Back to Search
Start Over
Aggregation of Convolutional Neural Network Estimations of Homographies by Color Transformations of the Inputs
- Source :
- IEEE Access, Vol 8, Pp 79552-79560 (2020)
- Publication Year :
- 2020
- Publisher :
- IEEE, 2020.
-
Abstract
- 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.
- Subjects :
- General Computer Science
Computer science
business.industry
General Engineering
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Pattern recognition
Convolutional neural network
Algorithm
homography estimation
Deep convolutional neural networks
General Materials Science
Deep homography
Artificial intelligence
lcsh:Electrical engineering. Electronics. Nuclear engineering
business
color transformations
lcsh:TK1-9971
Sports
Subjects
Details
- Language :
- English
- ISSN :
- 21693536
- Volume :
- 8
- Database :
- OpenAIRE
- Journal :
- IEEE Access
- Accession number :
- edsair.doi.dedup.....94269bcb410282efb3783b4bd150a3ab