Abstract: Disclosed are a method for deriving a temporal predictive motion vector, and an apparatus using the method. An image decoding method may comprise the steps of: determining whether or not a block to be predicted is brought into contact with a boundary of a largest coding unit (LCU); and determining whether or not a first call block is available according to whether or not the block to be predicted is brought into contact with the boundary of the LCU. Accordingly, unnecessary memory bandwidth may be reduced, and implementation complexity may also be reduced.

Abstract: To summarize an input image, an image summarization system extracts a background frame and object information of each of objects from an image stream, and selects objects which match a selection condition among extracted objects as a queue object. The image summarization system generates a summarized video based on the queue object and a background frame.

Abstract: Disclosed are a method for deriving a temporal predictive motion vector, and an apparatus using the method. An image decoding method may comprise the steps of: determining whether or not a block to be predicted is brought into contact with a boundary of a largest coding unit (LCU); and determining whether or not a first call block is available according to whether or not the block to be predicted is brought into contact with the boundary of the LCU. Accordingly, unnecessary memory bandwidth may be reduced, and implementation complexity may also be reduced.

Abstract: Disclosed are a method for deriving a temporal predictive motion vector, and an apparatus using the method. An image decoding method may comprise the steps of: determining whether or not a block to be predicted is brought into contact with a boundary of a largest coding unit (LCU); and determining whether or not a first call block is available according to whether or not the block to be predicted is brought into contact with the boundary of the LCU. Accordingly, unnecessary memory bandwidth may be reduced, and implementation complexity may also be reduced.

Abstract: To summarize an input image, an image summarization system extracts a background frame and object information of each of objects from an image stream, and receives a region of interest set in a predetermined region of the background frame. The image summarization system selects the extracted objects as queue objects, and generates a summarized video based on the queue object, the background frame, and the region of interest.

Abstract: Disclosed are a method for deriving a temporal predictive motion vector, and an apparatus using the method. An image decoding method may comprise the steps of: determining whether or not a block to be predicted is brought into contact with a boundary of a largest coding unit (LCU); and determining whether or not a first call block is available according to whether or not the block to be predicted is brought into contact with the boundary of the LCU. Accordingly, unnecessary memory bandwidth may be reduced, and implementation complexity may also be reduced.

Abstract: The present invention relates to a technique for encoding and decoding an image, and a method for encoding the image, according to the present invention, comprises the steps of: performing a prediction with respect to a current block; and transforming a residual which is generated by the prediction, wherein in the step of transforming, a first transform is performed on the residual, and then a second transform is performed on a lower frequency area, and wherein a mode of the second transform can be decided on the basis of a mode of the first transform.

Abstract: Disclosed are a method for deriving a temporal predictive motion vector, and an apparatus using the method. An image decoding method may comprise the steps of: determining whether or not a block to be predicted is brought into contact with a boundary of a largest coding unit (LCU); and determining whether or not a first call block is available according to whether or not the block to be predicted is brought into contact with the boundary of the LCU. Accordingly, unnecessary memory bandwidth may be reduced, and implementation complexity may also be reduced.

Abstract: Disclosed is an adaptive transform method based on an in-screen prediction, and an apparatus using the method. A method for encoding an image can comprise a step of determining in-screen prediction mode groups, and a step of transforming by using a different transform method according to the in-screen prediction mode group. As a result, transforming can be performed by applying the different transform method according to the in-screen prediction mode group.

Abstract: To summarize an input image, an image summarization system extracts a background frame and object information of each of objects from an image stream, and selects objects which match a selection condition among extracted objects as a queue object. The image summarization system generates a summarized video based on the queue object and a background frame.

Abstract: To summarize an input image, an image summarization system extracts a background frame and object information of each of objects from an image stream, and receives a region of interest set in a predetermined region of the background frame. The image summarization system selects the extracted objects as queue objects, and generates a summarized video based on the queue object, the background frame, and the region of interest.

