opencv2.4.4 背景减除算法收集
算法集合:https://code.google.com/p/bgslibrary/
测试:AdaptiveBackgroundLearning算法
#include <iostream>
#include <opencv/highgui.h>
#include <opencv/cv.h>
#include "AdaptiveBackgroundLearning.h" int main(int argc, char **argv)
{
CvCapture *capture = 0;
int resize_factor = 100; if(argc > 1)
{
std::cout << "Openning: " << argv[1] << std::endl;
capture = cvCaptureFromAVI(argv[1]);
}
else
{
capture = cvCaptureFromCAM(0);
resize_factor = 50; // set size = 50% of original image
} if(!capture)
{
std::cerr << "Cannot initialize video!" << std::endl;
return 1;
} IplImage *frame_aux = cvQueryFrame(capture);
IplImage *frame = cvCreateImage(cvSize((int)((frame_aux->width*resize_factor)/100) , (int)((frame_aux->height*resize_factor)/100)), frame_aux->depth, frame_aux->nChannels);
cvResize(frame_aux, frame); /* Background Subtraction Methods */ /*** Default Package ***/
//bgs = new FrameDifferenceBGS;
//bgs = new StaticFrameDifferenceBGS;
//bgs = new WeightedMovingMeanBGS;
//bgs = new WeightedMovingVarianceBGS;
//bgs = new MixtureOfGaussianV2BGS;
//bgs = new MixtureOfGaussianV2BGS;
//bgs = new AdaptiveBackgroundLearning;
IBGS *bgs;
bgs= new AdaptiveBackgroundLearning; /*** DP Package (adapted from Donovan Parks) ***/
//bgs = new DPAdaptiveMedianBGS;
//bgs = new DPGrimsonGMMBGS;
//bgs = new DPZivkovicAGMMBGS;
//bgs = new DPMeanBGS;
//bgs = new DPWrenGABGS;
//bgs = new DPPratiMediodBGS;
//bgs = new DPEigenbackgroundBGS;
//bgs = new DPTextureBGS; /*** TB Package (adapted from Thierry Bouwmans) ***/
//bgs = new T2FGMM_UM;
//bgs = new T2FGMM_UV;
//bgs = new T2FMRF_UM;
//bgs = new T2FMRF_UV;
//bgs = new FuzzySugenoIntegral;
//bgs = new FuzzyChoquetIntegral; /*** JMO Package (adapted from Jean-Marc Odobez) ***/
//bgs = new MultiLayerBGS; /*** PT Package (adapted from Hofmann) ***/
//bgs = new PixelBasedAdaptiveSegmenter; /*** LB Package (adapted from Laurence Bender) ***/
//bgs = new LBSimpleGaussian;
//bgs = new LBFuzzyGaussian;
//bgs = new LBMixtureOfGaussians;
//bgs = new LBAdaptiveSOM;
//bgs = new LBFuzzyAdaptiveSOM; /*** LBP-MRF Package (adapted from Csaba Kertész) ***/
//bgs = new LbpMrf; /*** AV Package (adapted from Antoine Vacavant) ***/
//bgs = new VuMeter; /*** EG Package (adapted from Ahmed Elgammal) ***/
//bgs = new KDE; int key = 0;
while(key != 'q')
{
frame_aux = cvQueryFrame(capture);
if(!frame_aux) break; cvResize(frame_aux, frame); cv::Mat img_input(frame);
cv::imshow("input", img_input); cv::Mat img_mask;
cv::Mat img_bkgmodel;
bgs->process(img_input, img_mask, img_bkgmodel); // automatically shows the foreground mask image
//imshow("img_mask",img_mask);
//imshow("img_bkgmodel",img_bkgmodel);
if(!img_mask.empty())
imshow("img_mask",img_mask);
// do something key = cvWaitKey(33);
} delete bgs; cvDestroyAllWindows();
cvReleaseCapture(&capture); return 0;
}
配置文件background.vcxproj
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|Win32">
<Configuration>Debug</Configuration>
<Platform>Win32</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|Win32">
<Configuration>Release</Configuration>
<Platform>Win32</Platform>
</ProjectConfiguration>
</ItemGroup>
<ItemGroup>
<ClCompile Include="AdaptiveBackgroundLearning.cpp" />
<ClCompile Include="GMG.cpp" />
<ClCompile Include="main4.cpp" />
</ItemGroup>
<ItemGroup>
<ClInclude Include="AdaptiveBackgroundLearning.h" />
<ClInclude Include="GMG.h" />
<ClInclude Include="IBGS.h" />
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{C9F9AAD6-4C2A-414F-ADBE-891F28F9E32F}</ProjectGuid>
<Keyword>Win32Proj</Keyword>
<RootNamespace>background</RootNamespace>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
<ConfigurationType>Application</ConfigurationType>
<UseDebugLibraries>true</UseDebugLibraries>
<CharacterSet>Unicode</CharacterSet>
<UseOfMfc>false</UseOfMfc>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
<ConfigurationType>Application</ConfigurationType>
<UseDebugLibraries>false</UseDebugLibraries>
<WholeProgramOptimization>true</WholeProgramOptimization>
<CharacterSet>Unicode</CharacterSet>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
</ImportGroup>
<ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
<Import Project="opencv_d.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<LinkIncremental>true</LinkIncremental>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<LinkIncremental>false</LinkIncremental>
</PropertyGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<ClCompile>
<PrecompiledHeader>
</PrecompiledHeader>
<WarningLevel>Level3</WarningLevel>
<Optimization>Disabled</Optimization>
<PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<GenerateDebugInformation>true</GenerateDebugInformation>
<AdditionalLibraryDirectories>%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
<AdditionalDependencies>%(AdditionalDependencies)</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PrecompiledHeader>
</PrecompiledHeader>
<Optimization>MaxSpeed</Optimization>
<FunctionLevelLinking>true</FunctionLevelLinking>
<IntrinsicFunctions>true</IntrinsicFunctions>
<PreprocessorDefinitions>WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<GenerateDebugInformation>true</GenerateDebugInformation>
<EnableCOMDATFolding>true</EnableCOMDATFolding>
<OptimizeReferences>true</OptimizeReferences>
</Link>
</ItemDefinitionGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
</ImportGroup>
</Project>
注意:在可执行文件下要有config文件夹
效果如下:
1,摄像头

2,视频文件

opencv2.4.4 背景减除算法收集的更多相关文章
- 【计算机视觉】基于样本一致性的背景减除运动目标检测算法(SACON)
SACON(SAmple CONsensus)算法是基于样本一致性的运动目标检测算法.该算法通过对每个像素进行样本一致性判断来判定像素是否为背景. 算法框架图 由上图可知,该算法主要分为四个主要部分, ...
