RT Journal Article
T1 Aggregation of Convolutional Neural Network Estimations of Homographies by Color Transformations of the Inputs
A1 Molina-Cabello, Miguel A.
A1 Elizondo, David A.
A1 Marcos Luque-Baena, Rafael
A1 Lopez-Rubio, Ezequiel
K1 Deep convolutional neural networks
K1 homography estimation
K1 color transformations
K1 Deep homography
K1 Algorithm
K1 Sports
AB The standard approach to the estimation of homographies consists in the application of the RANSAC algorithm to a set of tentative matches. More recent strategies based on deep learning, namely convolutional architectures, have become available. In this work, a new algorithm for the estimation of homographies is developed. It is rooted in a convolutional neural network for homography estimation, which is provided with a range of versions of the input pair of pictures. Such versions are generated by perturbation of the color levels of the input images. Each generated pair of images yields a distinct estimation of the homography, and then the estimations are combined together to obtain a final, more robust estimation. Experiments have been designed and carried out to test the validity of our approach, including qualitative and quantitative performance measures. In particular, it is demonstrated that our approach consistently outperforms the baseline approach consisting of using the output of the homography estimation deep network for the original input pair of images.
PB Ieee-inst electrical electronics engineers inc
SN 2169-3536
YR 2020
FD 2020-01-01
LK http://hdl.handle.net/10668/18970
UL http://hdl.handle.net/10668/18970
LA en
DS RISalud
RD Apr 15, 2025