# US 2021/0343076 A1 · Satellite sar artifact suppression for enhanced three-dimensional feature extraction, change detection, and visualizations

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0343076 A1
- Document ID: US20210343076A1
- Status: Published application
- Kind: A1
- Application number: 17/373,429
- Filed: 2021-07-12
- Published: 2021-11-04
- Earliest claimed: 2019-02-08
- Assignees: Ursa Space Systems Inc.
- Applicants: Ursa Space Systems Inc.
- Inventors: Jeffrey Scott Pennings; Justyna Weronika Kosianka; Daniela Irina Moody
- Web page: https://patentgrep.com/patent/US20210343076A1

## CPC

- G01S 13/9021: {SAR image post-processing techniques}
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 5/70: Denoising; Smoothing
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 15/00: Three-dimensional [3D] image rendering
- G06T 15/205: {Image-based rendering}
- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06T 17/05: Geographic models
- G06T 2207/10044: Radar image
- G06T 2207/20081: Training; Learning
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Systems and methods for satellite Synthetic Aperture Radar (SAR) artifact suppression for enhanced three-dimensional feature extraction, change detection, and/or visualizations are described. In some aspects, the described systems and methods include a method for suppressing artifacts from complex SAR data associated with a scene. In some aspects, the described systems and methods include a method for creating a photo-realistic 3D model of a scene based on complex SAR data associated with a scene. In some aspects, the described systems and methods include a method for identifying three-dimensional (3D) features and changes in SAR imagery.

## Claims

### Claim 1

A method for creating a photo-realistic 3D model of a scene based on complex Synthetic Aperture Radar (SAR) data associated with a scene, the method comprising:
mapping the complex SAR data associated with the scene to a 3D model of the scene;
suppressing one or more SAR artifacts from the complex SAR data based on the mapping to obtain cleaned complex SAR data;
resampling the cleaned complex SAR data to generate one or more two-dimensional (2D) SAR images of the scene; and
generating the photo-realistic 3D model of the scene based on the one or more 2D SAR images of the scene.

### Claim 2 (depends on 1)

The method of claim 1, wherein resampling the cleaned complex SAR data comprises resampling In-phase (I) and Quadrature-phase (Q) data of the complex SAR data to generate the one or more 2D images.

### Claim 3 (depends on 1)

The method of claim 1, wherein generating the photo-realistic 3D model of the scene comprises creating a photo-realistic 3D model of the scene at least in part by using perspective modeling with the one or more 2D SAR images to simulate the scene from one or more viewing angles.

### Claim 4 (depends on 1)

The method of claim 1, wherein generating the photo-realistic 3D model of the scene comprises generating the photo-realistic 3D model using InSAR and/or stereo radargrammetry,

### Claim 5 (depends on 1)

The method of claim 1, wherein generating the photo-realistic 3D model of the scene comprises updating a photogrammetric 3D model of the scene.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
generating a library of training data associated with the scene, wherein generating the library comprises:
obtaining simulated SAR data labeled with objects and features within the scene;
associating 2D imagery data with a high-fidelity 3D surface model of the scene and 3D objects within the scene through one or more machine learning search algorithms; and
extracting 3D features and objects from the simulated SAR data based on the photo-realistic 3D model of the scene.

### Claim 7

An apparatus comprising:
at least one processor; and
at least one storage medium having encoded thereon executable instructions that, when executed by the at least one processor, cause the at least one processor to carry out a method for creating a photo-realistic 3D model of a scene based on complex Synthetic Aperture Radar (SAR) data associated with a scene, the method comprising:
mapping the complex SAR data associated with the scene to a 3D model of the scene;
suppressing one or more SAR artifacts from the complex SAR data based on the mapping to obtain cleaned complex SAR data;
resampling the cleaned complex SAR data to generate one or more two-dimensional (2D) SAR images of the scene; and
generating the photo-realistic 3D model of the scene based on the one or more 2D SAR images of the scene.

### Claim 8 (depends on 7)

The apparatus of claim 7, wherein resampling the cleaned complex SAR data comprises resampling In-phase (I) and Quadrature-phase (Q) data of the complex SAR data to generate the one or more 2D images.

### Claim 9 (depends on 7)

The apparatus of claim 7, wherein generating the photo-realistic 3D model of the scene comprises creating a photo-realistic 3D model of the scene at least in part by using perspective modeling with the one or more 2D SAR images to simulate the scene from one or more viewing angles.

### Claim 10 (depends on 7)

The apparatus of claim 7, wherein generating the photo-realistic 3D model of the scene comprises generating the photo-realistic 3D model using InSAR and/or stereo radargrammetry,

### Claim 11 (depends on 7)

The apparatus of claim 7, wherein generating the photo-realistic 3D model of the scene comprises updating a photogrammetric 3D model of the scene.

### Claim 12 (depends on 7)

The apparatus of claim 7, wherein the method further comprises:
generating a library of training data associated with the scene, wherein generating the library comprises:
obtaining simulated SAR data labeled with objects and features within the scene;
associating 2D imagery data with a high-fidelity 3D surface model of the scene and 3D objects within the scene through one or more machine learning search algorithms; and
extracting 3D features and objects from the simulated SAR data based on the photo-realistic 3D model of the scene.

### Claim 13

At least one non-transitory computer-readable storage medium having encoded thereon executable instructions that, when executed by at least one processor, cause the at least one processor to carry out a method for creating a photo-realistic 3D model of a scene based on complex Synthetic Aperture Radar (SAR) data associated with a scene, the method comprising:
mapping the complex SAR data associated with the scene to a 3D model of the scene;
suppressing one or more SAR artifacts from the complex SAR data based on the mapping to obtain cleaned complex SAR data;
resampling the cleaned complex SAR data to generate one or more two-dimensional (2D) SAR images of the scene; and
generating the photo-realistic 3D model of the scene based on the one or more 2D SAR images of the scene.

### Claim 14 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein resampling the cleaned complex SAR data comprises resampling In-phase (I) and Quadrature-phase (Q) data of the complex SAR data to generate the one or more 2D images.

### Claim 15 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein generating the photo-realistic 3D model of the scene comprises creating a photo-realistic 3D model of the scene at least in part by using perspective modeling with the one or more 2D SAR images to simulate the scene from one or more viewing angles.

### Claim 16 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein generating the photo-realistic 3D model of the scene comprises generating the photo-realistic 3D model using InSAR and/or stereo radargrammetry,

### Claim 17 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein generating the photo-realistic 3D model of the scene comprises updating a photogrammetric 3D model of the scene.

### Claim 18 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein the method further comprises:
generating a library of training data associated with the scene, wherein generating the library comprises:
obtaining simulated SAR data labeled with objects and features within the scene;
associating 2D imagery data with a high-fidelity 3D surface model of the scene and 3D objects within the scene through one or more machine learning search algorithms; and
extracting 3D features and objects from the simulated SAR data based on the photo-realistic 3D model of the scene.
