Using visual odometry with viso2

In order to use viso2, go to your catkin workspace (~/dev/catkin_ws) and use the following commands:

$ cd src
$ wstool init
$ wstool set viso2 --git git://github.com/srv/viso2.git
$ wstool update

Now, to build it, run the following command:

$ cd ..
$ catkin_make

Once it is built, we set up our environment by using the following command:

$ source devel/setup.bash

Now we can run viso2_ros nodes, such as stereo_odometer, which is the one we are going to use here. But before that, we need to publish the frame transformation between our camera and the robot or its base link. The stereo camera driver is already prepared for that, but we have explained how it is done in the next sections.

Camera pose calibration

In order to set the transformation between the different frames in our robot system, we must publish the TF message of such transforms. The most appropriate and generic way to do so consists of using the camera_pose stack; we use the latest version from this...