• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.924-927
• /
• 2018

본 논문에서는 거동이 불편한 환자나 장애인들을 위해 신체에 착용하는 부가적인 장비 없이 멀리 있는 가전을 직접 움직이지 않고 편리하게 제어할 수 있는 RGB-D 카메라를 활용한 손 인식과 딥러닝 기반 IoT 장치 컨트롤 시스템을 제안한다. 특히, 제어하고자 하는 장치의 위치를 알기 위하여 YOLO 알고리즘을 이용하여 장치를 인식한다. 또한 그와 동시에 RGB-D 카메라의 라이브러리를 이용하여 사용자의 손을 인식, 현재 사용자 손의 위치와 사용자가 취하는 손동작을 통하여 해당 위치의 장치를 제어한다.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.5
• /
• pp.83-83
• /
• 2004

The analysis of relative pose(position and rotation) between stereo cameras is very important to determine the solution that provides three-dimensional information for an arbitrary moving target with respect to robot-end. In the space of free camera-model, the rotational parameters act on non-linear factors acquiring a kinematical solution. In this paper the general solution of active stereo that gives a three-dimensional pose of moving object is presented. The focus is to achieve a derivation of linear equation between a robot′s end and active stereo cameras. The equation is consistently derived from the vector of quaternion space. The calibration of cameras is also derived in this space. Computer simulation and the results of error-sensitivity demonstrate the successful operation of the solution. The suggested solution can also be applied to the more complex real time tracking and quite general and are applicable in various stereo fields.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.5
• /
• pp.89-90
• /
• 2004

The analysis of relative pose(position and rotation) between stereo cameras is very important to determine the solution that provides three-dimensional information for an arbitrary moving target with respect to robot-end. In the space of free camera-model, the rotational parameters act on non-linear factors acquiring a kinematical solution. In this paper the general solution of active stereo that gives a three-dimensional pose of moving object is presented. The focus is to achieve a derivation of linear equation between a robot's end and active stereo cameras. The equation is consistently derived from the vector of quaternion space. The calibration of cameras is also derived in this space. Computer simulation and the results of error-sensitivity demonstrate the successful operation of the solution. The suggested solution can also be applied to the more complex real time tracking and quite general and are applicable in various stereo fields.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.424-426
• /
• 2012

본 논문에서는 컬러영상 기반에서 배경과 잡음에 강인한 적응적 임계값 기반의 피부영역 기법을 제안하고 이를 활용한 응용프로그램을 제안한다. 배경과 전경을 분리시키는 코드북 알고리즘을 사용하여 배경을 제거하고, 분리된 영역에서 매 프레임 임계값과 모션에 따른 화소값을 검사하여 피부영역의 임계값을 갱신한다. 결과적으로 조명과 배경에 강인한 피부 영역 검출이 가능하며 이를 응용하여 사용자 인터페이스에 적용이 가능하다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1477-1479
• /
• 2015

기존의 연구와 같이 정확한 피부색 영역을 추출하기 위해 색상공간을 조절하는 방식은 조명이나 주변환경의 영향에 따라 잘못된 결과를 낼 수 있다. Camshift 알고리즘을 이용한 추적을 할 때에도 대상에게 맞춰진 피부색 히스토그램을 이용해서 추적하지 않으므로 범용성이 떨어진다. 이러한 문제점을 해결하기 위해 Camshift 알고리즘의 최초추적 윈도우를 결정하고 히스토그램을 결정하여손 피부색 추적성능을 향상시켰다. 보편적인 피부색 필터를 이용하여 인체 전경을 추출하고, haar like feature detection (특징검출)을 이용하여 손 영역을 검색한다. 이후 피부색 필터를 통해 이진화 된 이미지를 이용해 원 영상을 마스킹 한 후 사용자 고유의 피부색의 히스토그램을 결정한다. 이 방법으로 얻은 히스토그램을 Camshift알고리즘에 적용하면 기존방식 으로 생성한 히스토그램을 사용할 때보다 좋은 추적 성능을 보인다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.594-596
• /
• 2012

본 논문에서는 손 모션에 대하여 피부색 검출을 기반으로 전역적인 모션을 추적하고 모션 벡터를 생성하여 제스처를 인식하는 방법을 제안한다. 추적을 위하여 Shi-Tomasi 특징점 검출 방법과 Lucas-Kanade 옵티컬 플로우 추정 방법을 사용한다. 손 모션을 추적하는 경우 손의 모양이 다양하게 변화하므로 초기에 검출된 특징점을 계속적으로 추적하는 일반적인 방법으로는 손의 모션을 제대로 추적할 수 없다. 이에 본 논문에서는 프레임마다 새로운 특징점을 검출한 후 옵티컬 플로우를 추정하고 이상치(outlier)를 제거하여 손 모양의 변화에도 추적을 통한 모션 벡터 생성이 가능하도록 한다. 모션 벡터들로 인공 신경망을 사용한 판별 과정을 수행하여 최종적으로 손 모션 제스처에 대한 인식이 가능하도록 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.752-753
• /
• 2023

