Machine Learning Object Sizing for Mobile Damage Assessment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Determining the actual size of damaged objects in images captured by mobile devices is challenging without a reference object, complicating repair cost estimation.

Innovation Solution

A computing platform generates commands to capture images, determines reference objects and their dimensions, predicts objects in the image, and estimates repair costs using machine learning algorithms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a reference object is placed in the camera frame to determine actual size, then measurement precision is improved, but device complexity and ease of operation deteriorate

Engineering Contradiction:

Improveobject size measurementVSAvoidimage capture operation

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system uses the mobile device's own camera to capture images and automatically processes them through machine learning algorithms to determine object dimensions. The device serves itself by using its built-in camera and processing capabilities without requiring external reference objects or manual measurement tools, thereby maintaining ease of operation while achieving accurate measurement.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical approach of using physical reference objects with a computational approach using machine learning algorithms. Instead of relying on physical reference items being placed in the scene, the system uses image processing and AI models to automatically determine object sizes, eliminating the need for additional physical components and simplifying the user experience.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If image analysis is performed to determine damaged objects, then measurement precision is improved, but productivity deteriorates due to difficulty in determining all damaged objects

Engineering Contradiction:

Improvedamaged object identificationVSAvoiddamage assessment speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system replaces manual visual inspection with automated machine learning algorithms that can rapidly analyze images and identify damaged objects. The AI models process images to detect damage patterns, predict object types, and estimate dimensions much faster than manual assessment, thereby improving productivity while maintaining or enhancing measurement precision through sophisticated computational analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250299231A1Processing system having a machine learning engine for providing a surface dimension output

Publication Date: 2025.09.25 ALLSTATE INSURANCE COMPANY

AI summary

Systems and apparatuses for generating object dimension outputs and predicted object outputs are provided. The system may collect an image from a mobile device. The system may analyze the image to determine whether it contains one or more standardized reference objects. Based on analysis of the image and the one or more standardized reference objects, the system may determine an object dimension output. The system may also determine a predicted object output that includes additional objects predicted to be in a room corresponding to the image. Using object dimension outputs and the predicted object output, the system may determine an estimated repair cost.