Samsung Electronics Co., Ltd.

Ajou University Industry-academic Cooperation Foundation

Other

Hyundai Motor Company

Kia Corporation

Dongguk University Industry-academic Cooperation Foundation

Incheon National University Research & Buisness Foundation

Won Jun Hwang

Kyung Shik Roh

Suk June Yoon

Seung Yong Hyung

Hyo Seok Hwang

Young Bo Shim

Sung Hwan Ahn

Dong Soo Kim

Byung In Yoo

Jong Won Lee

Seon Min Rhee

Ji Yeun Kim

Ju Suk Lee

Ji Hyo Lee

Hyung Ho Kim

Dong Yi Kim

Woo Sup Han

Ki Won Kim

Moon-sik Jeong

Sang Won Lee

Soo Chul Lim

Gyu-tae Park

No San Kwak

Soon Yong Park

Jung Yun Choi

Dong-Keun Lee

Hee Kuk Lee

Sang Wook Ahn

Yun Seok Choe

Jin Man Kim

Xiangsheng Huang

Hee Sun Yun

Kyung Mi Kim

Kun Liang Liu

Jae Min Na

Hyeon Cho

Ouk Choi

Joon Pyo Hong

Young Chun Choi

Hyung Joo Suh

Il Jun Kang

Huang Xiangsheng

Dae Kwan Ko

Ho Chul Sin

Young Jun Kwak

Provided is a method of training a generative adversarial network (GAN) for converting between heterogeneous domains, the method including training a first GAN and a second GAN with at least one unpaired training data set comprised of a training image of a first domain and a training image of a second domain; using the trained first GAN to convert a first image of the first domain to an image of the second domain; using the trained second GAN to reconvert the converted image of the second domain to a second image of the first domain; and performing segmentation on at least one of the first image of the first domain, the converted image of the second domain, or the reconverted second image of the first domain.

Method and device for training generative adversarial network for converting between heterogeneous domain data

Provided are a device and method for human parsing. The method includes receiving at least one piece of image data and ground truth values for human parsing, generating a height distribution map and a width distribution map for the image data, acquiring attention maps and scaled feature maps for each of a height and a width of the image data using the distribution maps, calculating a distribution loss rate by concatenating the scaled feature maps, acquiring an improved feature map on the basis of the calculated distribution loss rate, and performing human parsing on an object included in the image data using the improved feature map.

Method and device for human parsing

A method of removing foreign objects from a brake device includes determining whether starting power is turned off in a state in which leakage of a hydraulic circuit is confirmed; and operating, while the starting power is turned off, a main master cylinder using standby power, and performing a foreign object removal mode in which hydraulic pressure is applied to a plurality of hydraulic regulating valves in the hydraulic circuit and released.

Method for removing foreign object from brake device

The present invention relates to a method and apparatus for unsupervised domain adaptation, including the steps of generating a first augmented domain associated with a source domain, generating a second augmented domain associated with a target domain, and performing unsupervised domain adaptation by using the first augmented domain and the second augmented domain as a bridge for connecting the source domain and the target domain, and it is possible to apply to other exemplary embodiments.

Method and apparatus for unsupervised domain adaptation

A generative adversarial network (GAN)-based system for generating a color image from an edge image includes: a first GAN training a model for converting the edge image into an intermediate image; and a second GAN training a model for converting the intermediate image into the color image, wherein an entropy of the intermediate image corresponds to a value between an entropy of the edge image and an entropy of the color image.

Generative adversarial network (GAN)-based system for generating color image from edge image

A method of measuring an interaction force includes: generating feature maps corresponding to a plurality of sequential images; generating pooling maps respectively corresponding to feature map groups including a predetermined number of feature maps among the feature maps; generating attention maps corresponding to the pooling maps; and sequentially receiving feature maps modified based on the attention maps and outputting interaction force information.

Method and apparatus for measuring interaction force based on sequential images using attention network

Disclosed herein are an endoscope system and a control method thereof. The control method includes acquiring plural omnidirectional images of the surroundings of an endoscope using a stereo omnidirectional camera mounted on the endoscope, calculating distances between the endoscope and an object around the endoscope using the acquired plural omnidirectional images, and executing an operation to avoid collision between the endoscope and the object around the endoscope based on the calculated distances, thus facilitating safe operation of the endoscope.

