Abstract: Provided is a method of correcting a medical image according to a patient's pose variation. The method includes attaching a marker to an object, generating a first non-real-time image and a first real-time image when the object is in a first pose, generating a second real-time image when the object is in a second pose, and correcting the first non-real-time image based on shift information of the marker when the object is changed from the first pose to the second pose.

Abstract: A three-dimensional map-generating apparatus and method using structured light. The apparatus for generating a three-dimensional map using structured light includes an odometer detecting the pose of a mobile robot, and a distance-measuring sensor including a light source module that emits light upward and a camera module that captures an image formed by light reflected from an obstacle, and measuring a distance to the obstacle using the captured image. The apparatus measures a distance to the obstacle using the distance-measuring sensor while changing the relative pose of the mobile robot, thereby generating a three-dimensional map.

Abstract: A face detection apparatus and method are provided. The apparatus may acquire a distance difference image through a stereo camera and create an object mask using the distance difference image to detect a face candidate area. The apparatus may also determine a size of a search window using the distance difference image and detect a facial area in the face candidate area. Accordingly, an operation speed for face detection can be improved.

Abstract: Provided is a method of correcting a medical image according to a patient's pose variation. The method includes attaching a marker to an object, generating a first non-real-time image and a first real-time image when the object is in a first pose, generating a second real-time image when the object is in a second pose, and correcting the first non-real-time image based on shift information of the marker when the object is changed from the first pose to the second pose.

Abstract: An apparatus and method capable of calculating a coordinate transformation parameter without having to utilize a rig are provided. The apparatus and method extract a first feature point based on a plane of first data, project the first feature point onto second data and then extract a second feature point from a part of the second data onto which the first feature point is projected. Then, calibration is performed based on the extracted feature points. Therefore, it is possible to perform calibration immediately as necessary without having to utilize a separate device such as a rig.

Abstract: A synthesis image in which medical images captured using different medical image capturing apparatuses are registered is generated by mapping the medical images to each other. The synthesis image may be used for image guidance while a diagnosis or a robotic surgery of a patient is being performed.

Abstract: An endoscope system and an endoscope includes a patterned light providing unit to provide patterned light having a pattern corresponding to a feature point; first and second capturing units to capture an object onto which the patterned light is irradiated; and a light transmitting unit to transmit the patterned light to the object and transmit light reflected by the object to the first and second capturing units.

Abstract: Technology for creating a feature map for localizing a mobile robot and extracting feature information of surroundings is provided. According to one aspect, feature information including a reflection function is extracted from information acquired using a 3D distance sensor and used as a basis for creating a feature map. Thus, a feature map that is less sensitive to change in the surrounding environment can be created, and a success rate of feature matching can be increased.

Abstract: A data input apparatus, medium, and method detecting a selected data key input. The data input apparatus may include an image output module, an image input module, and a control module, with the image output module generating an input image having a predetermined number of input keys for the input of data. The image input module may capture the generated input image, and the control module may then binarize the captured images of the respective input keys, e.g., using a predetermined threshold value. Accordingly, the proper selection of input keys can be determined by comparing the binarized images with previously stored binarized images.

Abstract: Apparatuses and methods for tracking a tumor for ultrasound therapy, and an ultrasound therapy system for performing ultrasound therapy are provided. The apparatus includes: a marker registration unit which registers at least one marker corresponding to a location of the tumor based on at least one location and feature of at least one lesion generated in at least one portion of the tumor designated by a therapeutic ultrasonic apparatus; a marker tracking unit which tracks the at least one registered marker from a medical image of the tumor during an ultrasound therapy and provides tracking results; and a marker renewing unit which, when at least one lesion is newly generated, renews the at least one registered marker based on at least one location and feature of the at least one newly generated lesion.

Abstract: Provided are an apparatus and method of measuring a distance using structured light. The apparatus includes a binarization unit binarizing an image, an image identification unit identifying an image having connected pixels in the binarized image, a length ratio calculation unit obtaining the length ratio of the major axis of the image having the connected pixels to a minor axis perpendicular to the major axis, a pixel mean calculation unit obtaining the mean of pixel values of the image having the connected pixels, and an image extraction unit extracting an image formed by the light irradiated from the light source, from the images having connected pixels using the length ratio and the mean of the pixel values.

Abstract: A method, apparatus, and medium for correcting a pose of a moving robot are provided. The method includes sensing an entrance using a distance-sensing sensor mounted on the moving robot, storing first distance data of the sensed entrance, after the moving robot travels, newly sensing the entrance using the distance-sensing sensor, and correcting the pose of the moving robot using the first distance data and second distance data corresponding to the entrance newly sensed after the moving robot travels.

Abstract: An apparatus and method capable of calculating a coordinate transformation parameter without having to utilize a rig are provided. The apparatus and method extract a first feature point based on a plane of first data, project the first feature point onto second data and then extract a second feature point from a part of the second data onto which the first feature point is projected. Then, calibration is performed based on the extracted feature points. Therefore, it is possible to perform calibration immediately as necessary without having to utilize a separate device such as a rig.

Abstract: A system, a method, and medium for detecting a moving object using a structured light, and a mobile robot including the system are provided. The system includes an image obtaining unit to obtain a first image at a predetermined position and a second image at a position after a movement of the system by using a light source; an image predicting unit to predict the second image at the position after the movement of the system by using the first image and information with respect to the movement of the system; and a comparing/analyzing unit to compare and analyze the second image obtained by the image obtaining unit and the second image predicted by the image predicting unit.

Abstract: Provided are an image processing apparatus and method for extracting foreground data from among image data. The image processing apparatus generates background data and compares the background data with received data to extract a foreground. The foreground may be extracted using information regarding distances from an image acquiring unit to objects included in received data.

Abstract: A dust detection method and apparatus of a cleaning robot. The dust detection method involves acquiring a floor image as a current floor image of a predetermined place at a current location of the cleaning robot in the predetermined place; obtaining a difference image between the current floor image and a background image selected from a feature map consisting of a plurality of floor images of the predetermined place; and detecting a dusty area based on the difference image and adjusting a cleaning power of the cleaning robot.

Abstract: A face detection apparatus and method are provided. The apparatus may acquire a distance difference image through a stereo camera and create an object mask using the distance difference image to detect a face candidate area. The apparatus may also determine a size of a search window using the distance difference image and detect a facial area in the face candidate area. Accordingly, an operation speed for face detection can be improved.

Abstract: A three-dimensional data matching system is disclosed. Data matching is performed by merging distance information and image information. Therefore, matching accuracy is improved even if a sensor with relatively low sensitivity is used. Matching data generated as a result of matching range data and CAD data is projected onto an image captured by a camera, an effective edge is extracted from the image, and an error of the matching data is corrected based on the effective edge, thereby improving matching accuracy.

Abstract: A method and apparatus for estimating a position and an orientation of a mobile robot. The apparatus includes: a ceiling image grabber for obtaining a ceiling image of an area where the mobile device travels; a mark detector for detecting a retro-reflective artificial mark from the ceiling image, the retro-reflective artificial mark including a first mark and a second mark, each including a non-reflective portion and an infrared reflective portion; and a position & orientation estimator for estimating a position and an orientation of the mobile device using a position of the artificial mark or encoder information according to whether detection of the artificial mark is successful.

Abstract: Technology for creating a feature map for localizing a mobile robot and extracting feature information of surroundings is provided. According to one aspect, feature information including a reflection function is extracted from information acquired using a 3D distance sensor and used as a basis for creating a feature map. Thus, a feature map that is less sensitive to change in the surrounding environment can be created, and a success rate of feature matching can be increased.