TrackDLO: Tracking Deformable Linear Objects Under Occlusion With Motion Coherence
- 9 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (10) , 6179-6186
Abstract
The TrackDLO algorithm estimates the shape of a Deformable Linear Object (DLO) under occlusion from a sequence of RGB-D images. TrackDLO is vision-only and runs in real-time. It requires no external state information from physics modeling, simulation, visual markers, or contact as input. The algorithm improves on previous approaches by addressing three common scenarios which cause tracking failure: tip occlusion, mid-section occlusion, and self-occlusion. This is achieved through the application of Motion Coherence Theory to impute the spatial velocity of occluded nodes, the use of the topological geodesic distance to track self-occluding DLOs, and the introduction of a non-Gaussian kernel that only penalizes lower-order spatial displacement derivatives to reflect DLO physics. Improved real-time DLO tracking under mid-section occlusion, tip occlusion, and self-occlusion is demonstrated experimentally. The source code and demonstration data are publicly released.Keywords
Funding Information
- Illinois Space Grant Consortium Undergraduate Research Opportunity Program
- NASA Space Technology Graduate Research Opportunity (80NSSC21K1292)
This publication has 32 references indexed in Scilit:
- Learning to Estimate 3-D States of Deformable Linear Objects from Single-Frame Occluded Point Clouds2023
- A Coarse-to-Fine Framework for Dual-Arm Manipulation of Deformable Linear Objects with Whole-Body Obstacle Avoidance2023
- Combining Vision and Tactile Data for Cable Grasping2021
- Tracking Partially-Occluded Deformable Objects while Enforcing Geometric Constraints2021
- Deformable Linear Object Prediction Using Locally Linear Latent Dynamics2021
- Auto-generated Wires Dataset for Semantic Segmentation with Domain-Independence2021
- Learning Topological Motion Primitives for Knot Planning2020
- An algorithm based on bidirectional searching and geometric constrained sampling for automatic manipulation planning in aircraft cable assemblyJournal of Manufacturing Systems, 2020
- Occlusion-robust Deformable Object Tracking without Physics Simulation2019
- Non-rigid Point Set Registration with Global-Local Topology Preservation2014