# US 11,310,443 B2 · Video processing method, apparatus and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,310,443 B2 - Document ID: US11310443B2 - Status: Granted - Kind: B2 - Application number: 17/244,703 - Filed: 2021-04-29 - Published: 2022-02-03 - Granted: 2022-04-19 - Earliest claimed: 2020-07-28 - Assignees: Beijing Xiaomi Pinecone Electronics Co., Ltd. - Applicants: Beijing Xiaomi Pinecone Electronics Co., Ltd. - Inventors: Binglin Chang; Kailun Ma; Zhenghui Shi; Qingmin Wang - Web page: https://patentgrep.com/patent/US11310443B2 ## CPC - G06T 7/11: Region-based segmentation - G06T 7/194: involving foreground-background segmentation - G06T 7/30: Determination of transform parameters for the alignment of images, i.e. image registration - G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80) - G06T 11/60: Creating or editing images; Combining images with text - G11B 27/036: Insert-editing - H04N 5/265: Mixing - H04N 5/272: Means for inserting a foreground image in a background image, i.e. inlay, outlay - H04N 5/91: Television signal processing therefor - G06T 2207/10016: Video; Image sequence - G06T 2207/20221: Image fusion; Image merging - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R) - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract The present disclosure relates to a video processing method and apparatus, and a storage medium. The method is applied to a terminal and includes: a background frame for a time static special effect is determined from video frames in a video to be processed; for each of the video frames in the video, an image area, where a target object is located is acquired from the respective video frame and the image area is fused into the background frame to generate a special effect frame with the time static special effect. ## Claims ### Claim 1 A video processing method, implemented by a terminal, the method comprising: selecting, from video frames in a video to be processed, a background frame for a static special effect; and for each of the video frames in the video, acquiring an image area, where a target object is located, from the respective video frame, and fusing the image area into the background frame, to generate a special effect frame with the static special effect, wherein selecting, from the video frames in the video to be processed, the background frame for the static special effect comprises: determining a first frame after the video to be processed enters a time static mode in which the static special effect is formed, as the background frame for the static special effect. ### Claim 2 (depends on 1) The method of claim 1, wherein fusing the image area into the background frame, to generate the special effect frame with the static special effect comprises: for each of video frames starting from a start frame in the video, fusing the image area, which is acquired from the respective video frame, into the background frame, to generate the special effect frame with the static special effect; or, for each of video frames between a start frame and an end frame in the video, fusing the image area, which is acquired from the respective video frame, into the background frame, to generate the special effect frame with the static special effect. ### Claim 3 (depends on 2) The method of claim 2, further comprising: displaying the video frames in the video when being recorded; in response to a number of video frames in a predetermined storage space not exceeding a storage amount threshold, buffering the video frames starting from the start frame; and fusing the image area, which is acquired from each of the buffered video frames, into the background frame to generate and display the special effect frame. ### Claim 4 (depends on 2) The method of claim 2, further comprising: detecting a posture of the target object in each of the video frames; determining a video frame, in which the posture of the target object is detected as a first predetermined posture, to be the start frame; and determining a video frame, in which the posture of the target object is detected as a second predetermined posture, to be the end frame. ### Claim 5 (depends on 1) The method of claim 1, wherein fusing the image area into the background frame to generate the special effect frame with the static special effect comprises: overlaying an area at a target position in the background frame with the image area; and feathering edges of the image area with which the background frame was overlaid to form the special effect frame. ### Claim 6 (depends on 5) The method of claim 5, wherein overlaying the area at the target position in the background frame with the image area comprises: determining an alignment parameter according to the position of the target object in each of the video frames; and overlaying, according to the alignment parameter, the area at the target position in the background frame with the image area of the target object. ### Claim 7 (depends on 6) The method of claim 6, wherein determining the alignment parameter according to the position of the target object in each of the video frames comprises: selecting a video frame from the video frames in the video as a reference frame; and determining the alignment parameter according to a position offset of the target object in the video frame relative to the target object in the reference frame. ### Claim 8 A terminal, comprising: a processor; and a memory for storing executable instructions executable by the processor, wherein the processor is arranged to: select, from video frames in a video to be processed, a background frame for a static special effect; and for each of the video frames in the video, acquire, through a multimedia component, an image area, where a target object is located, from the respective video frame and fuse the image area into the background frame, to generate a special effect frame with the static special effect, wherein the processor is further arranged to: determine a first frame after the video to be processed enters a time static mode in which the static special effect is formed, as the background frame for the static special effect. ### Claim 9 (depends on 8) The terminal of claim 8, wherein the processor is further arranged to: for each of video frames starting from a start frame in the video, fuse the image area, which is acquired from the respective video frame, into the background frame, to generate the special effect frame with the static special effect; or, for each of video frames between a start frame and an end frame in the video, fuse the image area, which is acquired from the respective video frame, into the background frame, to generate the special effect frame with the static special effect. ### Claim 10 (depends on 9) The terminal of claim 9, wherein the processor is further arranged to: display, through the multimedia component, the video frames in the video when being recorded; in response to a number of video frames in a predetermined storage space not exceeding a storage amount threshold, buffer the video frames starting from the start frame; and fuse the image area, which is acquired from each of the buffered video frames, into the background frame to generate and display the special effect frame. ### Claim 11 (depends on 9) The terminal of claim 9, wherein the processor is further arranged to: detect a posture of the target object in each of the video frames; determine a video frame, in which the posture of the target object is detected as a first predetermined posture, to be the start frame; and determine a video frame, in which the posture of the target object is detected as a second predetermined posture, to be the end frame. ### Claim 12 (depends on 8) The terminal of claim 8, wherein the processor is further arranged to: overlay an area at a target position in the background frame with the image area; and feather edges of the image area with which the background frame was overlaid to form the special effect frame. ### Claim 13 (depends on 12) The terminal of claim 12, wherein the processor is further arranged to: determine an alignment parameter according to the position of the target object in each of the video frames; and overlay, according to the alignment parameter, the area at the target position in the background frame with the image area of the target object. ### Claim 14 (depends on 13) The terminal of claim 13, wherein the processor is further arranged to: select a video frame from the video frames in the video as a reference frame; and determine the alignment parameter according to a position offset of the target object in the video frame relative to the target object in the reference frame. ### Claim 15 A non-transitory computer readable storage medium having computer executable instructions stored thereon, the computer executable instructions, when being executed by a processor, cause the processor to implement: selecting, from video frames in a video to be processed, a background frame for a static special effect; and for each of the video frames in the video, acquiring an image area, where a target object is located, from the respective video frame, and fusing the image area into the background frame, to generate a special effect frame with the static special effect, wherein selecting, from the video frames in the video to be processed, the background frame for the static special effect comprises: determining a first frame after the video to be processed enters a time static mode in which the static special effect is formed, as the background frame for the static special effect.