RT Conference_Proceedings
T1 Prospective Comparison of SURF and Binary Keypoint Descriptors for Fast Hyperspectral Remote Sensing Registration
A1 Rodríguez Molina, Adrián
A1 Ordóñez Iglesias, Álvaro
A1 Blanco Heras, Dora
A1 Argüello Pedreira, Francisco
A1 López Feliciano, José Francisco
K1 OpenMP
K1 Binary descriptor
K1 Hyperspectral
K1 Multispectral
K1 Image registration
AB Image registration is a crucial process that involves determining the geometric transformation required to align multiple images. It plays a vital role in various remote sensing image processing tasks that involve analyzing changes among images. To enable real-time response, it is essential to have computationally efficient registration algorithms, especially when dealing with large datasets as is the case of hyperspectral images. This article presents a comparative analysis of two descriptors used to characterize local features of images prior to their matching and registration. The objective is to analyze whether the LATCH binary keypoint descriptor, which produces compact descriptors, provides similar results to the gradient-based SURF descriptor in terms of execution time and registration precision. To obtain the best computational performance, multithreaded implementations using OpenMP have been proposed. LATCH has proven to be 7 times faster and as reliable as SURF in terms of accuracy on scale differences of up to 1.2 times.
YR 2023
FD 2023
LK http://hdl.handle.net/10347/32204
UL http://hdl.handle.net/10347/32204
LA eng
NO This a post-print of the article “Prospective Comparison of SURF and Binary Keypoint Descriptors for Fast Hyperspectral Remote Sensing Registration” published in the Proceedings of IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium. The published article is available on https://doi.org/10.1109/IGARSS52108.2023.10281734
NO This work was supported in part by grants PID2019--104834GB--I00, PID2020-116417RB-C42 (TALENT-HExPERIA project), TED2021--130367B--I00, and FJC2021-046760-I funded by MCIN/AEI/10.13039/501100011033 and by "European Union NextGenerationEU/PRTR". It was also supported by Xunta de Galicia - Consellería de Cultura, Educación, Formación Profesional e Universidades [grant numbers 2019-2022 ED431G-2019/04 and ED431C-2022/16], by APOGEO project [grant number MAC/1.1.b/226] - Interreg Program (MAC 2014-2020), and by European Regional Development Fund (ERDF). The work of Adrián Rodríguez-Molina was supported by the 2020-2 PhD Training Program for Research Staff of the University of Las Palmas de Gran Canaria.
DS Minerva
RD 4 may 2026