荘の学習メモ

1. Power on Intel RTF ( Do not change wifi setting ) 2. PC connect to wifi named: AERO -xxxxxx 3. Revise PC's IP address in qgc.conf file ( /etc/mavlink-router/config.d ) 4. Restart the router 5. Open QGroundControl and follow the calibration steps as tips cd /Downloads chmod +x ./QGroundControl.AppImage ./QGroundControl.AppImage

1. Turned off Fast Boot in UEFI (Press Delete button) 2. Replace "quiet splash" with nomodeset 3. Install nvidia driver sudo add-apt-repositorty ppa:graphics-drivers/ppa sudo app-get update sudo app-get install nvidia-387 Reference: (1)  https://askubuntu.com/questions/949496/installing-ubuntu-16-04-on-msi-ge72mvr-system-freezes-when-i-restart (2)  https://ubuntuforums.org/showthread.php?t=2389372 (3)  https://www.tecmint.com/install-nvidia-drivers-on-ubuntu/

1. Installation (1) Install the dependencies (2) Clone the DronecodeSDK repository (3) Checkout the release/branch (4) Update the submodules: (5) Build the (debug) C++ library (6) System-wide Install make clean #REQUIRED! make default sudo make default install # sudo required to install files to system directories! # First installation only sudo ldconfig # update linker cache *Head files and library path: /usr/local Reference: https://sdk.dronecode.org/en/contributing/build.html 2. Building the Examples (1) cd /home/DronecodeSDK Ex: cd example/takeoff_and_land/ mkdir build && cd build cmake .. make 3. Build project in Nsight for simulation (1) Setting head files and library path (2) Copy source code of example: takeoff_and_land offboard_velocity to Main.cpp (3) Revise communication part:  connection_url = "udp://:14540"; (4) Setting up a simulator Ex: jMAVSim (pre-installation is needed: jMAVSim/Gazebo Simulation...

1. 使用reVISION (xfOpenCV library) 若要用Stereo vision sample, 需有ZCU 102 / ZCU 104. Reference: (1)  使用Xilinx SDSoc在Xilinx zcu102开发板上编程HelloWorld (2)  Xilinx SDSoc 加载opencv库 2. 自定義加速函式 Reference:  xilinx_embedded_vision_acceleration 3. 使用OpenCV library (待測試...) Reference: (1)  SDx+yocto+OpenCV3.1+FPGA (2)  想在SDSoC中用OpenCV搞事情？来，用Zybo-Z7传授你入门秘籍！ 4. 於FPGA board 建構linux作業系統 Reference: (1)  CH01基于Ubuntu系统的ZYNQ-7000开发环境的搭建 (2)  CH02基于ZYNQ的嵌入式LINUX移植

記錄從raw image到depth map的工具及步驟。 (目的: 得到像直接使用ZED Camera SDK一樣的校正後影像及深度圖) [MATLAB (Stereo camera calibration)] 事先準備好左右相機的各角度拍攝校正板之影像，輸入APP即可得到Camera Matrix。 Reference:  Image Acquisition Toolbox  (可用來開啟XIMEA Camera) ステレオ キャリブレーション アプリ stereoCameraCalibrator Camera Calibration Toolbox for Matlab [OpenCV] Step1: Capture and save raw L/R images with chessboard in a folder. Step2: Calibration. Reference: Capture image , (1) StereoCapture.cpp Save image stereocalibrate.cpp (2) zed-opencv-native [Sum up of calibrating a XIMEA stereo camera] 1. Capture and save raw L/R images with chessboard in a folder. (nsight: Camera_realtime project) 2. Open Matlab input: stereoCameraCalibrator 3. Choose L/R images path and chessboard width (ex:23mm) 4. Click calibrate 5. Click Export camera parameter -> generate MATLAB script *Command: " cameraCalibrator" for single camera calibration

Resource:  http://www.cg.com.tw/3dsMax/ 快捷鍵：Alt + W 將視圖最大化， Alt +滑鼠中鍵移動可旋轉視圖 1. Attach Reference:  combine objects in 3D Studio Max 2. ProBoolean Reference:  如何在Poly模型上產生方洞和圓洞 3. 建立補面 Reference:  polygon的三種補面的方式 4. modifier Reference:  https://www.youtube.com/results?search_query=3ds+max+modifier 5. Align Reference:  Align(對齊工具) 講解 6. Slice plane Reference:  Slice Plane Tutorial 7. Extrude 可用2D平面圖來長出3D立體物件 8. 改變物件坐標軸位置 Reference:  How to reset Pivot Point to center of object in 3DS Max

最重要:  SLAM 完整學習資源 Triangulation 1.  OpenCVの三角測量関数『cv::triangulatepoints』 2.  slambook/ch7/triangulation.cpp Depth map 1.  disparity-map 2.  lsd-slam源码解读第五篇:DepthEstimation 3.  StereoBM 4.  Stereo_Matcher Pnp 1.  slambook/ch7/pose_estimation_3d2d.cpp SFM 1..  Robotic Vision : Sensors, Localization and Control 2.  ORB-SLAM代码详解之SLAM系统初始化 3.  SFM三维重建源码（Matlab）