Occlusion-Robust MVO: Multimotion Estimation Through Occlusion Via Motion Closure

Abstract

Visual motion estimation is an integral and wellstudied 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 occlusionrobust multimotion visual odometry (MVO) pipeline is evaluated on real-world data and the Oxford Multimotion Dataset.

Multimotion visual odometry

“…This paper is a continuation of ideas that were first presented at the Joint Industry and Robotics CDTs Symposium (Judd et al, 2018) and the Long-term Human Motion Prediction Workshop (Judd and Gammell, 2019b) and were published in Judd et al (2018a), Judd (2019) and Judd and Gammell (2020). It makes the following specific contributions:• Presents a unified and updated version of MVO that is adaptable to a variety of trajectory representations and estimation techniques.• Incorporates a continuous SE (3) white-noise-on jerk (WNOJ) prior into the estimator, extends it for geocentric third-party estimation, and examines its advantages and limitations in the context of the MEP, along with the previously presented discrete and white-noise-on-acceleration (WNOA) models.• Details the challenges of full-batch and sliding-window implementations of MVO, including handling temporary occlusions.• Compares pose-only, pose-velocity, and pose-velocity-acceleration estimators both quantitatively on indoor experiments (OMD) and qualitatively in the real world (KITTI).…”

“…Egomotion estimation techniques must be adapted to estimate the geocentric trajectories of dynamic objects that invalidate the static tracklet assumption. Initial versions of the ideas in Sections 4.2.1 and 4.2.2 were first published in Judd et al (2018a) and Judd and Gammell (2020), respectively, and they are further developed here. The ideas in Section 4.2.3 are presented here for the first time.…”

“…Detecting when an object becomes unoccluded requires determining when a newly segmented motion is actually the reappearance of a previously occluded motion, i.e., motion closure (Section 5.3). Initial versions of these ideas were first presented in Judd and Gammell (2019b) and Judd and Gammell (2020), and they are further developed and fully detailed for the first time here.…”

Dynamic response of reinforced concrete frames with stiffness degradation.

“…Recently, multi-object visual odometry techniques [12], [13] and graph-based optimisation Dynamic SLAM systems [7], [14], [15] have been explored to jointly localise This research is funded with the support of ARIA Research and the Australian Government via the Department of Industry, Science, and Resources CRC-P program (CRCPXI000007).…”