Shulou(Shulou.com)06/01 Report--

This article mainly introduces the relevant knowledge of "how to build a SVO-SLAM environment quickly". The editor shows you the operation process through an actual case. The operation method is simple, fast and practical. I hope this article "how to build a SVO-SLAM environment quickly" can help you solve the problem.

First, set up a working directory such as workspace, and then put everything you need below in that directory.

(tip: never use a Chinese name, even though your system is the default Chinese name. Otherwise, the following dependencies will be very difficult, and cmake cannot find the configuration file.)

Mkdir workspacecd workspace

Boost-C++ Librairies (thread and system are needed)

Sudo apt-get install libboost-all-dev

Eigen 3-Linear algebra

Apt-get install libeigen3-dev

OpenCV-Computer vision library for loading and displaying images (I downloaded OpenCV3.0)

Mkdir buildcd buildcmake.. make

Sophus-Lie groups

Cd workspacegit clone https://github.com/strasdat/Sophus.gitcd Sophusgit checkout a621ffmkdir buildcd buildcmake.. make

If you encounter "unit_complex*.imag () = 0." You need to change the code to "unit_complex*.imag (0.)" Fast-Corner Detector

Cd workspacegit clone https://github.com/uzh-rpg/fast.gitcd fastmkdir buildcd buildcmake.. make

G2o-General Graph Optimization OPTIONAL is patient and careful. The dependencies of each version of G2O are very complex and need to be patient to read the version number. Otherwise, a lot of mistakes will be lost. I also read a lot of blogs on the Internet before, but I didn't really solve the problem of dependencies. Below I sort out the process I have done, the complete and correct version.

First install the dependencies of G2o

Sudo apt-get install cmake libeigen4-dev libsuitesparse-dev, qt4-qmake libqglviewer-dev libsuitesparse-dev libcxsparse3.1.2 libcholmod-dev

Then download, compile, etc.:

Cd workspacegit clone https://github.com/RainerKuemmerle/g2o.gitcd g2omkdir buildcd buildcmake.. makesudo make install

Vikit_common-Some useful tools that we need vikit contains the camera model, some mathematical and interpolation functions required by SVO.

Cd workspacegit clone https://github.com/uzh-rpg/rpg_vikit.git

Set USE_ROS to FALSE in the pg_vikit/vikit_common/CMakeLists.txt file.

Cd rpg_vikit/vikit_commonmkdir buildcd buildcmake.. make

SVO

Cd workspacegit clone https://github.com/uzh-rpg/rpg_svo.gitcd rpg_svo/svo

In the file svo/CMakeLists.txt, set USE_ROS to FALSE.

Mkdir buildcd buildcmake.. make

Run SVO without ROS first, create a folder to store the data:

Mkdir Datasets

Then set an environment variable to store the path

Export SVO_DATASET_DIR=$ {HOME} / Datasets

Execute the script .bashrc, then go to the new folder to download the test data

Source ~ / .bashrccd ${SVO_DATASET_DIR} wget http://rpg.ifi.uzh.ch/datasets/sin2_tex2_h2_v8_d.tar.gz-O-| tar-xz

Then run SVO on the test data:

This is the end of cd svo/bin./test_pipeline 's content on "how to build a SVO-SLAM environment quickly". Thank you for reading. If you want to know more about the industry, you can follow the industry information channel. The editor will update different knowledge points for you every day.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.