Abstract: Disclosed herein are a method, apparatus, system, and computer-readable recording medium for image compression. An encoding apparatus performs preprocessing of feature map information, frame packing, frame classification, and encoding. A decoding apparatus performs decoding, frame depacking, and postprocessing in order to reconstruct feature map information. By encoding the feature map information, inter-prediction and intra-block prediction for a frame are performed. The encoding apparatus provides the decoding apparatus with a feature map information bitstream for reconstructing the feature map information along with an image information bitstream.

Abstract: Disclosed herein are a method, apparatus, system, and computer-readable recording medium for image compression. An encoding apparatus performs preprocessing of feature map information, frame packing, frame classification, and encoding. A decoding apparatus performs decoding, frame depacking, and postprocessing in order to reconstruct feature map information. By encoding the feature map information, inter-prediction and intra-block prediction for a frame are performed. The encoding apparatus provides the decoding apparatus with a feature map information bitstream for reconstructing the feature map information along with an image information bitstream.

Abstract: There are provided a method, apparatus, system, and computer-readable recording medium for image compression. An encoding apparatus performs domain transformation and quantization on feature map information and image information. The encoding apparatus rearranges the result of domain transformation and quantization so as to have a form advantageous to the encoding procedure and encodes the result of rearrangement, thereby generating a bitstream. A decoding apparatus receives the bitstream, decodes the received bitstream, and performs inverse transformation, dequantization, and inverse rearrangement using information transmitted through the bitstream. The result of inverse transformation, dequantization, and inverse rearrangement is used for the machine-learning task of a neural network.

Abstract: There are provided an apparatus, method, system, and recording medium for performing selective encoding/decoding on feature information. An encoding apparatus generates residual feature information. The encoding apparatus transmits the residual feature information to a decoding apparatus through a residual feature map bitstream. The residual feature information is the difference between feature information extracted from an original image and feature information extracted from a reconstructed image. Feature information of the reconstructed image is generated using the reconstructed image. Reconstructed feature information is generated using the feature information of the reconstructed image and reconstructed residual feature information.

Abstract: A photographing apparatus, a motion estimating apparatus, an image compensating method, a motion estimating method, and a non-transitory computer-readable recording medium are provided. The photographing apparatus includes: an image sensing unit which continuously captures a plurality of images by using a rolling shutter method; and an image processor which compensates for a uniformly accelerated motion of the photographing apparatus by using the plurality of images.

Abstract: An entropy encoding method and apparatus implementing the same, the method including: generating bitstreams of data groups by performing entropy encoding on a plurality of symbols of the data groups and storing the bitstreams in a storage unit by allocating a plurality of divided segments of the storage unit according to properties of the bitstreams.

Abstract: A photographing apparatus, a motion estimating apparatus, an image compensating method, a motion estimating method, and a non-transitory computer-readable recording medium are provided. The photographing apparatus includes: an image sensing unit which continuously captures a plurality of images by using a rolling shutter method; and an image processor which compensates for a uniformly accelerated motion of the photographing apparatus by using the plurality of images.

Abstract: An image pickup apparatus includes an image capturing unit which captures an image, a control unit which controls the image capturing unit to generate a wide-angle image, a composition calculating unit which calculates an optimum composition of image pickup using the generated wide-angle image, and a user interface unit which provides composition guide information to capture the image according to the calculated optimum composition of image pickup.

Abstract: A photographing apparatus, a motion estimating apparatus, an image compensating method, a motion estimating method, and a non-transitory computer-readable recording medium are provided. The photographing apparatus includes: an image sensing unit which continuously captures a plurality of images by using a rolling shutter method; and an image processor which compensates for a uniformly accelerated motion of the photographing apparatus by using the plurality of images.

Abstract: A video stabilization method includes: measuring an inter-frame camera motion based on a difference angle of a relative camera view direction in comparison with a reference camera view direction in each frame of a frame sequence of a video; generating a camera motion path of the frame sequence by using the inter-frame camera motion and determining a camera view direction adjustment angle based on a user's view direction by using the camera motion path; and compensating for the camera view direction by using the camera view direction adjustment angle in each frame.

