• 한국임상수의학회지
• /
• 제21권1호
• /
• pp.29-34
• /
• 2004

Serial ultrasonographic examinations were daily performed on 12 Shih-tzu bitches from 15 days after ovulation until parturition to determine the time of first detection and ultrasonographic appearance of the fetal and extra-fetal structures and to determine the size of gestational structures. Gestational age was timed from the day of ovulation (day 0), which was estimated to occur when plasma progesterone concentration was first increased above 4.0 ng/ml. The gestational length in 12 Shih-tzu bitches was 62.1 (range:60-64) days. The initial detection of the fetal and extra-fetal structures were: gestational sac at days 19.2 (16-21); zonary placenta in the uterine wall at days 25.9 (24-28); yolk sac membrane at days 24.1 (22-26); amniotic membrane at days 26.6 (24-28); embryo initial detection at days 22.3 (21-24); heartbeat at days 23.8 (23-25); limb buds at days 29.3 (27-31); fetal movement at days 32.3 (31-34); stomach at days 32.6 (29-34); urinary bladder at days 33.1 (29-35); skeleton at days 35.9 (34-38) and kidney at days 45.8 (45-48).

• 한국통신학회논문지
• /
• 제24권9B호
• /
• pp.1690-1696
• /
• 1999

동영상 데이터를 내용기반 검색을 하기 위해 비디오 시퀀스를 계층적 분할해야 한다. 컷 검출 알고리즘은 샷을 분류하는 중요한 처리이다. 일반적인 컷 검출 알고리즘은 이전 프레임과 현재 프레임을 비교하기 때문에 카메라의 움직임이나 물체의 움직임에 의해 화면변화가 크면 컷을 오검출 할 수도 있다. 본 논문에서는 컷 예상지점을 먼저 선정하고 컷 예상지점이 실제의 컷인가를 판별한다. 컷 예상지점의 프레임과 이웃 프레임의 특징차를 비교하므로써 실제 컷을 검출하므로 기존 알고리즘보다 오검출을 줄일 수 있다. MPEG비디오 시퀀스에서 DC영상을 추출하여 비교 프레임으로 사용하였다. 실험 결과, 제안한 알고리즘이 기존의 알고리즘보다 컷 검출율이 높은 것을 확인하였다.

• 스마트미디어저널
• /
• 제5권3호
• /
• pp.93-98
• /
• 2016

배회란 "어떤 곳을 중심으로 어슬렁거리며 이리저리 돌아다닌다." 라는 사전적인 의미를 가지고 있으며 대부분의 범죄가 발생하기 전에 이루어지는 행동이다. 따라서 배회행위를 검출함으로써 다양한 범죄를 사전에 예방할 수 있다. 본 논문에서는 Raspberry Pi를 이용한 배회행위 검출 알고리즘을 제안한다. 제안한 알고리즘은 적응형 차영상을 이용해 움직이는 객체를 검출하였고, 객체검출의 정확성을 높이기 위해 모폴로지 열림 연산을 사용한다. 객체가 검출되면 객체의 무게중심점을 이용하여 무게중심점의 각도 변화와 객체의 높이에 반비례하는 픽셀 이동 거리를 이용하여 배회행위를 검출한다. 배회행위로 검출되면 Raspberry Pi를 이용하여 경고음을 출력하여 사용자에게 알려준다.

• 한국멀티미디어학회논문지
• /
• 제14권4호
• /
• pp.481-493
• /
• 2011

모바일기기가 발달함에 따라 핸드폰에 수많은 기능들이 탑재되고 있다. 영상 통화 기능도 그 중 하나이다. 본 논문에서는 화자와 스마트폰 사이의 거리를 측정하기 위한 다중 색좌표계와 다중 임계치를 사용하는 방법을 제시한다. 첫 번째로 피부색의 색상정보에 근거하여 얼굴영역을 검출한다. 두 번째로 검출된 얼굴영역의 크기를 이용하여 스마트폰과 화자 사이의 거리를 측정한다. 특히 본 논문에서 제시하는 얼굴영역 검출 알고리즘 개발에 있어 고려한 점은 스마트폰의 기본기능과 함께 실시간으로 처리가 가능할 정도로 연산량이 적어야 하며, 움직임이 많은 핸드폰의 특성상 프레임과 프레임 사이의 움직임과 조명 및 배경에 따라 검출된 얼굴 영역이 급격히 변화하는 문제를 해결할 수 있는 얼굴영역 검출 알고리즘을 개발하고자 하였다.

