Hinge Health‘s patented method and system use 2D skeletons to match human poses for 3D reconstruction. The technology involves scoring, matching, grouping, and maintaining consistency across multiple video sequences. The method identifies humans across different camera views by assigning affinity scores and grouping based on optimal pairwise matches. GlobalData’s report on Hinge Health gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData

Report-cover

Data Insights Hinge Health Inc - Company Profile

Buy the Report

Data Insights

The gold standard of business intelligence.

Find out more

According to GlobalData’s company profile on Hinge Health, AI-assisted medical imaging was a key innovation area identified from patents. Hinge Health's grant share as of May 2024 was 11%. Grant share is based on the ratio of number of grants to total number of patents.

Method for matching human pose data between camera views

Source: United States Patent and Trademark Office (USPTO). Credit: Hinge Health Inc

A recently granted patent (Publication Number: US12008772B2) outlines a method for identifying humans across multiple camera views using two-dimensional (2D) skeletons. The method involves performing pairwise scoring between 2D skeletons from different camera views, assigning affinity scores to pairs based on distances between rays projected from the cameras to elements of the skeletons, and identifying the best match between skeletons from different views. The process also includes grouping the skeletons based on these matches, allowing for the identification of humans across different camera perspectives.

Furthermore, the patent details additional features such as excluding pairs with divergent rays from the affinity score, setting thresholds for distances between rays, and determining deviations of attributes in a putative three-dimensional (3D) skeleton from a typical human. The method also involves calibrating each camera view by determining positions and angles of the cameras and synchronizing frames taken simultaneously from multiple camera views. Additionally, the patent includes instructions for executing these operations on a non-transitory, computer-readable medium, enabling systems to obtain 2D skeletons from multiple camera views, perform pairwise scoring, identify best matches, and group skeletons accordingly, facilitating efficient human identification across different camera perspectives.

To know more about GlobalData’s detailed insights on Hinge Health, 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

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.