Computer Vision Object Detection and Pricing Automation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for object detection and valuation in images and videos are time-consuming and prone to inaccuracies, requiring manual estimation by professionals such as insurance adjusters, which leads to inefficient and unreliable insurance estimates.

Innovation Solution

A computer vision system utilizing convolutional neural networks (CNNs) for automatic detection, classification, and pricing of objects in images and videos, including preprocessing, bounding box generation, non-maximal suppression, and database comparison to generate accurate pricing reports.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual object detection and valuation methods are used, then professionals can review and verify objects, but the process becomes time-consuming and error-prone

Engineering Contradiction:

Improveaccuracy of object detection and valuationVSAvoidtime required for manual estimation

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical inspection with an automated computer vision system using convolutional neural networks. The CNN automatically detects, classifies, and prices objects in images, eliminating the need for manual estimation while maintaining or improving accuracy through algorithmic processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service automation where the computer vision system independently performs object detection, classification, and valuation without requiring professional intervention. The automated system serves itself by processing images and generating pricing reports autonomously.

Inventive Principle:

Principle #25Self-service

2Productivity

If manual estimation by professionals is used, then detailed review can be performed, but the process becomes mistake-ridden and inefficient

Engineering Contradiction:

Improvespeed of object detection and pricingVSAvoidaccuracy of insurance estimates

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent substitutes manual professional estimation with an automated neural network system that processes images rapidly and consistently. The convolutional neural network maintains high reliability through its trained models while dramatically increasing productivity by eliminating human error and working continuously without fatigue.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated computer vision systems are used, then speed and consistency improve, but system complexity increases

Engineering Contradiction:

Improverate of object detection and classificationVSAvoidcomplexity of computer vision system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the complex computer vision task into distinct functional modules: image processing, object detection, classification, and pricing determination. This segmentation allows each component to be optimized independently while working together as an integrated system, managing overall complexity through modular architecture.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12125074B2Computer vision systems and methods for automatically detecting, classifying, and pricing objects captured in images or videos

Publication Date: 2024.10.22 INSURANCE SERVICES OFFICE INC

AI summary

A system and method for automatically detecting, classifying, and processing objects captured in an image. The system receives an image from the image source and detects one or more objects in the image. The system then performs a high-level classification of each of the one or more objects in the image and extracts each of the one or more objects from the image. The system then performs a specific classification of each of the one or more objects and determines a price of each of the one or more objects. Finally, the system generates a pricing report comprising a price of each of the one or more objects.