• 대한원격탐사학회지
• /
• 제40권2호
• /
• pp.167-177
• /
• 2024

With advancements in satellite technology, interest in target detection and identification is increasing quantitatively and qualitatively. Synthetic Aperture Radar(SAR) images, which can be acquired regardless of weather conditions, have been applied to various areas combined with machine learning based detection algorithms. However, conventional studies primarily focused on the detection of stationary targets. In this study, we proposed a method to identify moving targets using an algorithm that integrates sub-aperture SAR images and cosine similarity calculations. Utilizing a transformer-based deep learning target detection model, we extracted the bounding box of each target, designated the area as a region of interest (ROI), estimated the similarity between sub-aperture SAR images, and determined movement based on a predefined similarity threshold. Through the proposed algorithm, the quantitative evaluation of target identification capability enhanced its accuracy compared to when training with the targets with two different classes. It signified the effectiveness of our approach in maintaining accuracy while reliably discerning whether a target is in motion.

• ETRI Journal
• /
• 제40권4호
• /
• pp.522-530
• /
• 2018

In this study, we developed a robotic walker that actively controls its speed and direction of movement according to the user's gait intention. Sensor fusion between a low-cost light detection and ranging (LiDAR) sensor and inertia measurement units (IMUs) helps determine the user's gait intention. The LiDAR determines the walking direction by detecting both knees, and the IMUs attached on each foot obtain the angular rate of the gait. The user's gait intention is given as the directional angle and the speed of movement. The two motors in the robotic walker are controlled with these two variables, which represent the user's gait intention. The estimated direction angle is verified by comparison with a Kinect sensor that detects the centroid trajectory of both the user's feet. We validated the robotic walker with an experiment by controlling it using the estimated gait intention.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.594-596
• /
• 2006

In this thesis, we propose a algorithm that is able to detect a user's motion. A minute noise of accelerometer arises cumulative error in case of converting velocity and distance, which makes it difficult to detect movement of sensor. We use a lowpass filter, ALS algorithm, and motion detection block to minimize such cumulative error. we experiment using a motion-detective module which is composed of accelerometer, micro-controller, and serial interface. Our scheme is capable of detecting such as up, down, left, right, forward, and backward movement of the module. It is expected that our scheme is applied to a game controller or user interface of a next generation PC.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2000년도 추계학술대회 논문집
• /
• pp.713-716
• /
• 2000

In this study, we present a mobile robot for ultrasonic scanning of weldment. magnetic Caterpillar mechanism is selected in order to travel on the inclined surface and vertical wall. A motion control board and motor driver are developed to control four DC-servo motors. A virtual device driver is also developed for the purpose of communicating between the control board and a host PC with Dual 'port ram. To provide the mobile robot with stable and accurate movement, PID control algorithm is applied to the mobile robot control. And a vision system for detecting the weld-line are developed with laser slit beam as a light source. In the experiments, movement of the mobile robot is tested inclined on a surface and a vertical wall.

• International Journal of Internet, Broadcasting and Communication
• /
• 제10권4호
• /
• pp.70-74
• /
• 2018

In order to ensure the flow of goods available and more flexible, reduce labor costs, many factories and industrial zones around the world are gradually moving to use automated solutions. One of them is to use Automated guided vehicles (AGV). Currently, there are a line tracing method as an AGV operating method, and a method of estimating the current position of the AGV and matching with a factory map and knowing the moving direction of the AGV. In this paper, we propose ceiling Light and guided line based moving direction estimation algorithm using multi-camera on the AGV in smart factory that can operate stable AGV by compensating the disadvantages of existing AGV operation method. The proposed algorithm is able to estimate its position and direction using a general - purpose camera instead of a sensor. Based on this, it can correct its movement error and estimate its own movement path.

• 대한전자공학회논문지
• /
• 제25권1호
• /
• pp.72-80
• /
• 1988

In this paper, new adaptive interframe filtering methods have been proposed to separate the luminance and chrominance components in NTSC composite signals. In thess methods, the composite signals are adaptivelty processed in three dimensions according to the local change or movement of the picture. For interframe processing, two algorithms have been proposed which adapt three filters in the horizontal, vertical and temporal directions to the magnitude f detection signal dependent upon both the movement and local change of the picture. The three kind of filters have been used at the sampling rate of four times the subcarrier frequency. The various quantitative measures have been introduced to compare the objective performance of the conventional methods and that of proposed ones by computer simulation.