Sony United Kingdom Limited

Jonathan Living

Robert Mark Stefan Porter

Simon Dominic Haynes

Ratna Rambaruth

Clive Henry Gillard

Nicholas Ian Saunders

James Edward Burns

An image processing apparatus in which output pixels of an output image are generated from one or more input images using motion vectors having a sub-pixel accuracy. A motion vector allocator allocates motion vectors in the pixels, and compares a current output pixel with test image areas pointed to by motion vectors in the pixels to detect a most suitable motion vector for the current output pixel. A pixel generator operates in a first mode if the output pixel is within a threshold displacement from an image region having substantially different motion characteristics to those of that output pixel, and in a second mode otherwise. The pixel generator includes a spatial filter generating an output pixel value at a required pixel position to a sub-pixel accuracy.

Generating output pixels of an output image from one or more input images using a set of motion vectors having a sub-pixel accuracy

A method of processing successive images of a video signal to generate a representative color value indicative of a representative color of an image sub-area. The method includes detecting a color property of the image sub-area in a current image, generating a filtered color property in respect of the current image by combining a color property for the current image with a filtered color property derived in respect of a corresponding sub-area of a previous image, and deriving the representative color value in dependence on a difference between the color property of the sub-area of the current image and the filtered color property.

Image processing for generating a representative color value indicative of a representative color of an image sub-area

A video data processing apparatus, that processes video data including a sequence of images, the apparatus including: an object tracker unit configured to detect a presence of one or more objects within an image and to track a detected object across successive images; an identity association unit configured to associate an identity with an object tracked by the object tracker unit; a counter unit configured to, for a first and second identity, count a number of images within which a tracked object associated with the first identity and a tracked object associated with the second identity have both been detected; and a similarity detector unit configured to determine whether two tracked objects are similar in appearance.

Object detection

An image processing method for selecting a subset of n (where n is two or more) images representative of a test set of images. The method includes detecting a degree of similarity between images in the test set of images so that the subset of images comprises those n images having substantially the lowest similarity with other images in the set.

Image processing

Image object detection apparatus in which test regions of a test image are compared with an image property model, a mask defining a subset of pixel positions within a test region, comprises means for comparing pixel properties in the test image defined by the test regions with the image property model to detect a property difference between the image property model and a test region; so that pixel property differences within the mask and pixel property differences outside the mask are combined with opposite respective polarities to form a difference value in respect of that test region, an object being detected in the test image at a test region corresponding to a lowest difference value between the image property model and pixels defined by the test region.

A data compression apparatus for performing data compression on input data comprises a quantisation parameter estimation arrangement for deriving an estimated value of a quantisation parameter used in a previous compression/decompression cycle applied to the input data, by detecting rounding effects in data values of at least a subset of the input data; and a parameter selection arrangement, responsive to the quantisation parameter estimation arrangement for selecting a quantisation parameter for use in compression of the input data.

Data compression

Object detection apparatus for detecting objects in a test image comprises means for comparing blocks of a test window of the image with reference data indicative of the presence of an object to generate index figures indicative of a degree of similarity between a region and the reference data; means for storing probability data corresponding to possible values of the index figure and the block position; means operable, in respect of a current block, for accessing a probability value from the storing means in dependence on that block's position within the test window and the index figure generated in respect of that block; and means for combining the probability values corresponding to blocks in a test window to generate a result indicative of the probability of that test window containing an object; in which the probability values in the storing means are ordered by block position then by index figure.

A system and associated methodology of detecting objects using multiple sets of object probability data relating to different respective expected object sizes relative to the image size. A list of locations in an image where an object has been detected is stored, the list defining a probability data set and a probability value for each detected object. Object locations in a set of object probability data as locations at which a local maximum probability value exceeds a threshold probability value are detected and, if that location is substantially similar to a location previously stored in the list, where the local maximum probability value exceeds that relating to the previously stored location. The storing is repeated successively in respect of each set of probability data.

Growing community of inventors

Nr. Stourbridge, United Kingdom

Jonathan Living