Patents by Inventor Chirag Majithia

Chirag Majithia has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Training data generation for dynamic objects using high definition map data
    Patent number: 11590989
    Abstract: According to an aspect of an embodiment, operations may comprise receiving a plurality of frame sets generated while navigating a local environment, receiving an occupancy map (OMap) representation of the local environment, for each of the plurality of frame sets, generating, using the OMap representation, one or more instances each comprising a spatial cluster of neighborhood 3D points generated from a 3D sensor scan of the local environment, and classifying each of the instances as dynamic or static, tracking instances classified as dynamic across the plurality of frame sets using a tracking algorithm, assigning a single instance ID to tracked instances classified as dynamic across the plurality of frame sets, estimating a bounding box for each of the instances in each of the plurality of frame sets, and employing the instances as ground truth data in a training of one or more deep learning classifiers.
    Type: Grant
    Filed: July 2, 2020
    Date of Patent: February 28, 2023
    Assignee: NVIDIA CORPORATION
    Inventor: Chirag Majithia
  • TRAINING DATA GENERATION FOR DYNAMIC OBJECTS USING HIGH DEFINITION MAP DATA
    Publication number: 20210001891
    Abstract: According to an aspect of an embodiment, operations may comprise receiving a plurality of frame sets generated while navigating a local environment, receiving an occupancy map (OMap) representation of the local environment, for each of the plurality of frame sets, generating, using the OMap representation, one or more instances each comprising a spatial cluster of neighborhood 3D points generated from a 3D sensor scan of the local environment, and classifying each of the instances as dynamic or static, tracking instances classified as dynamic across the plurality of frame sets using a tracking algorithm, assigning a single instance ID to tracked instances classified as dynamic across the plurality of frame sets, estimating a bounding box for each of the instances in each of the plurality of frame sets, and employing the instances as ground truth data in a training of one or more deep learning classifiers.
    Type: Application
    Filed: July 2, 2020
    Publication date: January 7, 2021
    Inventor: Chirag Majithia