专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11350105B2 Selection of video quality metrics and models to optimize bitrate savings in video encoding applications 有权
公开(公告)号：US11350105B2
公开(公告)日：2022-05-31
申请号：US17144924
申请日：2021-01-08
申请人： Euclid Discoveries, LLC
发明人： Dane P. Kottke , Katherine H. Cornog , John J. Guo , Myo Tun , Jeyun Lee , Nigel Lee
IPC分类号： H04N19/146 , H04N19/124 , H04N19/172 , H04N19/50 , H04N19/192 , H04N19/179 , H04N19/115 , H04N19/154 , G06T7/00
摘要： Videos may be characterized by objective metrics that quantify video quality. Embodiments are directed to target bitrate prediction methods in which one or more objective metrics may serve as inputs into a model that predicts a mean opinion score (MOS), a measure of perceptual quality, as a function of metric values. The model may be derived by generating training data through conducting subjective tests on a set of video encodings, obtaining MOS data from the subjective tests, and correlating the MOS data with metric measurements on the training data. The MOS predictions may be extended to predict the target (encoding) bitrate that achieves a desired MOS value. The target bitrate prediction methods may be applied to segments of a video. The methods may be made computationally faster by applying temporal subsampling. The methods may also be extended for adaptive bitrate (ABR) applications by applying scaling factors to predicted bitrates at one frame size to determine predicted bitrates at different frame sizes. A dynamic scaling algorithm may be used to determine predicted bitrates at different frame sizes.

2. 发明申请

US20210203951A1 Selection of Video Quality Metrics and Models to Optimize Bitrate Savings in Video Encoding Applications 有权
公开(公告)号：US20210203951A1
公开(公告)日：2021-07-01
申请号：US17144924
申请日：2021-01-08
申请人： Euclid Discoveries, LLC
发明人： Dane P. Kottke , Katherine H. Cornog , John J. Guo , Myo Tun , Jeyun Lee , Nigel Lee
IPC分类号： H04N19/146 , H04N19/124 , H04N19/172 , H04N19/50 , G06T7/00 , H04N19/192 , H04N19/179 , H04N19/115 , H04N19/154
摘要： Videos may be characterized by objective metrics that quantify video quality. Embodiments are directed to target bitrate prediction methods in which one or more objective metrics may serve as inputs into a model that predicts a mean opinion score (MOS), a measure of perceptual quality, as a function of metric values. The model may be derived by generating training data through conducting subjective tests on a set of video encodings, obtaining MOS data from the subjective tests, and correlating the MOS data with metric measurements on the training data. The MOS predictions may be extended to predict the target (encoding) bitrate that achieves a desired MOS value. The target bitrate prediction methods may be applied to segments of a video. The methods may be made computationally faster by applying temporal subsampling. The methods may also be extended for adaptive bitrate (ABR) applications by applying scaling factors to predicted bitrates at one frame size to determine predicted bitrates at different frame sizes. A dynamic scaling algorithm may be used to determine predicted bitrates at different frame sizes.

3. 发明授权

US11228766B2 Dynamic scaling for consistent video quality in multi-frame size encoding 有权
公开(公告)号：US11228766B2
公开(公告)日：2022-01-18
申请号：US17143929
申请日：2021-01-07
申请人： Euclid Discoveries, LLC
发明人： Dane P. Kottke , Katherine H. Cornog , John J. Guo , Myo Tun , Jeyun Lee , Nigel Lee
IPC分类号： H04N19/146 , H04N19/124 , H04N19/172 , H04N19/50 , H04N19/192 , H04N19/179 , H04N19/115 , H04N19/154 , G06T7/00
摘要： Videos may be characterized by objective metrics that quantify video quality. Embodiments are directed to target bitrate prediction methods in which one or more objective metrics may serve as inputs into a model that predicts a mean opinion score (MOS), a measure of perceptual quality, as a function of metric values. The model may be derived by generating training data through conducting subjective tests on a set of video encodings, obtaining MOS data from the subjective tests, and correlating the MOS data with metric measurements on the training data. The MOS predictions may be extended to predict the target (encoding) bitrate that achieves a desired MOS value. The target bitrate prediction methods may be applied to segments of a video. The methods may be made computationally faster by applying temporal subsampling. The methods may also be extended for adaptive bitrate (ABR) applications by applying scaling factors to predicted bitrates at one frame size to determine predicted bitrates at different frame sizes. A dynamic scaling algorithm may be used to determine predicted bitrates at the different frame sizes.

