Two-Stream Non-Uniform Concentration Reasoning Network for Single Image Air Pollution Estimation

Huilin Chen, Wenming Yang, Qingmin Liao

Abstract

With the increasing availability of portable cameras and smart phones, directly estimating PM <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> based on digital photography shows advantages in efficiency and economic costs. In this paper, a novel Two-stream Non-uniform Concentration Reasoning Network (TNCR-Net) is proposed for single image PM <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> concentration estimation. Motivated by locally non-uniform particle pollution concentration distribution in images, we adopt patch-based scheme and adaptive weighted average mechanism to obtain patch-wise concentration and relative weight based on spatially varying perceptual relevance of local particle pollution concentration. Then aggregate patch-wise concentrations according to relative weights. To learn more effective feature from particular pollution image, we use a two-stream network structure with the dark channel map as the input of one stream. Besides, we employ attention-based feature fusion method to flexibly aggregate the feature maps of the two streams. Experiments on real-world dataset indicate that our TNCR-Net outperforms other state-of-the-art methods with fewer parameters.
BibTeX
@inproceedings{chen2022two,
  author = {Huilin Chen and Wenming Yang and Qingmin Liao},
  title = {{Two-Stream Non-Uniform Concentration Reasoning Network for Single Image Air Pollution Estimation}},
  booktitle = {ICIP},
  year = {2022},
  doi = {10.1109/icip46576.2022.9897665},
}

Loading related content...

Figure