Matterport. has been granted a patent for methods that enhance the accuracy of automated classifications in machine learning. The techniques involve adjusting classifications of photo-realistic images based on related images and using these classifications to automatically segment and classify portions of a 3D model. GlobalData’s report on Matterport gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Matterport, 3d modelling and rendering was a key innovation area identified from patents. Matterport's grant share as of July 2024 was 64%. Grant share is based on the ratio of number of grants to total number of patents.
Automated classification improvement for 3d model images
The patent US12073609B2 outlines a method for classifying regions within a 3D model generated from a collection of digital images. The process begins with determining a target portion of the 3D model and identifying multiple source-regions in the digital images that correspond to this target portion. Each source-region is assigned a classification, which is then used to classify a target region in a target digital image. The method emphasizes the use of spatial metadata, including capture location and depth data, to identify source-regions effectively. Notably, the 3D model can represent structures such as buildings, with specific classifications potentially indicating room types.
Additionally, the method includes steps for aggregating classifications from the identified source-regions to derive an overall classification for the target region. This aggregation may involve calculating a confidence score based on the classifications of the source-regions, which can be presented to computing devices for further processing. The patent also covers the storage of instructions on non-transitory computer-readable media that enable the execution of this classification method by computing devices. Overall, the claims detail a systematic approach to enhancing the accuracy of region classification in 3D models derived from digital imagery.
To know more about GlobalData’s detailed insights on Matterport, 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.
