Automated Property Valuation Using Aerial Imagery and Machine Learning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The manual and time-consuming process of inventorying and valuing real property for municipal tax reassessments is inefficient, requiring extensive site visits and resource-intensive data collection.

Innovation Solution

A system utilizing aerial and satellite imagery, combined with machine learning and computer vision, automates the process by generating accurate sketches and building plans without on-site inspections, integrating data from multiple sources and training models for property valuation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual data collection and site visits are used for property inventorying, then measurement precision and reliability are maintained, but productivity is severely reduced and time consumption increases

Engineering Contradiction:
Improveproperty inventory accuracyVSAvoidproperty inventory throughput
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent uses aerial imagery and computer vision to create digital copies and sketches of properties, replacing the need for physical site visits. The system generates accurate property sketches, footprint measurements, and structural assessments from remote imagery, maintaining measurement precision while dramatically improving productivity by enabling batch processing of multiple properties simultaneously

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical process of manual data collection and physical inspection with an automated computer vision system. Machine learning models analyze aerial imagery to extract property characteristics, replacing the need for human appraisers to physically visit and measure each property, thereby resolving the contradiction between accuracy and throughput

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automated computer vision systems are used for property inventorying, then productivity and time efficiency are improved, but device complexity and initial resource requirements increase

Engineering Contradiction:
Improveproperty inventory throughputVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent develops a universal computer vision platform that can handle multiple property assessment tasks through a single system. The same aerial imagery and machine learning models are used to generate sketches, measure footprints, identify structural types, and assess property conditions, eliminating the need for separate specialized tools and reducing overall system complexity despite the advanced technology involved

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Measurement precision

If comprehensive on-site inspections are conducted for each property, then measurement precision is maintained, but loss of time and resource consumption increase

Engineering Contradiction:
Improveproperty valuation accuracyVSAvoidtime per property assessment
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary property assessments using aerial imagery and computer vision before any physical site visit is needed. The system pre-generates property sketches, measurements, and structural assessments from remote data, allowing appraisers to review and verify only the most critical properties in person, thereby significantly reducing total time consumption while maintaining accuracy

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12062071B1Method and system for inventorying and developing the value of real property
Publication Date: 2024.08.13 BARNETT DAVID M
  • US12062071B1 patent drawing

AI summary

A method and system of inventorying and developing value for real property. An aerial photograph of a property to be inventoried and valued is obtained, an outline or outlines of the structure and its location on the property are identified, outlines of the structural sections of the property are mapped, a partial sketch of the outline of the structure is created, wherein the outline includes square footage estimates for each section, and is oriented with the front of the structure to the bottom of the page, and the information is integrated across multiple images and the structural type of each section of the structure is identified. The method and system rely on machine learning in order to increase the accuracy of the method and system.