Hewlett-Packard Development Company, L.p.

Motorola Mobility LLC

Hewlett-Packard Company

Google Inc.

Daniel Maack Bloom

Donald J Stavely

Dan L Dalton

Jason E Yost

Mark John Bianchi

Yinhu Chen

Gregory V Hofer

David J Staudacher

Wilfred Francis Brake

Susan Yanqing Xu

Scott A Woods

Kurt Eugene Spears

Charles Edward Schinner

Valeriy F Marchevsky

Dalong Li

Clay Jessen

Amy E Battles

Charles H McConica

Casey L Miller

Darryl Greig

Oscar R Herrera E

Richard Turley

Quan Zhu

Weihua Sun

Jing-Nan Zhu

Stephen Bernard Pollard

Andrew Clark Goris

David Kay Campbell

Robert E Sobol

Christopher Andrew Whitman

James S Voss

James W Owens

By-Her W Richards

Jennifer Joy Thayer

Daniel G Franke

Lorne J Lameer

Elena Satraitis

A method, a system, and a computer program product for generating a selective color image. The method includes capturing a color image data within a current scene. The method further includes retrieving image color values from the color image data. The method further includes receiving a selection of at least one location within the color image data. The method further includes generating a color mask, including at least one unmasked area identified within a depth map of the current scene, and applying the color mask to the color image data to generate a color masked image data. The method further includes combining the color masked image data with monochromatic image data of the current scene to create a selective color image that includes the monochromatic image data with the at least one portion, and then the method includes providing the selective color image to at least one output device.

Selectively applying color to an image

A method, a system, and a computer program product for calibrating a depth sensor of a device. The method includes simultaneously capturing within a current scene: a red-green-blue (RGB) image by a RGB sensor of a device; and an infrared (IR) image by an IR sensor of the device. The method further includes concurrently capturing, via an IR sensor of the device, an uncalibrated depth image within the current scene. The method further includes calculating calibration data from the RGB image and the IR image and applying the calibration data to the uncalibrated depth image to generate a corrected depth image. The method further includes combining the RGB image and the corrected depth image to generate a RGB depth image. The method further includes, presenting the RGB depth image on an output device.

Dynamically calibrating a depth sensor

A method, a device, and a computer program product for background image replacement in image data. The method includes receiving, from at least one image sensor of a device, frame data. The device generates a first depth map based on the received frame data. The device generates first foreground image data and first background image data, based on the first frame data and the first depth map. The method further includes determining a least used color in the first foreground image data. The least used color is identified as a first background color. The method also includes generating modified frame data by replacing the first background image data with the first background color and storing the modified frame data to a memory of the device.

Dynamic chroma key for video background replacement

A method, a system, and a computer program product for generating a selective color image. The method includes capturing a color image data within a current scene. The method further includes retrieving image color values from the color image data. The method further includes receiving a selection of at least one location within the color image data. The method further includes generating a color mask and applying the color mask to the color image data to generate a color masked image data. The method further includes combining the color masked image data with monochromatic image data of the current scene to create a selective color image that includes the monochromatic image data with the at least one portion, and then the method includes providing the selective color image to at least one output device.

A method, system, and computer program product for an image capturing device having at least two cameras to obtain a focus point of a current scene. The method includes in response to performing a focus procedure via at least one camera of the image capturing device, determining whether a focus point has been found. The method further includes, in response to determining the focus point has not been found: (1) adjusting a number of focus scan steps of an auxiliary focus procedure utilized by only the at least one auxiliary camera and (2) performing the auxiliary focus procedure using the adjusted number of focus scan steps. The method further includes determining whether the focus point has been found, and in response to determining the focus point has been found, automatically synchronizing, to a main lens of the main camera, a current position of the lens of the at least one auxiliary camera.

Capturing an image using multi-camera automatic focus

A method, system, and computer program product to obtain a focus point of a current scene. The method includes performing a first focus procedure in a first direction via a main lens of a main camera of an image capturing device having at least two cameras. The method further includes concurrently performing a second autofocus procedure in a second direction that is opposite the first direction via at least one auxiliary lens of at least one auxiliary camera. The method further includes identifying a focus point within autofocus data collected during the first and second focus procedure. The method further includes, in response to determining the focus point was identified by the at least one auxiliary camera: terminating the first focus procedure; and automatically synchronizing a position of the main lens to that of the at least one auxiliary lens.

