The latest is orb-slam2, which supports monocular, binocular, and rgb-d interfaces.
Install prerequisite software: For convenience. It is best to download the library first under Windows (note the download version of this). Not mounted on system disk
(1) Update APT library
sudo apt-get update
(2) Install Git
sudo apt-get install git
(3) Installation CMake
sudo apt-get install CMake
(4) Install Pangolin (for visualization and user interface: Visualization and UI)
Understanding Pangolin URL: Https://github.com/stevenlovegrove/Pangolin
Installation dependencies:
A, OpenGL:
B, Glew:
sudo apt-get install Libglew-dev
C, Boost:
sudo apt-get install Libboost-dev libboost-thread-dev Libboost-filesystem-dev
D, Python2/python3:
sudo apt-get install Libpython2.7-dev
E, compile the base library
sudo apt-get install build-essential
Input in terminal
CD Pangolinmkdir build
CD Build
cmake-dcpp11_no_boost=1.
Make-j
(Make-j is not recommended for use with make.) If you use MAKE-J to compile with multiple processors, you may cause a panic.
(5) Installing OPENCV (manipulate images and features: Manipulating images and feature points)
Installation dependencies:
A, compiler Related:
sudo apt-get install build-essential
B, must rely on:
sudo apt-get install cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev
C, optional installation:
sudo apt-get install Python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libjasper-dev libdc139 4-22-dev
Install OpenCV:
A, website download OpenCV 2.4.11 for linux download address, extract into Ubuntu
B, into the OpenCV folder, configure the project
mkdir release
cd
cmake-d cmake_build_type=release-d cmake_install_prefix=/usr/local ...
C, compiling
Make
sudo make install
(6) Install Eigen (We use modified versions the THEDBOW2 library to perform place recognition--for location identification ANDG2O Library to Perfor M non-linear optimizations--for nonlinear optimization. Both modified libraries (which are BSD) are included in Thethirdparty folder.)
Download the Eigen download address and go to the Eigen folder (for example, EIGEN-EIGEN-07105F7124F9) after the decompression
mkdir build
CD Build
cmake.
Make
sudo make install
(7) Installing BLAS and lapack libraries
sudo apt-get install libblas-dev
sudo apt-get install Liblapack-dev
ROS (optional)We provide some examples to process the live input of a monocular, stereo or rgb-d camera. Building these examples are optional. In case you are want to use ROS, a version Hydro or newer is needed.
In fact, build.sh is the front of the Third-party Library compiled +orb_slam2 compiled, you can write a similar terminal command script, you do not need every time to compile the hand to knock. If you find that the compilation error, try to GitHub or the official online git clone source code, there are a lot of issus available for reference.
3. Install Orb_slam:
(1) Clone the repository:
git clone https://github.com/raulmur/ORB_SLAM2.git orb_slam2
(2) Compile: We provide a script build.sh to build a third-party library and orb-slam2. Make sure that you have all the required dependencies installed
CD orb_slam2
chmod +x build.sh./build.sh
Orb-slam2 the problem with the last compilation
Coercion type conversion problem
error message:
/home/melanie/tools/eigen/eigen/src/core/assignevaluator.h:817:3: Error:static Assertion Failed:you_mixed_ different_numeric_types__you_need_to_use_the_cast_method_of_matrixbase_to_cast_numeric_types_explicitly EIGEN_ Check_binary_compatibiliy (Func,typename actualdsttypecleaned::scalar,typename Src::Scalar); ^ Cmakefiles/orb_slam2.dir/build.make:350:recipe for target ' CMAKEFILES/ORB_SLAM2.DIR/SRC/OPTIMIZER.CC.O ' failed MAKE[2]: * * * [CMAKEFILES/ORB_SLAM2.DIR/SRC/OPTIMIZER.CC.O] Error 1 cmakefiles/makefile2:178:recipe for Target ' Cmakefiles/orb_slam2.dir/all ' failed make[1]: * * * * [Cmakefiles/orb_slam2.dir/all] Error 2 MAKEFILE:83:RECIP