Abstract: Disclosed are a device and a method for localizing a user indoors using a wireless local area network, and more particularly, a localization device and a localization method that improve localization accuracy by fusing various context information when localizing a user-portable/wearable device connected with a wireless network based on an RF-based wireless network such as ZigBee.

Abstract: An apparatus for controlling a rehabilitation robot providing walking assistance to a user is disclosed. The apparatus includes a command perceiving unit for receiving a explicit walking command mode of a user based on a conscious adjustment signal, a motion sensing unit for sensing action of the user, a biometric sensing unit for sensing a biometric state of the user, and a host control module for analyzing walking steps and perceiving intent to walk by using the walking command perceived by the command perceiving unit and the action sensed by the motion sensing unit, thereby controlling the rehabilitation robot. The apparatus for controlling a rehabilitation robot further includes a wearing-type suit having the apparatus disposed thereon.

Abstract: An apparatus for operation of a moving object in an unstructured environment includes a sensor unit configured to sense vibration of the moving object to produce a sensing signal; an image capturing unit configured to capture an image of a surrounding environment on which the moving object travels; a signal synchronization unit configured to synchronize the sensing signal from the sensor unit with the image captured by an image capturing unit through mapping therebetween; an amplitude extraction unit configured to extract a tilt of the moving object based on the sensing signal from the sensor unit and calculate a viewing angle and a moving distance of the moving object based on the calculated tilt; and an image correction unit configured to perform coordinate transformation on the captured image by using the viewing angle and the moving distance to generate a corrected image.

Abstract: A mobile robot apparatus includes a video recognition unit for recognizing a position of an opening button mounted around a door through video analysis after acquiring peripheral video information. Further, the mobile robot apparatus includes a mobile controller for performing an operation on the opening button at the position recognized by the video recognition unit to generate an opening selection signal, thereby allowing a door control apparatus to open the door according to the generated opening selection signal.

Abstract: Disclosed is a system for integrating gestures and sounds including: a gesture recognition unit that extracts gesture feature information corresponding to user commands from image information and acquires gesture recognition information from the gesture feature information; a background recognition unit acquiring background sound information using the predetermined background sound model from the sound information; a sound recognition unit that extracts the sound feature information corresponding to user commands from the sound information and extracts the sound feature information based on the background sound information and acquires the sound recognition information from the sound feature information; and an integration unit that generates integration information by integrating the gesture recognition information and the sound recognition information.

Abstract: Disclosed is a method of detecting an upper body. The method includes detecting an omega candidate area including a shape formed of a face and a shoulder line of a human from a target image, cutting the target image into the upper body candidate area including the omega candidate area, detecting a human face from the upper body candidate area, and judging whether the upper body of the human is included in the target image according to the result of detecting the human face.

Abstract: Disclosed is a method of extracting a text area, the method including generating a text area prediction value within an input second image based on a plurality of text area data stored in a database including geometric information about a text area of a first image, generating a text recognition result value by determining whether a text is recognized with respect to a probable text area within the input second image, and selecting a text area within the second image by combining the generated text area prediction value and text recognition result value.

Abstract: Provided are a system and a method for aiding a user's memory by using a robot. The present invention is provided to aid the user's memory by acquiring image data associated with surrounding situations according to a request from a user, granting a unique ID to data acquired according to a feedback from the user or collected from the outside, classifying and managing the collected data by considering user information, a position, a time, person information and the like, and selecting data which is managed according to a query selected by the user from predetermined queries. According to the present invention, daily activities can be recorded from a user-centered viewpoint and it is possible to easily access even a photo which is not stored in a DB of a robot in link with an SNS.

Abstract: Provided is a system for adjusting an image of a beam projector using a camera attached remote controller and a method thereof. The system for adjusting images of a beam projector according to the present invention includes: a remote controller photographing test images projected on a screen and detecting pattern images from the photographed test images and generating control information including at least one parameter necessary to adjust the images through the detected pattern images; and a beam projector receiving the control information for adjusting images from the remote controller and adjusting the input image by using parameters included in the received control information and outputting them to the screen. Therefore, the present invention adjusts colors and geometrical shapes of images at a user's viewpoint, thereby making it possible to improve the satisfaction of user and implement the system in various forms.

Abstract: The present invention detects a candidate ROI group associated with character strings/figure strings on the basis of a result acquired through prior learning of various types of license plates, verifies the interested region candidate group detected by using at least one condition of five predetermined conditions, and determines an MBR region in the selected ROI region from the verified interested region candidate group by considering a ratio between the height and width of the ROI region to recognize the license plate for the automobile. According to the present invention, it is possible to automatically detect the location of the license plate regardless of various types of license plate specifications defined for each of countries.

