NVIDIA had 55 patents in metaverse during Q1 2024. NVIDIA Corp has filed patents for sensor parameter calibration techniques for in-cabin monitoring systems, machine learning models for robot control, calibration techniques for interior depth sensors and image sensors, generating 3D representations from 2D images using encoder-based models, and parallel edge decimation on high resolution meshes. These patents focus on improving the accuracy and efficiency of various technologies related to monitoring systems, robot control, image processing, and computational geometry. GlobalData’s report on NVIDIA gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
NVIDIA grant share with metaverse as a theme is 27% in Q1 2024. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Sensor calibration using fiducial markers for in-cabin monitoring systems and applications (Patent ID: US20240104941A1)
The patent filed by NVIDIA Corp. describes sensor parameter calibration techniques for in-cabin monitoring systems, specifically focusing on an occupant monitoring system (OMS) used in vehicles or machines. The system involves determining calibration parameters for interior image sensors to reference 2D captured images to an in-cabin 3D coordinate system. This calibration process involves detecting fiducial points in images, determining 2D and 3D coordinates for these points, computing a rotation-translation transform, and configuring operations based on the calibration parameter. The system can be used for various applications, including autonomous machines, simulation operations, digital twin operations, light transport simulation, content creation, deep learning, real-time streaming, virtual, augmented, or mixed reality content generation, conversational AI, synthetic data generation, and cloud computing resources.
The patent also includes claims detailing the system's components and functionalities, such as processing units determining 2D and 3D coordinates, computing transforms, detecting fiducial points, and calibrating sensors based on these parameters. The system can use computer vision algorithms, deep neural networks, or machine learning algorithms for detection and calibration processes. Additionally, the system can determine the position of movable objects within the interior space, compute calibration accuracy metrics, and translate image spaces between different sensors. The processor described in the patent performs similar functions as the system, including detecting fiducial points, determining coordinates, and storing calibration parameters. The method outlined in the patent involves determining occupant information based on sensor images calibrated using fiducial markers and known 3D coordinates within the interior space of the machine.
To know more about GlobalData’s detailed insights on NVIDIA, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
