IP Library Granted Patent US 12,646,315
Granted Patent B2
US 12,646,315 · App. 18/453,240 · Granted Jun 2, 2026

Aquatic biomass estimation

Inventors: Yangli Hector Yee (San Francisco, CA); Terry Allan Smith (Saratoga, CA); Bianca Bahman (San Francisco, CA)
Assignee: TidalX AI Inc.
G06V20/05G06T7/62G06T17/05G06V20/188G06T2207/10028
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,646,315
App. No.
18/453,240
Granted
Jun 2, 2026
Kind
B2
Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for aquatic biomass estimation. One of the methods includes obtaining an image of an aquatic environment including aquatic grass; providing the image to a network model trained to construct a point cloud indicating a portion of the image that represents the aquatic grass; generating a floor model indicating a floor of the aquatic environment where the aquatic grass grows; identifying, using (i) the floor model and (ii) the point cloud indicating the aquatic grass, (i) a first subset of points in the point cloud as indicating aquatic grass and (ii) a second subset of points in the point cloud as indicating the floor of the aquatic environment; and generating, using the first subset of points in the point cloud, an indication of biomass within the aquatic environment.

Claims (59)

1 . A method comprising:

obtaining an image of an aquatic environment;

providing the image to a network model trained to construct a point cloud indicating a portion of the image that includes aquatic grass and a floor of the aquatic environment where the aquatic grass grows;

generating a floor model indicating the floor of the aquatic environment where the aquatic grass grows;

identifying, using (i) the floor model and (ii) the point cloud indicating the portion of the image that includes the aquatic grass and the floor of the aquatic environment where the aquatic grass grows, a first subset of points in the point cloud as indicating aquatic grass and a second subset of points in the point cloud as indicating the floor of the aquatic environment; and

generating, using the first subset of points in the point cloud, an indication of biomass within the aquatic environment.

2 . The method of claim 1 , comprising:

obtaining sensor data from the aquatic environment; and

determining, using the sensor data, a physical dimension of the aquatic grass.

3 . The method of claim 2 , wherein obtaining the sensor data comprises:

obtaining sonar data from one or more sonar enabled devices operating in the aquatic environment.

4 . The method of claim 2 , wherein obtaining the sensor data comprises:

obtaining image data from one or more submersible cameras operating in the aquatic environment.

5 . The method of claim 1 , wherein generating the floor model indicating the floor of the aquatic environment comprises:

modeling regions of seabed with a geometric structure indicating one or more of a plane or interpolating spline.

6 . The method of claim 1 , wherein the aquatic grass is seagrass located on a seabed.

7 . The method of claim 1 , comprising:

generating a signal indicating the biomass within the aquatic environment; and

providing the signal to a device, wherein the signal is configured to display an indication of the biomass within the aquatic environment.

8 . The method of claim 1 , wherein generating the indication of the biomass within the aquatic environment comprises:

determining a density of the aquatic grass;

determining, using the first subset of points in the point cloud, a volume of the aquatic grass; and

wherein generating the indication of the biomass within the aquatic environment comprises using (i) the density of the aquatic grass and (ii) the first subset of points in the point cloud.

9 . A system comprising one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

obtaining an image of an aquatic environment;

providing the image to a network model trained to construct a point cloud indicating a portion of the image that includes aquatic grass and a floor of the aquatic environment where the aquatic grass grows;

generating a floor model indicating the floor of the aquatic environment where the aquatic grass grows;

identifying, using (i) the floor model and (ii) the point cloud indicating the portion of the image that includes the aquatic grass and the floor of the aquatic environment where the aquatic grass grows, a first subset of points in the point cloud as indicating aquatic grass and a second subset of points in the point cloud as indicating the floor of the aquatic environment; and

generating, using the first subset of points in the point cloud, an indication of biomass within the aquatic environment.

10 . The system of claim 9 , wherein the operations comprise:

obtaining sensor data from the aquatic environment; and

determining, using the sensor data, a physical dimension of the aquatic grass.

11 . The system of claim 10 , wherein obtaining the sensor data comprises:

obtaining sonar data from one or more sonar enabled devices operating in the aquatic environment.

12 . The system of claim 10 , wherein obtaining the sensor data comprises:

obtaining image data from one or more submersible cameras operating in the aquatic environment.

13 . The system of claim 9 , wherein generating the floor model indicating the floor of the aquatic environment comprises:

modeling regions of seabed with a geometric structure indicating one or more of a plane or interpolating spline.

14 . The system of claim 9 , wherein the aquatic grass is seagrass located on a seabed.

