Abstract: Video stream data is selectively scaled so that sections within regions of interest (ROI) maintain high resolution while areas not within the region of interest are down-scaled to reduce bandwidth cost of transmission. A low compression encoder compresses sections of a video frame corresponding to one or more ROI without motion search or prediction mode decision to generate low-compression section data. The video frame is downscaled and a high compression encoder compresses the resulting downscaled video frame with prediction mode decision to generate high-compression frame data.

Abstract: Training a video decoder system may include masking one of at least two sets of video encoding parameters with invalid values to generate an invalid set. The at least two sets of video encoding parameters are provided to one or more neural networks to train them to predict valid values that correspond to values of the invalid set using an iterative training algorithm. Encoding parameters to encode are determined based on a prediction error of the one or more neural networks. Encoding parameters which are determined to be accurately predicted are dropped from the encoded data. A new video stream is encoded without the dropped encoding parameters.

Abstract: A method, system and computer readable instructions for video encoding comprising, determining one or more region of interest (ROI) parameters for pictures in a picture stream and a temporal down sampling interval. One or more areas outside the ROI in a picture in the picture stream are temporally down sampled according to the interval. The resulting temporally down sampled picture is then encoded and the encoded temporally down-sampled picture is transmitted. Additionally, a picture encoded in this way in an encoded picture stream may be decoded and areas outside an ROI of the picture may be temporally up sampled. The temporally up sampled areas outside the ROI are inserted into the decoded encoded picture stream.

Abstract: Training a video decoder system may include masking one of at least two sets of video encoding parameters with invalid values to generate an invalid set. The at least two sets of video encoding parameters are provided to one or more neural networks to train them to predict valid values that correspond to values of the invalid set using an iterative training algorithm. Encoding parameters to encode are determined based on a prediction error of the one or more neural networks. Encoding parameters which are determined to be accurately predicted are dropped from the encoded data. A new video stream is encoded without the dropped encoding parameters.

Abstract: Video stream data is selectively scaled so that sections within regions of interest (ROI) maintain high resolution while areas not within the region of interest are down-scaled to reduce bandwidth cost of transmission. A low compression encoder compresses sections of a video frame corresponding to one or more ROI without motion search or prediction mode decision to generate low-compression section data. The video frame is downscaled and a high compression encoder compresses the resulting downscaled video frame with prediction mode decision to generate high-compression frame data.

Abstract: Training a video decoder system may include generating at least two valid sets of video encoding parameters and masking one of the sets with invalid values to generate an invalid set. The valid sets of video encoding parameters may be provided to one or more neural networks to train them to predict valid values that correspond to values of the invalid set using an iterative training algorithm. A prediction error of the predicted valid values is determined from the results of the training of the neural networks and the valid video encoding parameters. The prediction error is inserted into encoding data and encoded parameters determined to be accurately predicted with the addition of the prediction error are dropped. A new video stream is encoded with the predication error and without the dropped encoding parameters.

Abstract: Gaze tracking data is analyzed to determine one or more regions of interest within an image of a video stream. The video stream data is selectively scaled so that sections within the regions of interest maintain high resolution while areas not within the region of interest are down-scaled to reduce bandwidth cost of transmission. A scheme for reduction of motion sickness by reducing the size of the high resolution area is also claimed.

Abstract: A method, system and computer readable instructions for video encoding comprising, determining one or more region of interest (ROI) parameters for pictures in a picture stream and a temporal down sampling interval. One or more areas outside the ROI in a picture in the picture stream are temporally down sampled according to the interval. The resulting temporally down sampled picture is then encoded and the encoded temporally down-sampled picture is transmitted. Additionally, a picture encoded in this way in an encoded picture stream may be decoded and areas outside an ROI of the picture may be temporally up sampled. The temporally up sampled areas outside the ROI are inserted into the decoded encoded picture stream.

Abstract: Training a video decoder system may include generating at least two valid sets of video encoding parameters and masking one of the sets with invalid values to generate an invalid set. The valid sets of video encoding parameters may be provided to one or more neural networks to train them to predict valid values that correspond to values of the invalid set using an iterative training algorithm. A prediction error of the predicted valid values is determined from the results of the training of the neural networks and the valid video encoding parameters. The prediction error is inserted into encoding data and encoded parameters determined to be accurately predicted with the addition of the prediction error are dropped. A new video stream is encoded with the predication error and without the dropped encoding parameters.

