Deep learning model to perform damage assessment on drone and aerial imagery. A brief summary of the item is not available. Add a brief summary about the item.
Deep learning package
by
Item created: Sep 30, 2024 Item updated: Jan 2, 2025 Number of downloads: 753
Description
This model performs damage assessment on drone and aerial imagery. It is trained to identify features of interest to disaster response managers from aerial images. The model is fine-tuned on the LADI v2 dataset, which contains 10,000 aerial images labeled by volunteers from the Civil Air Patrol. The Low Altitude Disaster Imagery (LADI) dataset was created to address the relative lack of annotated post-disaster aerial imagery in the computer vision community. Low altitude post-disaster aerial imagery from small planes and UAVs can provide high-resolution imagery to emergency management agencies to help them prioritize response efforts and perform damage assessments. In order to accelerate their workflow, computer vision can be used to automatically identify images that contain features of interest, including infrastructure such as buildings and roads, damage to such infrastructure, and hazards such as floods or debris.
For
LADI v2, the authors used CAP volunteers who were trained in the FEMA
damage assessment process, and collected damage labels using the
defined FEMA Preliminary Damage Assessment scale:
unaffected, affected, minor, major, destroyed. These damage levels have
specific criteria, helping reduce the subjectivity of identifying
whether a structure is damaged. This model is a pretrained classifier
trained on the LADI v2 dataset and serves as a basis for fine-tuning and
potential deployments.
The model performs multi-label classification and categorizes images as belonging to one or more of the following classes:
- bridges_any
- buildings_any
- buildings_affected_or_greater
- buildings_minor_or_greater
- debris_any
- flooding_any
- flooding_structures
- roads_any
- roads_damage
- trees_any
- trees_damage
- water_any
Using the model
Follow the guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.
Fine-tuning the model
This model cannot be fine-tuned using ArcGIS tools.
Input
High resolution individual drone imagery or an orthomosaic.
Output
Feature class containing classified disaster.
Applicable geographies
The model is expected to work well in US or similar kind of geographies .
Model architecture
This model uses the google/bit-50 model architecture for classification. Refer to https://github.com/LADI-Dataset/ladi-overview for model training code
Accuracy metrics
This model has metrics for each class is mentioned here.
Training data
The model has been trained on the LADI v2 dataset.
Sample results
Here are a few results from the model.
Predicted classes: buildings_any;flooding_any;water_any;flooding_structures;buildings_affected_or_greater
Developed by: Jeff Liu, Sam Scheele.
Funded by: Department of the Air Force under Air Force Contract No. FA8702-15-D-0001
License: MIT for code, CC-BY-4.0 for LADI datset
An in-depth description of the item is not available.
Layers
Tools
Tables
Basemap
Project Contents:
Solution Contents
Contents
Layers
Screenshots
Terms of Use
This work is licensed under the Esri Master License Agreement.
No special restrictions or limitations on using the item's content have been provided.
Details
Dashboard views: Desktop
Source:
Creating data in:
Published as:
Other Views:
Dependent items in the recycle bin
Applicable: 2d
Size: 89.777 MB
ID: 72748653112b47498764b1918c6a628d
Image Count: 0
Image Properties
Layer Drawing
Using tiles from a cache
Dynamically from data
Share
Owner
Folder
Categories
This item has not been categorized.
Credits (Attribution)
No acknowledgements.ESRI, MIT Lincoln Laboratory, United States Department of the Air Force
Comments (0)