-
公开(公告)号:US11356748B2
公开(公告)日:2022-06-07
申请号:US16675840
申请日:2019-11-06
Inventor: Zhenliang Jiang , Huifeng Shen
IPC: G06F15/16 , H04N21/845 , H04L65/60 , H04N21/2343 , H04N21/2187 , H04N21/262 , H04N21/231 , H04N21/235 , H04N21/232 , H04N21/236 , H04L65/612 , H04L65/65
Abstract: Embodiments of the present disclosure relate to a method, apparatus, and system for slicing live streaming. A method may include: acquiring the live streaming from a live source station server; slicing the live streaming to generate an index file and sliced files of the live streaming; and sending the index file and the sliced files of the live streaming to an object storage server, to cause the object storage server to store the index file and the sliced files of the live streaming.
-
公开(公告)号:US20210192217A1
公开(公告)日:2021-06-24
申请号:US16892910
申请日:2020-06-04
Inventor: Xiaoming Wang , Huaifei Xing , Wenpeng Ding , Huifeng Shen , Feifei Cao
Abstract: Embodiments of the present disclosure relate to a method and apparatus for processing a video. The method may include: acquiring object regions obtained by performing object detection on a target video frame, a type of an object in each of the object regions being a preset type; determining, for an object region in the acquired object regions, in response to determining that the object region satisfies a preset condition, that the object region is a non-ROI; using an object region other than the non-ROI in the object regions of the target video frame as a ROI; and acquiring a quantization parameter change corresponding to each ROI, and encoding the target video frame based on the quantization parameter change.
-
公开(公告)号:US11375209B2
公开(公告)日:2022-06-28
申请号:US16895430
申请日:2020-06-08
Inventor: Xiaoming Wang , Huaifei Xing , Wenpeng Ding , Huifeng Shen , Feifei Cao
IPC: H04N19/172 , H04N19/167
Abstract: Embodiments of the present disclosure relate to a method and apparatus for processing a video frame. The method may include: acquiring a sequence of video frames of a video; ascertaining, in the sequence of the video frames, a previous frame, and ascertaining, in the sequence of the video frames, a subsequent frame corresponding to the ascertained previous frame based on acquired number of frames from the previous frame to the subsequent frame. An update step is performed as follows: acquiring object regions detected respectively in the ascertained previous frame and the ascertained subsequent frame, and confidence levels of the object regions; fusing a confidence level of a first object region and a confidence level of a second object region, and updating the confidence level of the second object region based on the fusion result; and updating the ascertained previous frame and the ascertained subsequent frame.
-
公开(公告)号:US09961398B2
公开(公告)日:2018-05-01
申请号:US15429306
申请日:2017-02-10
Inventor: Yongxing Li , Huifeng Shen , Jun Ge , Jingbo Huang , Xu Li
IPC: H04N21/438 , H04N21/2387 , H04N21/472 , H04N21/44 , H04N21/234 , H04N21/434 , H04N21/433
CPC classification number: H04N21/4383 , H04N21/234 , H04N21/2387 , H04N21/4331 , H04N21/4345 , H04N21/44 , H04N21/47217
Abstract: Disclosed is a method and device for switching video streams. The method comprises: acquiring video streams of a video in response to receiving a playback request for the video sent by a terminal, the video streams comprising: a video stream with a first group of pictures (GOP) frame number and a video stream with a second GOP frame number; sending the video stream with the first GOP frame number to the terminal, searching for a third key frame in the video stream with the first GOP frame number, and extracting a decoding time stamp (DTS) of the third key frame; searching the video stream with the second GOP frame number for a frame having an identical DTS; determining whether the frame is a fourth key frame in response to finding the frame having the identical DTS; and sending the video stream with the second GOP frame number to the terminal.
-
公开(公告)号:US11659181B2
公开(公告)日:2023-05-23
申请号:US16892910
申请日:2020-06-04
Inventor: Xiaoming Wang , Huaifei Xing , Wenpeng Ding , Huifeng Shen , Feifei Cao
IPC: G06K9/00 , H04N19/124 , G06T7/70 , G06V20/40 , G06V10/25 , G06V40/10 , G06F18/22 , G06V10/80 , H04N19/102 , H04N19/167 , G06V10/22 , G06V10/764 , H04N19/169 , H04N19/115 , G06V10/28 , H04N19/17
CPC classification number: H04N19/124 , G06F18/22 , G06T7/70 , G06V10/22 , G06V10/25 , G06V10/28 , G06V10/764 , G06V10/811 , G06V20/41 , G06V40/10 , H04N19/102 , H04N19/115 , H04N19/167 , H04N19/169 , H04N19/17 , G06T2207/10016
Abstract: Embodiments of the present disclosure relate to a method and apparatus for processing a video. The method may include: acquiring object regions obtained by performing object detection on a target video frame, a type of an object in each of the object regions being a preset type; determining, for an object region in the acquired object regions, in response to determining that the object region satisfies a preset condition, that the object region is a non-ROI; using an object region other than the non-ROI in the object regions of the target video frame as a ROI; and acquiring a quantization parameter change corresponding to each ROI, and encoding the target video frame based on the quantization parameter change.
