Area monitoring for detection of leaks and/or flames
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
H04N-007/18
G01M-003/04
G08B-017/12
G08B-013/16
G08B-013/193
G08B-013/196
H04N-005/33
G08B-019/00
출원번호
US-0605945
(2015-01-26)
등록번호
US-9759628
(2017-09-12)
발명자
/ 주소
Mian, Zahid F.
Gamache, Ronald W.
Glasser, Nicholas
출원인 / 주소
INTERNATIONAL ELECTRONIC MACHINES CORPORATION
대리인 / 주소
Labatt, LLC
인용정보
피인용 횟수 :
0인용 특허 :
33
초록▼
A solution for monitoring an area for the presence of a flame and/or a leak, such as from a pressurized fluid, is provided. An imaging device can be used that acquires image data based on electromagnetic radiation having wavelengths only corresponding to at least one region of the electromagnetic sp
A solution for monitoring an area for the presence of a flame and/or a leak, such as from a pressurized fluid, is provided. An imaging device can be used that acquires image data based on electromagnetic radiation having wavelengths only corresponding to at least one region of the electromagnetic spectrum in which electromagnetic radiation from an ambient light source is less than the electromagnetic radiation emitted by at least one type of flame for which the presence within the area is being monitored. An acoustic device can be used that is configured to acquire acoustic data for the area and enhance acoustic signals in a range of frequencies corresponding to a leak of a pressurized fluid present in the area.
대표청구항▼
1. A system comprising: at least one sensing component, the at least one sensing component including: an imaging device, wherein the imaging device is configured to acquire image data for an area; andan acoustic device, wherein the acoustic device is configured to acquire acoustic data for the area;
1. A system comprising: at least one sensing component, the at least one sensing component including: an imaging device, wherein the imaging device is configured to acquire image data for an area; andan acoustic device, wherein the acoustic device is configured to acquire acoustic data for the area; anda computer system including at least one computing device, wherein the computer system is configured to monitor the area by performing a method comprising: evaluating the image data for a presence of a flame of the at least one type of flame, wherein the evaluating the image data includes: identifying an object in the image data as a possible flame, wherein the object has a size exceeding a flame size detection limit;evaluating a plurality of properties of the object in the image data using a plurality of flame detection rules, wherein the plurality of properties include a plurality of properties relating to a shape of the object and a plurality of properties relating to motion of the object, wherein each flame detection rule evaluates the object as a flame or not a flame using at least one of the plurality of properties, and wherein each of the plurality of properties is evaluated using at least one flame detection rule; andevaluating the object as a flame in response to the plurality of flame detection rules indicating that the object is a flame for a minimum amount of time of at least one second; andevaluating the acoustic data for a presence of at least one of: the flame or a leak of a pressurized fluid. 2. The system of claim 1, the method further comprising providing monitoring data for use by a user based on the evaluated presence of at least one of: the flame or the leak, wherein the providing the monitoring data includes the computer system providing supplemental information for use by the user in response to an indication of a presence of a flame in one of the image data or the acoustic data and a lack of an indication of the presence of the flame in the other of the image data or the acoustic data. 3. The system of claim 1, wherein the imaging device comprises: a camera sensitive to electromagnetic radiation having wavelengths up to approximately 1250 nanometers; anda low pass filter configured to filter electromagnetic radiation passing to the camera, wherein the low pass filter comprises a cut on wavelength of approximately 1150 nanometers. 4. The system of claim 1, wherein the type of flame comprises a hydrogen flame, and the at least one region comprises at least a portion of an infrared region between approximately 800 nanometers and approximately 1250 nanometers. 5. The system of claim 1, wherein the acoustic device is configured to enhance acoustic signals in a range of frequencies corresponding to the leak. 6. The system of claim 1, wherein the evaluating the object as a flame includes, for the image data corresponding to each of a plurality of image frames: identifying the object as a candidate flame in response to each of the plurality of flame detection rules indicating that the object is a flame;recording persistence data for the object indicating a number of consecutive frames that the object has been identified as a candidate flame; andevaluating a candidate flame as a flame in response to the persistence data indicating the object has been identified as a candidate flame for a number of consecutive frames corresponding to the minimum amount of time. 7. The system of claim 1, wherein the evaluating the acoustic data includes: determining whether the acoustic data includes any non-background peaks within a first range, wherein inclusion of at least one non-background peak within the first range indicates a presence of at least one of: a leak or a flame; anddetermining whether the acoustic data includes any non-background peaks within a second range in response to determining the inclusion of at least one non-background peak within the first range, wherein the inclusion of at least one non-background peak within the second range indicates the presence of a flame and no at least one non-background peak within the second range indicates the presence of a leak. 8. A system for monitoring an area, the system comprising: a computer system including at least one computing device, wherein the computer system is configured to monitor the area by performing a method comprising: evaluating image data for the area for a presence of a flame, wherein the evaluating includes: identifying an object in the image data as a possible flame, wherein the object has a size exceeding a flame size detection limit;evaluating a plurality of properties of the object in the image data using a plurality of flame detection rules, wherein the plurality of properties include a plurality of properties relating to a shape of the object and a plurality of properties relating to motion of the object, wherein each flame detection rule evaluates the object as a flame or not a flame using at least one of the plurality of properties, and wherein each of the plurality of properties is evaluated using at least one flame detection rule; andevaluating the object as a flame in response to each of the plurality of flame detection rules indicating that the object is a flame for a minimum amount of time. 9. The system of claim 8, wherein the method further comprises the computer system evaluating acoustic data for the area for a presence of at least one of: the flame or a leak of pressurized fluid. 