Amazon Technologies, Inc.

Elemental Technologies, Inc.

Brian Lewis

Jesse Jerome Rosenzweig

Ryan Paul Hegar

Trevor Wells

Samuel S Blackman

Jeffrey K Lassahn

John Saxton

Kevin Moore

David Montgomery

Leah Siddall

Various types of objects or occurrences can be automatically detected in input media being processed using a transcoder. The media content can be analyzed to determine various transitions, such as scene changes, which provide insight into useful locations for performing object recognition. Representative frames subsequent a transition are analyzed to determine whether they are appropriate for image analysis, using factors such as amount of motion, brightness, color, or pixel disparity within the frame. If a representative frame meets the various criteria, that frame is sent to an object recognition service for analysis. The output of the service can be a set of object tags that provide information identifying the object and its location in the media. The output tags can be encoded into the output video or stored to an associated metadata file, among other such options.

Automated indexing of media content

A content stream matching and processing process is provided. A computing device receives a plurality of content streams. The computing device processes the content streams to generate picture data information. The picture data information can be utilized to determine whether the content streams can be aligned. Based on the alignment, the computing device can characterize the similarity of the content streams.

Matching based on video data

Methods, systems, and computer-readable media for real-time video streaming with latency control are disclosed. Using a media streaming system, a current frame of a video input is acquired from an input pipeline. The current frame is associated with a timestamp. A mapped timestamp associated with the current frame is determined. The mapped timestamp represents the timestamp mapped to a clock associated with the media streaming system. Based at least in part on a comparison between the mapped timestamp and a deadline for frame output, the current frame is either transmitted to an output pipeline according to the deadline, held for evaluation against one or more subsequent deadlines, or discarded.

Real-time video streaming with latency control

An encoding or transcoding system uses hypothetical reference decoder occupancy data to at least calculate parameters for output buffers for data streams. An output thread receives HRD buffer occupancy data and calculates buffer occupancy based on duration, rather than absolute occupancy, and correlates the HRD buffer occupancy data with target durations for buffered packets prior to release from the buffer.

Encoder-sensitive stream buffer management

A method is disclosed for the decoding and encoding of a block-based video bit-stream such as MPEG2, H.264-AVC, VC1, or VP6 using a system containing one or more high speed sequential processors, a homogenous array of software configurable general purpose parallel processors, and a high speed memory system to transfer data between processors or processor sets. This disclosure includes a method for load balancing between the two sets of processors.

Video encoding and decoding using parallel processors

A video packaging and origination service can include one or more encoder components that receive content for encoding and transmitting to requesting entities. During the operation of the encoder components, individual encoders receive input signals for encoding and determine picture data related to the generation of an encoded segment. The encoder components exchange picture data information and individual encoder components select synchronization information based processing the exchanged picture data information. The exchange of picture data and synchronization can continue throughout the streaming process.

Video-based encoder alignment

A system including one or more cloud computing units and a ground unit. The one or more cloud computing units may be configured to process video content. The ground unit may be configured to pre-process the video content and deliver the video content to the one or more cloud computing units.

Heterogeneous video processing using private or public cloud computing resources

A method for implementing a deblocking filter including the steps of (A) reading pixel values for a plurality of macroblocks of an unfiltered video frame from an input buffer into a working buffer, where the working buffer has dimensions determined by a predefined input region of the deblocking filter and a portion of the working buffer forms a filter output region of the deblocking filter, (B) sequentially processing the pixel values in the working buffer through a plurality of filter processing stages using an array of software-configurable general purpose parallel processors, where each of the plurality of filter processing stages operates on a respective set of the pixel values in the working buffer, and (C) writing filtered pixel values from the filter output region of the working buffer to an output buffer after the plurality of filter processing stages are completed.

Method of efficiently implementing a MPEG-4 AVC deblocking filter on an array of parallel processors

An apparatus includes a processor, a graphics processing unit and a memory. The memory stores computer executable instructions. The computer executable instructions include a motion estimation kernel which when executed by the graphics processing unit performs motion estimation on a current frame using a reference frame. The current frame and the reference frame are stored in a globally shared memory of the graphics processing unit.

Video encoder using GPU

An apparatus including a graphics processing unit, a processor and a memory. The memory stores computer executable instructions. The computer executable instructions, when executed by the processor, configure the graphics processing unit to store a current frame, at least one reference frame, and a reconstructed frame in a globally shared memory of the graphics processing unit.

An apparatus comprising a graphics processing unit, a processor and a memory. The memory stores computer executable instructions. The computer executable instructions use (i) the graphics processing unit to perform prediction, decimation, transformation and quantization, and inverse-quantization and inverse-transformation and (ii) the processor to perform entropy encoding and rate control.

Techniques are disclosed for employing a set of stream processors to greatly accelerate common video encoding and transcoding tasks, with the goal of making these tasks run at a reasonable rate on off-the-shelf hardware. Stream processors are most commonly found in the graphics processing unit (GPU), a commodity piece of computer hardware used to generate images for display. Embodiments of the invention are particularly advantageous to accelerate video encoding and transcoding tasks in which the blocks being processed have dependencies on their neighboring blocks.

Growing community of inventors

Portland, OR, United States of America

Brian Lewis