How to use image data set to simulate a camera input for libviso2/ viso2_ros ?

edit

Hi everyone

I am new to ROS Indigo and am trying to work with the libviso2/ viso2_ros package for visual odometery. I have a fair enough idea as to how to use the package/node with a camera, but I have little idea as to how to make it work with pre-collected dataset of images. The datasets I am trying to experiment with are any of these. Libviso2 looks for a rectified camera image.

Please let me know if any other information is needed. Any help would be greatly appreciated.