Back to results
US 11,641,493 B2Granted
Method and electronic device for displaying bullet screens
AssigneeBeijing Dajia Internet Information Technology Co., Ltd.
InventorsCanchao Duan, Jiong Li, Qian Li, Dongsheng Tong, Huaqing Yang, Xiaoyu Yin, Yan Li
Life of this patent
Estimating the term…
Abstract
A method for displaying bullet screens can include: acquiring detection boxes by detecting human-body parts in a plurality of image frames in a target video; and determining a masked region of each of the image frames based on detection boxes in the each of the image frames and a ratio of the detection boxes in the each of the image frames in an image frame to which the detection boxes belong, wherein the client player does not display bullet screens in the masked region when playing the target video.
Claims10
A method for displaying bullet screens, comprising:
- acquiring human-body part detection boxes by detecting human-body parts displayed in a target image frame, the target image frame being one image frame of a plurality of image frames in a target video, and each of the human-body parts corresponding to one detection box;
- determining a masked region of the target image frame based on the detection boxes in the target image frame and an area ratio of the detection boxes to the target image frame;
- receiving a video playback request;
- and
- transmitting the target image frame in the target video, the masked region of the target image frame, and bullet screens to a client player based on the video playback request, wherein the client player hides the bullet screens in the masked region when playing the target video,
- wherein said determining the masked region of the target image frame comprises:
- acquiring key human-body parts in response to the area ratio being greater than or equal to a first threshold, the key human-body parts being some human-body parts of all human-body parts displayed in the target image frame;
- and
- determining the detection boxes corresponding to the key human-body parts as the masked region.
6 more elements
A method for displaying bullet screens, comprising:
- transmitting a video playback request to a server;
- receiving a target image frame in a target video, a masked region of the target image frame, and bullet screens from the server in response to the video playback request;
- and
- hiding the bullet screens in the masked region and displaying the bullet screens in a non-masked region in response to playing the target video,
- wherein the masked region of the target image frame is determined based on human-body part detection boxes in the target image frame and an area ratio of the detection boxes to the target image frame, the detection boxes being acquired by detecting human-body parts displayed in the target image frame, the target image frame being one image frame of a plurality of image frames in the target video, and each of the human-body parts corresponding to one detection box,
- wherein in response to the area ratio being greater than or equal to a first threshold, key human-body parts in the target video are acquired, the key human-body parts being some human-body parts of all human-body parts displayed in the target image frame;
- and the detection boxes corresponding to the key human-body parts are determined as the masked region.
4 more elements
An electronic device comprising:
- a processor;
- and
- a memory storing at least one instruction executable by the processor;
- wherein the at least one instruction, when executed by the processor, causes the processor to perform a method comprising:
- acquiring detection boxes by detecting human-body parts displayed in a target image frame, the target image frame being one image frame of a plurality of image frames in a target video, and each of the human-body parts corresponding to one detection box;
- determining a masked region of the target image frame based on the detection boxes in the target image frame and an area ratio of the detection boxes to the target image frame;
- receiving a video playback request;
- and
- transmitting the target image frame in the target video, the masked region of the target image frame, and bullet screens to a client player based on the video playback request, wherein the client layers hides the bullet screens in the masked region when playing the target video,
- wherein said determining the masked region of the target image frame comprises:
- acquiring key human-body parts in response to the area ratio being greater than or equal to a first threshold, the key human-body parts being some human-body parts of all human-body parts displayed in the target image frame;
- and
- determining the detection boxes corresponding to the key human-body parts as the masked region.
10 more elements
Dependencies are inferred from the claim text.