Abstract: An electronic device and a method thereof are provided. The electronic device includes: a memory and a processor configured to: acquire feature data of a plurality of images in a video using a first artificial neural network of a first artificial intelligence model; acquire a plurality of key frames of the video based on the feature data of the plurality of images using a second artificial neural network of the first artificial intelligence model; acquire first feature data of remaining key frames excluding at least one of the plurality of key frames using a first artificial neural network of a second artificial intelligence model; acquire second feature data including information about relationships between the remaining key frames based on the first feature data using a second artificial neural network of the second artificial intelligence model; and acquire texts for the plurality of key frames based on the second feature data.

Abstract: A depth estimating apparatus operated by at least one processor includes: a database which stores a photographed first color image, a training thermal image geometrically aligned with the first color image, and a second color image simultaneously photographed with the first color image as a training image set; and a training apparatus which trains a neural network in an unsupervised manner to output a chromaticity image and a binocular disparity image from the training thermal image. The training apparatus generates an estimated first color image from the second color image, the chromaticity image, and the binocular disparity image, and trains the neural network to minimize a difference between the estimated first color image and the photographed first color image.

Abstract: The present disclosure relates to an artificial intelligence (AI) system for simulating functions of the human brain, such as cognition and determination, by using a machine learning algorithm, such as deep learning, and to an application of the AI system.

Abstract: A depth estimating apparatus operated by at least one processor includes: a database which stores a photographed first color image, a training thermal image geometrically aligned with the first color image, and a second color image simultaneously photographed with the first color image as a training image set; and a training apparatus which trains a neural network in an unsupervised manner to output a chromaticity image and a binocular disparity image from the training thermal image. The training apparatus generates an estimated first color image from the second color image, the chromaticity image, and the binocular disparity image, and trains the neural network to minimize a difference between the estimated first color image and the photographed first color image.

Abstract: As an apparatus for adjusting camera exposure, the apparatus includes: a virtual image generator generating a plurality of virtual images by changing brightness of an image photographed by a camera; a feature image generator generating a plurality of feature images respectively indicating features of the plurality of virtual images; and an exposure controller corresponding a feature value of the plurality of feature images to brightness, estimating reference brightness that corresponds to the maximum feature value, increasing camera exposure when the reference brightness is brighter than the photographed image, and decreasing the camera exposure when the reference brightness is darker than the photographed image.

Abstract: A system for controlling exposure of a multi-view camera is disclosed. The system includes a plurality of cameras having different views, a single image-based camera parameter calculator calculating single image-based camera parameters for each of the plurality of cameras; an image intensity ratio calculator calculating an image intensity ratio corresponding to an image intensity difference in an overlapped region between image data obtained from the plurality of cameras; and a multi-image-based camera parameter calculator calculating multi-image-based camera parameters for correcting intensity differences between images of the plurality of cameras on the basis of the single image-based camera parameters and the image intensity ratio.

Abstract: A system for controlling exposure of a multi-view camera is disclosed. The system includes a plurality of cameras having different views, a single image-based camera parameter calculator calculating single image-based camera parameters for each of the plurality of cameras; an image intensity ratio calculator calculating an image intensity ratio corresponding to an image intensity difference in an overlapped region between image data obtained from the plurality of cameras; and a multi-image-based camera parameter calculator calculating multi-image-based camera parameters for correcting intensity differences between images of the plurality of cameras on the basis of the single image-based camera parameters and the image intensity ratio.

Abstract: Disclosed is a camera calibration method of a calibration apparatus, including: receiving plural pattern image information photographed by a camera; setting points where edges of patterns of the plural pattern image information overlap with each other as a plurality of primary features; and calibrating the camera by using the plurality of primary features, in which the plural pattern image information includes first vertical pattern image information, second vertical pattern image information complementary to the first vertical pattern image information, first horizontal pattern image information, and second horizontal pattern image information complementary to the first horizontal pattern image information.

Abstract: As an apparatus for adjusting camera exposure, the apparatus includes: a virtual image generator generating a plurality of virtual images by changing brightness of an image photographed by a camera; a feature image generator generating a plurality of feature images respectively indicating features of the plurality of virtual images; and an exposure controller corresponding a feature value of the plurality of feature images to brightness, estimating reference brightness that corresponds to the maximum feature value, increasing camera exposure when the reference brightness is brighter than the photographed image, and decreasing the camera exposure when the reference brightness is darker than the photographed image.

