公开(公告)号：US12118779B1

公开(公告)日：2024-10-15

申请号：US17936551

申请日：2022-09-29

申请人： UIPCO, LLC

发明人： Yangqiu Hu ,  David Lamar Rogers ,  Ting Lu ,  Jess W. Gingrich

IPC分类号： G06V20/10 ,  G06Q10/10 ,  G06V10/44 ,  G06V10/764 ,  G06V10/774 ,  G06V20/17 ,  G16H30/40

CPC分类号： G06V20/176 ,  G06Q10/10 ,  G06V10/44 ,  G06V10/764 ,  G06V10/774 ,  G06V20/17 ,  G16H30/40

摘要： A system and method for processing occluded aerial images of structures to assess structural damage is disclosed. The system employs a generative model that is trained on data created by adding occlusive features to clear aerial images. Both the clear images and their simulated occluded counterparts (image pairs) are inputted into the generative model as training data, and the model learns to recognize and discriminate patterns between the pairs. This process is fully automated and does not require manual labeling. Following training, the model is capable of receiving real (non-simulated) occluded images and generating a clarified image that can reveal structural details previously not apparent to automatically determine a damage classification for the property.

公开(公告)号：US11893538B1

公开(公告)日：2024-02-06

申请号：US17807326

申请日：2022-06-16

申请人： UIPCO, LLC

发明人： Jess W. Gingrich ,  Yangqiu Hu ,  David Rogers

IPC分类号： G06Q10/10 ,  G06Q10/20 ,  G06T7/00 ,  G06F30/13 ,  G06Q50/16 ,  G06N3/08 ,  G06Q30/0283 ,  G06Q50/26 ,  G06Q40/08

CPC分类号： G06Q10/10 ,  G06F30/13 ,  G06N3/08 ,  G06Q10/20 ,  G06Q30/0283 ,  G06Q50/16 ,  G06Q50/26 ,  G06T7/0002 ,  G06Q40/08 ,  G06T2207/10032 ,  G06T2207/20081 ,  G06T2207/30184

摘要： A system and method for capturing and automated processing aerial images of structures to assess structural damage is disclosed. The system comprises a computing system used to obtain images of selected locations associated with known structures at different points in time before and after a natural disaster. The images are used to automatically create three-dimensional models that are used to detect the specific portions of a structure that may be damaged as well as the spatial extent of that damage. In addition, the imagery can be fed into a damage classifier that automatically classifies the degree of damage and generates accurate estimates of repair costs. The system and method may be deployed to quickly assess damage of structures in a disaster area and provide reports of the damage to homeowners and/or insurers.