Abstract: A video stabilization method includes: measuring an inter-frame camera motion based on a difference angle of a relative camera view direction in comparison with a reference camera view direction in each frame of a frame sequence of a video; generating a camera motion path of the frame sequence by using the inter-frame camera motion and determining a camera view direction adjustment angle based on a user's view direction by using the camera motion path; and compensating for the camera view direction by using the camera view direction adjustment angle in each frame.

Abstract: A video stabilization method includes: measuring an inter-frame camera motion based on a difference angle of a relative camera view direction in comparison with a reference camera view direction in each frame of a frame sequence of a video; generating a camera motion path of the frame sequence by using the inter-frame camera motion and determining a camera view direction adjustment angle based on a user's view direction by using the camera motion path; and compensating for the camera view direction by using the camera view direction adjustment angle in each frame.

Abstract: A video encoding method and apparatus, and a video decoding method and apparatus, which are capable of improving efficiency of encoding a luminance component video signal by predicting information on various encoding modes of the luminance component video signal by using a result obtained by encoding a chrominance component video signal, are provided. Accordingly, a block mode and an intra-prediction mode of the luminance component video signal are predicted from a previously encoded and recovered chrominance component video signal, and the predicted block mode and the predicted intra-prediction mode are used to encode the luminance component video signal.

Abstract: A method of encoding an image includes checking a storage status of a buffer storing encoded data, at every data unit equal to or less than at least one macroblock; rearranging information about a macroblock so that encoded data of the macroblock is reduced, based on the storage status of the buffer; and storing data encoded by using data of the image and the information about the macroblock, which is rearranged based on the storage status of the buffer, in the buffer.

Abstract: An image pickup apparatus includes an image capturing unit which captures an image, a control unit which controls the image capturing unit to generate a wide-angle image, a composition calculating unit which calculates an optimum composition of image pickup using the generated wide-angle image, and a user interface unit which provides composition guide information to capture the image according to the calculated optimum composition of image pickup.

Abstract: A photographing apparatus, a motion estimating apparatus, an image compensating method, a motion estimating method, and a non-transitory computer-readable recording medium are provided. The photographing apparatus includes: an image sensing unit which continuously captures a plurality of images by using a rolling shutter method; and an image processor which compensates for a uniformly accelerated motion of the photographing apparatus by using the plurality of images.

Abstract: A method and apparatus for compensating for illumination of a reference block and a method and apparatus for encoding an image, using the illumination compensation method and apparatus, are provided. The method of compensating for illumination of a reference block includes: predicting the mean values of pixels of a current block and a reference block, based on restored values of pixels neighboring the current block, and restored values of pixels neighboring the reference block; and based on the predicted mean value of the pixels of the current block, the predicted mean value of the pixels of the reference block, and the values of the pixels of the current block and the reference block, determining an illumination compensation parameter.

Abstract: A method and apparatus for coding an image capable of performing a prediction coding process by using a correlation degree between neighboring pixels of a current block and neighboring pixels of a reference block, and an image decoding method and apparatus. In the method, reference block candidates having neighboring pixels similar to the neighboring pixels of the current block are selected, matching errors between selected reference block candidates and the current block are calculated, and a reference block candidate having the least matching error is determined to be a predicted block of the current block.

Abstract: Provided is a method for controlling a buffer in a transmitter and a receiver of a video transmission system in an environment where a channel transfer rate varies. The method includes: if a channel transfer rate is changed, changing a capacity of a buffer in a transmitter being used in proportion to the c rate, the buffer temporarily storing and outputting the video data to a receiver, or changing the delay time of a buffer in the receiver by gradually changing an operating clock in the receiver.

Abstract: Provided are a bit rate control method and apparatus for intra-only coding, the method including calculating a similarity between at least one block group from among block groups including a plurality of macroblocks in a current frame to be encoded and at least one block group in a previous frame, which corresponds to the at least one block group in the current frame, determining a target bit amount of a current block group including a current macroblock using a video characteristic of the previous frame if the calculated similarity is greater than a threshold value, determining a target bit amount of the current macroblock based on the determined target bit amount of the current block group, and calculating a quantization parameter of the current macroblock based on the determined target bit amount of the current macroblock and the amount of bits generated for up to a previous macroblock.