MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos
arXiv:2006.16479
Abstract
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 contribution is a new model, namely MSNet, which contains novel region proposal network designs and an unsupervised score refinement network for confidence score calibration in both bounding box and mask branches. We show that our model achieves state-of-the-art results compared to previous methods in our dataset. We will release our data, models and code.
arXiv commentWACV 2021
References in corpus (6)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- MetaAnchor: Learning to Detect Objects with Customized Anchors
- xBD: A Dataset for Assessing Building Damage from Satellite Imagery
- PolarMask: Single Shot Instance Segmentation with Polar Representation
- Benchmark Dataset for Automatic Damaged Building Detection from Post-Hurricane Remotely Sensed Imagery