CNN Floor Elevation Estimation for Remote Flood Risk Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The manual process of determining first floor height (FFH) for flood insurance is labor-intensive and costly, leading to many homeowners avoiding flood insurance due to high costs, and existing technologies lack the accuracy and reliability needed for precise flood risk assessment.
Innovation Solution
A computer-based system using convolutional neural networks (CNN) processes images to detect building features and combines this with digital elevation maps and building footprint data to automatically determine FFH, reducing the need for manual inspection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual inspection methods are used to determine first floor height, then measurement precision can be achieved, but device complexity and cost increase significantly
Solution Approach 1:
The patent replaces manual mechanical inspection methods with an automated computer-based system that uses image processing and machine learning algorithms. The system captures images of buildings and automatically determines first floor height through digital analysis, eliminating the need for physical manual measurement while maintaining accuracy.
Solution Approach 2:
The patent creates a digital copy of the building through image capture and processing. Instead of physically measuring the building, the system analyzes digital images to extract first floor height information, converting the physical measurement problem into a digital image analysis problem that can be solved automatically.
2Reliability
If manual inspection methods are used to determine first floor height, then accurate flood risk assessment can be achieved, but productivity decreases due to labor-intensive processes
Solution Approach 1:
The patent implements a self-service system where the computer-based algorithm automatically performs the entire first floor height determination process without human intervention. The system independently captures images, processes them through machine learning models, and generates flood risk assessments, eliminating the need for manual labor while maintaining reliability.
Solution Approach 2:
The patent enables continuous automated processing of building images to determine first floor heights. Unlike manual inspection which is discontinuous and labor-dependent, the system can continuously analyze multiple buildings in sequence, significantly increasing productivity while maintaining consistent assessment quality.
3Measurement precision
If manual inspection methods are used, then accurate FFH data can be obtained, but loss of time increases due to the labor-intensive nature of the process
Solution Approach 1:
The patent performs preliminary actions by pre-training machine learning models on building image data before actual FFH determination. The system prepares image processing algorithms and reference databases in advance, so that when actual building assessments are needed, the automated analysis can proceed rapidly without manual preparation time.
Data Source
AI summary
A method using a convolutional neural network to auto-determine a first floor height (FFH) and a FFH elevation (FFE) of a building. The FFH, and FFE of the building are determined with respect to the terrain or surface of the parcel of land on which the building is located. In turn, by knowing the FFH and/or FFE of the building on the parcel, it is possible to use that information while performing a flood risk assessment to a property without requiring a personal inspection of the parcel by a human.