Publication: Analysis of the Influence of Training Data on Road User Detection
dc.affiliation.dpto | UC3M. Departamento de Ingeniería de Sistemas y Automática | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Laboratorio de Sistemas Inteligentes | es |
dc.contributor.author | Guindel Gómez, Carlos | |
dc.contributor.author | Martín Gómez, David | |
dc.contributor.author | Armingol Moreno, José María | |
dc.contributor.author | Stiller, Christoph | |
dc.contributor.funder | Comunidad de Madrid | es |
dc.date.accessioned | 2021-05-25T10:19:20Z | |
dc.date.available | 2021-05-25T10:19:20Z | |
dc.date.issued | 2018-09-12 | |
dc.description.abstract | In this paper, we discuss the relevance of training data on modern object detectors used on onboard applications. Whereas modern deep learning techniques require large amounts of data, datasets with typical scenarios for autonomous vehicles are scarce and have a reduced number of samples. We conduct a comprehensive set of experiments to understand the effect of using a combination of two relatively small datasets to train an end-to-end object detector, based on the popular Faster R-CNN and enhanced with orientation estimation capabilities. We also test the adequacy of training models using partially available ground-truth labels, as a consequence of combining datasets aimed at different applications. Data augmentation is also introduced into the training pipeline. Results show a significant performance improvement in our exemplary case as a result of the higher variability of the training samples, thus opening a new way to improve the detection performance independently from the detector architecture. | en |
dc.description.sponsorship | This work was supported by the Spanish Government through the CICYT projects TRA2015-63708-R and TRA2016-78886-C3-1-R, and the Comunidad de Madrid through SEGVAUTO-TRIES (S2013/MIT-2713). | en |
dc.description.status | Publicado | es |
dc.format.extent | 6 | |
dc.identifier.bibliographicCitation | 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES). Proceedings. IEEE, 2018. Pp. 1-6. | en |
dc.identifier.doi | https://doi.org/10.1109/ICVES.2018.8519510 | |
dc.identifier.isbn | 978-1-5386-3543-8 | |
dc.identifier.publicationfirstpage | 1 | |
dc.identifier.publicationlastpage | 6 | |
dc.identifier.publicationtitle | 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES). Proceedings | en |
dc.identifier.uri | https://hdl.handle.net/10016/32744 | |
dc.identifier.uxxi | CC/0000029833 | |
dc.language.iso | eng | en |
dc.publisher | IEEE | en |
dc.relation.eventdate | September 12-14, 2018 | en |
dc.relation.eventnumber | 20 | |
dc.relation.eventplace | Madrid | es |
dc.relation.eventtitle | IEEE International Conference on Vehicular Electronics and Safety (ICVES2018) | en |
dc.relation.projectID | Gobierno de España. TRA2015-63708-R | es |
dc.relation.projectID | Gobierno de España. TRA2016-78886-C3-1-R | es |
dc.relation.projectID | Comunidad de Madrid. S2013/MIT-2713/SEGVAUTO-TRIES | es |
dc.rights | ©2018 IEEE. | en |
dc.rights.accessRights | open access | en |
dc.subject.eciencia | Ingeniería Industrial | es |
dc.subject.other | Object detection | en |
dc.subject.other | Training | en |
dc.subject.other | Proposals | en |
dc.subject.other | Estimation | en |
dc.subject.other | Feature extraction | en |
dc.subject.other | Detectors | en |
dc.subject.other | Task analysis | en |
dc.title | Analysis of the Influence of Training Data on Road User Detection | en |
dc.type | conference paper | * |
dc.type.hasVersion | AM | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- analysis_IEEE_ICVES_2018_ps.pdf
- Size:
- 399.29 KB
- Format:
- Adobe Portable Document Format