A Fast Method for Estimating Transient Scene Attributes

Abstract

We propose the use of deep convolutional neural networks to estimate the transient attributes of a scene from a single image. Transient scene attributes describe both the objective conditions, such as the weather, time of day, and the season, and subjective properties of a scene, such as whether or not the scene seems busy. Recently, convolutional neural networks have been used to achieve state-of-the-art results for many vision problems, from object detection to scene classification, but have not previously been used for estimating transient attributes. We compare several methods for adapting an existing network architecture and present state-of-the-art results on two benchmark datasets. Our method is more accurate and significantly faster than previous methods, enabling real-world applications.

Cite

Text

Baltenberger et al. "A Fast Method for Estimating Transient Scene Attributes." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016. doi:10.1109/WACV.2016.7477713

Markdown

[Baltenberger et al. "A Fast Method for Estimating Transient Scene Attributes." IEEE/CVF Winter Conference on Applications of Computer Vision, 2016.](https://mlanthology.org/wacv/2016/baltenberger2016wacv-fast/) doi:10.1109/WACV.2016.7477713

BibTeX

@inproceedings{baltenberger2016wacv-fast,
  title     = {{A Fast Method for Estimating Transient Scene Attributes}},
  author    = {Baltenberger, Ryan and Zhai, Menghua and Greenwell, Connor and Workman, Scott and Jacobs, Nathan},
  booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
  year      = {2016},
  pages     = {1-8},
  doi       = {10.1109/WACV.2016.7477713},
  url       = {https://mlanthology.org/wacv/2016/baltenberger2016wacv-fast/}
}