Abstract: Systems and methods for image processing, and specifically for color reconstruction of an output signal from a multispectral imaging sensor (MIS), are described. Embodiments of the present disclosure receive image sensor data from an image sensor of a camera device; apply a non-linear color space mapping to the image sensor data using a neural network to obtain image data, wherein the non-linear color space mapping comprises a non-negative homogeneous function; and store the image data in a memory of the camera device.

Abstract: A method for sample adaptive offset (SAO) filtering and SAO parameter signaling in a video encoder is provided that includes determining SAO parameters for largest coding units (LCUs) of a reconstructed picture, wherein the SAO parameters include an indicator of an SAO filter type and a plurality of SAO offsets, applying SAO filtering to the reconstructed picture according to the SAO parameters, and entropy encoding LCU specific SAO information for each LCU of the reconstructed picture in an encoded video bit stream, wherein the entropy encoded LCU specific SAO information for the LCUs is interleaved with entropy encoded data for the LCUs in the encoded video bit stream. Determining SAO parameters may include determining the LCU specific SAO information to be entropy encoded for each LCU according to an SAO prediction protocol.

Abstract: An image acquisition apparatus includes an image sensor including a microlens and a plurality of pixels arranged adjacent to each other and sharing the microlens; and a processor configured to process an input image acquired by the image sensor, wherein the processor may be further configured to: generate a plurality of parallax images by extracting and combining sub-images having a same parallax from the input image; generate RGB demosaic images by interpolating a color value of an empty pixel for each of the plurality of parallax images by using color values of surrounding pixels; generate a plurality of upsampled images by upsampling each of the RGB demosaic images to an input image size; and generate an output image by weighted-summing one upsampled image selected from the upsampled images and the other upsampled images based on a similarity therebetween.

Abstract: An image obtaining apparatus includes an image sensor including a micro lens and a plurality of neighboring pixels sharing the micro lens and a processor configured to generate, based on an input image received from the image sensor, a plurality of parallax images having a same parallax, group, from among the plurality of parallax images, first parallax images having similar image characteristics, perform at least one image processing operation on the first parallax images, and generate an output image by combining the first parallax images on which the at least one image processing operation is performed.

Abstract: An integrated high-speed image sensor includes a pixel array; a processor configured to determine a region of interest (ROI) and a region of non-interest (RONI) of the pixel array; an analog signal processing circuit configured to read out ROI image data at a first frame rate and read out RONI image data at a second frame rate; and a memory storing the ROI image data and the RONI image data.

Abstract: An image acquisition apparatus may include a multispectral image sensor configured to acquire an image of at least one object in an environment in which at least one illumination source exists, through eight or more channels with minimum overlap between the channels, and a processor configured to estimate illumination spectral data of the acquired image by using channel signals corresponding to the eight or more channels, and perform lens shading correction on the acquired image, based on the estimated illumination spectral data.

Abstract: A method and apparatus for image coding using hierarchical sample adaptive band offset. The method includes decoding a signal of a portion of an image, determining a band offset type and offset of a portion of the image, utilizing the band offset type and offset to determine a sub-band, and reconstructing a pixel value according to the determined offset value.

Abstract: A method for sample adaptive offset (SAO) filtering and SAO parameter signaling in a video encoder is provided that includes determining SAO parameters for largest coding units (LCUs) of a reconstructed picture, wherein the SAO parameters include an indicator of an SAO filter type and a plurality of SAO offsets, applying SAO filtering to the reconstructed picture according to the SAO parameters, and entropy encoding LCU specific SAO information for each LCU of the reconstructed picture in an encoded video bit stream, wherein the entropy encoded LCU specific SAO information for the LCUs is interleaved with entropy encoded data for the LCUs in the encoded video bit stream. Determining SAO parameters may include determining the LCU specific SAO information to be entropy encoded for each LCU according to an SAO prediction protocol.

Abstract: A method and apparatus for sample adaptive offset without sign coding. The method includes selecting an edge offset type for at least a portion of an image, classifying at least one pixel of at least the portion of the image into edge shape category, calculating an offset of the pixel, determining the offset is larger or smaller than a predetermined threshold, changing a sign of the offset based on the threshold determination; and performing entropy coding accounting for the sign of the offset and the value of the offset.

