Abstract: An apparatus and method for generating synthetic training data for motion recognition. The method includes generating a three-dimensional (3D) human body model in real time according to motion of a human body, converting volume data of the 3D human body model into a 3D linear structure and extracting skeletal joint information, generating a data set of a human body image and skeletal joint information by rendering the 3D human body model and the skeletal joint information, and providing the data set of the image and the skeletal joint information as synthetic training data for motion recognition.

Abstract: Provided are a method and an apparatus for determining a breathing status of a person using a depth camera. The method of determining a breathing status of a person using a depth camera may include acquiring a depth map by photographing one side of a person using a depth camera, extracting a region of the person by separating a background from the acquired depth map, extracting a breathing region from the extracted region of the person, obtaining a depth value for each point of the extracted breathing region for a preset time, and determining a breathing status including a volume of breathing and the number of the breathings by analyzing the obtained depth value. Therefore, it is possible to accurately determine the breathing status of the person in a non-contact manner.

Abstract: An apparatus and method for generating synthetic training data for motion recognition. The method includes generating a three-dimensional (3D) human body model in real time according to motion of a human body, converting volume data of the 3D human body model into a 3D linear structure and extracting skeletal joint information, generating a data set of a human body image and skeletal joint information by rendering the 3D human body model and the skeletal joint information, and providing the data set of the image and the skeletal joint information as synthetic training data for motion recognition.

Abstract: A method of increasing a photographing speed of a photographing device which capture an image through a combination of two or more photographing devices and generate and provide an image by using the captured image, thereby increasing a photographing speed. An RGB image obtaining device and a depth image obtaining device alternately perform photographing to obtain an image. Also, a second depth image and a second RGB image respectively corresponding to a first RGB image and a first depth image which are alternately obtained by performing alternate photographing are synthesized and output, thereby actually increasing a photographing speed by twice.

Abstract: An apparatus and method for analyzing a golf motion. The apparatus includes acquiring, by an image sensor of a camera unit, a 2D image of motion of a user, acquiring, by a depth sensor of the camera unit, a depth image to temporally alternate with acquisition of the 2D image, the depth image including depth values of pixels in the 2D image, increasing an image-capturing speed by generating a corresponding depth image or a corresponding 2D image, which corresponds to a reference 2D image or a reference depth image acquired at a predetermined time, outputting the reference 2D image and the corresponding depth image or the reference depth image and the corresponding 2D image as output data for motion analysis, extracting skeletal information of the user through analysis of output data, and displaying motion of the user on a display unit based on skeletal information.

Abstract: A user customized training system according to the present invention includes a sensor module configured to sense a user's motion; a memory in which a program for training is stored; and a processor configured to execute the program stored in the memory, wherein, when the program is executed, the processor acquires coordinates that correspond to the sensed motion, compares the user's motion with pre-stored erroneous motions on the basis of body information generated on the basis of the coordinates, provides a pre-stored set of motion data when a result of the comparison indicates that the user's motion corresponds to an erroneous motion, and, when the sensor module senses a motion of the user corresponding to the set of motion data, provides a training set corresponding to a result of analyzing the sensed motion.

Abstract: An apparatus and a method for providing a surveillance image based on a depth image. The apparatus according to the present invention includes: a first camera capturing a depth image for a subject in a predetermined capturing region; a second camera capturing a color image for the subject in the predetermined capturing region; a subject identification unit identifying a subject in the capturing region; an image processing unit extracting the color image corresponding to a region of the identified subject from the color image and synthesizing the extracted color image with a position corresponding to the depth image to generate a synthesized image; and a control unit providing the depth image when the subject is not identified by the subject identification unit and providing the synthesized image only when the subject is identified by the subject identification unit.

Abstract: An apparatus and method for analyzing a golf motion. The apparatus includes acquiring, by an image sensor of a camera unit, a 2D image of motion of a user, acquiring, by a depth sensor of the camera unit, a depth image to temporally alternate with acquisition of the 2D image, the depth image including depth values of pixels in the 2D image, increasing an image-capturing speed by generating a corresponding depth image or a corresponding 2D image, which corresponds to a reference 2D image or a reference depth image acquired at a predetermined time, outputting the reference 2D image and the corresponding depth image or the reference depth image and the corresponding 2D image as output data for motion analysis, extracting skeletal information of the user through analysis of output data, and displaying motion of the user on a display unit based on skeletal information.

Abstract: A method of increasing a photographing speed of a photographing device which capture an image through a combination of two or more photographing devices and generate and provide an image by using the captured image, thereby increasing a photographing speed. An RGB image obtaining device and a depth image obtaining device alternately perform photographing to obtain an image. Also, a second depth image and a second RGB image respectively corresponding to a first RGB image and a first depth image which are alternately obtained by performing alternate photographing are synthesized and output, thereby actually increasing a photographing speed by twice.

Abstract: A hand motion recognizing apparatus obtains an image with first resolution including a hand and an image with second resolution higher than the first resolution including the hand, maps the image with the first resolution and the image with the second resolution, extracts a hand position from the image with the first resolution, obtains a hand region corresponding to the hand position from the image with the second resolution mapped to the image with the first resolution, and subsequently estimates a hand motion from the hand region.

