RT-DLO: Real-Time Deformable Linear Objects Instance Segmentation

Deformable Linear Objects (DLOs) such as cables, wires, ropes, and elastic tubes are numerously present both in domestic industrial environments. Unfortunately, robotic systems handling DLOs rare have limited capabilities due to the challenging nature of perceiving them. Hence, we propose a novel approach named RT-DLO for real-time instance segmentation DLOs. First, semantically segmented from background. Afterward, method separate DLO instances is applied. It employs generation graph representation scene given semantic mask where nodes sampled center-lines whereas edges selected based on topological reasoning. experimentally evaluated against DLO-specific general-purpose deep learning approaches, achieving overall better performances terms accuracy inference time.