Kevin has submitted a journal paper on Multimotion Visual Odometry (MVO) to IJRR. This is his definitive version of the work we're doing in ESP on measuring moving scenes from a dynamic camera. You can learn more from the trailer video and multimedia extensions on YouTube and the paper preprint on arXiv.
- The International Journal of Robotics Research (IJRR)
- Submitted, Manuscript #IJR-21-4311
Visual motion estimation is a well-studied challenge in autonomous navigation. Recent work has focused on addressing multimotion estimation in highly dynamic environments. These environments not only comprise multiple, complex motions but also tend to exhibit significant occlusion.
Estimating third-party motions simultaneously with the sensor egomotion is difficult because an object’s observed motion consists of both its true motion and the sensor motion. Most previous works in multimotion estimation simplify this problem by relying on appearance-based object detection or application-specific motion constraints. These approaches are effective in specific applications and environments but do not generalize well to the full multimotion estimation problem (MEP).
This paper presents Multimotion Visual Odometry (MVO), a multimotion estimation pipeline that estimates the full SE(3) trajectory of every motion in the scene, including the sensor egomotion, without relying on appearance-based information. MVO extends the traditional visual odometry (VO) pipeline with multimotion segmentation and tracking techniques. It uses physically founded motion priors to extrapolate motions through temporary occlusions and identify the reappearance of motions through motion closure. Evaluations on real-world data from the Oxford Multimotion Dataset (OMD) and the KITTI Vision Benchmark Suite demonstrate that MVO achieves good estimation accuracy compared to similar approaches and is applicable to a variety of multimotion estimation challenges.