Qualcomm Incorporated

Piyush Sharma

Ramin Rezaiifar

Ashwin Deepak Swaminathan

Nitesh Shroff

Murali Chari

Vidya Narayanan

Pawan Kumar Baheti

Serafin Diaz Spindola

Bolan Jiang

Chiachi Sung

Christopher Brunner

Qi Xue

Chao Jia

Murali R Chari

Exemplary methods, apparatuses, and systems for image processing are described. One or more reference images are selected based on image quality scores. At least a portion of each reference image is merged to create an output image. An output image with motion artifacts is compared to a target to correct the motion artifacts of the output image.

Reference image selection for motion ghost filtering

An apparatus and method for a framework exposing an API (application programming interface) to web-based server applications on the internet or in the cloud is presented. The API allows server applications to retrieve sensor data from a mobile device via a low-power sensor core processor on a mobile device. This API eliminates effort and cost associated with developing and promoting a new mobile device client application. The API framework includes APIs that web-based application may use to fetch sensor data from one or more particular sensors on the mobile device.

Sensor API framework for cloud based applications

A mobile platform efficiently processes image data, using distributed processing in which latency sensitive operations are performed on the mobile platform, while latency insensitive, but computationally intensive operations are performed on a remote server. The mobile platform acquires image data, and determines whether there is a trigger event to transmit the image data to the server. The trigger event may be a change in the image data relative to previously acquired image data, e.g., a scene change in an image. When a change is present, the image data may be transmitted to the server for processing. The server processes the image data and returns information related to the image data, such as identification of an object in an image or a reference image or model. The mobile platform may then perform reference based tracking using the identified object or reference image or model.

Adaptable framework for cloud assisted augmented reality

A three-dimensional pose of the head of a subject is determined based on depth data captured in multiple images. The multiple images of the head are captured, e.g., by an RGBD camera. A rotation matrix and translation vector of the pose of the head relative to a reference pose is determined using the depth data. For example, arbitrary feature points on the head may be extracted in each of the multiple images and provided along with corresponding depth data to an Extended Kalman filter with states including a rotation matrix and a translation vector associated with the reference pose for the head and a current orientation and a current position. The three-dimensional pose of the head with respect to the reference pose is then determined based on the rotation matrix and the translation vector.

Head pose estimation using RGBD camera

A mobile platform efficiently processes sensor data, including image data, using distributed processing in which latency sensitive operations are performed on the mobile platform, while latency insensitive, but computationally intensive operations are performed on a remote server. The mobile platform acquires sensor data, such as image data, and determines whether there is a trigger event to transmit the sensor data to the server. The trigger event may be a change in the sensor data relative to previously acquired sensor data, e.g., a scene change in an image. When a change is present, the sensor data may be transmitted to the server for processing. The server processes the sensor data and returns information related to the sensor data, such as identification of an object in an image or a reference image or model. The mobile platform may then perform reference based tracking using the identified object or reference image or model.

Techniques disclosed herein involve determining motion occurring in a scene between the capture of two successively-captured images of the scene using intensity gradients of pixels within the images. These techniques can be used alone or with other motion-detection techniques to identify where motion has occurred in the scene, which can be further used to reduce artifacts that may be generated when images are combined.

Detecting and compensating for motion between a flash and a no-flash image

Techniques are described for generating an all-in focus image with a capability to refocus. One example includes obtaining a first depth map associated with a plurality of captured images of a scene. The plurality of captured images may include images having different focal lengths. The method further includes obtaining a second depth map associated with the plurality of captured images, generating a composite image showing different portions of the scene in focus (based on the plurality of captured images and the first depth map), and generating a refocused image showing a selected portion of the scene in focus (based on the composite image and the second depth map).

Method and apparatus for generating an all-in-focus image

Apparatuses and methods for reading a set of images to merge together into a high dynamic range (HDR) output image are described. Images have a respective HDR weight and a respective ghost-free weight. Images are merged together using the weighted average of the set of input images using the ghost-free weight. A difference image is determined based on a difference between each pixel within a HDR output image and each respective pixel within a reference image used to create the HDR output image.

Generation of ghost-free high dynamic range images

Methods, devices, and computer program products for capturing images with reduced blurriness in low light conditions are contained herein. In one aspect, a method of capturing an image is disclosed. The method includes capturing a plurality of first images with a first exposure length. The method further includes aligning each of the plurality of first images with each other and combining the aligned plurality of first images into a combined first image. The method further includes capturing a second image with a second exposure length, wherein the second exposure length is longer than the first exposure length and using the second image to adjust the brightness of the combined first image.

System and method to capture images with reduced blurriness in low light conditions

A mobile device detects a moveable foreground object in captured images, e.g., a series of video frames without depth information. The object may be one or more of the user's fingers. The object may be detected by warping one of a captured image of a scene that includes the object and a reference image of the scene without the object so they have the same view and comparing the captured image and the reference image after warping. A mask may be used to segment the object from the captured image. Pixels are detected in the extracted image of the object and the pixels are used to detect the point of interest on the foreground object. The object may then be tracked in subsequent images. Augmentations may be rendered and interacted with or temporal gestures may be detected and desired actions performed accordingly.

Growing community of inventors

San Diego, CA, United States of America

Piyush Sharma