Abstract: An image optimized rolling cache system extracts pixel information and address information of a corresponding pixel from an input image to store the extracted pixel information and the extracted address information, and processes the image by applying a vertical rolling mechanism or a horizontal rolling mechanism using the stored information.

Abstract: Provided are a fire detecting apparatus and a method thereof for detecting a fire, the method includes operations of extracting a feature of at least one object in an input image by using a value of a brightness difference between pixels of the input image or by using an RGB value of the input image; converting the extracted feature of the at least one object into an N dimensional feature; and performing Support Vector Machine (SVM) machine learning on the N dimensional feature of the at least one object.

Abstract: A method and system for detecting motion are provided. The method includes: generating a time domain matrix including vectors corresponding to variation of pixel values as elements of the time domain matrix, of a video image including a plurality of frames; generating a motion matrix from which a low frequency area of the video image is removed by multiplying the time domain matrix by a low rank matrix; and generating a result image including a plurality of frames in which vectors, which are elements of the motion matrix, are included as variation of motion pixel values.

Abstract: An image encoding and/or decoding apparatus and method are provided. The image encoding apparatus includes: a transform unit removing spatial redundancy by transforming an original image being input; an allowable noise obtaining unit obtaining an allowable noise from the original image; a quantization parameter determination unit determining a quantization parameter by using the allowable noise; a quantization unit generating a quantized coefficient, by quantizing a transform coefficient provided from the transform unit by using the quantization parameter; and an entropy encoding unit entropy encoding the quantized coefficient to remove statistical redundancy.

Abstract: An image optimized rolling cache system extracts pixel information and address information of a corresponding pixel from an input image to store the extracted pixel information and the extracted address information, and processes the image by applying a vertical rolling mechanism or a horizontal rolling mechanism using the stored information.

Abstract: Provided are a fire detecting apparatus and a method thereof for detecting a fire, the method includes operations of extracting a feature of at least one object in an input image by using a value of a brightness difference between pixels of the input image or by using an RGB value of the input image; converting the extracted feature of the at least one object into an N dimensional feature; and performing Support Vector Machine (SVM) machine learning on the N dimensional feature of the at least one object.

Abstract: A method and system for detecting motion are provided. The method includes: generating a time domain matrix including vectors corresponding to variation of pixel values as elements of the time domain matrix, of a video image including a plurality of frames; generating a motion matrix from which a low frequency area of the video image is removed by multiplying the time domain matrix by a low rank matrix; and generating a result image including a plurality of frames in which vectors, which are elements of the motion matrix, are included as variation of motion pixel values.

Abstract: The present invention provides a method and apparatus for detecting a noise distribution of an image close to a true distribution, and detecting an edge of the image precisely and quickly based on the detected noise distribution without performing a smoothing process for the image, and a computer readable medium processing the method. The method of detecting an edge of an image includes the steps of: detecting a noise distribution of an object image; and detecting an edge of the image based on the detected noise distribution.

Abstract: An apparatus for providing an omnidirectional stereo image with a single camera includes a first reflector reflecting a first omnidirectional view viewed from a first viewpoint, a second reflector positioned to be coaxial with and separated from the first reflector to reflect a second omnidirectional view viewed from a second viewpoint, a third reflector positioned to be coaxial with the first and second reflectors to reflect the second omnidirectional view reflected by the second reflector, wherein the second and third reflectors have a folded structure satisfying a single viewpoint constraint, and an image sensor positioned to be coaxial with the first, second and third reflectors to capture an omnidirectional stereo image containing the first omnidirectional view reflected by the first reflector and the second omnidirectional view reflected by the third reflector, and output the captured omnidirectional stereo image, wherein shapes of the first, second, and third reflectors and a relative positional relati

Abstract: A method, medium, and system reducing block noise of a digital image, including an encoding/decoding method, medium, and system. The method of reducing block noise of a digital image includes calculating a value of a boundary block that includes a boundary between two neighboring blocks, calculating the visibility of the boundary block by extracting specified characteristic values of the boundary block, classifying the boundary block according to a result of comparing the calculated visibility with a specified threshold value and whether the two neighboring blocks are corner blocks, and performing deblocking of the two neighboring blocks according to a result of classification.

Abstract: The present invention provides a method and apparatus for detecting a noise distribution of an image close to a true distribution, and detecting an edge of the image precisely and quickly based on the detected noise distribution without performing a smoothing process for the image, and a computer readable medium processing the method. The method of detecting an edge of an image includes the steps of: detecting a noise distribution of an object image; and detecting an edge of the image based on the detected noise distribution.