results of the test results, including the largest eigenvalues diagram, the minimum feature value graph , R chart (you can consider color display), picture superimposed on the test results, etc., and these intermediate results are output as an image file 6. Command Format: " xxx.exe picture file k parameters (= 0.04) Aperture_size (= 3 ). "
Platform: |
Size: 504832 |
Author: qian |
Hits:
Description: python写的基于opencv3.0的视频录制程序-python wrote based opencv 3.0 Video Recorder
Platform: |
Size: 1024 |
Author: shf |
Hits:
Description: 主要为opencv人脸的美化
人脸美化，我们用的皮肤检测，皮肤在颜色空间是特定的一个区域
检测到这个区域（感兴趣区域），完后对这个区域进行美化，就是滤波，主要是双边滤波和高斯滤波。
3.视频格式转换以及编码
处理好的矩阵颜色空间是rgb的，需要转换成yuv，yuv的颜色空间就是可以播放的，类似我们电视上面看的画面，编码就是传输时候需要发送流，只个流相当于针对数据的压缩，将yuv格式的视频帧编码成h264的格式
Rgb转换成yuv，opencv实现（美颜在这一步实现）
Yuv转换成h264，x264实现
H264转换成rtmp流，libxrtmp实现-Mainly opencv face beautification facial beautification, skin test our use, skin color space is a particular area of a detected region (region of interest), after this area landscaping, is filtered, mainly bilateral filtering and Gaussian filter. 3. Video format conversion and encoding process is a good matrix rgb color space, the need to convert yuv, yuv color space that can be played, similar to watching our television screen above, the coding is transmitted when you need to send traffic only stream equivalent for compressed data, video frame coded yuv format into h264 format Rgb convert yuv, opencv achieve (achieve beauty in this step) Yuv convert h264, x264 achieve H264 convert rtmp stream, libxrtmp achieve
Platform: |
Size: 14661632 |
Author: wangyaning |
Hits:
Description: 学习opencv的课后习题3~5章。纯C版本，配置是2.4.9+vs2010-Chapter three or four answers to exercises after class（OPENCV）
Platform: |
Size: 12288 |
Author: zz |
Hits:
Description: 基于opencv的去噪算法比较以及霍夫变换，另外有3篇有关去噪以及图像识别类的相关文献-Compare opencv based de-noising algorithm and Hough transform, and a further three relevant literature on denoising and image recognition class
Platform: |
Size: 14721024 |
Author: jerry |
Hits:
Description: 基于opencv的手势识别
1、hog : hog特征提取
2、hogTainer ： 样本训练，利用了SVM方式
3、gestureRecognition ： 手势识别，利用了训练得出的线性分类器进行识别分类
训练样本在hog文件夹中，对应gesture_a到gesture_e ，五种手势-Gesture recognition 1, hog: hog feature extraction 2, hogTainer: sample training, the use of SVM mode 3, gestureRecognition: gesture recognition using training resulting linear classifier for recognition and classification of training samples in hog folder corresponding to gesture_a gesture_e, five kinds of gestures
Platform: |
Size: 13327360 |
Author: BoYK |
Hits:
Description: opencv
def random_color(random):
Return a random color
icolor = random.randint(0, 0xFFFFFF)
return cv.Scalar(icolor & 0xff, (icolor >> 8) & 0xff, (icolor >> 16) & 0xff)
if __name__ == __main__ :
# some constants
width = 1000
height = 700
window_name = Drawing Demo
number = 100
delay = 5
line_type = cv.CV_AA # change it to 8 to see non-antialiased graphics
# create the source image
image = cv.CreateImage( (width, height), 8, 3)
# create window and display the original picture in it
cv.NamedWindow(window_name, 1)
cv.SetZero(image)
cv.ShowImage(window_name, image)
# create the random number
random = Random().....To Be continued-opencv
def random_color(random):
Return a random color
icolor = random.randint(0, 0xFFFFFF)
return cv.Scalar(icolor & 0xff, (icolor >> 8) & 0xff, (icolor >> 16) & 0xff)
if __name__ == __main__ :
# some constants
width = 1000
height = 700
window_name = Drawing Demo
number = 100
delay = 5
line_type = cv.CV_AA # change it to 8 to see non-antialiased graphics
# create the source image
image = cv.CreateImage( (width, height), 8, 3)
# create window and display the original picture in it
cv.NamedWindow(window_name, 1)
cv.SetZero(image)
cv.ShowImage(window_name, image)
# create the random number
random = Random().....To Be continued
Platform: |
Size: 1024 |
Author: Phindx |
Hits:
Description: Python script to detect faces. It uses two haar cascade trained to recognise faces and eyes. The haar cascade are included. In uses OpenCV so it is required.
The script is written in Python 3.
Platform: |
Size: 189440 |
Author: Magre94 |
Hits:
Description: 需要说明的是：本文示例图中的目标状态在计算上是最快捷的，首先取数很方便，一般地查看目标在第i个位置上的值，则需要访问数组goal[i]，而这里goal[i]==i，故而无需访问数组；第二，要想知道数码n的目标位置，则需要找到goal[i]==n，然后row=i/3,col=i%3. 但是这里的话，row=n/3,col=n%3. 当我们用8位无符号整型来表示各个数码值(0~8)时，n/3和n%3操作是非常快的，比访问数组还快。
程序还提供一种玩游戏模式，即用户自己通过W,S,A,D四个键分别控制空格往上、下、左、右四个方向移动一步，功能很简单，界面部分是用OpenCV做的。界面部分和搜索部分是完全分离的，demo文件中main函数部分显示了如何将它们组合使用。(Need explanation is: This paper sample figure in the target state is the most efficient in calculation, the first number is very convenient, generally view the targets in the I position on the value, requires access to an array of goal[i], where goal[i]==i, therefore no need to access the array; second, to know the digital n the position of the target, you need to find goal[i]==n, row=i/3 and col=i%3., but here, row=n/3, col=n%3. when we use 8 bit unsigned integer to the digital value (0~8), n/3 and n%3 operations are very fast, faster than accessing array.
Program also provides a play game mode, that is, users themselves through W, S, A, D, four keys, respectively, control space, up, down, left, right four directions move a step, the function is very simple, the interface part is done with OpenCV. The interface section is completely separate from the search section, and the main function section in the demo file shows how to combine them.)
Platform: |
Size: 466944 |
Author: llii
|
Hits:
«
1
2
...
26
27
28
29
30
31»