Flare stack monitoring

Patent metadata

Field	Value
Publication number	US-10041673-B2
Application number	US-201313951235-A
Country	US
Kind code	B2
Filing date	Jul 25, 2013
Priority date	Jul 25, 2013
Publication date	Aug 7, 2018
Grant date	Aug 7, 2018

Abstract

Methods, systems, and computer-readable and executable instructions are described herein. One method includes receiving a sequence of images of a flare stack area from a thermal imaging component, identifying a first portion of the flare stack area moving at a first threshold optical flow using the sequence of images of the flare stack area, and identifying a second portion of the flare stack area moving at a second threshold optical flow using the sequence of images of the flare stack area.

First claim

What is claimed:

1. A method for flare monitoring, comprising:
receiving a sequence of images of a flare stack area from a thermal imaging component;
identifying a first portion of the flare stack area moving in two dimensions at an identified first threshold optical flow using the sequence of images of the flare stack area, wherein the identified first threshold optical flow corresponds to a smoke portion of the flare stack area;
identifying a second portion of the flare stack area moving in two dimensions at an identified second threshold optical flow using the sequence of images of the flare stack area, wherein the identified second threshold optical flow corresponds to a flare portion of the flare stack area; and
segmenting a second image of the flare stack area to differentiate both the first and second portions of the flare stack area from non-smoke and non-flare elements of the image of the flare stack area.

2. The method of claim 1 , including:
applying a temperature-intensity map to the sequence of images; and
separating a foreground of the sequence of images from a background of the sequence of images using the temperature-intensity map.

3. The method of claim 1 , wherein the first threshold optical flow is greater than the second threshold optical flow.

4. The method of claim 1 , including identifying the first threshold optical flow and the second threshold optical flow utilizing historical images of the flare stack area from the thermal imaging component.

5. The method of claim 1 , including receiving a sequence of images of the flare stack area from an optical imaging component, wherein the sequence of images from the optical imaging component are combined with the sequence of images from the thermal imaging component.

6. The method of claim 5 , including receiving the sequence of optical imaging components during a threshold period of time, wherein the threshold period of time includes a dynamically changing period of time based on a number of parameters.

7. The method of claim 1 , wherein:
the sequence of images includes a video stream; and
identifying the first portion and the second portion includes calculating a dense optical flow between frames of the video stream.

8. A non-transitory computer-readable medium storing instructions executable by a processing resource to:
receive a sequence of images of a flare stack area captured by a thermal imaging component;
receive a visual identification of a smoke portion and a flare portion of the sequence of images of the flare stack area;
identify an identified first threshold optical flow of smoke movement in two dimensions using the received sequence of images and the received visual identification of the smoke portion of the images of the flare stack area;
identify an identified second threshold optical flow of flare movement in two dimensions using the received sequence of images and the received visual identification of the flare portion of the images of the flare stack area; and
segment a second image of the flare stack area to differentiate both the first and second portions of the flare stack area from non-smoke and non-flare elements of the image of the flare stack area.

9. The medium of claim 8 , wherein the instructions include instructions executable by the processing resource to identify a sub-area of the flare stack area of the sequence of images to process based on two-dimensional locations of the smoke portions and flare portions.

10. The medium of claim 8 , wherein the instructions executable to identify the first threshold optical flow and the second threshold optical flow include instructions to draw boundaries between pixels in the sequence of images of the identified smoke portion and the identified flare portion.

11. The medium of claim 8 , wherein the instructions executable to identify the first threshold optical flow and the second threshold optical flow include instructions to compute a distance between the flare portion and the smoke portion in each image of the sequence of images, wherein the distance includes a two-dimensional distance.

12. The medium of claim 11 , wherein the instructions executable to identify the first threshold optical flow and the second threshold optical flow include instructions to base the identification on a ground-truth rule of flare and smoke, wherein the ground-truth rule of flare and smoke is smoke particles move faster than fire particles.

13. The medium of claim 8 , wherein the instructions include instructions executable by the processing resource to determine a temperature to intensity map associated with the thermal imaging component.

14. The medium of claim 13 , wherein the instructions to determine the temperature to intensity map includes instructions executable to map pixel intensity to temperature output of the thermal imaging component.

Assignees

• Honeywell Int Inc

Inventors

• Pathangay Vinod
• Gellaboina Mahesh Kumar
• Mohideen Mohammed Ibrahim

Classifications

• G06T2207/20081

  Training; Learning · CPC title

• G06T7/0002

  Inspection of images, e.g. flaw detection · CPC title

• G06T2207/10016

  Video; Image sequence · CPC title

• G06T2207/10048

  Infrared image · CPC title

• F23N5/242 Primary

  using electronic means · CPC title