Google Inc.

Xiaoquan Yi

Huisheng Wang

Vijnan Shastri

Gal Chechik

Hrishikesh Balkrishna Aradhye

Huiseng Wang

Disclosed herein are methods and apparatuses for compressing a video signal. In one embodiment, the method includes storing a function derived from a set of human ratings in a memory, identifying within at least a portion of the video signal at least one content-based feature, inputting the at least one identified content-based feature into the stored function, determining a compression ratio based on the function using a processor and generating a compressed video signal at the determined compression ratio.

Method and apparatus for data compression using content-based features

A relative quality score is provided that takes into account properties of an encoded version of a source video. For example, one such quality score calculates a difference of higher and lower quality transcoded versions of the source video, and computes quality metrics for each to evaluate how similar the transcoded versions are to the source video. A relative quality score quantifying the quality improvement of the high-quality version over the low-quality version is computed. The relative quality score is adjusted based on a measurement of the quality of the source video. If the relative quality score for the video indicates a sufficient quality improvement of the high-quality version over the low-quality version, various actions are taken, such as retaining the high-quality version, and making the high-quality version available to users, e.g. via a video viewing user interface.

Relative quality score for video transcoding

A system and method provides content-adaptive bitrate video transcoding of a source video for a video hosting service. The system is coupled to a video coding complexity engine and video rate-distortion modeling engine of the video hosting service. The system is configured to receive the video coding complexity score of the source video and a trained rate-distortion model and a scaling model. A target bitrate estimation module of the system is configured to calculate an initial target bitrate based on the video coding complexity using the trained rate-distortion model. A bitrate refinement module of the system is configured to adjust the initial target bitrate with respect to the resolution and/or frame rate of the transcoded source video. An adaptive video coder of the system is configured to transcode the source video with the adjusted target bitrate.

Bitrate video transcoding based on video coding complexity estimation

A system and method provide a video coding system for adaptively transcoding videos based on video coding complexity (VCC). A VCC engine of the system is configured to generate a measure of how difficult to encode a source video based on a trained VCC model. A video rate-distortion modeling engine of the system is configured to estimate a rate-distortion model and a scaling model. The VCC model, rate-distortion model and the scaling model are trained on a video corpus of the system. The trained VCC model, rate-distortion model and the scaling model are used by an adaptive bitrate transcoding sub-system to transcode a source video with an optimized bitrate and visual quality. The trained VCC model, rate-distortion model and the scaling model are further used by an adaptive resolution transcoding sub-system to transcode a source video with an optimized resolution and visual quality.

Content-based adaptive video transcoding framework

A system and method provide an audio/video coding system for adaptively transcoding audio streams based on content characteristics of the audio streams. An audio stream metadata extraction module of the system is configured to extract metadata of a source audio stream. An audio stream classification module of the system is configured to classify the source audio stream into one of the several audio content categories based on the metadata of the source audio stream. An adaptive audio encoder of the system is configured to determine one or more transcoding parameters including target bitrate and sampling rate based on the metadata and classification of the source audio stream. An adaptive audio transcoder of the system is configured to transcode the source audio stream into an output audio stream using the transcoding parameters.

Adaptive audio transcoding

A system and method estimates video coding complexity of a source video for adaptively transcoding the source video. A video coding complexity engine of the system is configured to receive the source video in its native format and to encode the source video into an intermediate video format. The video coding complexity engine computes a video coding complexity score for the source video. The coding complexity score can be used by an adaptive bitrate transcoding sub-system and/or an adaptive resolution transcoding sub-system for transcoding the source video.

Growing community of inventors

Mountain View, CA, United States of America

Xiaoquan Yi