-
公开(公告)号:US11323750B2
公开(公告)日:2022-05-03
申请号:US16731269
申请日:2019-12-31
Inventor: Minglu Li , Huifeng Shen , Feifei Cao , Li You , Hongbai Dong
IPC: H04N21/222 , H04N21/2187 , H04N21/231 , H04N21/239 , H04N21/262 , H04N21/437 , H04N21/482
Abstract: A video system, a video processing method, a device and a computer readable medium are disclosed. The system includes: a front-end device and a cloud server; the front-end device is configured to collect video stream data, and set a video identifier and a service scenario identifier for the video stream data, upload the video identifier, the video stream data and the service scenario identifier to the cloud server; the cloud server is configured to generate a video file corresponding to the video identifier according to the service scenario identifier, the video identifier and the video stream data; and store the video file.
-
公开(公告)号:US20210195214A1
公开(公告)日:2021-06-24
申请号:US16895430
申请日:2020-06-08
Inventor: Xiaoming Wang , Huaifei Xing , Wenpeng Ding , Huifeng Shen , Feifei Cao
IPC: H04N19/172 , H04N19/167
Abstract: Embodiments of the present disclosure relate to a method and apparatus for processing a video frame. The method may include: acquiring a sequence of video frames of a video; ascertaining, in the sequence of the video frames, a previous frame, and ascertaining, in the sequence of the video frames, a subsequent frame corresponding to the ascertained previous frame based on acquired number of frames from the previous frame to the subsequent frame. An update step is performed as follows: acquiring object regions detected respectively in the ascertained previous frame and the ascertained subsequent frame, and confidence levels of the object regions; fusing a confidence level of a first object region and a confidence level of a second object region, and updating the confidence level of the second object region based on the fusion result; and updating the ascertained previous frame and the ascertained subsequent frame.
-
公开(公告)号:US10897620B2
公开(公告)日:2021-01-19
申请号:US16567976
申请日:2019-09-11
Inventor: Huaifei Xing , Jialiang Wang , Huifeng Shen , Feifei Cao
IPC: H04N19/154 , H04N19/14 , G06K9/00
Abstract: Embodiments of the present disclosure relate to a method and apparatus for processing a video. The method can include: acquiring a to-be-processed video, and dividing the video into at least one video segment according to a scene; for a video segment of the at least one video segment, extracting a feature of the video segment; inputting the feature and a target video quality into a pre-trained encoding parameter prediction model, to obtain an encoding parameter of the video segment, the encoding parameter prediction model being used to represent a corresponding relationship between the feature of the video segment and the encoding parameter under the target video quality; and performing an encoding process on the video according to the encoding parameter corresponding to the video segment of the at least one video segment, to generate an encoded video.
-
公开(公告)号:US20200245042A1
公开(公告)日:2020-07-30
申请号:US16675840
申请日:2019-11-06
Inventor: Zhenliang Jiang , Huifeng Shen
IPC: H04N21/845 , H04N21/2187 , H04N21/2343 , H04L29/06
Abstract: Embodiments of the present disclosure relate to a method, apparatus, and system for slicing live streaming. A method may include: acquiring the live streaming from a live source station server; slicing the live streaming to generate an index file and sliced files of the live streaming; and sending the index file and the sliced files of the live streaming to an object storage server, to cause the object storage server to store the index file and the sliced files of the live streaming.
-
10.
公开(公告)号:US20180084020A1
公开(公告)日:2018-03-22
申请号:US15430167
申请日:2017-02-10
Inventor: Yongxing Li , Huifeng Shen
CPC classification number: H04L65/4092 , H04L43/0894 , H04L43/16 , H04L65/4076 , H04L65/601 , H04L65/602 , H04L65/607 , H04L65/80
Abstract: A method and apparatus for adaptively providing multiple bit rate streaming media in a server. The method for adaptively providing multiple bit rate streaming media comprises: acquiring network quality information; in the case that it is determined based on the network quality information that bit rate switching is needed, selecting one queue from all queues as the transmitting queue, wherein multimedia data frames with different bit rates for the same media content are stored in different queues; reading the multimedia data frame from the transmitting queue and sending it, and deleting all multimedia data frames in other queues having the same media content as the already-sent multimedia data frame. The technical solutions provided by the present disclosure reduces bit rate switching delay while implementing adaptive bit rate switching, and implements quick and seamless adaptive bit rate switching.
-
-
-
-
-
-
-
-
-