Fast and Robust Initialization for Visual-Inertial SLAM
This work addresses the initialization challenge in visual-inertial SLAM for robotics and AR/VR applications, but it is incremental as it builds on prior methods.
The paper tackles the problem of initializing visual-inertial SLAM by improving an existing method to be more general, efficient, and robust, resulting in scale errors reduced from up to 156% to around 5% in under two seconds and further to less than 1% after ten seconds.
Visual-inertial SLAM (VI-SLAM) requires a good initial estimation of the initial velocity, orientation with respect to gravity and gyroscope and accelerometer biases. In this paper we build on the initialization method proposed by Martinelli and extended by Kaiser et al. , modifying it to be more general and efficient. We improve accuracy with several rounds of visual-inertial bundle adjustment, and robustify the method with novel observability and consensus tests, that discard erroneous solutions. Our results on the EuRoC dataset show that, while the original method produces scale errors up to 156%, our method is able to consistently initialize in less than two seconds with scale errors around 5%, which can be further reduced to less than 1% performing visual-inertial bundle adjustment after ten seconds.