Abstract: A method of modeling a composite emotion in a multidimensional vector space, is provided with creating an emotion vector space by defining dimensions of a vector space in consideration of stimuli affecting emotions, and dividing a defined multidimensional vector space into emotion regions. Further, the method of modeling a composite emotion in a multidimensional vector space includes creating a composite emotion by calculating a fuzzy partitioned matrix between a current state vector and respective representative vectors in the created emotion vector space.

Abstract: A system and method for analyzing the motions of an object based on the silhouettes of the object are provided. The system includes a foreground detector, a contour extractor, a model generator, a corner histogram generator, and a value of similarity measuring unit. The foreground detector detects a moving foreground object from an input image. The contour extractor extracts silhouette contour of the detected foreground object, and the model generator generates mean value histogram models as references to determine motions of the object.

Abstract: A method of extracting a foreground object image from a video sequence includes producing a reference background image by separating a background image from a frame image of the video sequence; producing edge information of the frame image and the reference background image; producing an edge difference image using the edge information; and extracting the foreground object image using the edge difference image based on the edge information.

Abstract: Disclosed are an apparatus and a method for sensing photoplethysmogram and fall. According to the present invention, the apparatus and for sensing photoplethysmogram and fall may include: a sensor unit that senses acceleration and photoplethysmogram; a photoplethysmogram/fall determining module that synthetically tests sensed acceleration signals and photoplethysmogram signals sensed by the sensor unit to determine whether emergency occurs due to fall or emergency occurs due to photoplethysmogram; and a communication module that transmits the test results.

Abstract: Provided are a thimble-type intermediation device and a method for recognizing a finger gesture using the same. The thimble-type intermediation device includes: a motion sensing unit sensing a motion of a user's finger and generating the sensed result as motion data; a tactile sensing block sensing a tactile behavior of the user's finger and generating the sensed result as tactile data; a control unit recognizing the gesture and tactile behavior of the user's finger on the basis of the generated motion data and tactile data, and outputting the recognition result as recognition result information; and a wireless communication unit transmitting the recognition result information to a robot system.

Abstract: Disclosed is a typewriter system and a text input method capable of accurately recognizing words by correcting words input using a mediated interface device based on a dictionary. A plurality of texts are combined by referencing a text recognition order set in which recognition results of texts are arranged according to a recognition order from texts input through the mediated interface device and the combined text is filtered using part index maps formed of part words that are an accumulated set of texts forming complete words. The part words passing through the part index maps is again filtered using a dictionary including context information formed of a set of words in a specific category, thereby making it possible to accurately recognize the words. The part words that cannot form words in a dictionary are removed in advance using the part index maps, thereby improving the recognition efficiency.

Abstract: An apparatus for controlling a robot and a method thereof are provided. The apparatus includes: a state interpretation unit determining whether or not a current situation belongs to a preset unstable state by evaluating the current situation based on a plurality of perception information items; and a target generation unit setting a target action of the robot by comparing the current situation and the determination result with a predetermined value system, and then, modifying the target action by receiving a feedback of the action performance result of the robot as perception information. According to the method and apparatus, by inputting a processing procedure and a value system to solve a variety of unstable states that can occur in situations of a user and circumstances surrounding the robot, the robot can actively respond with actions.

Abstract: A wireless sensor network communication apparatus and method selectively using infrared and radio frequency communication. The wireless sensor network communication apparatus includes a first communicating unit, a second communication unit, and a wireless node processor. The first communicating unit wakens a neighboring node in a sleep mode and transmits/receives the woken node and sensor data. The second communicating unit transmits/receives the woken neighboring node and the sensor data. The wireless node processor is wakened from the sleep mode, wakens the neighboring node in the sleep mode, and transmits the sensor data with a minimum low power through one of the first and second communicating unit. Accordingly, the apparatus can perform the wireless sensor network communication with lower power compared to the case that communication is performed only by the radio frequency communication function.

Abstract: The present invention relates to a remote control system, a remote server, a remote control agent, and a remote control method. According to the present invention, when controlling the remote apparatus to perform a target service, remote apparatus information and service information are searched and a service plan is generated based on the searched remote apparatus information and service information for execution of the target service. In addition, a remote apparatus control process generated by the service plan and the process is performed. Therefore, users can easily control the remote apparatus and can be provided desired services.

Abstract: Provided are a method and system for modeling a service using a Bayesian network and status information in a distributed environment. The method includes creating a scenario for modeling at least one service, categorizing the service into models according to properties based on the scenario, setting interrelationships including a chronological relationship, a hierarchical relationship, and correlation between the categorized models, and deriving information including a service goal and status information with respect to the models and completing service modeling. Accordingly, a service provider, which digitally provides various services in a ubiquitous environment, can efficiently and actively provide intelligent services. In addition, since a specific method of modeling a service based on probabilities is provided, an intelligent service is modeled efficiently and diversely.