Seiko Epson Corporation

Qualcomm Incorporated

Hewlett-packard Company

Marvellworld Trade Ltd.

Marvell International Limited

Hewlett-packard Corporation

Vasudev Bhaskaran

William Chen

Nikhil Balram

Changick Kim

Mainak Biswas

Gokce Dane

Viresh Ratnakar

Sujith Srinivasan

Upal Mahbub

Neri Merhav

Rakesh Nattoji Rajaram

Joseph S Shu

Giordano Bruno Beretta

Konstantinos Konstantinides

Balas K Natarajan

Sarma V Kolluru

Wonbok Lee

Vasanth Shreesha

Anoop Kumar Bhattacharjya

Bo Shen

Victor Ivashin

Sanjay Saran Garg

Shilpi Sahu

Ruby B Lee

Albert W Kovalick

Norihisa Hagiwara

Christian J Van Den Branden Lambrecht

Masoud Khansari

Murat Kunt

Embodiments include systems and methods that may be performed by a processor of a computing device. Embodiments may be applied for keypoint detection in an image. In embodiments, the processor of the computing device may apply to an image a first-stage neural network to define and output a plurality of regions, apply to each of the plurality of regions a respective second-stage neural network to output a plurality of keypoints in each of the plurality of regions, and apply to the plurality of keypoints a third-stage neural network to determine a correction for each of the plurality of keypoints to provide corrected keypoints.

Multi-stage neural network process for keypoint detection in an image

A method is presented. The method includes determining a number of landmarks in an image comprising multiple pixels. The method also includes determining a number of channels for the image based on a function of the number of landmarks. The method further includes determining, for each one of the number of channels, a confidence of each pixel of the multiple pixels corresponding to a landmark. The method still further includes identifying the landmark in the image based on the confidence.

Compact encoded heat maps for keypoint detection networks

Embodiments include systems and methods for keypoint detection in an image. In embodiments, a processor of a computing device may apply to an image a first neural network that has been trained to define and output a plurality of regions. The processor may apply to each of the plurality of regions a respective second neural network to that has been trained to output a plurality of keypoints in each of the plurality of regions. The processor may apply to the plurality of keypoints a third neural network that has been trained to determine a correction for each of the plurality of keypoints to provide corrected keypoints suitable for the execution of an image processing function.

A method performed by an electronic device is described. The method includes generating a depth map of a scene external to a vehicle. The method also includes performing first processing in a first direction of a depth map to determine a first non-obstacle estimation of the scene. The method also includes performing second processing in a second direction of the depth map to determine a second non-obstacle estimation of the scene. The method further includes combining the first non-obstacle estimation and the second non-obstacle estimation to determine a non-obstacle map of the scene. The combining includes combining comprises selectively using a first reliability map of the first processing and/or a second reliability map of the second processing The method additionally includes navigating the vehicle using the non-obstacle map.

Systems and methods for non-obstacle area detection

A method performed by an electronic device is described. The method includes performing vertical processing of a depth map to determine a vertical non-obstacle estimation. The method also includes performing horizontal processing of the depth map to determine a horizontal non-obstacle estimation. The method further includes combining the vertical non-obstacle estimation and the horizontal non-obstacle estimation. The method additionally includes generating a non-obstacle map based on the combination of the vertical and horizontal non-obstacle estimations.

In one example, a method includes identifying a pixel in an image frame that is a candidate for causing crosstalk between the image frame and a corresponding image frame in a multiview image system. The method further includes, for a pixel identified as a candidate for causing crosstalk, applying crosstalk correction to the pixel. The method further includes applying a location-based adjustment to the pixel, wherein the location-based adjustment is based at least in part on which of two or more portions of the image frame the pixel is in.

Crosstalk reduction with location-based adjustment in multiview video processing

Method and apparatus for reducing random noise in digital video streams are described. In one innovative aspect, the device includes a noise estimator. The device also includes a motion detector configured to determine a motion value indicative of motion between two frames of the video stream, the motion value based at least in part on the noise value. The device further includes a spatial noise reducer configured to filter the image data based at least in part on a blending factor and the noise value. The device also includes a temporal noise reducer configured to filter the video data based on the motion value and the noise value. The device also includes a blender configured to blend the spatial and temporal filtered values to provide a weighted composite filtered output image.

