Evaluating Local Features for Day-Night Matching

Abstract

This paper evaluates the performance of local features in the presence of large illumination changes that occur between day and night. Through our evaluation, we find that repeatability of detected features, as a de facto standard measure, is not sufficient in evaluating the performance of feature detectors; we must also consider the distinctiveness of the features. Moreover, we find that feature detectors are severely affected by illumination changes between day and night and that there is great potential to improve both feature detectors and descriptors.

Cite

Text

Zhou et al. "Evaluating Local Features for Day-Night Matching." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-49409-8_60

Markdown

[Zhou et al. "Evaluating Local Features for Day-Night Matching." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/zhou2016eccv-evaluating/) doi:10.1007/978-3-319-49409-8_60

BibTeX

@inproceedings{zhou2016eccv-evaluating,
  title     = {{Evaluating Local Features for Day-Night Matching}},
  author    = {Zhou, Hao and Sattler, Torsten and Jacobs, David W.},
  booktitle = {European Conference on Computer Vision},
  year      = {2016},
  pages     = {724-736},
  doi       = {10.1007/978-3-319-49409-8_60},
  url       = {https://mlanthology.org/eccv/2016/zhou2016eccv-evaluating/}
}