- PHP 经典有趣的算法收集(面试题)
1.一群猴子排成一圈,按1,2,…,n依次编号.然后从第1只开始数,数到第m只,把它踢出圈,从它后面再开始数,再数到第m只,在把它踢出去…,如此不停的进行下去,直到最后只剩下一只猴子为止,那只猴子就叫 ...
- 【计算机视觉】背景建模--Vibe 算法优缺点分析
一.Vibe 算法的优点 Vibe背景建模为运动目标检测研究邻域开拓了新思路,是一种新颖.快速及有效的运动目标检测算法.其优点有以下两点: 1.思想简单,易于实现.Vibe通常随机选取邻域20个样本为 ...
- 基于SNMP的路由拓扑发现算法收集
一.三层(网络层)发现 算法来源:王娟娟.基于SNMP的网络拓扑发现算法研究.武汉科技大学硕士学位论文,2008 数据结构: 待检路由设备网关链表:存放指定深度内待检路由设备的网关信息,处理后删除. ...
- js-数组算法收集版(转)
不管是在面试中还是在笔试中,我们都会被经常问到关于javascript数组的一些算法,比方说数组去重.数组求交集.数组扰乱等等.今天抽点时间把javascript中的一些常用的数组算法做一下总结,以方 ...
- 数据结构 + 算法 -> 收集
董的博客:数据机构与算法合集 背包问题应用(2011-08-26) 数据结构之红黑树(2011-08-20) 素数判定算法(2011-06-26) 算法之图搜索算法(一)(2011-06-22) 算法 ...
- 减治算法之寻找第K小元素问题
一.问题描写叙述 给定一个整数数列,寻找其按递增排序后的第k个位置上的元素. 二.问题分析 借助类似快排思想实现pation函数.再利用递归思想寻找k位置. 三.算法代码 public static ...
- asp中的md5/sha1/sha256算法收集
对于asp这种古董级的技术,这年头想找一些有用的资料已经不容易了,下面是一些常用的加密算法: md5 (将以下代码另存为md5.inc) <% Private Const BITS_TO_A_B ...
- Scala 大数据 常用算法收集
一:IP转数字,用于比大小,用在求IP段范围中 def ip2Long(ip: String): Long = { val fragments = ip.split("[.]") ...
随机推荐
- shell 后台执行命令
shell 后台执行命令方法: 1. nohup cmd & 后台会生成 nohup.out 文件 2.cmd >/路径/xx.log & 后台生成 xx. ...
- 小啃机器学习(1)-----ID3和C4.5决策树
第一部分:简介 ID3和C4.5算法都是被Quinlan提出的,用于分类模型,也被叫做决策树.我们给一组数据,每一行数据都含有相同的结构,包含了一系列的attribute/value对. 其中一个属性 ...
- MySQL Replication 常用架构
转自: http://www.cnblogs.com/ggjucheng/archive/2012/11/13/2768879.html 前言 MySQLReplicaion本身是一个比较简单的架构, ...
- json2.js使用参考
json2.js的源码地址: https://github.com/douglascrockford/JSON-js Visual Studio用户可以直接通过Nuget来获得. json2.js提供 ...
- Spark中shuffle的触发和调度
Spark中的shuffle是在干嘛? Shuffle在Spark中即是把父RDD中的KV对按照Key重新分区,从而得到一个新的RDD.也就是说原本同属于父RDD同一个分区的数据需要进入到子RDD的不 ...
- android下调试unity3d应用
原地址:http://blog.csdn.net/armoonwei/article/details/7032455 目前貌似不支持断点调试,但可以通过日志打印(logcat)来跟踪. 在androi ...
- Qt之启动外部程序(调用cmd.exe ping putty winscp 管道等等,比较牛叉)
http://blog.csdn.net/u011012932/article/details/50478833
- Android Paint中setTextSize
界面适配的时候发现Paint.setTextSize与TextView.setTextSize传入的单位不一致.Paint.setTextSize传入的单位是px,TextView.setTextSi ...
- Android 通过广播启动另一个应用的Activity
需求:现在有应用A和应用B,我需要在A应用中启动B应用中的某个Activity 实现:A应用中的Activity发送广播,关键代码如下: String broadcastIntent = " ...
- Memcache+Cookie解决分布式系统共享登录状态------------------------------Why Memcached?
每个用户请求向IIS发送一个请求,但IIS服务器的请求数有限,cpu支持的线程数有限,如果一秒钟向这台服务器发送10000次,那么则一般就会有问题,考虑集群, 请求数据分流,几台服务器共同对应一个公共 ...