4. 发明授权

US09621917B2 Continuous block tracking for temporal prediction in video encoding 有权
公开(公告)号：US09621917B2
公开(公告)日：2017-04-11
申请号：US14532947
申请日：2014-11-04
申请人： Euclid Discoveries, LLC
发明人： Dane P. Kottke , John J. Guo , Jeyun Lee , Sangseok Park , Christopher Weed , Justin Kwan , Nigel Lee
IPC分类号： H04B1/66 , H04N7/12 , H04N11/02 , H04N11/04 , H04N19/56 , H04N19/517 , H04N19/117 , H04N19/105 , H04N19/139 , H04N19/176 , H04N19/513 , H04N19/527 , H04N19/53 , H04N19/58
CPC分类号： H04N19/56 , H04N19/105 , H04N19/117 , H04N19/139 , H04N19/176 , H04N19/513 , H04N19/517 , H04N19/527 , H04N19/53 , H04N19/58
摘要： Continuous block tracking (CBT) tracks macroblock locations over reference frames to produce better inter-predictions than conventional block-based motion estimation/compression. CBT includes frame-to-frame tracking, estimating motion from a frame to a previous frame, and continuous tracking, related frame-to-frame motion vectors to block tracks. Frame-to-frame tracking may include block based or hierarchical motion estimations. CBT combined with enhanced predictive zonal search may create unified motion estimation. Accumulated CBT results may form trajectories for trajectory-based CBT predictions. Metrics measuring continuous track and motion vector quality can assess relative priority of CBT prediction against non-tracker-based predictions and to modify encoding choices. Continuous tracks can be analyzed for goodness-of-fit to translational motion models, with outliers removed from encoding. Translational motion models can be extended to entire frames in adaptive picture type selection. Outputs from CBT used in look-ahead processing, via look-ahead tracking, may provide rate control and scene change detection for the current frame being encoded.

5. 发明授权

US11159801B2 Video characterization for smart encoding based on perceptual quality optimization 有权
公开(公告)号：US11159801B2
公开(公告)日：2021-10-26
申请号：US16926089
申请日：2020-07-10
申请人： Euclid Discoveries, LLC
发明人： Dane P. Kottke , Katherine H. Cornog , John J. Guo , Myo Tun , Jeyun Lee , Nigel Lee
IPC分类号： H04N19/146 , H04N19/124 , H04N19/172 , H04N19/50 , G06T7/00 , H04N19/192 , H04N19/179 , H04N19/115 , H04N19/154
摘要： Videos may be characterized by objective metrics that quantify video quality. Embodiments are directed to target bitrate prediction methods in which one or more objective metrics may serve as inputs into a model that predicts a mean opinion score (MOS), a measure of perceptual quality, as a function of metric values. The model may be derived by generating training data through conducting subjective tests on a set of video encodings, obtaining MOS data from the subjective tests, and correlating the MOS data with metric measurements on the training data. The MOS predictions may be extended to predict the target (encoding) bitrate that achieves a desired MOS value. The target bitrate prediction methods may be applied to segments of a video. The methods may be made computationally faster by applying temporal subsampling. The methods may also be extended for adaptive bitrate (ABR) applications by applying scaling factors to predicted bitrates at one frame size to determine predicted bitrates at different frame sizes. A dynamic scaling algorithm may be used to determine predicted bitrates at the different frame sizes.

6. 发明申请

US20210203950A1 Dynamic Scaling for Consistent Video Quality in Multi-frame Size Encoding 有权
公开(公告)号：US20210203950A1
公开(公告)日：2021-07-01
申请号：US17143929
申请日：2021-01-07
申请人： Euclid Discoveries, LLC
发明人： Dane P. Kottke , Katherine H. Cornog , John J. Guo , Myo Tun , Jeyun Lee , Nigel Lee
IPC分类号： H04N19/146 , H04N19/124 , H04N19/172 , H04N19/50 , G06T7/00 , H04N19/192 , H04N19/179 , H04N19/115 , H04N19/154
摘要： Videos may be characterized by objective metrics that quantify video quality. Embodiments are directed to target bitrate prediction methods in which one or more objective metrics may serve as inputs into a model that predicts a mean opinion score (MOS), a measure of perceptual quality, as a function of metric values. The model may be derived by generating training data through conducting subjective tests on a set of video encodings, obtaining MOS data from the subjective tests, and correlating the MOS data with metric measurements on the training data. The MOS predictions may be extended to predict the target (encoding) bitrate that achieves a desired MOS value. The target bitrate prediction methods may be applied to segments of a video. The methods may be made computationally faster by applying temporal subsampling. The methods may also be extended for adaptive bitrate (ABR) applications by applying scaling factors to predicted bitrates at one frame size to determine predicted bitrates at different frame sizes. A dynamic scaling algorithm may be used to determine predicted bitrates at the different frame sizes.

