IP Library › Granted Patent US 12700125
Granted Patent B2
US 12700125 · App. 18/590,828 · Granted Aug 4, 2026

Systems and methods for location triangulation based on time based panoramic frames

Inventors: Sonia Kastner (San Francisco, CA); Seva Safris (Las Vegas, NV); Kira Greco (San Francisco, CA)
Assignee: Pano AI, Inc.
G06T7/70G06V10/25G06V20/52H04N5/265H04N7/181G06T2207/30181G06T2207/30244H04W4/021
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 12700125
App. No.
18/590,828
Granted
Aug 4, 2026
Kind
B2
Abstract

A method includes identifying an image captured by an image capture device set at a first angle about an axis, the image corresponding to a time at which the image was captured, identifying within the image, a region of interest including an object to be used for calibration, determining, an image coordinate at which the object is displayed within the image, determining a camera angle corresponding to a position of the image capture system relative to the axis when the image was captured, identifying a bearing of the object relative to the reference direction, the bearing of the object determined using a geolocation of the image capture system and the time at which the image was captured, and determining, using the image coordinate, the camera angle, and the bearing of the object, an angular offset between the first angle and the reference direction to determine a second angle.

Claims (60)

1 . A system comprising:

one or more processors communicably coupled to one or more image capture systems, the one or more processors to:

identify, in a first image obtained from a first image capture system located at a first set of geographic coordinates, responsive to a machine learning model applied to the first image, an incident at a first angle within a first range of angles about a first axis of rotation of the first image capture system, the first range of angles of the first image relative to a first reference direction;

identify, responsive to the machine learning model applied to a second image obtained from a second image capture system at a second set of geographic coordinates, in the second image, the incident at a second angle within a second range of angles about a second axis of rotation of the second image capture system, the second range of angles of the second image relative to a second reference direction;

select a first group of constituent images comprising the first image, each constituent image of the first group corresponding to the first range of angles about the first axis;

select a second group of constituent images comprising the second image, each constituent image of the second group corresponding to the second range of angles about the second axis;

generate a first composite image using the first group of constituent images including a location of the incident;

generate a second composite image using the second group of constituent images including the location of the incident;

determine a third set of geographic coordinates for a geolocation of the incident based on the first set of geographic coordinates, the first angle, the second set of geographic coordinates, and the second angle; and

provide an output indicating the third set of geographic coordinates.

2 . The system of claim 1 , comprising the one or more processors to maintain, in one or more data structures, the first set of geographic coordinates for a first station comprising the first image capture system and the second set of geographic coordinates for a second station comprising the second image capture system.

3 . The system of claim 1 , comprising the one or more processors to:

identify, in the first image, a first indicator of the geolocation of the incident, the first indicator corresponding to a first one or more pixel coordinates within the first image; and

determine the first angle using one or more data structures maintaining association between the first one or more pixel coordinates and the first range of angles.

4 . The system of claim 3 , comprising the one or more processors to:

identify, in the second image, a second indicator of the geolocation of the incident, the second indicator corresponding to a second one or more pixel coordinates within the second image; and

determine the second angle using the one or more data structures maintaining association between the second one or more pixel coordinates and the second range of angles.

5 . The system of claim 1 , comprising the one or more processors to:

determine the third set of geographic coordinates based at least on an intersection of a first line extending away from the first set of geographic coordinates along the first angle and a second line extending away from the second set of geographic coordinates along the second angle.

6 . The system of claim 1 , wherein the first reference direction is different from the second reference direction.

7 . The system of claim 1 , wherein the first reference direction is North and the second reference direction is North.

8 . The system of claim 1 , wherein the machine learning model is trained using a training set of images, each image included in the training set corresponding to a label indicating that the respective image includes one or more visual features indicative of the incident.

9 . The system of claim 1 , wherein the incident corresponds to a fire and the one or more visual features include a feature of a smoke corresponding to the fire.

10 . The system of claim 1 , wherein the one or more processors are to present, for display, a user interface including one or more interface elements to selectively display at least one of a portion of the first image comprising the incident or a portion of the second image comprising the incident.

