Back to results
US 11,107,256 B2Granted
Video frame processing method and apparatus
AssigneeBeijing Bytedance Network Technology Co., Ltd.
InventorsXinglong Wu, Guozhong Luo
Life of this patent
Estimating the term…
Abstract
Disclosed in the embodiments of the present application are a video frame processing method and apparatus. An embodiment of the method comprises: acquiring a video frame containing a hand, and detecting key points of the hand contained in the video frame; generating a special effect of the hand on the basis of the key points; and displaying the generated special effect in an image of the video frame.
Claims15
A method for processing a video frame, the method comprising:
- acquiring a video frame containing a human hand, and detecting key points of the human hand contained in the video frame;
- generating a special effect of the human hand based on the key points, wherein the special effect comprises a linear pattern, and wherein the generating a special effect of the human hand based on the key points further comprises:
- determining a position of at least one endpoint of the linear pattern based on positions of the key points,
- generating the linear pattern based on the position of the at least one endpoint,
- wherein the determining a position of at least one endpoint of the linear pattern based on positions of the key points further comprises:
- determining, in response to a determination that one finger of the human hand points to a preset directions, a position of one endpoint of a trunk line of the linear pattern based on a position of a fingerprint key point of the finger, and
- wherein the generating the linear pattern based on the position of the at least one endpoint further comprises:
- generating the trunk line based on the position of the one endpoint, wherein a difference between a direction of the trunk line and the preset direction is in a preset angle range;
- and
- displaying the generated special effect in a picture of the video frame.
7 more elements
An electronic apparatus, comprising:
- one or more processors;
- and
- at least one memory for storing one or more programs, wherein when executed by the one or more processors, the one or more programs cause the apparatus to:
- acquire a video frame containing a human hand, and detecting key points of the human hand contained in the video frame;
- generate a special effect of the human hand based on the key points, wherein the special effect comprises a linear pattern, and wherein the one or more programs upon execution by the one or more processors further cause the apparatus to:
- determine a position of at least one endpoint of the linear pattern based on positions of the key points,
- generate the linear pattern based on the position of the at least one endpoint,
- wherein the determining a position of at least one endpoint of the linear pattern based on positions of the key points further comprises:
- determining, in response to a determination that one finger of the human hand points to a preset directions, a position of one endpoint of a trunk line of the linear pattern based on a position of a fingerprint key point of the finger, and
- wherein the generating the linear pattern based on the position of the at least one endpoint further comprises:
- generating the trunk line based on the position of the one endpoint, wherein a difference between a direction of the trunk line and the preset direction is in a preset angle range;
- and
- display the generated special effect in a picture of the video frame.
10 more elements
A non-transitory computer-readable storage medium having a computer program stored thereon, wherein the program upon execution by a processor causes the processor at least to:
- acquire a video frame containing a human hand, and detecting key points of the human hand contained in the video frame;
- generate a special effect of the human hand based on the key points, wherein the special effect comprises a linear pattern, and wherein the program upon execution by the processor further causes the processor to:
- determine a position of at least one endpoint of the linear pattern based on positions of the key points, generate the linear pattern based on the position of the at least one endpoint,
- wherein the determining a position of at least one endpoint of the linear pattern based on positions of the key points further comprises:
- determining, in response to a determination that one finger of the human hand points to a preset directions, a position of one endpoint of a trunk line of the linear pattern based on a position of a fingerprint key point of the finger, and
- wherein the generating the linear pattern based on the position of the at least one endpoint further comprises:
- generating the trunk line based on the position of the one endpoint, wherein a difference between a direction of the trunk line and the preset direction is in a preset angle range;
- and
- display the generated special effect in a picture of the video frame.
6 more elements
Dependencies are inferred from the claim text.