{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lets-take-a-walk-on-superpixels-graphs","title":"Let's take a Walk on Superpixels Graphs: Deformable Linear Objects Segmentation and Model Estimation","arxiv_id":"1810.04461","date":"2018-10-10","proceeding":null,"authors":["Daniele De Gregorio","Gianluca Palli","Luigi Di Stefano"],"abstract":"While robotic manipulation of rigid objects is quite straightforward, coping\nwith deformable objects is an open issue. More specifically, tasks like tying a\nknot, wiring a connector or even surgical suturing deal with the domain of\nDeformable Linear Objects (DLOs). In particular the detection of a DLO is a\nnon-trivial problem especially under clutter and occlusions (as well as\nself-occlusions). The pose estimation of a DLO results into the identification\nof its parameters related to a designed model, e.g. a basis spline. It follows\nthat the stand-alone segmentation of a DLO might not be sufficient to conduct a\nfull manipulation task. This is why we propose a novel framework able to\nperform both a semantic segmentation and b-spline modeling of multiple\ndeformable linear objects simultaneously without strict requirements about\nenvironment (i.e. the background). The core algorithm is based on biased random\nwalks over the Region Adiacency Graph built on a superpixel oversegmentation of\nthe source image. The algorithm is initialized by a Convolutional Neural\nNetworks that detects the DLO's endcaps. An open source implementation of the\nproposed approach is also provided to easy the reproduction of the whole\ndetection pipeline along with a novel cables dataset in order to encourage\nfurther experiments.","url_abs":"http://arxiv.org/abs/1810.04461v1","url_pdf":"http://arxiv.org/pdf/1810.04461v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lets-take-a-walk-on-superpixels-graphs","repo_url":"https://github.com/m4nh/ariadne","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"lets-take-a-walk-on-superpixels-graphs","repo_url":"https://github.com/m4nh/cables_dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"superpixels","task_name":"Superpixels"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}