Abstract:
PURPOSE: A method for controlling a power source of a display device using a frontal face detection apparatus and an apparatus thereof are provided to manage the power source of the device, by grasping device usage intention of a user intellectually. CONSTITUTION: A face detection part (100) judges a face of a user existing in the front, and a power source checking part checks power source state of the display device. A power source control part (400) controls the power source of the display device, by using the repetitive result of face detection according to the power source state and the existence of the face. The face detection part includes a frontal face checking part (110) checking whether the face is a frontal face or not. A repetitive variable management part (300) manages repetitive variables defining time or frequency of performing the face detection repetitively. [Reference numerals] (100) Face detection part; (110) Frontal face checking part; (200) Display power checking part (displaydevice_sw); (300) Repetitive variable management part (time_remain); (400) Power source control part
Abstract:
PURPOSE: An image based hand detecting apparatus and method thereof are provided to accurately detect a hand in the dark by creating a comparing result. CONSTITUTION: A hand image detecting unit(50) detects the hand image of a hand shape from an input image. A feature point extraction unit(60) extracts a feature point from the detected hand shape. An image rotation unit(70) rotates the detected hand shape or the stored hand images. A matching unit(80) compares the detected hand image with the stored hand image. When a hand image matched with the detected hand image is existed, a hand shape recognition unit(90) selects the hand image as the matched hand image.
Abstract:
PURPOSE: A method and an apparatus for real-time face detection using a stereo vision are provided to perform face detection in foreground including face pattern from whole video by stereo vision processor thereby widely reducing face detection processing time. CONSTITUTION: A vision processing unit(320) calculates distance information by usage of a plurality of images including face pattern. Based on the distance information, the vision processing unit divides foreground image including the face pattern and background image not including the face pattern. According to distance information, a face detection unit(330) adjusts video size of the foreground image. The face detection unit detects the face pattern from adjusted foreground image.
Abstract:
본 발명은 스테레오 비전 시스템의 영상 처리 방법에 관한 것으로, 이를 위하여 본 발명은, 스테레오 영상 입력에 대한 전처리 과정을 수행하고, 동일한 물체로 판단되는 좌측 및 우측 영상의 픽셀간 양안차(disparity)를 생성하는 스테레오 매칭을 수행하여 스테레오 영상 정보를 획득하는 종래 방법과는 달리, 스테레오 비전 시스템에서 스테레오 영상이 입력되면, 영상 압축 모듈을 통해 저해상도 거리 정보를 획득하거나 스테레오 매칭 모듈을 이용하여 고해상도 거리 정보를 획득한 후, 저해상도 거리 정보 또는 고해상도 거리 정보에 대응하는 영상의 움직임 벡터를 이용하여 영상 노이즈를 제거함으로써, 움직임 벡터를 이용하여 영상 노이즈를 효과적으로 제거하여 스테레오 영상에 대한 정확한 거리 정보를 획득할 수 있는 것이다. 스테레오 비전 시스템, 스테레오 매칭(Stereo Matching)
Abstract:
PURPOSE: A user recognition device and a user recognition method are provided to use a walking pattern as ID information of a user, thereby improving a recognition rate of the user through simple configuration. CONSTITUTION: A sensing unit(110) senses vibration due to walking of a user to output an electrical signal. A pattern calculator(130) obtains a walking pattern of a pedestrian from the electrical signal. A user decider(150) compares the walking pattern with reference date. The user decider identifies a user based on the comparison result.
Abstract:
A stereo vision system and an image processing method thereof are provided to efficiently remove image noise by using a motion vector of an image, thereby obtaining exact distance information on a stereo image. An inputted stereo image is pre-processed. Low-resolution distance information using an image compression module about the pre-processed stereo image is obtained(616). High-resolution distance information is obtained through a stereo matching module(622). A motion vector is extracted by utilizing the image compression module. Image noise is eliminated by using the high-resolution distance information and the extracted motion vector(624). The motion vector is extracted through a motion estimation technique by alternately inputting the stereo image.
Abstract:
본 발명은 로봇 영상 시스템 및 검출 방법에 관한 것으로, 이동형 로봇이 사람의 위치를 검출하고, 움직이는 사람의 방향으로 장애물을 피해 접근하도록 하는 서비스를 제공함으로써, 이동형 로봇의 주의를 끌고자 손을 흔들거나 로봇 앞에서 움직이는 사람을 찾는 일을 비교적 적은 연산만으로도 수행하여 메인 프로세서와 배터리를 적게 소모하므로 이동형 로봇의 대기시간을 향상시킬 수 있다. 이동형 로봇, 영상, 사람, 장애물
Abstract:
PURPOSE: An apparatus for detecting a parallel frame in a system for optical transmission is provided to be easily obtained as a semiconductor device by detecting a frame at a low speed compared to the speed of STM-64 signal in the receiving end of a system for optical transmission. CONSTITUTION: A first retimer(410) and a second retimer(420) are for retiming a parallel input signal. A frame detector(430) detects a specific byte existed in a specific position within a predetermined frame by receiving the signal retimed and provides with a frame detecting position information. A coder(440) encodes frame detecting position information output from the frame detector. A frame determining and alignment controller(450) determines whether the frame of the encoded signal is normal or not according to the frame detecting information and outputs a signal alignment control signal according to the result thereof. A signal aligner(470) aligns the order of the signal retimed by the first retimer according to the signal alignment control signal.
Abstract:
PURPOSE: A controller of ring switch in a digital transmitting system is provided to freely set a path by performing the ring switch with one control command of ring switch transmitted from an outer processor for controlling the ring switch of the SDH(synchronous digital hierarchy) digital transmitting system. CONSTITUTION: If there is a difficulty in two east optical fibers(for transmission and receiving), a signal(ABCD)(an AB is a signal of a working band and a CD is a signal of a protection band) inputted to an optical fiber(620) performs a branch and a signal A is outputted to an optical fiber(670). A signal EBCD is formed by combining an inputting tributary signal E. The signal EBCD is outputted to east in a normal operation, however a ring switch is performed because the east line has a defect. The ring switch switches the signal EBCD to a signal CDEB(switches a working band and the protection band). The east input signal is branched, combined and passed in the normal operation, however an output is performed to west after forming a signal CFEB by branching a signal D to an output tributary signal and by combining an inputting tributary signal F in the CDEB using the CDEB as an outputting signal of the ring switch instead of the east input signal.