I plan to implement a sensor fusion of IMU + Visual odometry using an EKF. I came across the excellent robot_localization package which does pretty much all that I want. However, I need to use perform my task without using ROS, and work in an offline setting, where I have a dump of my IMU and Visual odometry data timestamped. Is there a way to use the package as a library, by calling functions as APIs? How would I go about it, has it been done?
If not, are there any alternatives that fuse IMU + visual odometry data using an EKF or a UKF? I ideally wish to code in Python, however I am comfortable in C++ as well.