摘要:
In order to assist a viewer in understanding the contents of a moving image, it is desired to plainly represent the contents of metadata to the viewer. The metadata relevant to the moving image has a stream data structure including one or more access units each being a data unit which can be independently processed. Each of the access units includes first data to specify an effective period defined with respect to a time axis of the moving image, object area data describing a spatio-temporal region in the moving image, and balloon data to display relevant data of the object by a balloon. The balloon data includes text data to be displayed in the inside of the balloon and to express the contents of the object and position specifying data to specify a display position of the balloon.
摘要:
Since there is a case where reproduction of metadata is limited according to the processing power of a reproduction apparatus or the designation from a user, the invention provides a data structure in which metadata whose preferential reproduction is desired can be selected and reproduced. The metadata relevant to a moving image includes a stream data structure including one or more access units each being a data unit which can be independently processed, and each of the access units includes first data to specify an effective period defined with respect to a time axis of the moving image, object area data describing a spatio-temporal region in the moving image, second data including one of or both of data to specify a display method relevant to the spatio-temporal region and data to specify a processing to be performed when the spatio-temporal region is specified, and third data to specify, in a case where one or more access units exist on a same screen in the moving image at a time of reproduction of the metadata, reproduction priority of each of the access units.
摘要:
According to one embodiment, an image processing apparatus includes a difference calculation unit, an intensity calculation unit, and an enhancing unit. The difference calculation unit calculates, for each partial area of an input image, a difference between a depth value of a subject and a reference value representing a depth as a reference. The intensity calculation unit calculates for each partial area an intensity, which has a local maximum value when the difference is 0 and has a greater value as the absolute value of the difference is smaller. The enhancing unit enhances each partial area according to the intensity to generate an output image.
摘要:
According to one embodiment, an image processing device includes an obtaining unit, a separating unit, a processing unit and a combining unit. The obtaining unit obtains a depth value of a subject imaged on an input image. The separating unit separates the input image into a first component that is a component including a gradation and a second component that is a component other than the first component. The processing unit enhances the first component in accordance with the depth value to generate a processed component. The combining unit combines the processed component and the second component to generate a combined component.
摘要:
An image resolution increasing method include setting a first block which is included in a low resolution image and is located at a first position, and a second block which is included in a high resolution image and is located at a second position, and setting, as an increasing resolution block of the first block, a third block expressed by a second vector obtained by projecting a first vector representing the second block to a linear manifold as a set of vectors that indicate fourth blocks of the second block size, the fourth blocks becoming the first block due to reduced resolution, in a Euclidean space having, as the number of dimensions, a product of the number of pixels arranged vertically in the second block size and the number of pixels arranged horizontally in the second block size.
摘要:
A super-resolution device and method for setting at least one of a plurality of pixels included in image data as target pixels, the image data including pixels arranged in a screen and pixel values representing brightness, an area including the target pixel and peripheral pixels as a target area, and an area for searching pixel value change patterns in the target pixel area; calculating a difference between a first change pattern and second change pattern; comparing a difference between the first and second change patterns; calculating a pixel value of a super-resolution image having a number of pixels larger than a number of pixels included in the image data on the basis of a decimal-accuracy-vector, an extrapolated vector, and pixel values obtained from the image data.
摘要:
A resolution enhancing method of a video includes reducing a training video, extracting a high-frequency component from the training video, calculating a first feature vector including a feature amount of a first spatio-temporal box in the reduced video, storing pairs of the first feature vectors and second spatio-temporal boxes in the high-frequency component videos at the same positions as those of the first spatio-temporal boxes, expanding an input video, retrieving a first feature vector similar to a second feature vector including a feature amount of a third spatio-temporal box of an object of the input video to be processed, as an element, and adding a second spatio-temporal box making a pair with the retrieved first feature vector to a fourth spatio-temporal box in the expanded video at the same position as that of the third spatio-temporal box in order to generate an output video.
摘要:
Although it is necessary to display a mouse cursor in order to specify an object area in a moving image, there is a fear that a standard cursor spoils the atmosphere of the moving image or the intention of a producer. Then, a data structure is desired in which the shape of the cursor can be freely specified according to the contents of the moving image or the object. In metadata of the moving image, the object area appearing in the moving image is divided into plural data (access units), and the access unit is made to be capable of specifying the cursor shape, and the cursor shape in the object area is made freely changeable.
摘要:
There is provided a structure of metadata which can express an object of a complicated shape. There are added vcr_shape_num indicating the number of sub-planar areas constituting an object area, vcr_rule_code indicating that an integration system to integrate the sub-planar areas and to determine a final object area is written, vcr_rule_length to indicate the length of data of the integration system, and data vcr_rule to indicate the integration system, and thereafter, vcr_subregion_data of data of each sub-planar area appearing in vcr_rule is described continuously by the number indicated by vcr_shape_num.
摘要:
According to one embodiment, an image processing apparatus includes first and second computation portions, a selection portion, a projection portion, and a weighted averaging portion. The first computation portion is configured to obtain magnitudes of correlations between a first vector and plural basis vectors. The selection portion is configured to select basis vectors from the plural basis vectors. The projection portion is configured to select a second region, obtain a first projection vector by projecting the first vector onto a subspace formed by the selected basis vectors and obtain a second projection vector for each second region by projecting a second vector onto the subspace. The second computation portion is configured to compute a distance between the first and second projection vectors. The weighted averaging portion is configured to weighted average a pixel value of the second pixel to obtain an output pixel value of a first pixel.