Maxar Technologies has patented a method for 3D reconstruction from satellite imagery using deep learning. The method involves providing overlapping 2D satellite images, imaging device parameters, and a trained Machine Learning Network to predict depth maps, resulting in a geocoded 3D surface model. GlobalData’s report on Maxar Technologies gives a 360-degree view of the company including its patenting strategy. Buy the report here.

According to GlobalData’s company profile on Maxar Technologies, was a key innovation area identified from patents. Maxar Technologies's grant share as of February 2024 was 69%. Grant share is based on the ratio of number of grants to total number of patents.

3d reconstruction from satellite imagery using deep learning

Source: United States Patent and Trademark Office (USPTO). Credit: Maxar Technologies Inc

A recently granted patent (Publication Number: US11922572B2) discloses a method for 3D reconstruction from satellite imagery using Machine Learning Networks (MLN). The method involves providing overlapping 2D satellite images and imaging device parameters to the MLN, which computes a depth map based on the parameters. The depth map is then used to generate a textured geocoded 3D surface model, represented either as a mesh, surface representation, or voxel representation. The MLN is trained on a set of multi-view 3D geocoded ground truth data to accurately reconstruct the 3D model.

Furthermore, the patent includes a method for training the MLN for 3D reconstruction, involving training on a set comprising textured geocoded 3D surface models and extracting multi-view 3D geocoded ground truth data for training purposes. The textured geocoded 3D surface model is represented as a mesh with interconnected nodes and edges defining surfaces, each associated with texture information. This training method ensures the MLN can accurately compute depth maps and generate 3D models from satellite imagery, with the ground truth data extracted or rendered from the textured geocoded models for training accuracy. The patent also emphasizes the use of real-world data for training the MLN, enhancing the accuracy and reliability of the 3D reconstructions from satellite images.

To know more about GlobalData’s detailed insights on Maxar Technologies, buy the report here.

Premium 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.