2023初探DSO-SLAM

1. 安装系统必须为Ubuntu-16.04.7（亲测Ubuntu 18.04.6和Ubuntu22.04编译失败）

地址：http://mirrors.zju.edu.cn/ubuntu-releases/16.04/

硬盘设置100G

2. 换源

ubuntu换镜像源（ubuntu换源）_Fighting_1997的博客-CSDN博客

3. sudo apt update

4. 下载dso： git clone https://github.com/NikolausDemmel/dso

5. 安装suitesparse and eigen3： sudo apt-get install libsuitesparse-dev libeigen3-dev

6. 安装opencv： sudo apt-get install libopencv-dev

7. 退回主页，安装pangolin

cd

git clone https://github.com/stevenlovegrove/Pangolin.git -b v0.6

cd Pangolin

mkdir build

cd build

cmake -DCPP11_NO_BOOST=1 ..

make-j

make-j闪退的时候换make

8. sudo apt install libglew-dev

安装ziplib. 建议安装，DSO用这个库来解压读取数据集压缩包中的图片，这样就不要每次都把下再的图片数据集进行解压了。

sudo apt-get install zlib1g-dev

cd thirdparty #找到DSO所在文件路径，切换到thirdparty文件夹下

tar -zxvf libzip-1.1.1.tar.gz

cd libzip-1.1.1/

./configure

make

sudo make install

sudo cp lib/zipconf.h /usr/local/include/zipconf.h

10. 编译DSO.

cd /home/hyj/DSO/dso

mkdir build

cd build

cmake ..

make -j

碰到错误

could not find boost

sudo apt install libboost-all-dev

编译成功bin目录下会有dso_dataset

a@ubuntu:~/dso/build/bin$ ls

dso_dataset

a@ubuntu:~/dso/build$ cmake ..
-- Boost version: 1.58.0
-- Found the following Boost libraries:
--   system
--   thread
--   chrono
--   date_time
--   atomic
--- found PANGOLIN, compiling dso_pangolin library.
--- found OpenCV, compiling dso_opencv library.
--- found ziplib (1.1.1), compiling with zip capability.
--- compiling dso_dataset.
-- Configuring done
-- Generating done
-- Build files have been written to: /home/a/dso/build
a@ubuntu:~/dso/build$ make
[  4%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/FullSystem.cpp.o
[  8%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/FullSystemOptimize.cpp.o
[ 12%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/FullSystemOptPoint.cpp.o
[ 16%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/FullSystemDebugStuff.cpp.o
[ 20%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/FullSystemMarginalize.cpp.o
[ 24%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/Residuals.cpp.o
[ 28%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/CoarseTracker.cpp.o
[ 32%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/CoarseInitializer.cpp.o
[ 36%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/ImmaturePoint.cpp.o
[ 40%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/HessianBlocks.cpp.o
[ 44%] Building CXX object CMakeFiles/dso.dir/src/FullSystem/PixelSelector2.cpp.o
[ 48%] Building CXX object CMakeFiles/dso.dir/src/OptimizationBackend/EnergyFunctional.cpp.o
[ 52%] Building CXX object CMakeFiles/dso.dir/src/OptimizationBackend/AccumulatedTopHessian.cpp.o
[ 56%] Building CXX object CMakeFiles/dso.dir/src/OptimizationBackend/AccumulatedSCHessian.cpp.o
[ 60%] Building CXX object CMakeFiles/dso.dir/src/OptimizationBackend/EnergyFunctionalStructs.cpp.o
[ 64%] Building CXX object CMakeFiles/dso.dir/src/util/settings.cpp.o
[ 68%] Building CXX object CMakeFiles/dso.dir/src/util/Undistort.cpp.o
[ 72%] Building CXX object CMakeFiles/dso.dir/src/util/globalCalib.cpp.o
[ 76%] Building CXX object CMakeFiles/dso.dir/src/IOWrapper/OpenCV/ImageDisplay_OpenCV.cpp.o
[ 80%] Building CXX object CMakeFiles/dso.dir/src/IOWrapper/OpenCV/ImageRW_OpenCV.cpp.o
[ 84%] Building CXX object CMakeFiles/dso.dir/src/IOWrapper/Pangolin/KeyFrameDisplay.cpp.o
[ 88%] Building CXX object CMakeFiles/dso.dir/src/IOWrapper/Pangolin/PangolinDSOViewer.cpp.o
[ 92%] Linking CXX static library lib/libdso.a
[ 92%] Built target dso
Scanning dependencies of target dso_dataset
[ 96%] Building CXX object CMakeFiles/dso_dataset.dir/src/main_dso_pangolin.cpp.o
[100%] Linking CXX executable bin/dso_dataset
[100%] Built target dso_dataset
a@ubuntu:~/dso/build$ ls
bin  CMakeCache.txt  CMakeFiles  cmake_install.cmake  lib  Makefile
a@ubuntu:~/dso/build$ cd bin
a@ubuntu:~/dso/build/bin$ ls
dso_dataset

11.

4.在TUM单目数据集上运行DSO

下载TUM单目数据集请到https://vision.in.tum.de/data/datasets/mono-dataset?redirect=1下载你所需要的zip包，我下载的是sequence_14，根据需要自行下载。下载好把zip包放到dso的bin目录下并解压，我的是

➜ bin git:(master) pwd

/home/zpq/dso_pkg/dso/build/bin

➜ bin git:(master) unzip sequence_14.zip

在bin目录下运行启动数据集：

./dso_dataset files=./sequence_14/images.zip calib=./sequence_14/camera.txt gamma=./sequence_14/pcalib.txt vignette=./sequence_14/vignette.png preset=0 mode=0

参考视频和博客：

https://www.bilibili.com/video/BV1wo4y1S71s/?spm_id_from=333.999.0.0

DSO 初探_白巧克力亦唯心的博客-CSDN博客

初探DSO-SLAM并运行dso_ros_回忆是本书的博客-CSDN博客_dso slam

[学习SLAM]编译安装DSO并在线运行摄像头_苏源流的博客-CSDN博客_dso tum