L. Gao, J. Su, J. Cui, X. Zeng, X. Peng, and L. Kneip. Efficient globally-optimal correspondence-less visual odometry for planar ground vehicles. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Paris, France, May 2020
In this video, we present our ICRA'20 contribution on visual odometry with planar ground vehicles. The platform is equipped with a downward-facing camera, and thus observes noisy texture with substantial image-to-image optical flow. This scenario complicates the matching of frame-to-frame correspondences. Our correspondence-less solution reliably tracks the vehicle throughout entire sequences and produces globally optimal results using the branch-and-bound algorithm.
Link to arxiv: https://arxiv.org/abs/2203.00291
Link to our lab's webpage: http://mpl.sist.shanghaitech.edu.cn
