# US 10,234,380 B1 · Background radiance estimation and gas concentration-length quantification method for optical gas imaging camera > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,234,380 B1 - Document ID: US10234380B1 - Status: Granted - Kind: B1 - Application number: 15/720,708 - Filed: 2017-09-29 - Published: 2019-04-04 - Granted: 2019-03-19 - Earliest claimed: 2017-09-29 - Assignees: Konica Minolta Laboratory U.S.A., Inc. - Applicants: Konica Minolta Laboratory U.S.A., Inc. - Inventors: Leiming Wang; Ting Xu - Web page: https://patentgrep.com/patent/US10234380B1 ## CPC - G01N 21/3504: for analysing gases, e.g. multi-gas analysis - G01M 3/38: by using light (G01M3/02 takes precedence) - G06T 7/0004: {Industrial image inspection} - G01N 2021/3509: {Correlation method, e.g. one beam alternating in correlator/sample field} - G01N 2021/3531: {without instrumental source, i.e. radiometric} - G06T 2207/10048: Infrared image - G06T 2207/30108: Industrial image inspection - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) - G01M: TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A gas concentration-length quantification method may include acquiring a first image including a gas plume with a camera; identifying and segmenting pixels corresponding to the gas plume in the first image; creating a mask image corresponding to the first image, where only pixels of the mask image corresponding to the gas plume in the first image have non-zero values; generating a background image corresponding to the first image using an image inpainting algorithm with the first image and the mask image as inputs; calculating a gas concentration-length for each pixel corresponding to the gas plume in the first image, based on the first image and the background image data; and triggering an alert when the gas concentration-length for at least one pixel exceeds a threshold level. ## Claims ### Claim 1 A gas concentration-length quantification method, comprising: acquiring a first image including a gas plume with a camera; identifying and segmenting pixels corresponding to the gas plume in the first image; creating a mask image corresponding to the first image, wherein only pixels of the mask image corresponding to the gas plume in the first image have non-zero values; generating a background image corresponding to the first image using an image inpainting algorithm with the first image and the mask image as inputs; calculating a gas concentration-length for each pixel corresponding to the gas plume in the first image, based on the first image and the background image data; and triggering an alert when the gas concentration-length for at least one pixel exceeds a threshold level. ### Claim 2 (depends on 1) The method according to claim 1, wherein the camera is an optical gas imaging camera sensitive to infrared radiation and the first image is an infrared image. ### Claim 3 (depends on 1) The method according to claim 1, wherein the mask image is a binary image. ### Claim 4 (depends on 1) The method according to claim 1, further comprising selecting a region of interest enclosing the gas plume, wherein at least one step of the group of steps consisting of creating a mask image, generating a background image, and calculating the gas concentration-length is performed within the region of interest. ### Claim 5 (depends on 4) The method according to claim 4, wherein the region of interest encloses a substantially homogeneous background scene. ### Claim 6 (depends on 1) The method according to claim 1, further comprising: colorizing the first image; converting the generated background image back to a gray scale image prior to calculating the gas concentration-length for each pixel, wherein the generated background image uses the colorized first image as an input and is colorized. ### Claim 7 (depends on 6) The method according to claim 6, wherein colorizing the first image uses a convolutional neural network. ### Claim 8 (depends on 1) The method according to claim 1, wherein the image inpainting method is a Telea algorithm. ### Claim 9 (depends on 1) The method according to claim 1, wherein the image inpainting method is a Navier-Stokes algorithm. ### Claim 10 A gas concentration-length quantification system, comprising: a camera; a processing unit connected to the camera, wherein the processor performs: reading a first image including a gas plume from the camera; identifying and segmenting pixels corresponding to the gas plume in the first image; creating a mask image corresponding to the first image wherein only pixels of the mask image corresponding to the gas plume in the first image have non-zero values; generating a background image corresponding to the first image using an image inpainting algorithm with the first image and the mask image as inputs; calculating a gas concentration-length for each pixel corresponding to the gas plume in the first image, based on the first image and the background image data; and triggering an alert when the gas concentration-length for at least one pixel exceeds a threshold level. ### Claim 11 (depends on 10) The system according to claim 10, wherein the camera is an optical gas imaging camera sensitive to infrared radiation and the first image is an infrared image. ### Claim 12 (depends on 10) The system according to claim 10, wherein the mask image is a binary image. ### Claim 13 (depends on 10) The system according to claim 10, further comprising selecting a region of interest enclosing the gas plume, wherein at least one step of the group of steps consisting of creating a mask image, generating a background image, and calculating the gas concentration-length is performed within the region of interest. ### Claim 14 (depends on 13) The system according to claim 13, wherein the region of interest encloses a substantially homogeneous background scene. ### Claim 15 (depends on 10) The system according to claim 10, further comprising: colorizing the first image; converting the generated background image back to a gray scale image prior to calculating the gas concentration-length for each pixel, wherein the generated background image uses the colorized first image as an input and is colorized. ### Claim 16 (depends on 15) The system according to claim 15, wherein colorizing the first image uses a convolutional neural network. ### Claim 17 (depends on 10) The system according to claim 10, wherein the image inpainting method is a Telea algorithm. ### Claim 18 (depends on 10) The system according to claim 10, wherein the image inpainting method is a Navier-Stokes algorithm. ### Claim 19 A non-transitory computer readable medium (CRM) storing computer readable program code embodied therein that: reads a first image including a gas plume; identifies and segments pixels corresponding to the gas plume in the first image; creates a mask image corresponding to the first image wherein only pixels of the mask image corresponding to the gas plume in the first image have non-zero values; generates a background image corresponding to the first image using an image inpainting algorithm with the first image and the mask image as inputs; calculates a gas concentration-length for each pixel corresponding to the gas plume in the first image, based on the first image and the background image data; and triggers an alert when the gas concentration-length for at least one pixel exceeds a threshold level.