11 . A method comprising:

identifying, by one or more processors coupled with memory, in a first image obtained from a first image capture system located at a first set of geographic coordinates, responsive to a machine learning model applied to the first image, an incident at a first angle within a first range of angles about a first axis of rotation of the first image capture system, the first range of angles of the first image relative to a first reference direction;

identifying, by the one or more processors, responsive to the machine learning model applied to a second image obtained from a second image capture system at a second set of geographic coordinates, in the second image, the incident at a second angle within a second range of angles about a second axis of rotation of the second image capture system, the second range of angles of the second image relative to a second reference direction;

selecting, by the one or more processors, a first group of constituent images comprising the first image, each constituent image of the first group corresponding to the first range of angles about the first axis;

selecting, by the one or more processors, a second group of constituent images comprising the second image, each constituent image of the second group corresponding to the second range of angles about the second axis;

generating, by the one or more processors, a first composite image using the first group of constituent images including a location of the incident;

generating, by the one or more processors, a second composite image using the second group of constituent images including the location of the incident;

determining, by the one or more processors, a third set of geographic coordinates for a geolocation of the incident based on the first set of geographic coordinates, the first angle, the second set of geographic coordinates, and the second angle; and

providing, by the one or more processors, an output indicating the third set of geographic coordinates.

12 . The method of claim 11 , comprising:

maintaining, by the one or more processors, in one or more data structures, the first set of geographic coordinates for a first station comprising the first image capture system and the second set of geographic coordinates for a second station comprising the second image capture system.

13 . The method of claim 11 , comprising:

identifying, by the one or more processors, in the first image, a first indicator of the geolocation of the incident, the first indicator corresponding to a first one or more pixel coordinates within the first image;

determining, by the one or more processors, the first angle using one or more data structures maintaining association between the first one or more pixel coordinates and the first range of angles;

identifying, by the one or more processors, in the second image, a second indicator of the geolocation of the incident, the second indicator corresponding to a second one or more pixel coordinates within the second image; and

determining, by the one or more processors, the second angle using the one or more data structures maintaining association between the second one or more pixel coordinates and the second range of angles.

14 . The method of claim 11 , comprising:

determining, by the one or more processors, the third set of geographic coordinates based at least on an intersection of a first line extending away from the first set of geographic coordinates along the first angle and a second line extending away from the second set of geographic coordinates along the second angle, and wherein the first reference direction is North and the second reference direction is North.

15 . The method of claim 11 , wherein the machine learning model is trained using a training set of images, each image included in the training set corresponding to a label indicating that the respective image includes one or more visual features indicative of the incident.

16 . The method of claim 11 , wherein the incident corresponds to a fire and the one or more visual features include a feature of a smoke corresponding to the fire.

17 . The method of claim 11 , comprising:

presenting, by the one or more processors, for display, a user interface including one or more interface elements to selectively display at least one of a portion of the first image comprising the incident or a portion of the second image comprising the incident.

18 . A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:

identify, in a first image obtained from a first image capture system located at a first set of geographic coordinates, responsive to a machine learning model applied to the first image, an incident at a first angle within a first range of angles about a first axis of rotation of the first image capture system, the first range of angles of the first image relative to a first reference direction;

identify, responsive to the machine learning model applied to a second image obtained from a second image capture system at a second set of geographic coordinates, in the second image, the incident at a second angle within a second range of angles about a second axis of rotation of the second image capture system, the second range of angles of the second image relative to a second reference direction;

select a first group of constituent images comprising the first image, each constituent image of the first group corresponding to the first range of angles about the first axis;

select a second group of constituent images comprising the second image, each constituent image of the second group corresponding to the second range of angles about the second axis;

generate a first composite image using the first group of constituent images including a location of the incident;

generate a second composite image using the second group of constituent images including the location of the incident;

determine a third set of geographic coordinates for a geolocation of the incident based on the first set of geographic coordinates, the first angle, the second set of geographic coordinates, and the second angle; and

provide an output indicating the third set of geographic coordinates.

19 . The non-transitory computer readable medium of claim 18 , wherein the instructions when executed by the one or more processors, cause the one or more processors to:

maintain, in one or more data structures, the first set of geographic coordinates for a first station comprising the first image capture system and the second set of geographic coordinates for a second station comprising the second image capture system.

20 . The non-transitory computer readable medium of claim 18 , wherein the instructions when executed by the one or more processors, cause the one or more processors to:

identify, in the first image, a first indicator of the geolocation of the incident, the first indicator corresponding to a first one or more pixel coordinates within the first image; and

determine the first angle using one or more data structures maintaining association between the first one or more pixel coordinates and the first range of angles.