Using a Priori Knowledge to Improve Scene Understanding

Abstract

Semantic segmentation algorithms that can robustly segment objects across multiple camera viewpoints is crucialfor assuring navigation and safety in emerging applicationssuch as autonomous driving. Existing algorithms treat eachimage in isolation, but autonomous vehicles often revisit thesame locations. We propose leveraging this a priori knowledge to improve semantic segmentation of images from se-quential driving datasets. We examine several methods tofuse these temporal scene priors, and introduce a prior fusion network that is able to learn how to transfer this information. Our model improves the accuracy of dynamic object classes from 69.1% to 73.3%, and static classes from 88.2% to 89.1%.

Cite

Text

Schroeder and Alahi. "Using a Priori Knowledge to Improve Scene Understanding." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00067

Markdown

[Schroeder and Alahi. "Using a Priori Knowledge to Improve Scene Understanding." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/schroeder2019cvprw-using/) doi:10.1109/CVPRW.2019.00067

BibTeX

@inproceedings{schroeder2019cvprw-using,
  title     = {{Using a Priori Knowledge to Improve Scene Understanding}},
  author    = {Schroeder, Brigit and Alahi, Alexandre},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2019},
  pages     = {487-489},
  doi       = {10.1109/CVPRW.2019.00067},
  url       = {https://mlanthology.org/cvprw/2019/schroeder2019cvprw-using/}
}