Amazon Technologies, Inc.

Srinivas Rajagopalan

Lei Li

Hai Wei

Charles Benjamin Franklin Waggoner

Yang Yang

Charles Benjamin Waggoner

Zongyi Liu

Srikanth Kiran Kotagiri

Deepthi Nandakumar

Techniques for content-adaptive video sampling for automated video quality monitoring are described. As one example, a computer-implemented method includes receiving a request to train a machine learning model on a training video file comprising at least one labeled defect, performing an encode on the training video file to generate one or more compression features for each compressed frame of the training video file, training the machine learning model to identify a proper subset of candidate defect frames of the training video file based at least in part on the one or more compression features for each compressed frame of the training video file and the at least one labeled defect, receiving an inference request for an input video file, performing an encode on the input video file to generate one or more compression features for each compressed frame of the input video file, generating, by the machine learning model, a proper subset of candidate defect frames of the input video file based at least in part on the one or more compression features for each compressed frame of the input video file, and determining a defect in the input video file based at least in part on the proper subset of candidate defect frames of the input video file.

Content-adaptive video sampling for cost-effective quality monitoring

An adaptive video compression system may receive video data to be compressed, such as for delivery to a user device by a video streaming service. For example the video data may be an entire video file or a segment of a video file. The adaptive video compression system determines a suitable encoding scheme for compressing the video data. In order to determine the encoding scheme, the video data may be analyzed to extract a plurality of features interests of the video data, which may represent one or more characteristics of the video data. The features may be concatenated and collectively expressed as a feature vector. The feature vector is then used to determine a classification for the video data. Accordingly, an encoding scheme is determined for the video data based on the classification of the video data, and applied to video data to compress the video data.

Adaptive video compression

The disclosure is related to allocation of bits in a media stream. In an example, a video stream is segmented into groups of pixels. A determination of a class type is made for individual ones of the groups of pixels. The determination can be based at least in part on semantic similarity of the class type and of a scene represented in the groups of pixels. A further determination occurs for sets of classified data associated with regions of interest (ROIs) according to the determined class type. Masking data associated with the sets of classified data is provided and confidence measures associated with the sets of classified data and the ROIs are determined. Bits are then allocated for groups of pixels based on the masking data and the confidence measures. Thereafter, a bit stream with the bits can be transmitted for playback on a computing device.

Confidence-based encoding

Growing community of inventors

Seattle, WA, United States of America

Srinivas Rajagopalan