Amazon Technologies, Inc.

Vivek A Shah

Jonathan Edward Suchland

Kadirvelu Rathnavelu

Samir Raj Hegde

Jason Garrett Volpe

John James Terrill

Nicholas Ryan Gilmour

Christopher Fredrick Vitas

Charles Cummins

Mihir Kumar Choudhary

Ario Jafarzadeh

John Matthew Nance

Oleg Rybakov

Robert James Hanson

James Connelly Petts

Olga I Kuznetsova

Roy N Harkness

Alexander S Borst

Michael R Brauwerman

Dynin Hong Khem

Theodore H Romer

Che-Chun Su

Nikhil Raghu Varma

Scott Oja Ward

Christopher Frederick Vitas

Systems, methods, and computer-readable media are disclosed for selection of a preferred image from multiple captured images. An image corresponding to a photograph time t=0 may be retrieved from a circular buffer and stored as a preferred image. Alterative images captures before and after the t=0 image may be retrieves and stored in an alternative image location. The t=0 image and preferred images may be presented to a user in a user interface. The user may select a preferred image for the photograph from among the t=0 image and the alternative images.

Selection of a preferred image from multiple captured images

Systems, methods, and computer-readable media are disclosed for selection of a preferred image from multiple captured images. An image corresponding to a photograph time t=0 may be retrieved from a circular buffer and stored as a preferred image. Alternative images captures before and after the t=0 image may be retrieves and stored in an alternative image location. The t=0 image and preferred images may be presented to a user in a user interface. The user may select a preferred image for the photograph from among the t=0 image and the alternative images.

The display of images, such as panoramic images, in a limited display space can be aided through the use of motion-based control, whereby a user can rotate and/or translate a computing device in order to view different portions of the image, including translating or zooming within the image. Sensors can be used to determine the motion for adjusting the display. The same or other sensors can also assist a user in capturing such an image. For example, a compass can determine the relative orientation of the device and a gyroscope can determine rotation of the device, to determine an appropriate path of motion for the capture and any deviation from that path. The user can be provided with information enabling the user to follow the path with an appropriate device orientation.

Motion-based image views

A plurality of depth planes corresponding to a scene within a field of view of a camera of a computing device can be computed based on stereographic techniques, infrared transceivers, ultrasonic transceivers, among other approaches. The depth planes can be utilized to independently meter subject matter of interest (e.g., person, object, region, etc.) corresponding to each depth plane to obtain image statistics for each depth plane. The image statistics can be analyzed to determine optimal settings (e.g., focus, exposure, white balance, etc.) for each depth plane, and a camera can be configured to acquire image data according to the optimal settings for one or more of the depth planes. Further, the image statistics can be leveraged for processing portions of the image data that are not optimized during capture. Thus, a final image can reflect optimizations for multiple subject matter of interest located at various distances from a computing device.

Image optimization techniques using depth planes

A plurality of instances of image data can be analyzed, and favored aspects of each instance identified and utilized in generating an enhanced output image. For example, a plurality of instances of image data can be analyzed to identify metric values associated with each pixel location, such as contrast, saturation, and exposedness. A weight map corresponding to each metric is generated for each instance of image data, each weight map indicating a value for the metric at each pixel location of the instance of image data. The weight maps associated with each instance of image data are merged, and a Gaussian pyramid of the merged weight map for each instance of image data is determined along with a Laplacian pyramid for each instance of image data. The Gaussian pyramids and Laplacian pyramids are merged into a Laplacian pyramid, which is then collapsed to form an enhanced output image.

Enhanced image generation based on multiple images

The ability of a user to acquire satisfactory images in varying imaging conditions can be improved by enabling the user to select one or more scene settings that are appropriate for current conditions. In some embodiments, a camera instructed to capture an image can instead capture multiple images, each with different camera settings corresponding to a respective scene setting. The user can then view at least some of these images, and select one or more images that appeal to the user. In some embodiments, this selection process can be used to determine the appropriate settings for the current conditions, and then enable the user to capture images using those settings. The user can also customize, change the selection of, or obtain additional scene settings.

Multi-setting preview for image capture

The display of images, such as lenticular images, in a limited display space can be aided through the use of motion-based control, whereby a user can rotate and/or translate a computing device in order to cause different views of a lenticular image to be displayed. Sensors can be used to determine the motion in order to select the appropriate view to display. Approaches can further assist the user in creating lenticular images. The user can specify various configurations in which to display different views in a lenticular. If the user is capturing the images, one or more previously-acquired images can be used as a guide to help the user to align the images. Various processing can be performed to cause the individual views of the lenticular to match as closely as possible in factors such as alignment, brightness, and color range, among other such options.

Lenticular image capture

Disclosed are various embodiments for generating automobile parts bundles associated with maintenance events. A maintenance schedule is retrieved and various maintenance events are identified. Various maintenance tasks associated with maintenance events are also identified. Parts associated with these maintenance tasks are placed into parts bundles associated with the maintenance event and a unique identifier within a parts catalog.

Generating parts bundles

Growing community of inventors

Redmond, WA, United States of America

Vivek A Shah