Intel Corporation

Intel Corproation

Avigdor Dori Eldar

Omer Levy

Hormuzd M Khosravi

Fabian Trumper

Tsippy Mendelson

Jonathan Abramson

Tal Shustak

Nimrod Diamant

Carey W Smith

Uri Blumenthal

Moshe Valenci

Amos Goldman

Zvi Vlodavsky

Noam Teomim

Dror Cohen

Ariel Rosenblatt

Alex Nayshtut

Karanvir S Grewal

Omer Ben-Shalom

Howard C Herbert

Purushottam Goel

Izoslav Tchigevsky

Kfir Viente

Venkat R Gokulrangan

Adi Shaliv

Ovadya Menadeva

Gilad Baruch

Alexandra Manevitch

David Hines

Raizy Kellerman

Dominic Fulginiti

Orly Weisel

Michael Navon

Edward V Jimison, Jr

Yael Yanai

Tchigevsky Izoslav

Itamar Sharoni

Eran Rousseau

Carry Smith

Ahuva Kroiser

Sagi Levi

Trumper Fabian

Liad Aben Zour

Tal Roth

The present disclosure provides at least an apparatus for a depth enhanced image editing. In an example, the apparatus includes memory; instructions; and processor circuitry to execute the instructions to: obtain image information, the image information including edited image data, edited calibration data, and unedited original depth data; and align the original depth data to the edited image data based on the edited calibration data.

Editor for images with depth data

An example system disclosed herein includes a camera to: capture a first image set of a first view of an object when the camera is in a first position, the first image set including first infrared data and first RGB data; capture a second image set of a second view of the object when the camera is in a second position, the second image set including second infrared data and second RGB data; and capture a third image set of a third view of the object when the camera is in a third position, the third image set including third infrared data and third RGB data. The example system also includes at least one processor to: identify a plurality of features among the first view, the second view, and the third view; align the second view relative to the first view by using one or more of the features; align the third view relative to the first view by using one or more of the features; determine first three-dimensional data from the first infrared data; determine second three-dimensional data from the second infrared data; determine third three-dimensional data from the third infrared data; average the first three-dimensional data, the second three-dimensional data, and the third three-dimensional data; create a calibration model based on the average; determine a refined view based on the calibration model; and compute a three dimensional to two dimensional projection based on the refined view.

Camera calibration using depth data

The present disclosure provides at least an apparatus for a depth enhanced image editing. In an example, the apparatus includes a processor and a storage, comprising instructions that when executed with the processor cause the apparatus to store a received depth enhanced image. In an example, the depth enhanced image comprises image data, depth data, and calibration data. The apparatus may apply an edit to the image data and the calibration data without editing the depth data in response to a request for an image edit. The apparatus may further return an edited depth enhanced image.

A method to provide transfer of data without the use of a network from an application program to an embedded device. A routing service establishes a communication channel without the use of a local area network. The routing service then manages the control of this communication channel for the transfer of data and closes the channel in an appropriate period.

Routing of messages

Methods, apparatus, systems and articles of manufacture to prepare a set of equations for a successive over relaxation processor are disclosed. An example apparatus includes an identifier to identify a set of equations that corresponds to pixels of an input image. Example apparatus also include a partitioner to divide the set of equations into partitions that contain mutually independent subsets of the equations and a collector to collect the subsets of the set of equations into groups, based on the partitions, to be solved in parallel by the successive over relaxation processor.

Methods and apparatus to enable parallel processing when solving linear equations in a computer vision processing system

An electronic device for quantifying parallax motion is described. The electronic device includes a detecting unit to detect at least three fiducial markers in an image with parallax, wherein the at least three fiducial markers are part of a straight line in an input image; an estimating unit to estimate a best fit line to a curved line formed by the at least three fiducial markers, wherein the curved line is a result of parallax applied to the input image; a calculating unit to calculate an error between the best fit line and the curved line formed by the at least three fiducial markers; and a comparing unit to compare the error to a threshold limit.

Quantification of parallax motion

An example apparatus for classifying target objects using three-dimensional geometric filtering includes a patch receiver to receive patches with objects to be classified. The apparatus also includes a geometric filter to filter out patches including objects with sizes outside a target range using three dimensional geometry to generate filtered patches. The apparatus further includes a background remover to remove background pixels from the filtered patches to generate preprocessed patches. The apparatus includes a classification score calculator to calculate a classification score for each of the preprocessed patches.

Target object classification using three-dimensional geometric filtering

Techniques described herein are related to a system, medium, and method of depth data filling of shadows for image processing comprising obtaining a location of at least one gap of missing depth data on pixel image data of at least one image, calculating a shadow band length corresponding to a size and position of the gap on the image, and calculated by using, at least in part, background and foreground depth values, and providing depth values of multiple pixel locations extending along the shadow band length.

Method and system of depth data filling of shadows for image processing

Described herein are technologies related to technologies to facilitate real-time computer vision applications, especially those with autonomous or semi-autonomous locomotive robots (e.g., drones or self-driving cars). More particularly, the technologies described herein facilitate, for example, real-time motion estimation using dense optical flow. The technologies accelerate dense optical flow (DOF) processing of images by using the parallel processing techniques of a single-instruction, multiple data (SIMD) computing system.

Dense optical flow acceleration

A digital image processing technique, such as an image warping operation, is stored in a pre-computed lookup table (LUT) prior to image processing. The LUT represents a pixel-to-pixel mapping of pixel coordinates in a source image to pixel coordinates in a destination image. For vectors containing only inlier pixels, a fast remap table is generated based on the original LUT. Each SIMD vector listed in the fast remap is indexed to the coordinates of one of the source pixels that maps to one of the destination pixels in the vector. Other SIMD vectors that contain at least one outlier pixel are listed in an outlier index. For each vector indexed in the fast remap, linear vector I/O operations are used to load the corresponding source pixels instead of using scatter/gather vector I/O load operations via the LUT. The remaining outlier pixels are processed using scatter/gather I/O operations via the LUT.

Accelerated lens distortion correction with near-continuous warping optimization

Techniques for a system, article, and method of background-foreground segmentation for image processing may include obtaining pixel data including both non-depth data and depth data for at least one image, where the non-depth data includes color data or luminance data or both and associated with the pixels; determining whether a portion of the image is part of a background or foreground of the image based on the depth data and without using the non-depth data; and determining whether a border area between the background and foreground formed by using the depth data are part of the background or foreground depending on the non-depth data without using the depth data.

Method and system of background-foreground segmentation for image processing

Systems and methods may provide for obtaining data associated with an image and using a plurality of threads in a graphics processor to conduct a single instruction multiple data (SIMD) scan of the data. Additionally, systems and methods may provide for generating a plurality of connection tables corresponding to the plurality of threads based on the SIMD scan. In one example, a plurality of threads in the graphics processor are used to conduct a single phase merge of the plurality of connection tables onto a global connected components labeling (CCL) table for the image.

Connected component labeling in graphics processors

Growing community of inventors

Modiin, Israel

Avigdor Dori Eldar