Amazon Technologies, Inc.

Mark Eugene Pearson

Peter Van Tuyl Bentley

Manlio Armando Lo Conte

Robert James Hanson

Matthew Alan Townsend

William Christopher Banta

Dynin Hong Khem

Kevin Michael Gordon

Devices, systems and methods are disclosed for improving a playback of video data and generation of a video summary. For example, annotation data may be generated for individual video frames included in the video data to indicate content present in the individual video frames, such as faces, objects, pets, speech or the like. A video summary may be determined by calculating a priority metric for individual video frames based on the annotation data. In response to input indicating a face and a period of time, a video summary can be generated including video segments focused on the face within the period of time. The video summary may be directed to multiple faces and/or objects based on the annotation data.

Video summarization using selected characteristics

A system and method for generating a short video summary from video data. For example, the system may receive input video data including video clips and may select snippets from each video clip to include in the short video summary. To select a snippet, the system may calculate a priority metric for individual frames in a video clip, may generate a priority metric graph for the video clip and may select a portion of the video clip associated with a peak of the priority metric graph. Thus, the snippets may include a short duration of time (e.g., 1-4 seconds) corresponding to the peak of the priority metric graph. The system may reorder the snippets based on characteristics of content represented in the snippet.

Video microsummarization

Devices, systems and methods are disclosed for smoothing rendering data (e.g., panning data and/or magnification data) prior to rendering a video clip. The rendering data may be recorded using a first sampling rate and the system may determine B&#xe9;zier points using a second sampling rate. The B&#xe9;zier points may be aligned with the rendering data and may be used to generate smoothed rendering data. The smoothed rendering data may be used to render a video clip that may be displayed to a user. If the user inputs additional rendering data during playback of the video clip, the system may generate second smoothed rendering data. For example, the system may record additional rendering data for a second half of the video clip and generate second smoothed rendering data, including a first half of the first smoothed rendering data, based on the additional rendering data.

Smoothing video panning

Devices, systems and methods are disclosed for improving a display of panoramic video data by including an angle indicator as a visual representation of a direction of a displayed portion of the panoramic video data relative to a reference location. For example, the angle indicator may illustrate an angle of the displayed portion of the video data relative to a front of the video capture device, using 360 degrees, and the user of the device may specify a desired angle and/or desired portion of the video data to display. In addition, the device may generate video tags including angle information based on the user input. For example, the device may determine the desired angle and/or desired portion of the video data to display and may generate a video tag associating the angle with a timestamp and/or video frame.

Direction indicators for panoramic images

Devices, systems and methods are disclosed for improving a display of panoramic video data by including a first angle indicator, as a visual representation of a direction of a displayed portion of the panoramic video data relative to a reference location, along with a second angle indicator indicating an object of interest. The second angle indicator may display a fixed angle or a recommended angle to improve navigation within the panoramic video data. The fixed angle may be determined by the user or the device and may remain stationary during playback of the panoramic video data, allowing the user to switch between directional views without panning. The recommended angle may be determined based on a location of a tracked object, allowing the user to display the tracked object without panning. The second angle indicator may be represented by an icon illustrating the object of interest.

Growing community of inventors

Mercer Island, WA, United States of America

Mark Eugene Pearson