Corpus ID: 220265460

MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos

@article{Zhu2020MSNetAM,
  title={MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos},
  author={Xiaoyu Zhu and Junwei Liang and Alexander G. Hauptmann},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.16479}
}
  • Xiaoyu Zhu, Junwei Liang, Alexander G. Hauptmann
  • Published 2020
  • Computer Science
  • ArXiv
  • In this paper, we study the problem of efficiently assessing building damage after natural disasters like hurricanes, floods or fires, through aerial video analysis. We make two main contributions. The first contribution is a new dataset, consisting of user-generated aerial videos from social media with annotations of instance-level building damage masks. This provides the first benchmark for quantitative evaluation of models to assess building damage using aerial videos. The second… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES

    Feature Pyramid Networks for Object Detection

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Damage Assessment from Social Media Imagery Data During Disasters

    VIEW 12 EXCERPTS
    HIGHLY INFLUENTIAL

    Improving Object Localization with Fitness NMS and Bounded IoU Loss

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL

    PolarMask: Single Shot Instance Segmentation with Polar Representation

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    xbd: A dataset for assessing building damage from satellite imagery, 2019

    • Ritwik Gupta, Richard Hosfelt, +6 authors Matthew Gaston
    • 2019
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    A Latent Analysis of Earth Surface Dynamic Evolution Using Change Map Time Series

    VIEW 1 EXCERPT

    Adam: A Method for Stochastic Optimization

    VIEW 1 EXCERPT