본 논문에서는 손가락 관절의 운동범위와 MediaPipe 손 추적기를 이용하여 3 차원 손 추적 방법을 설계하였다. MediaPipe 손 추적기가 추정한 신뢰할 수 있는 2 차원 좌표를 바탕으로 손 랜드마크의 깊이를 추정한 후, 손가락 관절 운동범위와 부합한 결과를 도출하였다. 본 논문에서 제안한 3 차원 손 추적 방법은 전용 하드웨어 없이 동작하며 기존의 3 차원 손 추적기에 비해 보다 직관적인 인간-컴퓨터 인터페이스 확산에 긍정적 영향을 줄 것으로 기대한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.7
• /
• pp.4132-4138
• /
• 2014

The purpose of this assessment was to provide the basic data for setting up education in terms of 'Hand wash' as one of the health plan & education programs for adolescents. The task analyzed the behavior of students regarding hand washing, which were ranged from middle school to high school. The SPSS 18.0 statistical program, frequency-test and cross-analysis were used for data analysis by 2011, 2012 and 2013, which were the recent 3 years, the Korea Youth Risk Behavior Web-based Survey data. In the data, the response of "Never washed" from students before having a meal accounted for 29.4% in 2011, 30.5% in 2012 and 18.5% in 2013, respectively. Unlike other subjects, these facts suggest that this kind of behavior should be considered significant under the assessment. By tracking the trend over three years, some facts were confirmed in that students living in the metropolitan and medium-sized cities were less likely to wash their hands than students in small- sized towns. In terms of gender, female students were less likely to wash their hands than male students. Regarding the type of school, more students in the public middle & high schools had a tendency to respond "Never hand wash" than the students in the special-purpose high schools. Furthermore, as the grade was increased in middle school and high school, students were less likely to wash their hands before meals in school. Therefore, Health promotion and health education for students should be conducted more carefully with more emphasis on this point.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_2
• /
• pp.1299-1310
• /
• 2018

In this study, we analyzed distribution and movement trends using in-situ observations and particle tracking methods to understand the movement of the drift ice in the Arctic Ocean. The in-situ movement data of the drift ice in the Arctic Ocean used ITP (Ice-Tethered Profiler) provided by NOAA (National Oceanic and Atmospheric Administration) from 2009 to 2018, which was analyzed with the location and speed for each year. Particle tracking simulates the movement of the drift ice using daily current and wind data provided by HYCOM (Hybrid Coordinate Ocean Model) and ECMWF (European Centre for Medium-Range Weather Forecasts, 2009-2017). In order to simulate the movement of the drift ice throughout the Arctic Ocean, ITP data, a field observation data, were used as input to calculate the relationship between the current and wind and follow up the Lagrangian particle tracking. Particle tracking simulations were conducted with two experiments taking into account the effects of current and the combined effects of current and wind, most of which were reproduced in the same way as in-situ observations, given the effects of currents and winds. The movement of the drift ice in the Arctic Ocean was reproduced using a wind-imposed equation, which analyzed the movement of the drift ice in a particular year. In 2010, the Arctic Ocean Index (AOI) was a negative year, with particles clearly moving along the Beaufort Gyre, resulting in relatively large movements in Beaufort Sea. On the other hand, in 2017 AOI was a positive year, with most particles not affected by Gyre, resulting in relatively low speed and distance. Around the pole, the speed of the drift ice is lower in 2017 than 2010. From seasonal characteristics in 2010 and 2017, the movement of the drift ice increase in winter 2010 (0.22 m/s) and decrease to spring 2010 (0.16 m/s). In the case of 2017, the movement is increased in summer (0.22 m/s) and decreased to spring time (0.13 m/s). As a result, the particle tracking method will be appropriate to understand long-term drift ice movement trends by linking them with satellite data in place of limited field observations.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.3
• /
• pp.112-118
• /
• 2009

Skin color segmentation techniques have been widely utilized for face/hand detection and tracking in many applications such as a diagnosis system using facial information, human-robot interaction, an image retrieval system. In case of a video image, it is common that the skin color model for a target is updated every frame for the robust target tracking against illumination change. As for a single image, however, most of studies employ a fixed skin color model which may result in low detection rate or high false positive errors. In this paper, we propose a novel method for effective skin color segmentation in a single image, which modifies the conditions for skin color segmentation iteratively by the image feedback of segmented skin color region in a given image.