Cisco Technology, Inc.

Siping Tao

Sijia Chen

Wayne Liu

Hui Liu

Rui Zhang

Qiyong Liu

Bo Ling

Sawyer Shan

Kai Li

A method, a device and computer readable storage media facilitate providing screen content including a plurality of video frames that are displayed by a computing device. During coding of the screen content, a suitable predictor is found that is used to code pixel blocks from one or more frames. The suitable predictor is found by selecting a pixel block of a current frame, conducting a direction based search by comparing pixel blocks within a search window of a reference frame with the selected pixel block of the current frame to determine whether a match exists, and, in response to a determination that no sufficient match has been found, conducting a feature oriented search by comparing pixel blocks of the reference frame with the selected pixel block of the current frame to find a suitable match based upon a common feature.

Utilizing a search scheme for screen content video coding

Techniques are provided for reference frame management for screen content video coding using hash or checksum functions. A video data stream including a plurality of frames is received, each frame including a plurality of pixels that define content within the frame. A plurality of hash code values associated with partitioned portions of a current frame are determined, where each hash code value is determined as an output value from a hash or checksum function based upon an input value comprising pixel values for a corresponding partition within the current frame. The current frame is compared with a plurality of reference frames based upon a comparison of the hash code values of the current frame with hash code values of the reference frames. A reference frame is selected as a candidate reference frame for coding the current frame.

Reference frame management for screen content video coding using hash or checksum functions

Techniques are provided to improve user experience at endpoint devices that are participating in a multipoint screen content sharing session. A server in a multipoint communication system receives video frames from a sending endpoint device in the communication session that involves one or more other endpoint devices that are to receive video frames from the sending endpoint device. The video frames include key reference frames that use either intra-frame prediction or inter-frame prediction based only on other key reference frames. The server stores the key reference frames. When a new receiving endpoint device joins the communication session, the server sends all the stored key reference frames to the new receiving endpoint device. All video frames received from the sending endpoint device are forwarded to existing ordinary receiving endpoint devices. Key reference frames and some, but not all, non-key reference video frames are forwarded to existing low-capacity receiving endpoint devices.

Efficient frame forwarding in large scale real-time screen content sharing meetings

In one embodiment, a process determines a size of a video unit (e.g., frame) to transmit from a sender to a receiver across a communication channel for an associated video stream, and also determines an updated packet loss rate on the channel. In response, the process may dynamically determine both a number N of video data packets and a number M of forward error correction (FEC) packets to transmit for the video unit based on the size of the video unit, the updated packet loss rate on the channel, and an error resilience requirement for the video stream. In an illustrative embodiment, N and M are determined during transmission of the video stream through a look-up operation into a table indexed by the size of the video unit and the updated packet loss rate as co-indices, the co-indices co-indexing a pre-determined N and M pair.

Growing community of inventors

Anhui, China

Siping Tao