Mostrar el registro sencillo del ítem

dc.contributor.authorPuertas, Enrique
dc.contributor.authorDe las Heras, Gonzalo
dc.contributor.authorFernández-Andrés, Javier
dc.contributor.authorSánchez Soriano, Javier
dc.date.accessioned2023-02-28T11:20:48Z
dc.date.available2023-02-28T11:20:48Z
dc.date.issued2022
dc.identifier.issn2306-5729spa
dc.identifier.urihttps://hdl.handle.net/10641/3286
dc.description.abstractThis publication presents a dataset of Spanish roundabouts aerial images taken from a UAV, along with annotations in PASCAL VOC XML files that indicate the position of vehicles within them. Additionally, a CSV file is attached containing information related to the location and characteristics of the captured roundabouts. This work details the process followed to obtain them: image capture, processing, and labeling. The dataset consists of 985,260 total instances: 947,400 cars, 19,596 cycles, 2262 trucks, 7008 buses, and 2208 empty roundabouts in 61,896 1920 × 1080 px JPG images. These are divided into 15,474 extracted images from 8 roundabouts with different traffic flows and 46,422 images created using data augmentation techniques. The purpose of this dataset is to help research into computer vision on the road, as such labeled images are not abundant. It can be used to train supervised learning models, such as convolutional neural networks, which are very popular in object detectionspa
dc.language.isoengspa
dc.publisherDataspa
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subjectRoundaboutsspa
dc.subjectAerialspa
dc.subjectDatasetspa
dc.subjectObject detectionspa
dc.subjectMachine learningspa
dc.subjectAutonomous drivingspa
dc.subjectDeep learningspa
dc.subjectNeural networksspa
dc.subjectRetinaNetspa
dc.titleDataset: Roundabout Aerial Images for Vehicle Detection.spa
dc.typejournal articlespa
dc.type.hasVersionAMspa
dc.rights.accessRightsopen accessspa
dc.description.extent1061 KBspa
dc.identifier.doi10.3390/data7040047spa
dc.relation.publisherversionhttps://www.mdpi.com/2306-5729/7/4/47spa


Ficheros en el ítem

FicherosTamañoFormatoVer
2data-07-00047.pdf1.035MbPDFVer/

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

Atribución-NoComercial-SinDerivadas 3.0 España
Excepto si se señala otra cosa, la licencia del ítem se describe como Atribución-NoComercial-SinDerivadas 3.0 España