An image processing method is provided The image processing includes images obtained using a Red-Clear-Clear-Blue (RCCB) color filter array. An image processing method for processing an RCCB image obtained by an image capturing device comprising an array of photosensors with a mosaic of RCCB filters comprises interpolating the RCCB image to obtain dense C-channel data from a sparse C-channel, and chromatic filtering, based on the RCCB image data and the dense C-channel, to obtain an RGB image by obtaining the dense R-channel and B-channel, and filtering the R-channel and B-channel using the guide image. The computational load on the image processing equipment and the processing time are reduced, while enhancing the obtained image quality, including in low light conditions.

A computer implemented method (82) for colour video processing, the method comprising: receiving a CFA image from a CFA imaging device, wherein the CFA image comprises CFA image pixels defining a plurality of image regions, each image region having at least one pixel of a first colour and at least one pixel of a second colour, at least one image region representing a portion of an object; receiving a full colour image from a colour imaging device, wherein the full colour image represents the portion of the object; storing the full colour image in a memory; isolating pixels of the first colour of the CFA image to generate a first colour channel comprising pixels of the first colour channel; isolating pixels of the first colour of the full colour image to generate a second colour channel comprising pixels of the second colour channel; processing the pixels of the first colour channel using a first computer vision algorithm to generate first image metadata; processing the pixels of the second colour channel using the first computer vision algorithm to generate second image metadata; and generating processed data using the first image metadata and/or the second image metadata, the processed data comprising a plurality of data points representing the object.

Disclosed is an electronic device which includes a first image sensor that photographs in a first field of view to generate a first signal, and an image signal processor that generates first image data based on the first signal, the first image data being of a non-Bayer pattern. When a zoom factor is less than a first value, the image signal processor crops the first image data to generate second image data, executes remosaic on the second image data to generate third image data of a Bayer pattern, and executes down-scaling on the third image data to generate fourth image data.

An image processing method, and electronic device are provided. The image processing method includes: obtaining a raw RGBW image by an RGBW sensor; processing the raw RGBW image by a pre-processor to obtain a raw RGB image; processing the raw RGB image by an image signal processor to obtain a target image. By adopting the image processing method of the present disclosure, conventional image processing modules are compatible with RGBW sensors without modification, and thus do not need to be replaced in practical applications, which saves hardware costs and facilitates product upgrades.

The present disclosure relates to pre-processing of video images. In particular, the video images are pre-processed in an object-based manner, i.e., by applying different pre-processing to different objects detected in the image. Moreover, the pre-processing is applied to a group of images. As such, object detection is performed in a plurality of images and the pre-processing for the plurality of images may be adapted to the decoded images and is applied to the decoded images.

A method includes obtaining a Bayer input image. The method also includes generating, using at least one processing device of an electronic device, multiple YUV image frames based on the Bayer input image using non-linear scaling, where the YUV image frames are associated with different exposure settings. The method further includes generating, using the at least one processing device of the electronic device, a fused image based on the YUV image frames. In addition, the method includes applying, using the at least one processing device of the electronic device, global tone-mapping to the fused image in order to generate a tone-mapped fused image, where the global tone-mapping is based on a first cubic spline curve.

An image processing device includes: an image sensor configured to generate first image data by using a color filter array; and processing circuitry configured to select a processing mode from a plurality of processing modes for the first image data, the selecting being based on information about the first image data; generate second image data by reconstructing the first image data using a neural network processor based on the processing mode; and generate third image data by post-processing the second image data apart from the neural network processor based on the processing mode.

An imaging device includes an image sensing device and an image signal processor. The imaging sensing device includes a pixel array of sensing pixels comprising a first pixel for sensing incident light and having a first dynamic range and a second pixel for sensing incident light and having a second dynamic range, the pixel array of sensing pixels structured to have a ratio of a number of the first pixels to all sensing pixels to be higher than a ratio of a number of second pixels to all sensing pixels. The image signal processor is configured to receive and process pixel data from the image sensing device to generate a high dynamic range (HDR) image corresponding to a larger dynamic range than the first dynamic range or the second dynamic range, based on pixel data of the first pixels and pixel data of the second pixels in the pixel array.

Apparatuses, systems, and techniques to process image data. In at least one embodiment, a neural network is trained to perform demosacing of two-dimensional image data obtained from an image sensor.

A method with image processing includes: receiving an input image including Bayer images captured by a plurality of lenses included in a lens assembly; generating channel separation images by separating each of the Bayer images by a plurality of channels; determining corresponding points such that pixels in the channel separation images are displayed at the same position on a projection plane, for each of the plurality of lenses; performing binning on the channel separation images, based on a brightness difference and a distance difference between a target corresponding point and a center of a pixel including the target corresponding point, corresponding to each of the corresponding points in channel separation images that correspond to a same channel and that are combined into one image, for each of the plurality of lenses; restoring the input image for each of the plurality of lenses based on binned images generated by performing the binning; and outputting the restored input image.