Expert-driven Rule-based Refinement of Semantic Segmentation Maps for Autonomous Vehicles

Simple item page
dc.contributor.authorManibardo, Eric L.
dc.contributor.authorLana, Ibai
dc.contributor.authorDel Ser, Javier
dc.contributor.authorCarballo, Alexander
dc.contributor.authorTakeda, Kazuya
dc.contributor.institutionIA
dc.date.accessioned2024-07-24T11:54:28Z
dc.date.available2024-07-24T11:54:28Z
dc.date.issued2023
dc.descriptionPublisher Copyright: © 2023 IEEE.
dc.description.abstractSemantic segmentation aims at assigning labels to every pixel of a given image. In the context of autonomous vehicles, semantic segmentation models should be trained with data collected from the traffic network through which vehicles are expected to circulate. Road regulation, weather conditions, and other context features may differ between regions, making local semantic segmentation datasets extremely valuable. However, the high ground truth annotation costs represent a hindrance to the development of such models. The upsurge of powerful feature learning architectures leaves room for semantic segmentation models trained on an unsupervised fashion. This observation vertebrates the purpose of this work: to produce coarse segmentation maps for scene understanding without the need of annotated data. We depart from an unsupervised model that yields low-quality results. The proposed methodology establishes a set of guidelines for the enhancement of segmentation maps. Obtained results expose an improvement of the segmentation quality thanks to the application of our devised guidelines, paving the way for the automatic generation of semantic segmentation datasets.en
dc.description.sponsorshipThe authors would like to thank the Basque Government for its funding support through the EMAITEK, ELKARTEK and BIKAINTEK PhD support programs (48AFW22019-00002).
dc.description.statusPeer reviewed
dc.identifier.citationManibardo , E L , Lana , I , Del Ser , J , Carballo , A & Takeda , K 2023 , Expert-driven Rule-based Refinement of Semantic Segmentation Maps for Autonomous Vehicles . in IV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings . IEEE Intelligent Vehicles Symposium, Proceedings , vol. 2023-June , Institute of Electrical and Electronics Engineers Inc. , 34th IEEE Intelligent Vehicles Symposium, IV 2023 , Anchorage , United States , 4/06/23 . https://doi.org/10.1109/IV55152.2023.10186738
dc.identifier.citationconference
dc.identifier.doi10.1109/IV55152.2023.10186738
dc.identifier.isbn9798350346916
dc.identifier.urihttps://hdl.handle.net/11556/2407
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85168009940&partnerID=8YFLogxK
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartofIV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings
dc.relation.ispartofseriesIEEE Intelligent Vehicles Symposium, Proceedings
dc.relation.projectIDEusko Jaurlaritza, 48AFW22019-00002
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsautonomous vehicles
dc.subject.keywordsScene understanding
dc.subject.keywordssemantic segmentation
dc.subject.keywordsunsupervised learning
dc.subject.keywordsComputer Science Applications
dc.subject.keywordsAutomotive Engineering
dc.subject.keywordsModeling and Simulation
dc.titleExpert-driven Rule-based Refinement of Semantic Segmentation Maps for Autonomous Vehiclesen
dc.typeconference output
Files