Granted Patent B2

US 12,568,286 · App. 18/565,100 · Granted Mar 3, 2026

Inventors: Juncheng Zhu (Guangdong, CN); Yuxuan Zhuang (Guangdong, CN); Jing Sun (Guangdong, CN)

Assignee: Guangzhou Boguan Telecommunication Technology Co., Ltd.

H04N21/8146G06T7/13H04N21/2187H04N21/23412H04N21/23418H04N21/23424G06T2207/10016G06T2207/10048

Abstract

Claims (74)

1 . A method for generating live-streaming data, comprising:

acquiring current contour information of a live-streaming object by using a thermal imaging device;

generating target special effect data by binding preset special effect data with the current contour information of the live-streaming object;

synthesizing a real-scene shooting image of the live-streaming object with the target special effect data into a special effect frame image; and

converting the special effect frame image into live-streaming stream data;

wherein generating the target special effect data by binding the preset special effect data with the current contour information of the live-streaming object comprises:

extracting a key feature point in a standard contour model;

determining a first binding position corresponding to the key feature point in the current contour information of the live-streaming object; and

obtaining the target special effect data by binding the preset special effect data with the current contour information of the live-streaming object at the first binding position.

2 . The method according to claim 1 , wherein acquiring the current contour information of the live-streaming object by using the thermal imaging device comprises:

collecting temperature field information in a target region in a real live-streaming space by using the thermal imaging device, wherein the temperature field information comprises temperature data of the live-streaming object and temperature data of an environmental object;

in response to determining that a difference value between the temperature data of the environmental object and a preset standard temperature is greater than a preset threshold value, generating a thermal image of the live-streaming object according to the temperature data of the live-streaming object; and

obtaining the current contour information of the live-streaming object by extracting the thermal image.

3 . The method according to claim 1 , further comprising:

in response to determining that the current contour information of the live-streaming object changes, updating the first binding position to a second binding position based on the key feature point;

adjusting the preset special effect data according to the second binding position; and

generating new target special effect data by binding adjusted preset special effect data with changed contour information of the live-streaming object at the second binding position, and synthesizing the real-scene shooting image of the live-streaming object with the new target special effect data into a new special effect frame image.

4 . The method according to claim 1 , wherein synthesizing the real-scene shooting image of the live-streaming object with the target special effect data into the special effect frame image comprises:

acquiring a real-scene shooting image of a current frame of the live-streaming object; and

synthesizing the real-scene shooting image of the current frame with the target special effect data into the special effect frame image, and rendering the special effect frame image.

5 . The method according to claim 1 , wherein converting the special effect frame image into the live-streaming stream data comprises:

encoding and encapsulating the special effect frame image into the live-streaming stream data.

6 . The method according to claim 1 , further comprising:

forwarding the live-streaming stream data to a user client through a user-side live-streaming server.

7 . The method according to claim 1 , further comprising:

in response to determining that there are a plurality of live-streaming objects in a preset region, acquiring contour information of the plurality of live-streaming objects; and

in response to determining that the contour information of the plurality of live-streaming objects overlaps, separating the contour information of the plurality of live-streaming objects, and reconstructing contour information of an overlapping portion obtained by separation.

8 . An electronic device, comprising:

a processor, and

a memory, configured to store executable instructions of the processor,

wherein when performing the executable instructions, the processor is configured to:

acquire current contour information of a live-streaming object by using a thermal imaging device;

generate target special effect data by binding preset special effect data with the current contour information of the live-streaming object;

synthesize a real-scene shooting image of the live-streaming object with the target special effect data into a special effect frame image; and

convert the special effect frame image into live-streaming stream data;

wherein the processor is further configured to:

extract a key feature point in a standard contour model;

determine a first binding position corresponding to the key feature point in the current contour information of the live-streaming object; and

obtain the target special effect data by binding the preset special effect data with the current contour information of the live-streaming object at the first binding position.

9 . The electronic device according to claim 8 , wherein the processor is configured to:

collect temperature field information in a target region in a real live-streaming space by using the thermal imaging device, wherein the temperature field information comprises temperature data of the live-streaming object and temperature data of an environmental object;

in response to determining that a difference value between the temperature data of the environmental object and a preset standard temperature is greater than a preset threshold value, generate a thermal image of the live-streaming object according to the temperature data of the live-streaming object; and

obtain the current contour information of the live-streaming object by extracting the thermal image.

10 . The electronic device according to claim 8 , wherein the processor is configured to:

in response to determining that the current contour information of the live-streaming object changes, update the first binding position to a second binding position based on the key feature point;

adjust the preset special effect data according to the second binding position; and

generate new target special effect data by binding adjusted preset special effect data with changed contour information of the live-streaming object at the second binding position, and synthesize the real-scene shooting image of the live-streaming object with the new target special effect data into a new special effect frame image.

11 . The electronic device according to claim 8 , wherein the processor is configured to:

acquire a real-scene shooting image of a current frame of the live-streaming object; and

synthesize the real-scene shooting image of the current frame with the target special effect data into the special effect frame image, and render the special effect frame image.

12 . The electronic device according to claim 8 , wherein the processor is configured to:

encode and encapsulate the special effect frame image into the live-streaming stream data.

13 . The electronic device according to claim 1 , wherein the processor is configured to:

forward the live-streaming stream data to a user client through a user-side live-streaming server.

14 . The electronic device according to claim 8 , wherein the processor is configured to:

in response to determining that there are a plurality of live-streaming objects in a preset region, acquire contour information of the plurality of live-streaming objects; and

in response to determining that the contour information of the plurality of live-streaming objects overlaps, separate the contour information of the plurality of live-streaming objects, and reconstruct contour information of an overlapping portion obtained by separation.

15 . A non-transitory computer-readable storage medium having a computer program stored thereon, wherein when performing the computer program, a processor is configured to:

acquire current contour information of a live-streaming object by using a thermal imaging device;

generate target special effect data by binding preset special effect data with the current contour information of the live-streaming object;

synthesize a real-scene shooting image of the live-streaming object with the target special effect data into a special effect frame image; and

convert the special effect frame image into live-streaming stream data;

wherein the processor is configured to:

extract a key feature point in a standard contour model;

determine a first binding position corresponding to the key feature point in the current contour information of the live-streaming object; and

obtain the target special effect data by binding the preset special effect data with the current contour information of the live-streaming object at the first binding position.

16 . The non-transitory computer-readable storage medium according to claim 15 , wherein the processor is configured to:

collect temperature field information in a target region in a real live-streaming space by using the thermal imaging device, wherein the temperature field information comprises temperature data of the live-streaming object and temperature data of an environmental object;

in response to determining that a difference value between the temperature data of the environmental object and a preset standard temperature is greater than a preset threshold value, generate a thermal image of the live-streaming object according to the temperature data of the live-streaming object; and

obtain the current contour information of the live-streaming object by extracting the thermal image.

17 . The non-transitory computer-readable storage medium according to claim 15 , wherein the processor is configured to:

in response to determining that the current contour information of the live-streaming object changes, update the first binding position to a second binding position based on the key feature point;

adjust the preset special effect data according to the second binding position; and

generate new target special effect data by binding adjusted preset special effect data with changed contour information of the live-streaming object at the second binding position, and synthesize the real-scene shooting image of the live-streaming object with the new target special effect data into a new special effect frame image.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (29)