This inventor holds 1 USPTO granted patent. Top assignee: Scale Ai, Inc.. Active years: 2023.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2023
Title: Jeffrey Alan Anders and Automated Point-Cloud Annotation
Introduction
Jeffrey Alan Anders is an inventor based in Denver, Colorado, whose patent work addresses the automated annotation of point-cloud data. His disclosed invention uses machine-learning models to detect and localize objects and generate cuboid annotations.
Latest Patents
Anders is associated with 1 patent: “Pre-labeling Data with Cuboid Annotations.” The invention describes processing point-cloud data to detect, associate, and localize objects, producing tracks made up of cuboid annotations. An object-detection model performs coarse localization, while a refinement model uses two-dimensional projections and predicted cuboid tracks to improve localization. The system selects keyframes, interpolates annotations for intervening frames, and presents the resulting tracks for user review and editing.
Career Highlights
Anders is associated with Scale AI, Inc. His patent describes techniques for streamlining the preparation of annotated data by combining machine-learning predictions with human review.
Collaborations
The provided information lists Elliot Branson and Chiao-Lun Cheng as Anders’s coworkers. Their specific roles in the patent or related work are not specified.
Conclusion
Jeffrey Alan Anders’s disclosed invention focuses on making point-cloud annotation more efficient through automated object detection, cuboid tracking, and refinement, with user editing available for review.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile