Method and apparatus for modeling smoke turbulence based on patch
US-2017178344-A1 · Jun 22, 2017 · US
US10593181B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10593181-B2 |
| Application number | US-201716097972-A |
| Country | US |
| Kind code | B2 |
| Filing date | Mar 22, 2017 |
| Priority date | May 4, 2016 |
| Publication date | Mar 17, 2020 |
| Grant date | Mar 17, 2020 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
The invention relates to a smoke detection device (1) for detecting smoke (7) from a fire (6) in a monitoring area (3), comprising a camera interface (8) for receiving an image sequence having chronologically successive individual images from a monitoring camera (2), wherein the individual images (4) show the monitoring area (3), and comprising an evaluating device (9) for detecting at least one moving object in the monitoring area (3), wherein the evaluating device (9) is designed to detect a motion of the at least one moving object from at least two individual images (4) of the image sequence (5), characterized by a filter device (10) for distinguishing the moving object as smoke (7) or as a non-smoke object on the basis of the motion of the moving object.
Opening claim text (preview).
The invention claimed is: 1. A smoke detection device ( 1 ) for detecting smoke ( 7 ) from a fire ( 6 ) in a monitoring area ( 3 ), the smoke detection device comprising: a camera interface ( 8 ) for accepting an image sequence having temporally successive individual images from a monitoring camera ( 2 ), wherein the individual images ( 4 ) show the monitoring area ( 3 ), an evaluation device ( 9 ) for determining at least one moving object in the monitoring area ( 3 ), wherein the evaluation device ( 9 ) is designed to determine a movement of the at least one moving object from at least two individual images ( 4 ) in the image sequence ( 5 ), and a filter device ( 10 ) for distinguishing the moving object as smoke ( 7 ) or a non-smoke object on the basis of the movement of the moving object, wherein the evaluation device ( 9 ) comprises a speed measuring unit for determining a speed v F of the average optical flow ( 16 ) of the moving object and for determining a speed v G of a contour area ( 17 ) of the moving object. 2. The smoke detection device ( 1 ) as claimed in claim 1 , wherein the filter device ( 10 ) comprises a comparison unit ( 11 ), wherein the comparison unit ( 11 ) is designed to (a) detect the moving object as smoke ( 7 ) if v G <v F , (b) to detect the moving object as a non-smoke object if v G >=v F , or both (a) and (b). 3. The smoke detection device ( 1 ) as claimed in claim 1 , wherein the filter device ( 10 ) comprises a comparison unit ( 11 ) having two safety factors b 1 and b 2 with 0<b 1 <=b 2 <1, wherein the comparison unit ( 10 ) is designed to (a) detect the moving object as smoke ( 7 ) if v G <b 1 *v F , (b) to detect the moving object as a non-smoke object if v G >=b 2 *v F , or both (a) and (b). 4. The smoke detection device ( 1 ) as claimed in claim 1 , wherein the average optical flow ( 16 ) of the moving object has an averaged flow direction, and wherein the contour area ( 18 ) is arranged on that side of the moving object which is contrary to the averaged flow direction. 5. The smoke detection device ( 1 ) as claimed in claim 1 , wherein the monitoring area ( 3 ) comprises a base, wherein the contour area ( 17 ) is arranged on that side of the moving object which faces the base. 6. A The smoke detection device ( 1 ) for detecting smoke ( 7 ) from a fire ( 6 ) in a monitoring area ( 3 ), the smoke detection device comprising: a camera interface ( 8 ) for accepting an image sequence having temporally successive individual images from a monitoring camera ( 2 ), wherein the individual images ( 4 ) show the monitoring area ( 3 ), an evaluation device ( 9 ) for determining at least one moving object in the monitoring area ( 3 ), wherein the evaluation device ( 9 ) is designed to determine a movement of the at least one moving object from at least two individual images ( 4 ) in the image sequence ( 5 ), and a filter device ( 10 ) for distinguishing the moving object as smoke ( 7 ) or a non-smoke object on the basis of the movement of the moving object, wherein the filter device ( 10 ) comprises a turbulence analysis unit ( 12 ) for distinguishing the moving object as smoke ( 7 ) and a non-smoke object on the basis of turbulence in the moving object. 