20230141319. METHODS AND SYSTEMS FOR USING TRAINED GENERATIVE ADVERSARIAL NETWORKS TO IMPUTE 3D DATA FOR MODELING PERIL simplified abstract (STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY)
Contents
- 1 METHODS AND SYSTEMS FOR USING TRAINED GENERATIVE ADVERSARIAL NETWORKS TO IMPUTE 3D DATA FOR MODELING PERIL
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 METHODS AND SYSTEMS FOR USING TRAINED GENERATIVE ADVERSARIAL NETWORKS TO IMPUTE 3D DATA FOR MODELING PERIL - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Original Abstract Submitted
METHODS AND SYSTEMS FOR USING TRAINED GENERATIVE ADVERSARIAL NETWORKS TO IMPUTE 3D DATA FOR MODELING PERIL
Organization Name
STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY
Inventor(s)
Ryan Knuffman of Danvers IL (US)
METHODS AND SYSTEMS FOR USING TRAINED GENERATIVE ADVERSARIAL NETWORKS TO IMPUTE 3D DATA FOR MODELING PERIL - A simplified explanation of the abstract
This abstract first appeared for US patent application 20230141319 titled 'METHODS AND SYSTEMS FOR USING TRAINED GENERATIVE ADVERSARIAL NETWORKS TO IMPUTE 3D DATA FOR MODELING PERIL
Simplified Explanation
The abstract describes a method and system for using a trained generative adversarial network (GAN) to improve peril modeling and vehicle orientation/navigation. It involves receiving a semantically-segmented 3D point cloud, generating a gap-filled point cloud, and generating a digital map.
- The method/system uses a trained GAN to enhance peril modeling and vehicle orientation/navigation.
- It starts by receiving a semantically-segmented 3D point cloud, which is a collection of data points representing objects in a 3D space.
- The GAN then generates a gap-filled point cloud by filling in missing or incomplete data points in the original point cloud.
- Finally, the system generates a digital map based on the completed point cloud, providing a visual representation of the environment.
Potential Applications
- Improved peril modeling: The technology can be used to enhance the accuracy and detail of modeling natural disasters or other perils, aiding in risk assessment and mitigation.
- Autonomous vehicles: By improving vehicle orientation and navigation, the system can contribute to the development of self-driving cars and other autonomous vehicles.
- Urban planning: The generated digital maps can assist in urban planning and infrastructure development by providing detailed and up-to-date information about the environment.
Problems Solved
- Incomplete or missing data in 3D point clouds can hinder accurate modeling and analysis.
- Vehicle orientation and navigation systems may struggle with complex or changing environments.
- Traditional methods of peril modeling and map generation may lack the level of detail and accuracy provided by the trained GAN.
Benefits
- Enhanced accuracy: The GAN-based approach improves the completeness and quality of 3D point clouds, resulting in more accurate modeling and navigation.
- Time and cost savings: The automated generation of digital maps reduces the need for manual data collection and processing, saving time and resources.
- Improved safety: The technology can contribute to safer navigation for autonomous vehicles and better risk assessment for perils, leading to improved safety measures.
Original Abstract Submitted
a method for using a trained generative adversarial network to improve peril modeling includes receiving a semantically-segmented 3d point cloud; generating a gap-filled point cloud; and generating a digital map. a computing system for using a trained generative adversarial network to improve vehicle orientation and navigation includes one or more processors, and one or more memories having stored thereon computer-executable instructions that, when executed, cause the computing system to: receive a semantically-segmented 3d point cloud; generate a gap-filled point cloud; and generate a digital map. a non-transitory computer-readable medium includes computer-executable instructions that, when executed, cause a computer to: receive a semantically-segmented 3d point cloud; generate a gap-filled point cloud; and generate a digital map.
