Lane following learning based on semantic segmentation with chroma key and image superposition

e-Archivo Repository

Show simple item record

dc.contributor.author Corrochano Jiménez, Javier
dc.contributor.author Alonso Weber, Juan Manuel
dc.contributor.author Sesmero Lorente, María Paz
dc.contributor.author Sanchis de Miguel, María Araceli
dc.date.accessioned 2022-05-09T10:51:36Z
dc.date.available 2022-05-09T10:51:36Z
dc.date.issued 2021-12
dc.identifier.bibliographicCitation Corrochano, J., Alonso-Weber, J. M., Sesmero, M. P., & Sanchis, A. (2021). Lane following Learning Based on Semantic Segmentation with Chroma Key and Image Superposition. In Electronics (Vol. 10, Issue 24, p. 3113). MDPI AG.
dc.identifier.issn 2079-9292
dc.identifier.uri http://hdl.handle.net/10016/34737
dc.description.abstract There are various techniques to approach learning in autonomous driving; however, all of them suffer from some problems. In the case of imitation learning based on artificial neural networks, the system must learn to correctly identify the elements of the environment. In some cases, it takes a lot of effort to tag the images with the proper semantics. This is also relevant given the need to have very varied scenarios to train and to thus obtain an acceptable generalization capacity. In the present work, we propose a technique for automated semantic labeling. It is based on various learning phases using image superposition combining both scenarios with chromas and real indoor scenarios. This allows the generation of augmented datasets that facilitate the learning process. Further improvements by applying noise techniques are also studied. To carry out the validation, a small-scale car model is used that learns to automatically drive on a reduced circuit. A comparison with models that do not rely on semantic segmentation is also performed. The main contribution of our proposal is the possibility of generating datasets for real indoor scenarios with automatic semantic segmentation, without the need for endless human labeling tasks.
dc.description.sponsorship This work was supported by the Spanish Government under projects PID2019-104793RBC31/ AEI/10.13039/501100011033, RTI2018-096036-B-C22/AEI/10.13039/501100011033, TRA2016- 78886-C3-1-R/AEI/10.13039/501100011033, and PEAVAUTO-CM-UC3M and by the Region of Madrid’s Excellence Program (EPUC3M17).
dc.format.extent 24
dc.language.iso eng
dc.publisher MDPI AG
dc.rights © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
dc.rights Atribución 3.0 España
dc.rights.uri http://creativecommons.org/licenses/by/3.0/es/
dc.subject.other Automated driving
dc.subject.other Chroma key
dc.subject.other Feature extraction
dc.subject.other Imitation learning
dc.subject.other Lane following
dc.subject.other Noise addition
dc.subject.other Semantic segmentation
dc.title Lane following learning based on semantic segmentation with chroma key and image superposition
dc.type article
dc.subject.eciencia Informática
dc.identifier.doi https://doi.org/10.3390/electronics10243113
dc.rights.accessRights openAccess
dc.relation.projectID Comunidad de Madrid. PEAVAUTO-CM-UC3M
dc.relation.projectID Gobierno de España. PID2019-104793RBC31/ AEI/10.13039/501100011033
dc.relation.projectID Gobierno de España. TRA2016- 78886-C3-1-R/AEI/10.13039/501100011033
dc.relation.projectID Gobierno de España. RTI2018-096036-B-C22/AEI/10.13039/501100011033
dc.type.version publishedVersion
dc.identifier.publicationfirstpage 3113
dc.identifier.publicationissue 24
dc.identifier.publicationlastpage 3137
dc.identifier.publicationtitle Electronics (Switzerland)
dc.identifier.publicationvolume 10
dc.identifier.uxxi AR/0000030516
dc.contributor.funder Comunidad de Madrid
dc.contributor.funder Ministerio de Economía y Competitividad (España)
dc.contributor.funder Ministerio de Ciencia e Innovación (España)
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)


The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record