Vision-based sound simulation for correcting acoustics at a location

Patent metadata

Field	Value
Publication number	US-12348954-B2
Application number	US-202218147915-A
Country	US
Kind code	B2
Filing date	Dec 29, 2022
Priority date	Dec 29, 2022
Publication date	Jul 1, 2025
Grant date	Jul 1, 2025

Abstract

The disclosure provides a method for audio calibration that uses audio simulation and reconstructed surface information from images or video recordings along with recorded sound. The surface component of the method introduces knowledge that enables audio wave propagation simulation for a particular location. Using the simulation results the sound distribution can be optimized. For example, unwanted audio reflection and occlusion can be recognized and resolved. In one example, the disclosure provides a method for improving acoustics at a location that includes: (1) generating a geometric model of a location using visual data obtained from the location, wherein the location includes an audio system, and (2) simulating, using the geometric model, movement of sound waves in the location that originate from the audio system. The disclosure also provides a computer system, a computer program product, and a mobile computing device that include features for improving acoustics at a location.

First claim

What is claimed is:

1. A method for improving acoustics at a location, comprising:
generating a geometric model of a location using visual data obtained from the location, wherein the location includes an audio system and the geometric model includes a configuration of the audio system obtained from the visual data; and
simulating, using the geometric model, movement of sound waves in the location that originate from the audio system.

2. The method as recited in claim 1 , further comprising providing an acoustic analysis for the location based on the simulating.

3. The method as recited in claim 2 , wherein the acoustic analysis includes potential audio issues associated with configuration of the audio system, configuration improvements for the audio system, configuration improvements for the location, or a combination thereof.

4. The method as recited in claim 1 , further comprising obtaining the visual data using a mobile computing device.

5. The method as recited in claim 4 , wherein the visual data includes one or more of photographs, video, LiDAR data, or positional data.

6. The method as recited in claim 1 , wherein the geometric model includes estimated objects, surfaces, layout, and material information.

7. The method as recited in claim 1 , wherein the generating the geometric model includes reconstructing surface geometries, reconstructing material of the geometries, detecting objects, estimating object poses, estimating listener position, and estimating screen position.

8. The method as recited in claim 1 , further comprising verifying the geometric model before the simulating.

9. The method as recited in claim 1 , wherein the simulating includes computing the movement of the sound waves from the audio system to at least one listener's position represented in the geometric model.

10. The method as recited in claim 9 , wherein the computing uses a physically based audio wave propagation model.

11. The method as recited in claim 1 , wherein the simulating includes multiple iterations using different modifications of the geometric model.

12. The method as recited in claim 1 , wherein the audio system includes multiple speakers and the simulating includes adjusting frequency equalization per each of the speakers and improving output of the speakers based on a listener's position represented in the geometric model.

13. The method as recited in claim 1 , further comprising obtaining audio measurements at the location using a microphone and providing acoustic analysis using the audio measurements.

14. The method as recited in claim 13 , wherein at least a portion of the visual data corresponds to obtaining the audio measurements and the method further comprises estimating a position of the microphone using the at least a portion of the visual data.

15. The method as recited in claim 13 , wherein the acoustic analysis includes gain normalization and frequency equalization for the audio system.

16. The method as recited in claim 1 , wherein the location is a room.

17. A computing system for improving acoustics at a location, comprising:
one or more processors to perform operations including:
generating a geometric model of a location using visual data obtained from the location, wherein the location includes an audio system and the geometric model includes a configuration of the audio system obtained from the visual data; and
simulating, using the geometric model, movement of sound waves in the location that originate from the audio system.

18. The computing system as recited in claim 17 , wherein the operations further include providing an acoustic analysis for the location based on the simulating.

19. The computing system as recited in claim 18 , wherein providing the acoustic analysis includes using audio measurements from the location.

20. The computing system as recited in claim 18 , wherein the acoustic analysis includes potential audio issues associated with configuration of the audio system and configuration improvements for the audio system.

21. The computing system as recited in claim 20 , wherein the acoustic analysis further includes potential audio issues associated with configuration of objects in the location and configuration improvements for the objects.

22. The computing system as recited in claim 18 , wherein the generating the geometric model includes one or more of reconstructing surface geometries, reconstructing material of the geometries, detecting objects, estimating object poses, estimating listener position, and estimating screen position.

23. The computing system as recited in claim 18 , wherein the one or more operations include verifying the geometric model before the simulating.

24. The computing system as recited in claim 18 , wherein the simulating includes computing the movement of the sound waves from the audio system to at least one listener's position using a physically based audio wave propagation model.

25. The computing system as recited in claim 24 , wherein the simulating includes multiple iterations using different modifications of the geometric model.

26. The computing system as recited in claim 18 , wherein the one or more processors are located with a server in a cloud computing environment.

27. A non-transitory computer readable medium having a series of operating instructions that direct operations of one or more processors to improve acoustics at a location, the operations including:
generating a geometric model of a location using visual data obtained from the location, wherein the location includes an audio system and the geometric model includes a configuration of the audio system obtained from the visual data; and
simulating, using the geometric model, movement of sound waves in the location that originate from the audio system.

Assignees

• Nvidia Corp

Inventors

• Stengel Michael
• Lopes Ward
• Kim Joohwan
• Luebke David

Classifications

• G01S17/89 Primary

  for mapping or imaging · CPC title

• G01S17/86

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title

• H04S7/302

  Electronic adaptation of stereophonic sound system to listener position or orientation (H04S7/301 takes precedence) · CPC title

• H04S7/301

  Automatic calibration of stereophonic sound system, e.g. with test microphone · CPC title

• H04S7/40 Primary

  Visual indication of stereophonic sound image · CPC title