Consistent Temporal Variations in Many Outdoor Scenes

Nathan Jacobs, Nathaniel Roman, Robert Pless

CVPR 2007

doi:10.1109/CVPR.2007.383258 /cvpr/2007/jacobs2007cvpr-consistent/

Abstract

This paper details an empirical study of large image sets taken by static cameras. These images have consistent correlations over the entire image and over time scales of days to months. Simple second-order statistics of such image sets show vastly more structure than exists in generic natural images or video from moving cameras. Using a slight variant to PCA, we can decompose all cameras into comparable components and annotate images with respect to surface orientation, weather, and seasonal change. Experiments are based on a data set from 538 cameras across the United States which have collected more than 17 million images over the the last 6 months.

CVPR Semantic Scholar

Cite

Text

Jacobs et al. "Consistent Temporal Variations in Many Outdoor Scenes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.383258

Markdown

[Jacobs et al. "Consistent Temporal Variations in Many Outdoor Scenes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/jacobs2007cvpr-consistent/) doi:10.1109/CVPR.2007.383258

BibTeX

@inproceedings{jacobs2007cvpr-consistent,
  title     = {{Consistent Temporal Variations in Many Outdoor Scenes}},
  author    = {Jacobs, Nathan and Roman, Nathaniel and Pless, Robert},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2007},
  doi       = {10.1109/CVPR.2007.383258},
  url       = {https://mlanthology.org/cvpr/2007/jacobs2007cvpr-consistent/}
}