System and method for artificial intelligence based determination of damage to physical structures

US11410287B2 · kind B2 · utility

Assignee

• Genpact Luxembourg S.à r.l. II · LU

Inventors

• Siva Tian · New York, US
• Krishna Dev Oruganty · Brown Center, US
• Adrita Barari · Bengaluru, IN
• Edmond John Schneider · Forest Meadow Mobile Home Park, US
• Nitish Kumar · Eindhoven, NL
• Amit Arora · Germantown, US
• Vikram Mahidhar · Lexington, US
• Chirag Jain · Delhi, IN
• Abhilash Nvs · Bhubaneshwar, IN

Key dates

• Filing date: May 15, 2020
• Grant date: Aug 9, 2022
• Expiry date: May 22, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2207/20084
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A method and system are provided for assessing damage to a structure. According to one embodiment, the method includes using a classifier that is trained to associate respective portions of in an image of a structure with respective external parts of the structure to detect several of external parts of a structure in a first image of the structure. The method also includes using a first machine learning system, trained to perform segmentation of an image, to identify one or more image segments in a second image, where each image segment represents damage of a particular type and, using a second machine learning system, trained to associate image segments with external parts identified in an image, to associate a first image segment with a first external part, indicating damage to the first external part.