Method and apparatus of reducing random noise in digital video streams

Techniques described in the disclosure are generally related to enhancing portions of an image relative to other portions of the image. The example techniques may utilize depth information in conjunction with one or more viewer perceivable information to enhance portions of the image relative to other portions. The techniques may then display the enhanced image to provide the viewer with a possibly more realistic image.

Image enhancement

Systems and methods for compressing video data are provided. The method includes segmenting a video frame, selecting a coding mode, and encoding. The segmenting includes segmenting the video frame of the video data into a sequence of coding blocks. The selecting includes selecting the coding mode from a plurality of coding modes. The selecting of the coding mode is based on an allowable bit budget and occurs for each coding block. The encoding includes encoding each coding block based on the coding mode. The allowable bit budget varies according to a bit utilization of prior encoded coding blocks and varies such that the video frame does not exceed a specified compression ratio.

Systems and methods for perceptually lossless video compression

In one example, a method includes identifying a first set of pixels in co-located pairs in a corresponding pair of multiview image frames for which the co-located pairs have a disparity between the pixels that is greater than a selected disparity threshold. The method further includes identifying a second set of pixels in at least one of the image frames that are within a selected distance of an intensity transition greater than a selected intensity transition threshold. The method further includes applying crosstalk correction to pixels that are identified as being in at least one of the first set and the second set.

Crosstalk reduction in multiview video processing

Devices, systems, apparatuses, methods, and other embodiments associated with bit resolution enhancement are described. In one embodiment, an apparatus includes logic configured to produce a high-resolution pixel from a low-resolution pixel. The apparatus includes logic configured to classify the high-resolution pixel as being in a smooth region of an image based on at least one of a gradient value and a variance value associated with the low-resolution pixel. The apparatus includes logic configured to selectively re-classify the high-resolution pixel as not being in the smooth region of the image based on a set of neighboring high-resolution pixels associated with high-resolution pixel. The apparatus includes logic configured to selectively filter the high-resolution pixel based on whether the high-resolution pixel remains classified as being in the smooth region of the image.

Bit resolution enhancement

Devices, systems, methods, and other embodiments associated with configuring devices are described. In one embodiment, a method includes receiving, from a remote device, a search input for an adjustment parameter. The method searches for the adjustment parameter in a television device based, at least in part, on the search input, wherein the adjustment parameter is a setting in the television device that controls how content is displayed. After the adjustment parameter is found, the adjustment parameter is returned to the remote device, which is caused to display the adjustment parameter. An input parameter value for changing the adjustment parameter is received from the remote device. The television device is reconfigured by locally changing the adjustment parameter based at least in part on the input parameter value, wherein a content is displayed on the television device based on at least the changed adjustment parameter.

Device configuration

A video processing system includes a network processing module configured to receive video content. A decoder module is configured to decode the video content received from the content transmitting system, and separately provide each of the decoded video content and data describing transmission features of the video content. A video quality estimation module is configured to estimate a quality factor based on the data describing the transmission features of the video content, wherein the quality factor corresponds to an estimation of a visual quality of the video content. A database control module configured to select, based on the quality factor, one of a plurality of predetermined settings for video post-processing. A video post-processing module is configured to receive the decoded video content separately provided from the decoder module, and process the decoded video content based on the selected one of the predetermined settings.

System and methods for adjusting settings of a video post-processor

To improve contrast ratio of the image on a backlit display plane such as a liquid crystal display ('LCD'), each area of the image that has separately controllable backlight may be given full backlight until an average or composite brightness of the image in that area is less than a threshold value at which light leakage through the image from full-strength backlight begins to be noticeable by a viewer. For image areas with composite brightness less than that threshold, backlight brightness may be reduced in proportion to how much below the threshold the area's composite image brightness is. Backlight brightness may also be adjusted for other image aspects such as (1) the presence of bright pixels in an otherwise relatively dark area, (2) whether the area is adjacent to one or more other areas in which the image information is in motion, and/or (3) time-averaging of image information over several successive frames of such information.

Growing community of inventors

Sunnyvale, CA, United States of America

Vasudev Bhaskaran