Apical Limited

Arm Limited

Alexey Kornienko

David Hanwell

Maxim Novikov

Nerhun Yildiz

Viacheslav Chesnokov

Thomas James Cooksey

Ozgur Tasdizen

Vladimir Dolzhenko

Yury Khrustalev

Dumidu Sanjaya Talagala

Jinhui He

Alexis Leonardo Lluis Gomez

A method comprising obtaining image data representative of pixel intensities associated with an image. Irrespective of a respective magnitude of the pixel intensities, the image data is processed with a logarithmic transformation to transform the pixel intensities to transformed pixel intensities, thereby generating transformed image data representative of the transformed pixel intensities. The logarithmic transformation, L(x), is representable as:()=log(())+where x represents a pixel intensity to be transformed, f(x) represents a function of x and P, M and N represent constants.

Image processing

An image processor comprising an input module for receiving image data from an image sensor; an image processing module arranged to perform one or more operations on at least a portion of the image data to generate processed image data; and a characteristic processing module arranged to perform one or more characteristic processing operations on at least a portion of the characteristic data to generate processed characteristic data. The portion of the characteristic data is associated with the portion of the image data; the one or more characteristic processing operations are associated with the one or more image processing operations. The image processor further comprises an output module for outputting the processed image data and processed characteristic data.

Image data pre-processing for neural networks

An image signal processor, comprising an input module for obtaining input data from a camera, whereby the camera is arranged to capture a representation of a real-world environment. The image signal processor further comprises at least one adjustment module for compressing the input data and producing compressed input data, and a localization and mapping module arranged to generate one or more data points from the compressed input data. The image signal processor also comprises an output module for outputting at least the one or more data points.

Image signal processor, method, and system for environmental mapping

The present disclosure provides an image processing apparatus and system which downscales an image which is generated from data provided by a sensor. The downscaled image is then analyzed to determine the location of one or more regions of interest in the image. The regions of interest can then be cropped from the original image and those cropped regions of interest processed by a computer vision engine.

A method including streaming input image data representing an input frame of a video into temporary storage. Transformation data representing at least one transformation for application to the input image data is obtained. Ordering data indicating a variable order in which portions of output image data are to be generated is obtained, the ordering data being based on at least one characteristic of the input frame. The transformation data is used to identify portions of input image data to be processed to generate corresponding portions of output image data. The identified portions of input image data are processed to generate the corresponding portions of output image data in the order indicated by the ordering data.

Examples of the present disclosure relate to a method for reducing artefacts caused by the presence of flicker during capture of a video. A sequence of frames of the video are captured, the frames each comprising a plurality of predefined regions each comprising a plurality of pixels. A time-varying oscillation of the flicker is characterized based on variations, across the sequence of frames, of data relating to pixel intensities in at least one said region. Based on the characterizing of the time-varying oscillation of the flicker, a flicker correction is applied to a frame of the video.

Method of flicker reduction

Examples of the present disclosure relate to an image processing apparatus comprising a filter to convert a first image data signal into an output image data signal. The filter is configured to resample the first image data signal, having a first sample rate, by a resampling factor, such that the output image data signal has an output sample rate that is different to the first sample rate. The filter is also configured to apply a phase alteration to the first image data signal to compensate a group delay in the first image data signal.

Image processing filter

A method of calibrating image data, the method comprising the steps of obtaining the image data and applying a shading correction mesh to the image data, wherein the shading correction mesh comprises a plurality of nodes, and is used to generate shading correction values for each pixel location in the image data. The blocks of the generated shading correction values are then grouped each group of blocks comprising a plurality of blocks, and each block comprising a plurality of pixel locations. An analysis of each of the groups of blocks of generated shading correction values is performed, and an updated shading correction mesh based on the analysis of the groups of one or more blocks is generated.

A method of determining an exposure ratio for use with a multi-exposure image capture system operable to capture a first image of a scene with a first exposure and a second image of the scene with a second exposure shorter than the first exposure. The exposure ratio is a ratio of the first exposure to the second exposure. The method comprises obtaining image data representative of an image captured using an image sensor of the image capture system and setting the exposure ratio in dependence on a distribution of counts relating to values of a characteristic of respective pixels of the image and a weighting function which varies with the values of the characteristic.

Exposure ratio control

Image data representative of at least a portion of an image comprising first and second sets of pixels associated with first and second colour channels, respectively, is received. It is determined that a first pixel of the first set of pixels is a saturated pixel. First data based on a value of the first pixel of the second set of pixels is obtained for a first image region comprising the first pixel of the first set of pixels and a first pixel of the second set of pixels. Second data based on respective values of second pixels of the first and second sets of pixels are obtained, based on the first data, for a second image region. The second data is processed to generate output data representative of an estimated value associated with the first colour channel for the first pixel.

Growing community of inventors

Loughborough, United Kingdom

Alexey Kornienko