Samsung Electronics Co., Ltd.

Doron Sabo

Assaf Tzabari

Roee Sfaradi

Omry Sendik

Raz Zvi Nossek

Ilya Osadchiy

Michael Dinerstein

Tomer Peleg

Pablo Szekely

Aviad Cohen

Stas Dubinchik

Liran Azaria

Aya Wolf

Yarden Sharabi

Sapir Kontente

Shachar Praisler

A method for processing images acquired by a multi-spectral RGB-NIR (red/green/blue/near infra-red) sensor includes receiving a RGB-NIR digital image from a multi-spectral RGB-NIR sensor, interpolating an NIR contribution to each R, G and B pixel value, wherein an NIR image is obtained, subtracting the NIR contribution from each R, G and B pixel value in the RGB-NIR digital image wherein a decontaminated RGB-NIR image is obtained, constructing a red, green and blue (RGB) Bayer image from the decontaminated RGB-NIR image, and processing the Bayer image wherein a full color image is obtained. The RGB-NIR digital image includes red (R) pixels, green (G) pixels, blue (B) pixels, and NIR pixels, and every other row in the RGB-NIR digital image includes NIR pixels that alternate with green pixels, and every other row in the RGB-NIR digital image includes green pixels that alternate with red and blue pixels.

RGB-NIR processing and calibration

Aspects of the method, apparatus, non-transitory computer readable medium, and system include estimating extrinsic camera parameters of a plurality of cameras based on detection of corners in a camera calibration arrangement by projecting an image of the detected corners onto an image plane of at least one of the plurality of cameras. The aspects further include incrementally tuning a location estimate for the detected corners based on pixels of the projected image, and adjusting the extrinsic camera parameters of the at least one of the plurality of cameras based on the tuned location estimate. The aspects further include generating a virtual image based on the pixels of the projected image mapped to a virtual image plane.

Surround view system

Learning-based color correction (e.g., auto while balance (AWB)) procedures may be trained based on datasets from different sensors using a pre-processing procedure. Each input pixel may be converted into a sensor-independent representation through multiplication by a sensor-specific color conversion function (e.g., a 3&#xd7;3 matrix). The sensor-specific color conversion function may be obtained based on a sensor type. For example, the sensor-specific color conversion function, such as a 3&#xd7;3 matrix, may be obtained by a corresponding sensor calibration procedure performed using laboratory images of a color checker chart subject to standard illuminants. Parameters of the sensor-specific color conversion function may be optimized in a chromaticity space. For instance, a sensor-specific 3&#xd7;3 matrix for color conversion may be optimized using a distance in the chromaticity space between calibration data (e.g., calibration configurations) and sensor-independent targets (e.g., a target sensor-independent representation for each calibration configuration).

Data pre-processing for cross sensor automatic white balance

Disclosed is an image processing method employing a post processing technique that may eliminate flicker artifacts from captured video in real time. An example method involves receiving from an image sensor a sequence of input frames representing a scene and identifying and tracking a light source represented within the input frames. Flickering of the light source may be identified by detecting frame to frame color characteristic variation of a region representing the light source. A sequence of output frames may be generated with the flickering removed by selectively modifying image data of pixels within the region.

Flicker mitigation via image signal processing

Systems and methods for setting the white balance of an image are described. Embodiments of the systems and methods may receive image data comprising a plurality of exposures, generate a plurality of white balance values based on merge information from a high dynamic range (HDR) merge of the exposures, and adjust a white balance of each pixel of the image data based on the white balance values.

Leveraging HDR sensors for handling mixed illumination auto white balance

A system of convolutional neural networks (CNNs) that synthesize middle non-existing frames from pairs of input frames includes a coarse CNN that receives a pair of images acquired at consecutive points of time, a registration module, a refinement CNN, an adder, and a motion-compensated frame interpolation (MC-FI) module. The coarse CNN outputs from the pair of images a previous feature map, a next feature map, a coarse interpolated motion vector field (IMVF) and an occlusion map, the registration module uses the coarse IMVF to warp the previous and next feature maps to be aligned with pixel locations of the IMVF frame, and outputs registered previous and next feature maps, the refinement CNN uses the registered previous and next feature maps to correct the coarse IMVF, and the adder sums the coarse IMVF with the correction and outputs a final IMVF.

Efficient CNN-based solution for video frame interpolation

A method of rectifying stereo images includes providing a plurality of pairs of sets of keypoints extracted from a pair of current stereo images and from a pair of previous stereo images wherein each pair of stereo images includes a left image and a right image respectively obtained from a left camera and a right camera; providing a plurality of pairs of sets of next-choice-match points extracted from the pair of current stereo images and the pair of previous stereo images; finding one or more anchor points in a left previous image; finding a right linking point which is the corresponding keypoint in the right previous image, and a left linking point which is the corresponding keypoint in the left current image; finding a closing point; and calculating a cost from the right linking point, the left linking point, and the closing point.

Growing community of inventors

Petah-Tikva, Israel

Doron Sabo