Abstract: Provided is a method for decoding an image. The method includes: deciding a prediction mode that corresponds to a chroma component block; deciding a transform skip mode of the chroma component block from a plurality of transform skip mode candidates, according to the prediction mode that corresponds to the chroma component block; and reverse-transforming the chroma component block on the basis of the transform skip mode that is decided.

Abstract: The present invention relates to a technique for encoding and decoding an image, and a method for encoding the image, according to the present invention, comprises the steps of: performing a prediction with respect to a current block; and transforming a residual which is generated by the prediction, wherein in the step of transforming, a first transform is performed on the residual, and then a second transform is performed on a lower frequency area, and wherein a mode of the second transform can be decided on the basis of a mode of the first transform.

Abstract: The present invention relates to a method for inducing a merge candidate block and a device using same. An image decoding method involves decoding motion estimation region (MER) related information; determining whether or not a predicted target block and a spatial merge candidate block are included in the same MER; and determining the spatial merge candidate block to be an unavailable merge candidate block when the predicted target block and the spatial merge candidate block are included in the same MER. Accordingly, by parallely performing the method for inducing a merge candidate, parallel processing is enabled and the computation amount and implementation complexity are reduced.

Abstract: The present invention relates to a method for inducing a merge candidate block and a device using same. An image decoding method involves decoding motion estimation region (MER) related information; determining whether or not a predicted target block and a spatial merge candidate block are included in the same MER; and determining the spatial merge candidate block to be an unavailable merge candidate block when the predicted target block and the spatial merge candidate block are included in the same MER. Accordingly, by parallely performing the method for inducing a merge candidate, parallel processing is enabled and the computation amount and implementation complexity are reduced.

Abstract: The present invention relates to a method for inducing a merge candidate block and a device using same. An image decoding method involves decoding motion estimation region (MER) related information; determining whether or not a predicted target block and a spatial merge candidate block are included in the same MER; and determining the spatial merge candidate block to be an unavailable merge candidate block when the predicted target block and the spatial merge candidate block are included in the same MER. Accordingly, by parallely performing the method for inducing a merge candidate, parallel processing is enabled and the computation amount and implementation complexity are reduced.

Abstract: The present invention relates to a method and apparatus for intra prediction. The intra prediction method for a decoder, according to the present invention, comprises the steps of entropy-decoding a received bitstream, generating reference pixels to be used in the intra prediction of a prediction unit; generating a prediction block from the reference pixels on the basis of a prediction mode for the prediction unit and reconstructing an image from the prediction block and a residual block, which is obtained as a result of entropy encoding, wherein the reference pixels and/or the prediction block pixels are predicted on the basis of a base pixel, and the predicted pixel value can be the sum of the pixel value of the base pixel and the difference between the pixel values of the base pixel and the generated pixel.

Abstract: Disclosed is an adaptive transform method based on an in-screen prediction, and an apparatus using the method. A method for encoding an image can comprise a step of determining in-screen prediction mode groups, and a step of transforming by using a different transform method according to the in-screen prediction mode group. As a result, transforming can be performed by applying the different transform method according to the in-screen prediction mode group.

Abstract: In one example embodiment, thumbnail management for video content includes detecting a plurality of scene change points from the video content, determining a number of analysis windows based on the plurality of detected scene change points, selecting a frame in each of the analysis windows, and storing the selected frame as the thumbnail for the respective analysis window.

Abstract: Depth camera-based human subject detecting includes receiving an image captured by a depth camera, converting the image, in a depth camera coordinate system, to an image in a real space coordinate system based on an angle and a position of the depth camera relative to at least one subject of the image, detecting at least one subject from the image in the real space coordinate system, calculating a distance from the depth camera to the at least one subject based on the image in the real space coordinate system and determining whether the at least one subject is a person using criteria that varies depending on the respective distance from the depth camera to the at least one subject.