Qualcomm Incorporated

Qualcomm Technologies, Inc.

Pia Zobel

Roee Hardoon

Sungwon Lee

Tauseef Kazi

Assaf Weissman

Bing Han

Nitin Bandwar

Systems and techniques are provided for conserving resources when performing motion estimation. An example process can include determining, based on an input image and a reference image, motion vectors identifying motion between the input image and the reference image; determining whether the motion indicated by the motion vectors is below a first threshold; based on a determination that the motion indicated by the motion vectors is below the first threshold, refraining from determining a local motion between the input image and the reference image; determining a transform matrix based on the motion vectors and without using a local motion between the input image and the reference image; and adjusting the input image based on the transform matrix.

Scale image resolution for motion estimation

Various systems and methods are provided for capturing an image of a group of individuals in a scene. Facial detection may be performed to identify one or more individuals of the group. One or more features of each identified individual are monitored to determine an image quality score for the individual, indicative of how the individual will appear in a captured image of the group. A determination is made as to whether the image quality score for the individual satisfies one or more image quality threshold values. If the image quality score for the individual satisfies the one or more threshold values, a sub-image may be captured of the individuals. Sub-images for each individual may be combined to form a single composite image of the group.

Method and system for smart group portrait

Methods and apparatuses are disclosed for processing a plurality of captured image frames. An example method may include receiving a first image frame and a second image frame from a camera sensor. The example method may also include determining a first portion of the second image frame with a temporal difference from a corresponding first portion of the first image frame, wherein a second portion of the second image frame is without a temporal difference from a corresponding second portion of the first image frame. The example method may also include processing the second image frame, including processing the first portion of the second image frame, and preventing processing the second portion of the second image frame.

Processing multiple image frames

A method, apparatus, and manufacture for generating an HDR image is provided. An original image is received from an HDR interlaced sensor that includes at least two fields captured with different exposures. The fields are separated from each other to provide separate images, and each of the separate images is upscaled. Next, blending is performed on each of the upscaled separate images to generate a high-dynamic range image, and ghost identification is performed on the high-dynamic range image. Subsequently, detail identification is performed on the high-dynamic range image. The detail identification includes identifying areas in the non-ghost areas of the high-dynamic range image that have details, and modifying the high-dynamic image by replacing each of the areas identified to have details with the corresponding area from the original image.

Growing community of inventors

Hinanit, Israel

Pia Zobel