10. The system of claim 9, further comprising: an imaging device, wherein the imaging device is configured to acquire image data for the area based on electromagnetic radiation having wavelengths only corresponding to at least one region of the electromagnetic spectrum in which electromagnetic radiation from an ambient light source is less than the electromagnetic radiation emitted by at least one type of flame; andan acoustic device, wherein the acoustic device is configured to acquire the acoustic data for the area and enhance acoustic signals in a range of frequencies corresponding to a leak of a pressurized fluid present in the area. 11. The system of claim 9, wherein the evaluating the acoustic data includes: the computer system evaluating the acoustic data for inclusion of any non-background peaks in a first range of frequencies, wherein inclusion of at least one non-background peak is indicative of a presence of a leak or a flame; andthe computer system evaluating the acoustic data for inclusion of any non-background peaks in a second range of frequencies in response to determining the inclusion of at least one non-background peak within the first range, wherein inclusion of at least one non-background peak within the second range indicates the presence of a flame. 12. A method of monitoring an area, the method comprising: receiving, on a computer system including at least one computing device, image data for the area, wherein the image data is based on electromagnetic radiation having wavelengths only corresponding to at least one region of the electromagnetic spectrum in which electromagnetic radiation from an ambient light source is less than the electromagnetic radiation emitted by at least one type of flame produced by at least one type of fluid present in the area; andthe computer system evaluating the image data for the presence of the flame of the at least one type of flame, wherein the evaluating the image data includes: the computer system identifying an object in the image data as a possible flame, wherein the object has a size exceeding a flame size detection limit;the computer system evaluating a plurality of properties of the object in the image data using a plurality of flame detection rules, wherein the plurality of properties include a plurality of properties relating to a shape of the object and a plurality of properties relating to motion of the object, wherein each flame detection rule evaluates the object as a flame or not a flame using at least one of the plurality of properties, and wherein each of the plurality of properties is evaluated using at least one flame detection rule; andthe computer system evaluating the object as a flame in response to the plurality of flame detection rules indicating that the object is a flame for a minimum amount of time of at least one second. 13. The method of claim 12, wherein the at least one type of flame comprises a hydrogen flame, and the at least one region comprises at least a portion of an infrared region between approximately 800 nanometers and approximately 1250 nanometers. 14. The method of claim 12, wherein the computer system evaluating the object as a flame includes, for the image data corresponding to each of a plurality of image frames: identifying the object as a candidate flame in response to each of the plurality of flame detection rules indicating that the object is a flame;recording persistence data for the object indicating a number of consecutive frames that the object has been identified as a candidate flame; andevaluating a candidate flame as a flame in response to the persistence data indicating the object has been identified as a candidate flame for a number of consecutive frames corresponding to the minimum amount of time. 15. The method of claim 12, further comprising: receiving, on the computer system, acoustic data for the area;the computer system evaluating the acoustic data for the presence of a leak of the fluid; andproviding monitoring data for use by the user based on the evaluated presence of the leak. 16. The method of claim 12, further comprising the computer system evaluating acoustic data for the presence of the flame, and wherein the evaluating the acoustic data includes: evaluating the acoustic data for inclusion of any non-background peaks in a first range of frequencies, wherein inclusion of at least one non-background peak is indicative of a presence of a leak or a flame; andevaluating the acoustic data for inclusion of any non-background peaks in a second range of frequencies in response to determining the inclusion of at least one non-background peak within the first range, wherein inclusion of at least one non-background peak within the second range indicates the presence of a flame. 17. The method of claim 16, further comprising: the computer system extracting peak value data from the acoustic data for the area;the computer system comparing the peak value data with running background spectra data; andthe computer system identifying any peak present in the peak value data exceeding the running background spectra data by a minimum amount as a non-background peak. 18. The method of claim 16, further comprising the computer system suppressing an indication of a presence of a flame in one of the image data or the acoustic data based on a lack of an indication of the presence of the flame in the other of the image data or the acoustic data. 19. The method of claim 16, further comprising the computer system providing monitoring data for use by a user based on the evaluated presence of the flame, wherein the providing the monitoring data includes the computer system providing supplemental information for use by the user in response to an indication of a presence of a flame in one of the image data or the acoustic data and a lack of an indication of the presence of the flame in the other of the image data or the acoustic data. 20. The method of claim 12, further comprising: the computer system generating annotated image data of the area to emphasize a portion of the area visible in the image data in response to the evaluated presence of the flame; andthe computer system providing monitoring data for use by a user, wherein the monitoring data includes the annotated image data of the area when the evaluating indicates the presence of the flame.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (33)
Anderson,Kaare Josef, Apparatus for detecting a fire by IR image processing.
Kern Mark T. (Goleta CA) Hodges Steven E. (Santa Barabara CA) Snider Danny G. (Ventura CA) Shamordola Kenneth A. (Santa Barbara CA), Fire sensor system utilizing optical fibers for remote sensing.
Seume Jorg,DEX ; Vortmeyer Nicolas,DEX ; Gleis Stephan,DEX ; Hermann Jakob,DEX ; Vortmeyer Dieter,DEX, Method and device for acoustic modulation of a flame produced by a hybrid burner.
Anderson, Kaare J.; Miller, Mark S.; Renken, Christopher H.; Snyder, Brian L.; Socha, Sr., David M., Multi-sensor fire detector with reduced false alarm performance.
Hall Gregory H. (Rockledge FL) Barnes Heidi L. (Covington LA) Medelius Pedro J. (Merritt Island FL) Simpson Howard J. (Melbourne FL) Smith Harvey S. (Bay St. Louis MS), Plural-wavelength flame detector that discriminates between direct and reflected radiation.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.