Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/32232
Appears in Collections:Computing Science and Mathematics Journal Articles
Peer Review Status: Refereed
Title: AiRound and CV-BrCT: Novel Multiview Datasets for Scene Classification
Author(s): Machado, Gabriel
Ferreira, Edemir
Nogueira, Keiller
Oliveira, Hugo
Brito, Matheus
Gama, Pedro Henrique Targino
Santos, Jefersson Alex dos
Keywords: Data fusion
dataset
deep learning
feature fusion
multimodal machine learning
remote sensing
Issue Date: 2021
Date Deposited: 4-Feb-2021
Citation: Machado G, Ferreira E, Nogueira K, Oliveira H, Brito M, Gama PHT & Santos JAd (2021) AiRound and CV-BrCT: Novel Multiview Datasets for Scene Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, pp. 488-503. https://doi.org/10.1109/JSTARS.2020.3033424
Abstract: It is undeniable that aerial/satellite images can provide useful information for a large variety of tasks. But, since these images are always taken from above, some applications can benefit from complementary information provided by other perspective views of the scene, such as ground-level images. Despite a large number of public repositories for both georeferenced photographs and aerial images, there is a lack of benchmark datasets that allow the development of approaches that exploit the benefits and complementarity of aerial/ground imagery. In this article, we present two new publicly available datasets named AiRound and CV-BrCT. The first one contains triplets of images from the same geographic coordinate with different perspectives of view extracted from various places around the world. Each triplet is composed of an aerial RGB image, a ground-level perspective image, and a Sentinel-2 sample. The second dataset contains pairs of aerial and street-level images extracted from southeast Brazil. We design an extensive set of experiments concerning multiview scene classification, using early and late fusion. Such experiments were conducted to show that image classification can be enhanced using multiview data.
DOI Link: 10.1109/JSTARS.2020.3033424
Rights: This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
Licence URL(s): http://creativecommons.org/licenses/by/4.0/

Files in This Item:
File Description SizeFormat 
09238485.pdfFulltext - Published Version4.51 MBAdobe PDFView/Open



This item is protected by original copyright



A file in this item is licensed under a Creative Commons License Creative Commons

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.