Abstract: An image acquisition apparatus includes: a sensor unit including a plurality of first image sensors that are based on a wavelength band of 380 nm to 780 nm; and at least one processor. The at least one processor is configured to: acquire common illumination information from an image output from at least one of the plurality of first image sensors, and color-convert an image output from each of the plurality of first image sensors based on the common illumination information.

Abstract: Provided are a color interpolation method and an image acquisition device for a multispectral filter array. The color interpolation method includes acquiring a raw multispectral image on the basis of a multispectral filter array, generating a guide image for color interpolation of the raw multispectral image, generating a difference image between the raw multispectral image and the guide image, generating a demosaiced difference image by performing color interpolation based on the difference image, and generating a demosaiced multispectral image based on the demosaiced difference image and the guide image.

Abstract: A method of performing color calibration of a multispectral image sensor (MIS) includes obtaining test measurement data of at least one color chart that is measured by a test MIS under at least one lighting environment, obtaining reference measurement data of the at least one color chart that is measured by a reference MIS under the at least one lighting environment, the reference MIS being calibrated in advance, and generating, based on the test measurement data and the reference measurement data, at least one transformation model configured to transform measurements between the test MIS and the reference MIS.

Abstract: An integrated gaze tracker includes a pixel array configured to capture an image to provide an output signal comprising the image; a memory configured to store an image data unit to be read out in units of lines based on the output signal of the pixel array; and a processor configured to generate a gaze vector based on partial image data comprising the image data unit, among entire image data included in the output signal.

Abstract: Techniques for signaling of sample adaptive offset (SAO) information that may reduce the coding rate for signaling such information in the compressed bit stream are provided. More specifically, techniques are provided that allow SAO information common to two or more of the color components to be signaled using one or more syntax elements (flags or indicators) representative of the common information. These techniques reduce the need to signal SAO information separately for each color component.

Abstract: A method and apparatus for image coding using hierarchical sample adaptive band offset. The method includes decoding a signal of a portion of an image, determining a band offset type and offset of a portion of the image, utilizing the band offset type and offset to determine a sub-band, and reconstructing a pixel value according to the determined offset value.

Abstract: A method of generating a training dataset of a neural network learning model of an electronic device includes: receiving an open images dataset; generating a target image from the open images dataset; generating an input image from the open images dataset; and generating a training dataset of a neural network learning model for compensating for an image captured by an image sensor that includes a meta-prism and a pixel array, the training dataset including the target image and the input image.

Abstract: A method and apparatus for sample adaptive offset without sign coding. The method includes selecting an edge offset type for at least a portion of an image, classifying at least one pixel of at least the portion of the image into edge shape category, calculating an offset of the pixel, determining the offset is larger or smaller than a predetermined threshold, changing a sign of the offset based on the threshold determination; and performing entropy coding accounting for the sign of the offset and the value of the offset.

Abstract: A sensor tube according to the present disclosure includes a body including a body extension having opposite ends connected to measurement air connection pipes and an opening, the measurement air connecting pipes being connected to a humidity sensor to deliver moisture to the humidity sensor using measurement air or allow the measurement air released from the humidity sensor to flow therethrough, and the opening being formed in the body extension to cause an interior space of the body extension and the outside to be in communication with each other such that the moisture is introduced into the interior space of the body extension from the outside through the opening, and an opening/closing part that selectively opens or closes the opening by being operated by a difference in pressure between the interior space of the body extension and the outside.

Abstract: Provided is an apparatus for obtaining an image includes an image sensor and a signal processing unit that includes a demosaicing unit configured to reconstruct a green signal to have a full pixel resolution by using the input image, a sharpening filter unit configured to generate a first image by sharpening the reconstructed green signal for each preset direction, a direction image generation unit which generates a second image by removing a base band and extracting only a detail band, a gray detection unit configured to detect a gray region of the white balance-processed input image, an edge detection unit configured to detect an edge direction of the white balance-processed input image, and a selection unit configured to generate a third image by blending the first image and the second image, based on the detected gray region and the detected edge direction.

Abstract: A sensor tube according to the present invention comprises: a tubular body for connecting two connection pipes to each other, wherein the two connection pipes are connected to a humidity sensor, so that the connection pipes transfer steam to the humidity sensor by using circulating air or air discharged from the humidity sensor flow in the connection pipes; and a cover surrounding at least a part of the outer surface of the body to prevent foreign substances having a predetermined size or larger from passing, wherein the body is formed as a porous sintered body which allows stream to be introduced from the outside of the body into the body and be transferred by the circulating air.