Abstract: Training a video decoder system comprising, generating at least two sets of video encoding parameters wherein the at least two sets of video encoding parameters are valid, masking a set of the at least two sets of encoding parameters with invalid values to generate an invalid set of video encoding parameters, providing a set of the at least two sets of video encoding parameters to a neural network, training the neural network to predict valid video encoding parameter values for the invalid set using an iterative training algorithm, determining which encoding parameters need to be encoded based on analysis of a prediction error of the trained recurrent neural network, dropping the encoding parameters from the encoded data which are determined to be accurately predicted by the trained recurrent neural network, encoding a new video stream without the dropped encoding parameters. A coder and decoder system with neural network is also disclosed.

Abstract: Training a video decoder system comprising, generating at least two sets of video encoding parameters wherein the at least two sets of video encoding parameters are valid, masking a set of the at least two sets of encoding parameters with invalid values to generate an invalid set of video encoding parameters, providing a set of the at least two sets of video encoding parameters to a neural network, training the neural network to predict valid video encoding parameter values for the invalid set using an iterative training algorithm, determining which encoding parameters need to be encoded based on analysis of a prediction error of the trained recurrent neural network, dropping the encoding parameters from the encoded data which are determined to be accurately predicted by the trained recurrent neural network, encoding a new video stream without the dropped encoding parameters. A coder and decoder system with neural network is also disclosed.

Abstract: In aspects of the present disclosure, a software encoder augments a hardware encoder by implementing portions of a video encoding task that are not supported by the hardware encoder while the hardware encoder implements other portions of the encoding task. The use of a software encoder to augment a hardware encoder in this manner can extend the useful life of a hardware encoder, allow the system to adapt to changes in video coding standards, and in some cases improve performance of encoding implemented by hardware or software alone. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

Abstract: Gaze tracking data is analyzed to determine one or more regions of interest within an image of a video stream. The video stream data is selectively scaled so that sections within the regions of interest maintain high resolution while areas not within the region of interest are down-scaled to reduce bandwidth cost of transmission. A scheme for reduction of motion sickness by reducing the size of the high resolution area is also claimed.

Abstract: A software security layer may be used to protect a system against exploitation of a hardware encoder accelerator by malicious data embedded in the one or more frames of encoded digital streaming data. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

Abstract: Mode searching and early termination of a video picture may include determining the cost value of a simple intra-mode prediction of the video picture; determining the cost value of an inter-mode prediction of the video picture; determining a threshold value based on a given quantization parameter (QP); comparing the cost value of the simple intra-mode prediction to the sum of the cost value of the inter-mode prediction and the threshold value; and performing a mode-prediction of the video picture in accordance with the result obtained. Fast compression of variable length symbols may include receiving a variable length symbol with one or more tokens; combining the one or more tokens in the variable length symbol to form a token combination; and determining a bit representation of the token combination in correspondence to a probability threshold associated with the token combination.

Abstract: A software security layer may be used to protect a system against exploitation of a hardware encoder accelerator by malicious data embedded in the one or more frames of encoded digital streaming data. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

Abstract: In methods for encoding and decoding digital pictures certain prediction parameters may be omitted from the output on the encoder side or the input on the decoder side. An encoder can identify prediction parameter values that can be omitted by determining whether a decoder emulator can reproduce the prediction parameter values from other information, such as predicted pixel and prediction error values of one or more previously decoded sections from the same or a different picture.

Abstract: In aspects of the present disclosure, a software encoder augments a hardware encoder by implementing portions of a video encoding task that are not supported by the hardware encoder while the hardware encoder implements other portions of the encoding task. The use of a software encoder to augment a hardware encoder in this manner can extend the useful life of a hardware encoder, allow the system to adapt to changes in video coding standards, and in some cases improve performance of encoding implemented by hardware or software alone. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

Abstract: Apparatus and methods for decoding streaming data containing one or more coded pictures in which each picture contains a plurality of slices and each slice containing a plurality of macroblocks are disclosed. A first decoding subtask is performed on all macroblocks in the coded picture or a section thereof. After performing the first decoding subtask on all macroblocks in the coded picture or a section thereof, a second decoding subtask is performed on all the macroblocks in the coded picture or section thereof. One or more of the first and second tasks includes examining a slice or macroblock within the coded picture to determine if there are any errors, and if an error is present, handling the error.

Abstract: Prediction of and recovery from display buffer underflow are described. A first time delay for displaying a first group of one or more frames of a video picture stream located in an output frame buffer is calculated. A second time delay for displaying a second group of one or more frames in the picture stream is calculated. The second group directly follows the first group in the output buffer and is currently decoded by a decoder, but not yet deposited into the output frame buffer. A third time delay for decoding a third group of one or more frames in the picture stream is calculated. The third group directly follows the second group and is not yet decoded by the decoder. The decoder switches to or remains in a fast decoding mode if the sum of the first and second time delays is less than the third time delay.