000162033 001__ 162033 000162033 005__ 20251017144626.0 000162033 0247_ $$2doi$$a10.1109/IROS58592.2024.10801797 000162033 0248_ $$2sideral$$a144624 000162033 037__ $$aART-2024-144624 000162033 041__ $$aeng 000162033 100__ $$aCasao, Sara$$uUniversidad de Zaragoza 000162033 245__ $$aSpectralWaste Dataset: Multimodal Data for Waste Sorting Automation 000162033 260__ $$c2024 000162033 5060_ $$aAccess copy available to the general public$$fUnrestricted 000162033 5203_ $$aThe increase in non-biodegradable waste is a worldwide concern. Recycling facilities play a crucial role, but their automation is hindered by the complex characteristics of waste recycling lines like clutter or object deformation. In addition, the lack of publicly available labeled data for these environments makes developing robust perception systems challenging. Our work explores the benefits of multimodal perception for object segmentation in real waste management scenarios. First, we present SpectralWaste, the first dataset collected from an operational plastic waste sorting facility that provides synchronized hyperspectral and conventional RGB images. This dataset contains labels for several categories of objects that commonly appear in sorting plants and need to be detected and separated from the main trash flow for several reasons, such as security in the management line or reuse. Additionally, we propose a pipeline employing different object segmentation architectures and evaluate the alternatives on our dataset, conducting an extensive analysis for both multimodal and unimodal alternatives. Our evaluation pays special attention to efficiency and suitability for real-time processing and demonstrates how hyperspectral imaging can bring a boost to RGB-only perception in these realistic industrial settings without much computational overhead. 000162033 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T45-23R$$9info:eu-repo/grantAgreement/ES/DGA/T58-23R$$9info:eu-repo/grantAgreement/ES/MICINN/PID2021-125514NB-I00$$9info:eu-repo/grantAgreement/ES/MICINN/PID2022-136454NB-C22 000162033 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/ 000162033 592__ $$a0.681$$b2024 000162033 593__ $$aComputer Science Applications$$c2024 000162033 593__ $$aSoftware$$c2024 000162033 593__ $$aControl and Systems Engineering$$c2024 000162033 593__ $$aComputer Vision and Pattern Recognition$$c2024 000162033 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion 000162033 700__ $$0(orcid)0000-0002-6773-9315$$aPeña, Fernando$$uUniversidad de Zaragoza 000162033 700__ $$aSabater, Alberto 000162033 700__ $$aCastillón, Rosa 000162033 700__ $$0(orcid)0000-0002-7490-4067$$aSuárez, Darío$$uUniversidad de Zaragoza 000162033 700__ $$0(orcid)0000-0002-5176-3767$$aMontijano, Eduardo$$uUniversidad de Zaragoza 000162033 700__ $$0(orcid)0000-0002-7580-9037$$aMurillo, Ana C.$$uUniversidad de Zaragoza 000162033 7102_ $$15007$$2035$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Arquit.Tecnología Comput. 000162033 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát. 000162033 773__ $$g2024 (2024), 5852-5858$$pProc. IEEE/RSJ Int. Conf. Intell. Rob. Syst.$$tProceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems$$x2153-0858 000162033 787__ $$tSpectralWaste Dataset: Multimodal Data for Waste Sorting Automation$$tDataset website$$w10.5281/zenodo.10880543$$whttps://sites.google.com/unizar.es/spectralwaste 000162033 8564_ $$s753985$$uhttps://zaguan.unizar.es/record/162033/files/texto_completo.pdf$$yPostprint 000162033 8564_ $$s3294916$$uhttps://zaguan.unizar.es/record/162033/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint 000162033 909CO $$ooai:zaguan.unizar.es:162033$$particulos$$pdriver 000162033 951__ $$a2025-10-17-14:24:11 000162033 980__ $$aARTICLE