Seiko Epson Corporation

Foveon, Inc.

Intel Corporation

Rastislav Lukac

Ken Doyle

Sanghoon Bae

Shri Ramaswami

Bojan Ljubuncic

Christopher V Olekas

Jarno Nikkanen

Gazi Naser Ali

Jie Wang

Alireza Yasan

Ravi Basavaraj

Krishna Kumar Madaparambil

Susan Yang

Chihiro Tajima

Techniques are provided for infrared (IR) crosstalk correction for hybrid Red-Green-Blue-IR (RGB-IR) sensors. A methodology implementing the techniques according to an embodiment includes estimating illumination characteristics applied to a subject. The estimation is based on the subject image provided by a hybrid RGB-IR sensor, which comprises a plurality of pixels, each of the pixels associated with an R, G, B, or IR channel. The method further includes selecting a set of correction model parameters from a calibration database, the selection based on the estimated illumination characteristics, and generating a correction model based on the selected set of correction model parameters. The correction model provides correction weights for the RGB channels. The method further includes generating RGB correction values as a product of the correction weights and the IR channel and adjusting the RGB channels by the correction values to reduce IR crosstalk between the IR channel and the RGB channels.

Infrared crosstalk correction for hybrid RGB-IR sensors

An apparatus comprising a memory to store a first image captured by a first camera and a second image captured by a second camera; and a processor comprising circuitry, the processor to identify viewpoint information defining a view for a stitched image, the stitched image to be generated from a combination of a plurality of images comprising the first image and the second image; and based on the viewpoint information and a projection type, determine transformation parameters for at least one reference region associated with overlapping regions of the first image and the second image in order to: localize overlapping regions of the first image and the second image to determine stitching parameters; combine the first image and the second image using the stitching parameters; and assign data of the combined first image and the second image to the stitched image.

Surround camera system with seamless stitching for arbitrary viewpoint selection

A method, system, and article are directed to haze reduction for image processing.

Method and system of haze reduction for image processing

The present disclosure is directed to systems and methods of detecting and minimizing the effect of light flickering in a stitched HDR image formed using a plurality of images obtained using image acquisition sensor circuitry. Light flicker mitigation (LFM) circuitry receives a signal containing data representative of a plurality of images. Multi-feature extraction circuits in the LFM circuitry extract data representative of one or more features from some or all of the pixels included in the plurality of images. Light flicker detection and analysis circuits in the LFM circuitry detect flickering pixels in the plurality of images. Exposure index conversion circuits in the LFM circuitry determine one or more output corrections to apply to the plurality of images as the images are stitched to form a single HDR image in which flickering pixels are minimized, mitigated, or eliminated.

Light flicker mitigation in machine vision systems

A method, system, and article is directed to generating multi-exposure camera statistics for image processing by rearranging and sampling image data of multiple exposure images.

Method and system of generating multi-exposure camera statistics for image processing

A method for adjusting predetermined ISO-dependent image processing parameters for images captured by a digital camera includes measuring the exposure deviation in exposure units from an optimal exposure as determined by the camera during an image capture process, deriving an estimated camera sensitivity from the exposure deviation, and adjusting the ISO-dependent image processing parameters for images captured by the camera as a function of the derived estimated camera sensitivity.

Method of adjusting digital camera image processing parameters

Methods, apparatuses and systems may provide for applying an image to a filter, wherein the filter includes data-adaptive weights. Additionally, an output scaling factor may be determined based on one or more statistical operators applied to the data-adaptive weights and the output scaling factor may be applied to an output of the filter.

Adaptive filtering with weight analysis

Methods, apparatuses and systems may provide for creating a reference signal for a restoration process using a plurality of pixels corresponding to various color channels within a spatial neighborhood of a target pixel location. Additionally, first weights may be set in pixel locations within the spatial neighborhood to control contributions of pixel values and values of the reference signal in calculating one or more intermediate restoration factors. Moreover, second weights may be set in pixel locations within the spatial neighborhood to control contributions of the intermediate restoration factors in calculating one or more final restoration factors. In one example, at least one of the one or more final restoration factors and the reference signal are combined in the target pixel location to restore one or more values in the target pixel location.

Restoring color and infrared images from mosaic data

A pixel sensor array includes a plurality of pixel sensors having a first gain and a plurality of pixel sensors having a second gain less than the first gain.

Imaging array having photodiodes with different light sensitivities and associated image restoration methods

A method for performing highlight restoration on a digital image includes comparing the pixels in the image with a saturation level value to identify saturated pixels. A saturation map of saturated pixels is generated. Each selected saturated pixel is identified as a restorable pixel only if at least one color channel of the pixel is unsaturated. For each restorable pixel, a group of the closest unsaturated pixels above, below, to the left, and to the right of the select saturated pixel is identified. A replacement pixel value is generated for each saturated color channel of the restorable pixel, using a combination of the pixel values of the unsaturated color channels of the restorable pixel and the pixel values of the corresponding color channels of the nearby unsaturated pixels.

Method for processing highlights and saturated regions in a digital image

A method for sharpening an original digital image includes generating a smoothed image from the original image. A residual image is generated from the smoothed image and the original image. A sharpened smoothed image is generated. The residual image and the sharpened smoothed image are combined to produce a sharpened version of the original image.

Growing community of inventors

San Jose, CA, United States of America

Rastislav Lukac