Identifying a focus point in a scene utilizing a plurality of cameras

Various embodiments provide improved image resolution using a High Dynamic Range (HDR) image sensor. A computing device calculates long exposure settings and short exposure settings for image sensors of a computing device. The long exposure settings and the short exposure settings are applied to a first image sensor of the image sensors, and only the short exposure settings are applied to a second image sensor of the image sensors. Some embodiments use an interleaved High Dynamic Range (iHDR) image sensor as the first image sensor, and a Clear or Mono image sensor for the second image sensor. Various embodiments generate a synchronized image that includes a first image generated by the first image sensor and a second image generated by the second image sensor. Upon receiving the synchronized image, some embodiments fuse the first image and the second image to improve the image resolution of the first image capture.

High dynamic range sensor resolution using multiple image sensors

For selective local registration based on registration error, a method determines a first registration error between a template image and a source image. The method further warps the source image to compensate for camera motion in response to the first registration error exceeding a registration error threshold. In addition, the method determines a second registration error between the template image and the warped source image. The method generates a pixel difference mask using the template image. The method further selectively performs local registration for the source image based on the pixel difference mask in response to the second registration error exceeding the registration error threshold.

Selective local registration based on registration error

For deblurring an image, a method records both short-exposed pixels at a higher frame rate for a short-exposure region and normal-exposed pixels at a normal frame rate for full resolution. In addition, the method deblurs a normal-exposed image as a function of the short-exposed pixels and the normal-exposed pixels.

Deblurring an image

The present application provides an image processing circuit, a hand-held electronic device and a method for compensating for motion in an image received by an image sensor. The method includes sub-dividing an array of individual sensor cells from an image sensor adapted for receiving an image into at least a first sub-group and a second sub-group of sensor cells. Multiple timing signals are then generated for use in reading data out of the individual sensor cells of the image sensor. Data values are then read out from the individual sensor cells, wherein the data values from the individual sensor cells of the first sub-group of sensor cells are read out at a first rate using a first timing signal, and the data values from the individual sensor cells of the second sub-group of sensor cells are read out at a second rate using a second timing signal. The second rate is different than the first rate, where the sensor cells in the second sub-group of sensor cells are sampled more frequently than the sensor cells in the first sub-group of sensor cells. Motion of the image sensor is then determined from the data values read out of the individual sensor cells of the second sub-group of sensor cells. The image derived from the data values read out of the individual sensor cells of the first sub-group of sensor cells is then modified using the motion detected for producing a processed image.

Image processing circuit, hand-held electronic device and method for compensating for motion in an image received by an image sensor

A method and apparatus for invoking a High Dynamic Range ('HDR') mode in a camera are disclosed. The method comprises detecting that the camera is operating in a preview mode. The method further comprises determining a dynamic range, Auto Exposure ('AE') metadata, and a motion level associated with a plurality of frames captured in the preview mode. Finally, the method comprises invoking the HDR mode when each of the determined dynamic range, the AE metadata, and the motion level is above a first threshold value, a second threshold value, and a third threshold value, respectively.

System for auto-HDR capture decision making

A camera system may include an image sensor to generate real-time image data of a scene having a subject. A pose evaluator can generate a pose metric signal having a pose value that provides a variable measure of a pose quality for the subject in the scene. A pose feedback indicator can provide user-perceptible feedback demonstrating the value of the pose metric signal, such that the variable measure of the pose quality is provided.

Camera system for determining pose quality and providing feedback to a user

A system and method for focusing an image capture device are disclosed. One embodiment is a method comprising moving an autofocus window in response to detected movement of the image capture device.

Implementing autofocus in an image capture device while compensating for movement

Systems and methods of smile detection are disclosed. An exemplary method comprises generating a search map () for a subset of an image (). The method also comprises identifying a plurality of candidates (-) representing mouth corners. The method also comprises generating parabolas () between each pair of candidates representing mouth corners. The method also comprises analyzing contour of at least one of the parabolas to determine whether the mouth curves substantially upward to form a smile or curves substantially downward to form a frown.

Smile detection systems and methods

A device to apply detection schemes to texture information of a face detected within an image to generate mouth corner candidates and identify best matching mouth corners by applying a geometric model to the moth corner candidates.

Growing community of inventors

Loveland, CO, United States of America

Daniel Maack Bloom