Patent No.: US 10,909,847 B1

BUILDING URBAN AREA NOISE POLLUTION MAPS AND MITIGATING NOISE FROM EMERGENCY VEHICLES

Date of Patent: Feb. 2, 2021

Applicant: All Turtles Corporation, San Francisco, CA (US)

Inventor: Phil Libin, San Francisco, CA (US)

Assignee: All Turtles Corporation, San Francisco, CA (US)

Appl. No.: 16/546,389

Filed: Aug. 21, 2019

Related U.S. Application Data

Provisional application No. 62/733,477, filed on Sep. 19, 2018.

U.S. Cl.

CPC ....... G08G 1 (2019.01); G10L 0965 (2013.01); G06N 20/00 25/51 (2013.01); G01C 21/26 (2013.01)

ABSTRACT

Constructing a noise pollution map for an area includes a first subset of users performing initial noise recordings in the area using audio devices, using machine learning to provide classification of noises in the initial recordings, a second subset of users, larger than the first, capturing noise in the area using audio devices, creating summaries of noises using the classification to classify noises captured by the second subset, and aggregating the summaries to construct the noise pollution map. The audio devices may include headsets, smart speakers, smart televisions, and/or computers. The summaries may include source information, amplitude and frequency characteristics, duration, parameters of the audio devices, user location surroundings, and/or user movement information.

I. CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to U.S. Prov. App. No. 62/733,477, filed on Sep.19, 2018, entitled "BUILDING URBAN AREA NOISE POLLUTION MAPS AND MITIGATING NOISE FROM EMERGENCY VEHICLES".

II. TECHNICAL FIELD

This application is directed to information technologies for measuring and mitigating urban noise.

III. BACKGROUND OF THE INVENTION

Urban area noise negatively affects hundreds of millions worldwide, causing health issues such as sleep disturbance, cardiovascular effects, and hearing impairment. Studies highlight the impact of noise on vulnerable populations, particularly children and the elderly.

IV. SUMMARY OF THE INVENTION

The described system constructs a noise pollution map using machine learning and user-generated noise recordings. It features a three-phase process leveraging various audio technologies to measure, classify, and summarize noise data.

V. DETAILED DESCRIPTION OF VARIOUS EMBODIMENTS

1. System Design
The system consists of:

  • Phase 1: Users provide noise samples which are uploaded to the cloud.
  • Phase 2: Machine learning algorithms classify noise sources using the collected data.
  • Phase 3: Local software on devices captures and summarizes ongoing noise.

This architecture allows for continuous tracking of noise pollution and supports urban planning decisions. Additionally, emergency vehicles can utilize directional sound systems to optimize navigation through traffic while minimizing noise disruption.

VI. CLAIMS

The invention claims include methods for constructing noise pollution maps using two subsets of users:

  1. A method involving the classification of noises from initial recordings.
  2. A method of utilizing various audio devices for continuous noise tracking and summarization.
  3. Cloud interactions for aggregating and analyzing noise summaries, leading to actionable insights for pollution management.