7. 发明授权

US10757419B2 Video characterization for smart encoding based on perceptual quality optimization 有权
公开(公告)号：US10757419B2
公开(公告)日：2020-08-25
申请号：US16420796
申请日：2019-05-23
申请人： Euclid Discoveries, LLC
发明人： Dane P. Kottke , Katherine H. Cornog , John J. Guo , Myo Tun , Jeyun Lee , Nigel Lee
IPC分类号： H04N19/146 , G06T7/00 , H04N19/124 , H04N19/50 , H04N19/172 , H04N19/192 , H04N19/179 , H04N19/115 , H04N19/154
摘要： Videos may be characterized by objective metrics that quantify video quality. Embodiments are directed to target bitrate prediction methods in which one or more objective metrics may serve as inputs into a model that predicts a mean opinion score (MOS), a measure of perceptual quality, as a function of metric values. The model may be derived by generating training data through conducting subjective tests on a set of video encodings, obtaining MOS data from the subjective tests, and correlating the MOS data with metric measurements on the training data. The MOS predictions may be extended to predict the target (encoding) bitrate that achieves a desired MOS value. The target bitrate prediction methods may be applied to segments of a video. The methods may be made computationally faster by applying temporal subsampling. The methods may also be extended for adaptive bitrate (ABR) applications by applying scaling factors to predicted bitrates at one frame size to determine predicted bitrates at different frame sizes. A dynamic scaling algorithm may be used to determine predicted bitrates at the different frame sizes.

8. 发明申请

US20190289296A1 Video Characterization For Smart Encoding Based On Perceptual Quality Optimization 审中-公开
公开(公告)号：US20190289296A1
公开(公告)日：2019-09-19
申请号：US16420796
申请日：2019-05-23
申请人： Euclid Discoveries, LLC
发明人： Dane P. Kottke , Katherine H. Cornog , John J. Guo , Myo Tun , Jeyun Lee , Nigel Lee
IPC分类号： H04N19/146 , G06T7/00 , H04N19/124 , H04N19/50 , H04N19/172
摘要： Videos may be characterized by objective metrics that quantify video quality. Embodiments are directed to target bitrate prediction methods in which one or more objective metrics may serve as inputs into a model that predicts a mean opinion score (MOS), a measure of perceptual quality, as a function of metric values. The model may be derived by generating training data through conducting subjective tests on a set of video encodings, obtaining MOS data from the subjective tests, and correlating the MOS data with metric measurements on the training data. The MOS predictions may be extended to predict the target (encoding) bitrate that achieves a desired MOS value. The target bitrate prediction methods may be applied to segments of a video. The methods may be made computationally faster by applying temporal subsampling. The methods may also be extended for adaptive bitrate (ABR) applications by applying scaling factors to predicted bitrates at one frame size to determine predicted bitrates at different frame sizes. A dynamic scaling algorithm may be used to determine predicted bitrates at the different frame sizes.

9. 发明申请

US20150256850A1 Continuous Block Tracking For Temporal Prediction In Video Encoding 有权
标题翻译：连续块跟踪用于视频编码中的时间预测
公开(公告)号：US20150256850A1
公开(公告)日：2015-09-10
申请号：US14532947
申请日：2014-11-04
申请人： Euclid Discoveries, LLC
发明人： Dane P. Kottke , John J. Guo , Jeyun Lee , Sangseok Park , Christopher Weed , Justin Kwan , Nigel Lee
IPC分类号： H04N19/56 , H04N19/117 , H04N19/517
CPC分类号： H04N19/56 , H04N19/105 , H04N19/117 , H04N19/139 , H04N19/176 , H04N19/513 , H04N19/517 , H04N19/527 , H04N19/53 , H04N19/58
摘要： Continuous block tracking (CBT) tracks macroblock locations over reference frames to produce better inter-predictions than conventional block-based motion estimation/compression. CBT includes frame-to-frame tracking, estimating motion from a frame to a previous frame, and continuous tracking, related frame-to-frame motion vectors to block tracks. Frame-to-frame tracking may include block based or hierarchical motion estimations. CBT combined with enhanced predictive zonal search may create unified motion estimation. Accumulated CBT results may form trajectories for trajectory-based CBT predictions. Metrics measuring continuous track and motion vectors quality can assess relative priority of CBT predictions against non-tracker-based predictions and to modify encoding choices. Continuous tracks can be analyzed for goodness-of-fit to translational motion models, with outliers removed from encoding. Translational motion models can be extended to entire frames in adaptive picture type selection. Outputs from CBT used in look-ahead processing, via look-ahead tracking, may provide rate control and scene change detection for the current frame being encoded.
摘要翻译：连续块跟踪（CBT）跟踪参考帧上的宏块位置，以产生比传统的基于块的运动估计/压缩更好的相互预测。 CBT包括帧到帧跟踪，估计从帧到先前帧的运动，以及连续跟踪，相关的帧到帧运动向量来阻塞轨道。帧到帧跟踪可以包括基于块或分层运动估计。 CBT结合增强的预测区域搜索可以创建统一的运动估计。累积的CBT结果可能形成基于轨迹的CBT预测的轨迹。测量连续轨迹和运动矢量质量的度量可以评估CBT预测与非基于跟踪器的预测的相对优先级，并修改编码选择。可以对平移运动模型的适合度分析连续轨迹，从编码中删除异常值。平移运动模型可以扩展到自适应图像类型选择中的整个帧。通过预先跟踪，在前瞻处理中使用的CBT的输出可以为正在编码的当前帧提供速率控制和场景变化检测。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式