Multi-branch convolutional descriptors for content-based remote sensing image retrieval

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

Context-based remote sensing image retrieval (CBRSIR) is an important problem in computer vision with many applications such as military, agriculture, and surveillance. In this study, inspired by recent developments in person re-identification, we design and fine-tune a multi-branch deep learning architecture that combines global and local features to obtain rich and discriminative image representations. Additionally, we propose a new evaluation strategy that fully separates the test and training sets and where new unseen data is used for querying, thereby emphasizing the generalization capability of retrieval systems. Extensive evaluations show that our method significantly outperforms the existing approaches by up to 10.7% in mean precision@20 on popular CBRSIR datasets. Regarding the new evaluation strategy, our method attains excellent retrieval performance, yielding more than 95% precision@20 score on the challenging PatternNet dataset.

Originele taal-2Engels
TitelVISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
RedacteurenGiovanni Maria Farinella, Petia Radeva, Jose Braz
UitgeverijSCITEPRESS-Science and Technology Publications, Lda.
Pagina's242-249
Aantal pagina's8
Volume5
ISBN van elektronische versie9789897584022
StatusGepubliceerd - 1 jan 2020
Evenement15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2020 - Valletta, Malta
Duur: 27 feb 202029 feb 2020

Congres

Congres15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2020
LandMalta
StadValletta
Periode27/02/2029/02/20

Vingerafdruk Duik in de onderzoeksthema's van 'Multi-branch convolutional descriptors for content-based remote sensing image retrieval'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Imbriaco, R., Alkanat, T., Bondarev, E., & de With, P. H. N. (2020). Multi-branch convolutional descriptors for content-based remote sensing image retrieval. In G. M. Farinella, P. Radeva, & J. Braz (editors), VISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Vol. 5, blz. 242-249). SCITEPRESS-Science and Technology Publications, Lda..