7. The smoke detection device ( 1 ) as claimed in claim 6 , wherein the evaluation device ( 9 ) is designed to determine a first correspondence R 1 of the moving object as a degree of comparison of at least one first image area in a first individual image and in a second individual image ( 4 ), wherein the two individual images ( 4 ) have a temporal spacing dt, and the evaluation device ( 9 ) is designed to determine at least a second correspondence R 2 of the moving object as a degree of comparison of the first image area in the first individual image and in a third individual image ( 4 ), wherein the first individual image ( 4 ) and the third individual image ( 4 ) have a temporal spacing of n*dt, wherein the turbulence analysis unit ( 12 ) comprises two factors c 1 and c 2 with 0<c 1 <=c 2 <1 and is designed to detect the moving object as smoke ( 7 ) if R 2 <c 1 *R 1 and to detect the moving object as a non-smoke object if R 2 >=c 2 *R 1 . 8. The smoke detection device ( 1 ) as claimed in claim 7 , wherein the evaluation device ( 9 ) is designed to normalize the first correspondence R 1 and the second correspondence R 2 with a region of interest (ROI) to a relative first correspondence {tilde over (R)} 1 and a relative second correspondence {tilde over (R)} 2 , and the turbulence analysis unit ( 12 ) comprises two factors d 1 and d 2 with 0<d 1 <=d 2 <1 and is designed to detect the moving object as smoke ( 7 ) if {tilde over (R)} 2 <d 1 *{tilde over (R)} 1 and to detect the moving object as a non-smoke object if {tilde over (R)} 2 >d 2 *{tilde over (R)} 1 . 9. A method using a smoke detection device ( 1 ) according to the invention as claimed in claim 1 , wherein the evaluation device ( 9 ) determines the movement of the moving object in the monitoring area ( 3 ) on the basis of at least two individual images ( 4 ) in an image series of the monitoring area ( 3 ), and the filter device ( 10 ) determines the moving object as smoke ( 7 ) and a non-smoke object on the basis of the movement of the moving object. 10. A non-transitory computer readable media comprising program code for carrying out all steps of the method as claimed in claim 9 when the program is executed by the smoke detection device. 11. The smoke detection device ( 1 ) as claimed in claim 1 , the smoke detection device including a non-transitory computer readable media comprising program code. 12. A smoke detection device ( 1 ) for detecting smoke ( 7 ) from a fire ( 6 ) in a monitoring area ( 3 ), the smoke detection device comprising: a camera interface ( 8 ) for accepting an image sequence having temporally successive individual images from a monitoring camera ( 2 ), wherein the individual images ( 4 ) show the monitoring area ( 3 ), an evaluation device ( 9 ) for determining at least one moving object in the monitoring area ( 3 ), wherein the evaluation device ( 9 ) is designed to determine a movement of the at least one moving object from at least two individual images ( 4 ) in the image sequence ( 5 ), and a filter device ( 10 ) for distinguishing the moving object as smoke ( 7 ) or a non-smoke object on the basis of the movement of the moving object, wherein the filter device ( 10 ) comprises a turbulence analysis unit ( 12 ) for distinguishing the moving object as smoke ( 7 ) and a non-smoke object on the basis of turbulence in the moving object, and wherein the turbulence is vortices which are shown as temporally and spatially random variations in the individual images.
involving reference images or patches · CPC title
by measuring the direct influence of the streaming fluid on the properties of a detecting optical wave · CPC title
by using a video camera to detect fire or smoke · CPC title
Video; Image sequence · CPC title
Surveillance · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.