-
公开(公告)号：US11412292B2
公开(公告)日：2022-08-09
申请号：US17234741
申请日：2021-04-19
发明人： Qianyi Wang , Yu Gao , Zhibin Wang , En Li , Rong Li
IPC分类号： H04N21/44 , H04N21/8549 , G06T11/20 , G06T11/00 , H04N21/431 , H04N21/4788
摘要： A video processing method, a video processing device, and a storage medium are provided. The video processing method includes: determining target image frames corresponding to a dynamic special effect in a video and determining an attribute of a special effect element corresponding to the dynamic special effect in each of the target image frames and coordinates of the special effect element. The video processing method also includes: rendering the special effect element on a drawing interface based on the attribute and the coordinates of the special effect element; filling the target image frames into the drawing interface as a background and forming drawing interface frames with the dynamic special effect; and outputting the drawing interface frames corresponding to each of the target image frames.
-
公开(公告)号：US11461876B2
公开(公告)日：2022-10-04
申请号：US16993061
申请日：2020-08-13
发明人： Jingjin Zhou , Pei Cheng , Yirong Zeng , Bin Fu , Yu Gao , Xiaolong Zhu
摘要： Embodiments of this application disclose a video data processing method and apparatus, and a storage medium. After historical and current video frames are acquired from a video stream, two point position sets of a human body are obtained from the historical video frame and the current video frame, respectively. A jitter amplitude of a human body key point in the current video frame is analyzed according to the point position set of the human body in the current video frame and the point position set of the human body in the historical video frame; an adjustment reference position of the human body in the current video frame is determined according to the jitter amplitude; and subsequently a human body part below the adjustment reference position in the current video frame is adjusted and the adjusted current video frame is outputted for display as part of the video stream.
-
公开(公告)号：US11140436B2
公开(公告)日：2021-10-05
申请号：US15962663
申请日：2018-04-25
发明人： Qianyi Wang , Yanggang Dai , Lei Ying , Faqiang Wu , Lingrui Cui , Zhenhai Wu , Yu Gao
IPC分类号： H04N21/442 , H04N21/433 , G06K9/00 , H04N5/76 , H04N21/414 , H04N21/4788 , H04N21/44 , H04N21/4223 , H04N5/232
摘要： A method of performing video synthesis by a terminal is described. Circuitry of the terminal receives a first operation to trigger capture of first media information and detects at least one of a facial expression change of a user based on a first preset condition or a gesture of the user based on a second preset condition during the capture of the first media information. The circuitry of the terminal sends the detected at least one of the facial expression change or the gesture of the user to a server as key information. The circuitry of the terminal receives second media information that corresponds to the key information from the server and performs video synthesis on the first media information and the second media information.
-
公开(公告)号：US20200372613A1
公开(公告)日：2020-11-26
申请号：US16993061
申请日：2020-08-13
发明人： Jingjin ZHOU , Pel Cheng , Yirong Zeng , Bin Fu , Yu Gao , Xiaolong Zhu
摘要： Embodiments of this application disclose a video data processing method and apparatus, and a storage medium. After historical and current video frames are acquired from a video stream, two point position sets of a human body are obtained from the historical video frame and the current video frame, respectively. A jitter amplitude of a human body key point in the current video frame is analyzed according to the point position set of the human body in the current video frame and the point position set of the human body in the historical video frame; an adjustment reference position of the human body in the current video frame is determined according to the jitter amplitude; and subsequently a human body part below the adjustment reference position in the current video frame is adjusted and the adjusted current video frame is outputted for display as part of the video stream.
-
公开(公告)号：US11012740B2
公开(公告)日：2021-05-18
申请号：US16231873
申请日：2018-12-24
发明人： Qianyi Wang , Yu Gao , Zhibin Wang , En Li , Rong Li
IPC分类号： H04N21/44 , H04N21/8549 , H04N21/431 , H04N21/4788 , G06T11/20 , G06T11/00
摘要： A video processing method, a video processing device, and a storage medium are provided. The video processing method includes: determining target image frames corresponding to a dynamic special effect in a video and determining an attribute of a special effect element corresponding to the dynamic special effect in each of the target image frames and coordinates of the special effect element. The video processing method also includes: rendering the special effect element on a drawing interface based on the attribute and the coordinates of the special effect element; filling the target image frames into the drawing interface as a background and forming drawing interface frames with the dynamic special effect; and outputting the drawing interface frames corresponding to each of the target image frames.
