Abstract

The dataset contains the source code and model weights utilized for the experimental validation on segmentation of deformable linear objects. The developed approach is called RT-DLO. A novel method to separate the DLO instances is applied. It employs the generation of a graph representation of the scene given the semantic mask where the graph nodes are sampled from the DLOs center-lines whereas the graph edges are selected based on topological reasoning. RT-DLO also describes each DLO instance with a sequence of 2D coordinates. The associated publication is the following: A. Caporali, K. Galassi, B. L. Žagar, R. Zanella, G. Palli and A. C. Knoll, "RT-DLO: Real-Time Deformable Linear Objects Instance Segmentation," in IEEE Transactions on Industrial Informatics, doi: 10.1109/TII.2023.3245641.