Endoscope system and control method thereof

Surgical trocars, and image acquisition method using the same, include a body having a passage configured to receive at least one surgical instrument, and at least one camera movably coupled to an outer wall of the body.

Surgical trocars and image acquisition method using the same

A radiographic apparatus may comprise: a radiation irradiating module configured to irradiate radiation to an object; and/or a processing module configured to automatically set a part of a region to which the radiation irradiating module is able to irradiate the radiation, to a region of interest, and further configured to determine at least one of a radiation irradiation position and a radiation irradiation zone of the radiation irradiating module based on the region of interest.

Methods of tracing regions of interest, radiographic apparatuses, methods of controlling the radiographic apparatuses, and radiography methods

An augmented reality image display system may be implemented together with a surgical robot system. The surgical robot system may include a slave system performing a surgical operation, a master system controlling the surgical operation of the slave system, an imaging system generating a virtual image of the inside of a patient's body, and an augmented reality image display system including a camera capturing a real image having a plurality of markers attached to the patient's body or a human body model. The augmented reality image system may include an augmented reality image generator which detects the plurality of markers in the real image, estimates the position and gaze direction of the camera using the detected markers, and generates an augmented reality image by overlaying a region of the virtual image over the real image, and a display which displays the augmented reality image.

Augmented reality image display system and surgical robot system comprising the same

Provided are an X-ray imaging apparatus that is capable of tracking a position of an object of interest using a Kalman filter so as to reduce the amount of X-ray radiation exposure of a subject, calculating covariance indicative of accuracy of the tracing, and controlling a collimator so that the position of the object of interest and calculated covariance may be correlated with a position and an area of a region into which X-rays are radiated, and a method of controlling the X-ray imaging apparatus.

X-ray imaging apparatus and method of controlling the same

A surgical robot system includes a slave system to perform a surgical operation on a patient and an imaging system that includes an image capture unit including a plurality of cameras to acquire a plurality of affected area images, an image generator detecting an occluded region in each of the affected area images acquired by the plurality of cameras, removing the occluded region therefrom, warping each of the affected area images from which the occluded region is removed, and matching the affected area images to generate a final image, and a controller driving each of the plurality of cameras of the image capture unit to acquire the plurality of affected area images and inputting the acquired plurality of affected area images to the image generator to generate a final image.

Surgical robot system and method of controlling the same

An image processing apparatus and method may accurately separate only humans among moving objects, and also accurately separate even humans who have no motion via human segmentation using a depth data and face detection technology. The apparatus includes a face detecting unit to detect a human face in an input color image, a background model producing/updating unit to produce a background model using a depth data of an input first frame and face detection results, a candidate region extracting unit to produce a candidate region as a human body region by comparing the background model with a depth data of an input second or subsequent frame, and to extract a final candidate region by removing a region containing a moving object other than a human from the candidate region, and a human body region extracting unit to extract the human body region from the candidate region.

Image processing apparatus and image processing method

An image processing apparatus for searching for a feature point by use of a depth image and a method thereof are provided. The image processing apparatus includes an input unit configured to input a three-dimensional image having depth information, a feature point extraction unit configured to obtain a designated point from an object image extracted from the depth image to obtain a feature point that is located at a substantially farthest distance from the designated point, and to obtain other feature points that are located at substantially farthest distances from feature points that are previously obtained as well as the designated point. The apparatus includes a control unit configured to control the input unit and the feature point extraction unit so that time in estimating a structure of the object is reduced, and a recognition result is enhanced.

Image processing apparatus and method thereof

A method and apparatus to generate an object descriptor using extended curvature gabor filters. The method and apparatus may increase a recognition rate of even a relatively small image with use of an extended number of curvature gabor filters having controllable curvatures and may reduce the amount of calculation required for face recognition by performing the face recognition using only some of the extended curvature gabor filters which have a great effect on the recognition rate. The object descriptor generating method includes extracting gabor features from an input object image by applying a plurality of curvature gabor filters, generated via combination of a plurality of curvatures and a plurality of Gaussian magnitudes, to the object image, and generating an object descriptor for object recognition by projecting the extracted features onto a predetermined base vector.

Method and apparatus to generate object descriptor using extended curvature gabor filter

Growing community of inventors

Seoul, South Korea

Won Jun Hwang