AI Disaster Damage Assessment Using Prone Area Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for identifying disaster-affected areas using aerial images from drones or satellites are limited, as they lack detailed information and require significant manual labor, and often have insufficient data for accurate damage assessment due to the rarity of disasters.
Innovation Solution
A method and apparatus that utilize Artificial Intelligence (AI) to extract feature information from disaster-prone areas, combining it with disaster-affected area information to identify affected regions and determine the type and extent of damage through a learning model trained with labeled data, including additional images like pre-disaster, neighborhood, and geographical images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If aerial images from drones or satellites are used to identify disaster damage, then the coverage area is improved, but the measurement precision and detail information deteriorate
Solution Approach 1:
The patent combines multiple data sources including aerial images, disaster-prone area features, and additional information from various databases to create a comprehensive disaster damage assessment system that maintains both wide coverage and detailed precision
Solution Approach 2:
The patent segments the analysis into multiple components: disaster-affected area identification, disaster-prone area feature extraction, and additional information integration, allowing each component to contribute to both coverage and precision
2Measurement precision
If manual labor is used to identify disaster damage, then the measurement precision is improved, but the productivity deteriorates
Solution Approach 1:
The patent replaces manual mechanical analysis with an automated AI-based learning system that processes aerial images and disaster-prone area features to identify disaster damage, maintaining high precision while dramatically improving assessment speed
Solution Approach 2:
The system performs self-service through automated feature extraction and damage identification algorithms that analyze the data without requiring continuous manual intervention, enabling both high precision and productivity
3Device complexity
If only aerial images are used for disaster damage identification, then the device complexity is reduced, but the measurement precision deteriorates
Solution Approach 1:
The patent creates a multi-functional system that processes not only aerial images but also disaster-prone area features and additional information from various sources, making the system universally applicable to different disaster types while maintaining high precision
Data Source
AI summary
An operation method of a server for identifying disaster affected areas. The operation method of the server may include acquiring at least one first disaster image; deriving an affected area from each of the at least one first disaster image and acquiring affected area related information through labeling based on the derived affected area; and training a first learning model using the at least one first disaster image and the affected area related information.