-
6.发明授权公开(公告)号：US10380427B2
公开(公告)日：2019-08-13
申请号：US16107704
申请日：2018-08-21
发明人： Qianyi Wang , Yanggang Dai , Feng Shi , Faqiang Wu , Lingrui Cui , Tao Xiong , Yu Gao , Yunsheng Wu
IPC分类号： G06K9/00 , G06K9/62 , G11B27/036 , G06F16/78 , G06F16/00
摘要： A partner matching method in a costarring video is performed by a terminal. The terminal obtains a video recorded by a first user identifier and a video in which a second role that matches the first role is played and an associated second user identifier. After obtaining a total score of videos in which the second role is played by each second user identifier in each user type, the terminal ranks the videos in which the second role is played by the second user identifiers for each user type and displays a ranking result of the videos in which the second role is played for each user type. After obtaining a video selected from the ranking result, the terminal synthesizes a complete video from the selected video in which the second role is played and the video in which the first role is played.
-
公开(公告)号：US09508118B2
公开(公告)日：2016-11-29
申请号：US15104563
申请日：2015-06-24
发明人： Antai Guo , Bo Ren , Yu Gao , Yang Yang , Yinsong Liu
CPC分类号： G06T3/0093 , G06T3/40
摘要： The method of the present disclosure includes: acquiring a pair of operation control points including an operation start point and an operation end point; calculating a vector from the operation start point to the operation end point; determining an image deforming area, where the image deforming area consists of a contracted sub-area and a stretched sub-area; determining a pixel step value of each pixel in the image deforming area, where a pixel step value of a pixel in the contracted sub-area is greater than a preset step value threshold, and a pixel step value of a pixel in the stretched sub-area is less than the step value threshold; generating an offset parameter relative to the image according to a vector direction of the vector and the pixel step value of the pixel; and performing interpolation calculation on the offset parameter, to obtain a stretched image.
摘要翻译： 本公开的方法包括：获取包括操作开始点和操作终点的一对操作控制点; 计算从操作开始点到操作终点的向量; 确定图像变形区域，其中图像变形区域由收缩的子区域和拉伸的子区域组成; 确定所述图像变形区域中的每个像素的像素步长值，其中所述收缩子区域中的像素的像素阶跃值大于预设步长阈值，以及所述延伸子区域中的像素的像素步长值， 面积小于步值阈值; 根据矢量的矢量方向和像素的像素步长值，生成相对于图像的偏移参数; 并对偏移参数进行插补计算，以获得拉伸图像。
-
公开(公告)号：US20160321780A1
公开(公告)日：2016-11-03
申请号：US15104563
申请日：2015-06-24
发明人： Antai Guo , Bo Ren , Yu Gao , Yang Yang , Yinsong Liu
CPC分类号： G06T3/0093 , G06T3/40
摘要： The method of the present disclosure includes: acquiring a pair of operation control points including an operation start point and an operation end point; calculating a vector from the operation start point to the operation end point; determining an image deforming area, where the image deforming area consists of a contracted sub-area and a stretched sub-area; determining a pixel step value of each pixel in the image deforming area, where a pixel step value of a pixel in the contracted sub-area is greater than a preset step value threshold, and a pixel step value of a pixel in the stretched sub-area is less than the step value threshold; generating an offset parameter relative to the image according to a vector direction of the vector and the pixel step value of the pixel; and performing interpolation calculation on the offset parameter, to obtain a stretched image.
摘要翻译： 本公开的方法包括：获取包括操作开始点和操作终点的一对操作控制点; 计算从操作开始点到操作终点的向量; 确定图像变形区域，其中图像变形区域由收缩的子区域和拉伸的子区域组成; 确定所述图像变形区域中的每个像素的像素步长值，其中所述收缩子区域中的像素的像素阶跃值大于预设步长阈值，以及所述延伸子区域中的像素的像素步长值， 面积小于步值阈值; 根据矢量的矢量方向和像素的像素步长值，生成相对于图像的偏移参数; 并对偏移参数进行插补计算，以获得拉伸图像。
-
-
-
-
-
-
-
搜索结果
8 条记录 (耗时 0.018 秒)
