Jump to Content
  1. Oxford
  2. MPLS
  3. Eng. Sci.
  4. ORI

Estimation, Search, and Planning (ESP) Research Group

ESP @ IROS 2020 — Occlusion-Robust MVO

ESP has three papers at IROS this year, which is being held virtually as an on-demand conference. All our work is already available and includes Kevin's most recent paper on occlusion-robust Multimotion Visual Odometry (MVO). You can watch a short video and his presentation about the work on YouTube and read the paper on arXiv.

  1. K. M. Judd
  2. J. D. Gammell
Occlusion-robust MVO: Multimotion estimation through occlusion via motion closure
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Digital Object Identifier (DOI)
doi: 10.1109/IROS45743.2020.9341355
Google Scholar
Google Scholar


Visual motion estimation is an integral and well-studied challenge in autonomous navigation. Recent work has focused on addressing multimotion estimation, which is especially challenging in highly dynamic environments. Such environments not only comprise multiple, complex motions but also tend to exhibit significant occlusion.

Previous work in object tracking focuses on maintaining the integrity of object tracks but usually relies on specific appearance-based descriptors or constrained motion models. These approaches are very effective in specific applications but do not generalize to the full multimotion estimation problem.

This paper presents a pipeline for estimating multiple motions, including the camera egomotion, in the presence of occlusions. This approach uses an expressive motion prior to estimate the SE(3) trajectory of every motion in the scene, even during temporary occlusions, and identify the reappearance of motions through motion closure. The performance of this occlusion-robust multimotion visual odometry (MVO) pipeline is evaluated on real-world data and the Oxford Multimotion Dataset.