Granted Patent B2

US 12,542,040 · App. 18/446,503 · Granted Feb 3, 2026

Inventors: Huachao Lu (Hangzhou, CN); Su Liu (Hangzhou, CN); Diquan Xu (Hangzhou, CN); Tao Pu (Hangzhou, CN); Ziwei Wei (Hangzhou, CN); Lianpeng Wu (Hangzhou, CN)

Assignee: ZHEJIANG PIXFRA TECHNOLOGY CO., LTD.

G08B17/10G06T7/73G06V10/25G06V20/52H04N23/695G06T2207/30232

Abstract

Claims (63)

1 . A system for smoke detection using an object detection device, the object detection device including a first imaging component and a moveable component configured to move the first imaging component, comprising:

at least one storage device including a set of instructions; and

at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is directed to perform operations including:

obtaining a current image of a first subject acquired by the first imaging component at a current time;

determining whether the first subject and a second subject among one or more second subjects belong to a same object, the one or more second subjects being represented in one or more previous images acquired by the first imaging component at a previous time;

in response to determining that the first subject and the one of the one or more second subjects belong to the same object, causing the moveable component to move the first imaging component; and

in response to determining that the first subject and the second subject belong to different subjects, stopping the moveable component to move the first imaging component.

2 . The system of claim 1 , wherein the determining whether the first subject and the second subject belong to the same object includes:

determining one or more target regions in the previous image, the one or more target regions including the one or more second subjects; and

determining whether the first subject and the second subject belong to the same object based on the one or more target regions.

3 . The system of claim 2 , wherein the determining whether the first subject and the second subject of the one or more second subjects belong to the same object based on the one or more target regions includes:

determining first position information of a reference point represented the first subject in the current image, the first position information corresponding to current position parameters of the first imaging component acquiring the current image;

determining second position information of each of the one or more target regions represented one second subject in the previous image, the second position information corresponding to previous position parameters of the first imaging component acquiring the previous image; and

determining whether the first subject and the second subject belong to the same object based on the first position information and the second position information.

4 . The system of claim 3 , wherein the determining whether the first subject and the second subject belong to the same object based on the first position information and the second position information includes:

determining equivalent first position information of the reference point, the equivalent first position information including position information of the reference point if the current image is acquired at the previous position parameters; and

determining whether the first subject and the second subject belong to the same object by determining whether the reference point is within one of the one or more target regions based on the equivalent first position information and the second position information.

5 . The system of claim 4 , wherein the determining equivalent first position information of the reference point includes:

determining a difference between the current position parameters and the previous position parameters; and

determining the equivalent first position information of the reference point based on the difference between the current position parameters and the previous position parameters.

6 . The system of claim 3 , wherein the determining whether the first subject and the second subject of the one or more second subjects belong to the same object based on the first position information and the second position information includes:

determining equivalent second position information of the one or more target regions, the equivalent second position information including position information of the one or more target regions if the previous image is acquired at the current position parameters; and

determining whether the first subject and the second subject belong to the same object by determining whether the reference point is within one of the one or more target regions based on the equivalent second position information and the first position information.

7 . The system of claim 6 , wherein the determining equivalent second position information includes:

determining a difference between the current position parameters and the previous position parameters; and

determining the equivalent second position information of the one or more target regions based on the difference between the current position parameters and the previous position parameters.

8 . The system of claim 3 , wherein the determining whether the first subject and the second subject of the one or more second subjects belong to the same object based on the first position information and the second position information includes:

determining first spatial position information under a reference coordinate system by converting the first position information under a first coordinate system to the reference coordinate system;

determining second spatial position information under the reference coordinate system by converting the second position information under a second coordinate system to the reference coordinate system; and

determining whether the first subject and the second subject belong to the same object by determining whether the reference point is within one of the one or more target regions based on the first spatial position information and the second spatial position information.

9 . The system of claim 1 , wherein the operations further include:

in response to determining that the first subject and the second subject belongs to different subjects,

obtaining a second image of the first subject acquired by a second imaging component of the object detection device, the second image including temperature information of the first subject;

determining, based on the second image, whether the first subject is smoke of a combustion;

in response to determining that the first subject is smoke of the combustion, reporting first position information of the first object and the current position parameters.

10 . The system of claim 1 , wherein the operations further include:

causing the moveable component to move the first imaging component after a second image of the first subject is acquired by the second imaging component.

11 . The system of claim 1 , wherein the operations further include:

in response to determining that the first subject and the second subject belong to different subjects, adding the first subject into the one or more second subjects.

12 . The system of claim 1 , wherein the operations further include:

in response to determining that the first subject and the second subject belong to the same object, updating second position information of the second subject using first position information of the first subject.

13 . A method for smoke detection using an object detection device, the object detection device including a first imaging component and a moveable component configured to move the first imaging component, comprising:

obtaining a current image of a first subject acquired by the first imaging component at a current time;

determining whether the first subject and a second subject among one or more second subjects belong to a same object, the one or more second subjects being represented in one or more previous images acquired by the first imaging component at a previous time; and

in response to determining that the first subject and the one of the one or more second subjects belong to the same object, causing the moveable component to move the first imaging component; and

in response to determining that the first subject and the second subject belong to different subjects, stopping the moveable component to move the first imaging component.

14 . The method of claim 13 , wherein the determining whether the first subject and the second subject belong to the same object includes:

determining one or more target regions in the previous image, the one or more target regions including the one or more second subjects; and

determining whether the first subject and the second subject belong to the same object based on the one or more target regions.

15 . The method of claim 14 , wherein the determining whether the first subject and the second subject of the one or more second subjects belong to the same object based on the one or more target regions includes:

determining first position information of a reference point represented the first subject in the current image, the first position information corresponding to current position parameters of the first imaging component acquiring the current image;

determining second position information of each of the one or more target regions represented one second subject in the previous image, the second position information corresponding to previous position parameters of the first imaging component acquiring the previous image; and

determining whether the first subject and the second subject belong to the same object based on the first position information and the second position information.

16 . The method of claim 15 , wherein the determining whether the first subject and the second subject belong to the same object based on the first position information and the second position information includes:

determining equivalent first position information of the reference point, the equivalent first position information including position information of the reference point if the current image is acquired at the previous position parameters; and

determining whether the first subject and the second subject belong to the same object by determining whether the reference point is within one of the one or more target regions based on the equivalent first position information and the second position information.

17 . The system of claim 13 , wherein the method further includes:

in response to determining that the first subject and the second subject belong to the same object, updating second position information of the second subject using first position information of the first subject.

18 . A non-transitory computer readable medium, comprising executable instructions that, when executed by at least one processor, direct the at least one processor to perform a method for smoke detection using an object detection device, the object detection device including a first imaging component and a moveable component configured to move the first imaging component, the method comprising:

obtaining a current image of a first subject acquired by the first imaging component at a current time;

determining whether the first subject and a second subject among one or more second subjects belong to a same object, the one or more second subjects being represented in one or more previous images acquired by the first imaging component at a previous time; and

in response to determining that the first subject and the one of the one or more second subjects belong to the same object, causing the moveable component to move the first imaging component; and

in response to determining that the first subject and the second subject belong to different subjects, stopping the moveable component to move the first imaging component.

Assignments (2)

Priority Claims (1)

Continuity (2)

References Cited (17)