15 . The system of claim 9 , wherein the operations comprise:

generating a signal indicating the biomass within the aquatic environment; and

providing the signal to a device, wherein the signal is configured to display an indication of the biomass within the aquatic environment.

16 . The system of claim 9 , wherein generating the indication of the biomass within the aquatic environment comprises:

determining a density of the aquatic grass;

determining, using the first subset of points in the point cloud, a volume of the aquatic grass; and

wherein generating the indication of the biomass within the aquatic environment comprises using (i) the density of the aquatic grass and (ii) the first subset of points in the point cloud.

17 . One or more non-transitory computer storage media encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

obtaining an image of an aquatic environment;

providing the image to a network model trained to construct a point cloud indicating a portion of the image that includes aquatic grass and a floor of the aquatic environment where the aquatic grass grows;

generating a floor model indicating the floor of the aquatic environment where the aquatic grass grows;

identifying, using (i) the floor model and (ii) the point cloud indicating the portion of the image that includes the aquatic grass and the floor of the aquatic environment where the aquatic grass grows, a first subset of points in the point cloud as indicating aquatic grass and a second subset of points in the point cloud as indicating the floor of the aquatic environment; and

generating, using the first subset of points in the point cloud, an indication of biomass within the aquatic environment.

18 . The media of claim 17 , wherein the operations comprise:

obtaining sensor data from the aquatic environment; and

determining, using the sensor data, a physical dimension of the aquatic grass.

19 . The media of claim 18 , wherein obtaining the sensor data comprises:

obtaining sonar data from one or more sonar enabled devices operating in the aquatic environment.

20 . The media of claim 18 , wherein obtaining the sensor data comprises:

obtaining image data from one or more submersible cameras operating in the aquatic environment.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 22, 2024
From: X DEVELOPMENT LLC
To: TIDALX AI INC.
Reel/Frame 068477/0306 →
CORRECTIVE ASSIGNMENT TO CORRECT THE RECEIVING PARTY COMPANY NAME FROM "GOOGLE LLC" TO "X DEVELOPMENT LLC" PREVIOUSLY RECORDED ON REEL 065415 FRAME 0835. ASSIGNOR(S) HEREBY CONFIRMS THE CORRECTIVE ASSIGNMENT. Recorded Nov 2, 2023
From: YEE, YANGLI HECTOR; SMITH, TERRY ALLAN; BAHMAN, BIANCA
To: X DEVELOPMENT LLC
Reel/Frame 065441/0861 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 1, 2023
From: YEE, YANGLI HECTOR; SMITH, TERRY ALLAN; BAHMAN, BIANCA
To: GOOGLE LLC
Reel/Frame 065415/0835 →
Continuity (2)
Provisional Application 63399501 · Aug 19, 2022
Related Publication 20240062539A1 · Feb 22, 2024
References Cited (24)
US 5506616A · Scheps · 1996 [cited by examiner]
US 7796809B1 · Carder · 2010 [cited by examiner]
US 11493629B1 · Shahrestani · 2022 [cited by examiner]
US 11520042B1 · Douglass · 2022 [cited by examiner]
US 20090105952A1 · Grace · 2009 [cited by examiner]
US 20150206327A1 · Lauenstein · 2015 [cited by examiner]
US 20160259054A1 · Proctor · 2016 [cited by examiner]
US 20160341827A1 · Horner · 2016 [cited by examiner]
US 20180306916A1 · Kronander · 2018 [cited by examiner]
US 20190094356A1 · Hunt · 2019 [cited by examiner]
US 20190340440A1 · Atwater · 2019 [cited by examiner]
US 20200180740A1 · Christ · 2020 [cited by examiner]
US 20200379104A1 · Zimmerman · 2020 [cited by examiner]
US 20210031891A1 · Englot · 2021 [cited by examiner]
US 20210149543A1 · Nguyen · 2021 [cited by examiner]
US 20210209351A1 · Young · 2021 [cited by examiner]
US 20220214689A1 · Pavlica · 2022 [cited by examiner]
US 20230267731A1 · Shang · 2023 [cited by examiner]
US 20240062539A1 · Yee · 2024 [cited by examiner]
US 20240124111A1 · Swanson · 2024 [cited by examiner]
US 20240221180A1 · Siak · 2024 [cited by examiner]
US 20240355115A1 · Young · 2024 [cited by examiner]
US 20240355116A1 · Young · 2024 [cited by examiner]
Ventura et al., “High spatial resolution underwater data for mapping seagrass transplantation: A powerful tool for visualization and analysis”, Elsevier, Dec. 22, 2021 (Year: 2021). [cited by examiner]