dc.creator | Carranza García, Manuel | es |
dc.creator | Torres Mateo, Jesús | es |
dc.creator | Lara Benítez, Pedro | es |
dc.creator | García Gutiérrez, Jorge | es |
dc.date.accessioned | 2022-02-18T09:03:49Z | |
dc.date.available | 2022-02-18T09:03:49Z | |
dc.date.issued | 2021 | |
dc.identifier.citation | Carranza García, M., Torres Mateo, J., Lara Benítez, P. y García Gutiérrez, J. (2021). On the Performance of One-Stage and Two-Stage Object Detectors in Autonomous Vehicles Using Camera Data. Remote Sensing, 13 (1) | |
dc.identifier.issn | 2072-4292 | es |
dc.identifier.uri | https://hdl.handle.net/11441/130053 | |
dc.description.abstract | Object detection using remote sensing data is a key task of the perception systems of
self-driving vehicles. While many generic deep learning architectures have been proposed for this
problem, there is little guidance on their suitability when using them in a particular scenario such
as autonomous driving. In this work, we aim to assess the performance of existing 2D detection
systems on a multi-class problem (vehicles, pedestrians, and cyclists) with images obtained from the
on-board camera sensors of a car. We evaluate several one-stage (RetinaNet, FCOS, and YOLOv3)
and two-stage (Faster R-CNN) deep learning meta-architectures under different image resolutions
and feature extractors (ResNet, ResNeXt, Res2Net, DarkNet, and MobileNet). These models are
trained using transfer learning and compared in terms of both precision and efficiency, with special
attention to the real-time requirements of this context. For the experimental study, we use theWaymo
Open Dataset, which is the largest existing benchmark. Despite the rising popularity of one-stage
detectors, our findings show that two-stage detectors still provide the most robust performance.
Faster R-CNN models outperform one-stage detectors in accuracy, being also more reliable in the
detection of minority classes. Faster R-CNN Res2Net-101 achieves the best speed/accuracy tradeoff
but needs lower resolution images to reach real-time speed. Furthermore, the anchor-free FCOS
detector is a slightly faster alternative to RetinaNet, with similar precision and lower memory usage. | es |
dc.description.sponsorship | Ministerio de Economía y Competitividad TIN2017-88209-C2-2-R | es |
dc.description.sponsorship | Junta de Andalucía US-1263341 | es |
dc.description.sponsorship | Junta de Andalucía P18-RT-2778 | es |
dc.format | application/pdf | es |
dc.format.extent | 23 | es |
dc.language.iso | eng | es |
dc.publisher | MDPI | es |
dc.relation.ispartof | Remote Sensing, 13 (1) | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | Autonomous vehicles | es |
dc.subject | Convolutional neural networks | es |
dc.subject | Deep learning | es |
dc.subject | Object detection | es |
dc.subject | Transfer learning | es |
dc.title | On the Performance of One-Stage and Two-Stage Object Detectors in Autonomous Vehicles Using Camera Data | es |
dc.type | info:eu-repo/semantics/article | es |
dcterms.identifier | https://ror.org/03yxnpp24 | |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos | es |
dc.relation.projectID | TIN2017-88209-C2-2-R | es |
dc.relation.projectID | US-1263341 | es |
dc.relation.projectID | P18-RT-2778 | es |
dc.relation.publisherversion | https://www.mdpi.com/2072-4292/13/1/89 | es |
dc.identifier.doi | 10.3390/rs13010089 | es |
dc.journaltitle | Remote Sensing | es |
dc.publication.volumen | 13 | es |
dc.publication.issue | 1 | es |
dc.contributor.funder | Ministerio de Economía y Competitividad (MINECO). España | es |
dc.contributor.funder | Junta de Andalucía | es |