Features
Features:

Product Tour >

Edraw AI >

Paid Plans:

Individuals >

Business >

Eduaction >
Resources
Blog

History

How-tos & Tips

Discovery

Biography

Business Analysis

Examples

AI concept Map

Free AI Mind Map Generator

Onenote Mind Map

Bcg Matrix Examples

Nike Marketing Strategy

Unilever SWOT Analysis

Make Mind Maps in Google Docs

Guide

FAQs

What's New

Resource Center
Templates
All Templates

Brain Storming Templates

Strategy and Planning Templates

Project Management Templates

Product Management Templates

Human Resources Templates

Agile Workflow Templates

Marketing Templates

Education Templates

Fun and Games Templates

User Gallery
Download
Pricing
Enterprise

MindMap Gallery The mind map of int_main

The mind map of int_main

This is a clear mind map of int_main, which mainly explains loading image related information, creating a monocular system, reading images, etc. Each content is further divided into several levels for explanation. A mind map is a visual thinking tool that is presented through the radioactive structure of a central idea or problem. It consists of themes, branches, and keywords, aiming to mimic the neural network structure of the human brain. This graphical approach helps promote memory, organize information, and stimulate creativity.

Edited at 2022-05-31 15:01:52

708842407@qq.com

Recent works View more works>>

The mind map of int_main
This is a clear mind map of int_main, which mainly explains loading image related information, creating a monocular system, reading images, etc. Each content is further divided into several levels for explanation. A mind map is a visual thinking tool that is presented through the radioactive structure of a central idea or problem. It consists of themes, branches, and keywords, aiming to mimic the neural network structure of the human brain. This graphical approach helps promote memory, organize information, and stimulate creativity.

The mind map of int_main

708842407@qq.com

Recent works View more works>>

The mind map of int_main
This is a clear mind map of int_main, which mainly explains loading image related information, creating a monocular system, reading images, etc. Each content is further divided into several levels for explanation. A mind map is a visual thinking tool that is presented through the radioactive structure of a central idea or problem. It consists of themes, branches, and keywords, aiming to mimic the neural network structure of the human brain. This graphical approach helps promote memory, organize information, and stimulate creativity.

Recommended to you
Outline

40k classes
- 2.4k
- 4
- 1
Oliveettom
Cisco IOS interface
- 691
- 6
Roy Mustang
application development and deployment
- 1.1k
- 18
- 2
Roy Mustang
Data Sanitization Tools
- 468
- 4
Roy Mustang
DATA COLLECTION MEASURES
- 779
- 6
- 1
Roy Mustang
Android
- 534
- 2
- 1
Roy Mustang
Java Training
- 2.0k
- 19
- 3
Roy Mustang
Active reading techniques
- 696
- 5
- 3
Study Smarter
Classification of visual languages
- 447
- 3
Study Smarter
Game Theory
- 1.8k
- 18
- 2
Fiona_

int main( ) (mono_tum.cc)

LoadImages() 载入图像相关信息

LoadImages(strFile, vstrImageFilenames, vTimestamps)

ORB_SLAM2::System SLAM（）创建一个单目系统

ORB_SLAM2::System SLAM(argv[1],argv[2],ORB_SLAM2::System::MONOCULAR,true) 创建一个单目的SLAM系统，并将yaml中的参数输入各个变量*

创建mpVocabulary

创建mpKeyFrameDatabase

创建mpMap

创建mpFrameDrawer

创建mpMapDrawer

创建mpTracker

mpTracker = new Tracking(this, mpVocabulary, mpFrameDrawer, mpMapDrawer, mpMap, mpKeyFrameDatabase, strSettingsFile, mSensor); 1.yaml中参数导入：相机参数、ORB特征提取参数、 2.创建 ORB特征提取对象 mpORBextractorLeft、mpIniORBextractor ORBextractor构造函数：计算各层金字塔尺度因子、每层金字塔特征点数量，及为提取特征点做准备

创建mpLocalMapper 启动线程

创建mpLoopCloser 启动线程

创建mpViewer 启动线程

cv::imread（）读取图片

SLAM.TrackMonocular(im,tframe) 用该接口即可完成SLAM系统的更新

计算时间

循环执行

SLAM.TrackMonocular(im,tframe) 用该接口即可完成SLAM系统的更新（->System.cc）

check mode change（定位模式是否激活）

check reset

cv::Mat Tcw =mpTracker->GrabImageMonocular(）最重要部分（->Tracking.cc）

// 输入左目RGB或RGBA图像 // 输出世界坐标系到该帧相机坐标系的变换矩阵 cv::Mat Tcw = mpTracker->GrabImageMonocular(im,timestamp);

1.图像转为mImGray

2.构造Tracking::mCurrentFrame (->Frame.cc)

//mState初始值NO_IMAGES_YET mpIniORBextracto的特征点数为mpORBextractorLeft的2倍 if(mState==NOT_INITIALIZED || mState==NO_IMAGES_YET) mCurrentFrame = Frame(mImGray,timestamp,mpIniORBextractor,mpORBVocabulary,mK,mDistCoef,mbf,mThDepth); else mCurrentFrame = Frame(mImGray,timestamp,mpORBextractorLeft,mpORBVocabulary,mK,mDistCoef,mbf,mThDepth);

ExtractORB(0,imGray) 提取特征点和描述子

1.计算图像金字塔 void ORBextractor::ComputePyramid(image) 2.提取图像金字塔中各层图像的特征点（allKeypoints）及方向（keypoint->angle） void ORBextractor:: ComputeKeyPointsOctTree(allKeypoints); keypoints = DistributeOctTree(vToDistributeKeys, minBorderX, maxBorderX, minBorderY, maxBorderY,mnFeaturesPerLevel[level], level);未学习 3.遍历高斯金字塔每层，计算其提取出的关键点的描述子储存在descriptors里 computeDescriptors(workingMat, keypoints, desc, pattern); 4. 对关键点的位置坐做尺度恢复，恢复到原图的位置

UndistortKeyPoints() 对特征点位置去畸变

ComputeImageBounds(imGray) 计算去畸变后的图像边界（仅第一帧执行）

AssignFeaturesToGrid() 将特征点分配到图像网格中

3.Track() 跟踪线程

初始化 MonocularInitialization() 更新绘图线程mpFrameDrawer->Update( ）

1、创建单目初始化器 mpInitializer 2、查找初始帧F1和第二帧F2的匹配点,返回匹配点数 nmatches=matcher.SearchForInitialization(...） 3、通过H模型或F模型进行单目初始化，得到两帧间相对运动 Rcw, tcw（最关键） mpInitializer->Initialize(...) ??? 4、初始地图点 CreateInitialMapMonocular(); ??? mState=OK 后续将执行跟踪

跟踪

返回Tcw