article · Sensors · 2012
Multispectral Image Feature Points
Cristhian Aguilera, Fernando Barrera, Felipe Lumbreras, Ángel D. Sappa, Ricardo Toledo
Cited by 169Open access
Abstract
This paper presents a novel feature point descriptor for the multispectral image case: Far-Infrared and Visible Spectrum images. It allows matching interest points on images of the same scene but acquired in different spectral bands. Initially, points of interest are detected on both images through a SIFT-like based scale space representation. Then, these points are characterized using an Edge Oriented Histogram (EOH) descriptor. Finally, points of interest from multispectral images are matched by finding nearest couples using the information from the descriptor. The provided experimental results and comparisons with similar methods show both the validity of the proposed approach as well as the improvements it offers with respect to the current state-of-the-art.
Cite this paper
Aguilera, C., Barrera, F., Lumbreras, F., Sappa, Á. D., & Toledo, R. (2012). Multispectral Image Feature Points. Sensors, 12(9), 12661–12672. https://doi.org/10.3390/s120912661
Aguilera, Cristhian, et al. “Multispectral Image Feature Points.” Sensors, vol. 12, no. 9, 2012, pp. 12661–72, https://doi.org/10.3390/s120912661.
Aguilera, Cristhian, Fernando Barrera, Felipe Lumbreras, Ángel D. Sappa, and Ricardo Toledo. 2012. “Multispectral Image Feature Points.” Sensors 12 (9): 12661–72. https://doi.org/10.3390/s120912661.
Aguilera, C. et al. (2012) ‘Multispectral Image Feature Points’, Sensors, 12(9), pp. 12661–12672. Available at: https://doi.org/10.3390/s120912661.
@article{aguilera2012multispectral,
title = {{Multispectral Image Feature Points}},
author = {Aguilera, Cristhian and Barrera, Fernando and Lumbreras, Felipe and Sappa, Ángel D. and Toledo, Ricardo},
journal = {Sensors},
volume = {12},
number = {9},
pages = {12661--12672},
year = {2012},
doi = {10.3390/s120912661}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.