Abstract

The dataset contains the source code and model weights utilized for the experimental validation on segmentation of deformable linear objects, associated to a novel algorithm called Ariadne+. The proposed approach uses deep learning and standard computer vision techniques aiming at their reliable and time effective instance segmentation of wires. The source code comprises a deep convolutional neural network employed for generating a binary mask showing where wires are present in the input image, and graph theory applied to create the wire paths from the binary mask through an iterative approach maximizing the graph coverage. In addition, a B-Spline model of each instance is provided. The dataset is associated to the related publication: A. Caporali, R. Zanella, D. D. Greogrio and G. Palli, "Ariadne+: Deep Learning--Based Augmented Framework for the Instance Segmentation of Wires," in IEEE Transactions on Industrial Informatics, vol. 18, no. 12, pp. 8607-8617, Dec. 2022, doi: 10.1109/TII.2022.3154477.