Abstract: Provided is an apparatus and method for obtaining depth information using an optical pattern. The apparatus for obtaining depth information using the optical pattern may include: a pattern projector to generate the optical pattern using a light source and an optical pattern projection element (OPPE), and to project the optical pattern towards an object area, the OPPE comprising a pattern that includes a plurality of pattern descriptors; an image obtaining unit to obtain an input image by photographing the object area; and a depth information obtaining unit to measure a change in a position of at least one of the plurality of pattern descriptors in the input image, and to obtain depth information of the input image based on the change in the position.

Abstract: A hand motion recognizing apparatus obtains an image with first resolution including a hand and an image with second resolution higher than the first resolution including the hand, maps the image with the first resolution and the image with the second resolution, extracts a hand position from the image with the first resolution, obtains a hand region corresponding to the hand position from the image with the second resolution mapped to the image with the first resolution, and subsequently estimates a hand motion from the hand region.

Abstract: Provided is a gesture processing method for continuous value input. The gesture processing method includes acquiring a gesture input, extracting a moving direction of a pointing means interoperating with the gesture input, extracting a direction change angle of the pointing means, when the pointing means is moved after the moving direction and the direction change angle are extracted, extracting a relative position indicating a continuous movement amount of the pointing means, matching the extracted relative position with a continuous value of a control item, combining the moving direction of the pointing means, the direction change angle of the pointing means, and the relative position to control setting of the control item, and executing a control instruction for the control item.

Abstract: There are provided a device for providing haptic feedback based on user gesture recognition and a method of operating the same. The device includes a detection unit configured to detect a gesture performed by a user, a recognition unit configured to process detection information in which the user's gesture is detected by the detection unit and recognize a specific gesture performed by the user, and a control unit configured to determine whether haptic feedback information is output in consideration of the user's specific gesture recognized by the recognition unit, deliver the haptic feedback information output according to the determination result to at least one external device of a mobile terminal and a speaker, and provide haptic feedback to the user.

Abstract: A method performed in an apparatus based on touch screen may comprise grouping Korean consonants into at least one consonant-group and Korean vowels into at least one vowel-group and determining a delegate consonant for each of the at least one consonant-group and a delegate vowel for each of the at least one vowel-group; allocating the delegate consonant and the delegate vowel to independent keys in a predetermined order, and displaying the keys; and displaying at least one key corresponding to at least one family consonant belonging to a same group with the delegate consonant to a key selected among the displayed keys. Therefore, all Korean consonants and vowels can be inputted by using a restricted number of keys, and inputted quickly and easily without any learning or training.

Abstract: Provided is an apparatus and method for obtaining depth information using an optical pattern. The apparatus for obtaining depth information using the optical pattern may include: a pattern projector to generate the optical pattern using a light source and an optical pattern projection element (OPPE), and to project the optical pattern towards an object area, the OPPE comprising a pattern that includes a plurality of pattern descriptors; an image obtaining unit to obtain an input image by photographing the object area; and a depth information obtaining unit to measure a change in a position of at least one of the plurality of pattern descriptors in the input image, and to obtain depth information of the input image based on the change in the position.

Abstract: Provided are an apparatus and method for processing motion picture and a record medium, which decompose a motion picture into unit frames and insert copyright information into the unit frames, enabling to determine the infringement of copyright when the motion picture is illegally circulated. The apparatus includes a processing unit, a merging unit and an output unit. The processing unit decomposes a motion picture into a plurality of unit frames, and generates a main frame, a sub-frame including copyright information for the motion picture and a degree frame which is paired with the sub-frame, based on the unit frames. The merging unit merges the sub-frame into the main frame according to a degree of mergence of the degree frame. The output unit continuously outputs the merged frames in time order.

Abstract: A method for controlling a game character is provided. The method includes analyzing a game situation in which a character appears; and controlling a behavior of the character depending on a result of the analyzing. Accordingly, situation recognition and behavior control depending on the recognized situation are simultaneously performed using the same algorithm, so that the calculation amount can be reduced, and thus high artificial intelligence can be implemented with less computer resources. Also, a game developer does not need to implement individual behavior rules of characters depending on game situations since a situation of the game may be recognized through learning of an artificial neural network using a game database of game situations, and thus the behavior of characters can be controlled depending on the recognized situation.

Abstract: A database query system is provided. The database cache system includes: a network library which processes an access request issued by the online game server by using an input output completion port (IOCP); at least one database connection module which provides a connector for reading data from the database or recording data to the database; a database cache which stores data read from the database by the database connection module; and at least one cache buffer which is allotted to an IOCP worker thread corresponding to a database query request issued by the online game server and stores data read from the database, which is to be transmitted to the online game server.

Abstract: A user manual supporting method for use in an electronic appliance includes converting a series of operations performed by the user to operate the electronic appliance and converting the operations into a pattern of user operation sequence, and checking if an error is present in the pattern of user operation sequence to retrieve a pattern of erroneous operation sequence corresponding to the pattern of user operation sequence having the error. Thereafter, a manual content associated with the pattern of erroneous operation pattern is extracted and the extracted manual content is provided to the user. The manual content the manual content includes text and/or graphics information for notifying the user of a missing operation in the pattern of user operation sequence, or for guiding a normal operation against the pattern of erroneous operation sequence.