An Evaluation of Local Feature Detectors and Descriptors for Infrared Images
Abstract
This paper provides a comparative performance evaluation of local features for infrared (IR) images across different combinations of common detectors and descriptors. Although numerous studies report comparisons of local features designed for ordinary visual images, their performance on IR images is far less charted. We perform a systematic investigation, thoroughly exploiting the established benchmark while also introducing a new IR image data set. The contribution is two-fold: we (i) evaluate the performance of both local float type and more recent binary type detectors and descriptors in their combinations under a variety (6 kinds) of image transformations, and (ii) make a new IR image data set publicly available. Through our investigation we gain novel and useful insights for applying state-of-the art local features to IR images with different properties.
Cite
Text
Johansson et al. "An Evaluation of Local Feature Detectors and Descriptors for Infrared Images." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-49409-8_59Markdown
[Johansson et al. "An Evaluation of Local Feature Detectors and Descriptors for Infrared Images." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/johansson2016eccv-evaluation/) doi:10.1007/978-3-319-49409-8_59BibTeX
@inproceedings{johansson2016eccv-evaluation,
title = {{An Evaluation of Local Feature Detectors and Descriptors for Infrared Images}},
author = {Johansson, Johan and Solli, Martin and Maki, Atsuto},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {711-723},
doi = {10.1007/978-3-319-49409-8_59},
url = {https://mlanthology.org/eccv/2016/johansson2016eccv-evaluation/}
}